diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-04-03 05:53:45 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-04-03 05:53:45 +0200 |
commit | cd6362befe4cc7bf589a5236d2a780af2d47bcc9 (patch) | |
tree | 3bd4e13ec3f92a00dc4f6c3d65e820b54dbfe46e /net | |
parent | Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jik... (diff) | |
parent | netpoll: Use skb_irq_freeable to make zap_completion_queue safe. (diff) | |
download | linux-cd6362befe4cc7bf589a5236d2a780af2d47bcc9.tar.xz linux-cd6362befe4cc7bf589a5236d2a780af2d47bcc9.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Here is my initial pull request for the networking subsystem during
this merge window:
1) Support for ESN in AH (RFC 4302) from Fan Du.
2) Add full kernel doc for ethtool command structures, from Ben
Hutchings.
3) Add BCM7xxx PHY driver, from Florian Fainelli.
4) Export computed TCP rate information in netlink socket dumps, from
Eric Dumazet.
5) Allow IPSEC SA to be dumped partially using a filter, from Nicolas
Dichtel.
6) Convert many drivers to pci_enable_msix_range(), from Alexander
Gordeev.
7) Record SKB timestamps more efficiently, from Eric Dumazet.
8) Switch to microsecond resolution for TCP round trip times, also
from Eric Dumazet.
9) Clean up and fix 6lowpan fragmentation handling by making use of
the existing inet_frag api for it's implementation.
10) Add TX grant mapping to xen-netback driver, from Zoltan Kiss.
11) Auto size SKB lengths when composing netlink messages based upon
past message sizes used, from Eric Dumazet.
12) qdisc dumps can take a long time, add a cond_resched(), From Eric
Dumazet.
13) Sanitize netpoll core and drivers wrt. SKB handling semantics.
Get rid of never-used-in-tree netpoll RX handling. From Eric W
Biederman.
14) Support inter-address-family and namespace changing in VTI tunnel
driver(s). From Steffen Klassert.
15) Add Altera TSE driver, from Vince Bridgers.
16) Optimizing csum_replace2() so that it doesn't adjust the checksum
by checksumming the entire header, from Eric Dumazet.
17) Expand BPF internal implementation for faster interpreting, more
direct translations into JIT'd code, and much cleaner uses of BPF
filtering in non-socket ocntexts. From Daniel Borkmann and Alexei
Starovoitov"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1976 commits)
netpoll: Use skb_irq_freeable to make zap_completion_queue safe.
net: Add a test to see if a skb is freeable in irq context
qlcnic: Fix build failure due to undefined reference to `vxlan_get_rx_port'
net: ptp: move PTP classifier in its own file
net: sxgbe: make "core_ops" static
net: sxgbe: fix logical vs bitwise operation
net: sxgbe: sxgbe_mdio_register() frees the bus
Call efx_set_channels() before efx->type->dimension_resources()
xen-netback: disable rogue vif in kthread context
net/mlx4: Set proper build dependancy with vxlan
be2net: fix build dependency on VxLAN
mac802154: make csma/cca parameters per-wpan
mac802154: allow only one WPAN to be up at any given time
net: filter: minor: fix kdoc in __sk_run_filter
netlink: don't compare the nul-termination in nla_strcmp
can: c_can: Avoid led toggling for every packet.
can: c_can: Simplify TX interrupt cleanup
can: c_can: Store dlc private
can: c_can: Reduce register access
can: c_can: Make the code readable
...
Diffstat (limited to 'net')
342 files changed, 15444 insertions, 7311 deletions
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 5704ed9c3a23..9d010a09ab98 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -38,9 +38,9 @@ struct vlan_info { static inline unsigned int vlan_proto_idx(__be16 proto) { switch (proto) { - case __constant_htons(ETH_P_8021Q): + case htons(ETH_P_8021Q): return VLAN_PROTO_8021Q; - case __constant_htons(ETH_P_8021AD): + case htons(ETH_P_8021AD): return VLAN_PROTO_8021AD; default: BUG(); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 6ee48aac776f..3c32bd257b73 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -22,11 +22,11 @@ bool vlan_do_receive(struct sk_buff **skbp) return false; skb->dev = vlan_dev; - if (skb->pkt_type == PACKET_OTHERHOST) { + if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) { /* Our lower layer thinks this is not local, let's make sure. * This allows the VLAN to have a different MAC than the * underlying device, and still route correctly. */ - if (ether_addr_equal(eth_hdr(skb)->h_dest, vlan_dev->dev_addr)) + if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, vlan_dev->dev_addr)) skb->pkt_type = PACKET_HOST; } @@ -106,6 +106,12 @@ u16 vlan_dev_vlan_id(const struct net_device *dev) } EXPORT_SYMBOL(vlan_dev_vlan_id); +__be16 vlan_dev_vlan_proto(const struct net_device *dev) +{ + return vlan_dev_priv(dev)->vlan_proto; +} +EXPORT_SYMBOL(vlan_dev_vlan_proto); + static struct sk_buff *vlan_reorder_header(struct sk_buff *skb) { if (skb_cow(skb, skb_headroom(skb)) < 0) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 27bfe2f8e2de..6f142f03716d 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -559,7 +559,7 @@ static const struct net_device_ops vlan_netdev_ops; static int vlan_dev_init(struct net_device *dev) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; - int subclass = 0, i; + int subclass = 0; netif_carrier_off(dev); @@ -613,17 +613,10 @@ static int vlan_dev_init(struct net_device *dev) vlan_dev_set_lockdep_class(dev, subclass); - vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats); + vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan_dev_priv(dev)->vlan_pcpu_stats) return -ENOMEM; - for_each_possible_cpu(i) { - struct vlan_pcpu_stats *vlan_stat; - vlan_stat = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i); - u64_stats_init(&vlan_stat->syncp); - } - - return 0; } @@ -689,13 +682,13 @@ static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, st p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i); do { - start = u64_stats_fetch_begin_bh(&p->syncp); + start = u64_stats_fetch_begin_irq(&p->syncp); rxpackets = p->rx_packets; rxbytes = p->rx_bytes; rxmulticast = p->rx_multicast; txpackets = p->tx_packets; txbytes = p->tx_bytes; - } while (u64_stats_fetch_retry_bh(&p->syncp, start)); + } while (u64_stats_fetch_retry_irq(&p->syncp, start)); stats->rx_packets += rxpackets; stats->rx_bytes += rxbytes; @@ -718,20 +711,19 @@ static void vlan_dev_poll_controller(struct net_device *dev) return; } -static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo, - gfp_t gfp) +static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; struct netpoll *netpoll; int err = 0; - netpoll = kzalloc(sizeof(*netpoll), gfp); + netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); err = -ENOMEM; if (!netpoll) goto out; - err = __netpoll_setup(netpoll, real_dev, gfp); + err = __netpoll_setup(netpoll, real_dev); if (err) { kfree(netpoll); goto out; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index c7e634af8516..8ac8a5cc2143 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -56,8 +56,8 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) if (data[IFLA_VLAN_PROTOCOL]) { switch (nla_get_be16(data[IFLA_VLAN_PROTOCOL])) { - case __constant_htons(ETH_P_8021Q): - case __constant_htons(ETH_P_8021AD): + case htons(ETH_P_8021Q): + case htons(ETH_P_8021AD): break; default: return -EPROTONOSUPPORT; diff --git a/net/Kconfig b/net/Kconfig index e411046a62e3..d1f6f968fc09 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -89,8 +89,12 @@ config NETWORK_SECMARK to nfmark, but designated for security purposes. If you are unsure how to answer this question, answer N. +config NET_PTP_CLASSIFY + def_bool n + config NETWORK_PHY_TIMESTAMPING bool "Timestamping in PHY devices" + select NET_PTP_CLASSIFY help This allows timestamping of network packets by PHYs with hardware timestamping capabilities. This option adds some diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index d27b86dfb0e9..d1c55d8dd0a2 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -926,7 +926,7 @@ static struct aarp_entry *iter_next(struct aarp_iter_state *iter, loff_t *pos) struct aarp_entry *entry; rescan: - while(ct < AARP_HASH_SIZE) { + while (ct < AARP_HASH_SIZE) { for (entry = table[ct]; entry; entry = entry->next) { if (!pos || ++off == *pos) { iter->table = table; @@ -995,7 +995,7 @@ static const char *dt2str(unsigned long ticks) { static char buf[32]; - sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100 ) / HZ); + sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100) / HZ); return buf; } diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 02806c6b2ff3..786ee2f83d5f 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -293,7 +293,7 @@ static int atif_probe_device(struct atalk_iface *atif) /* Perform AARP probing for a proxy address */ static int atif_proxy_probe_device(struct atalk_iface *atif, - struct atalk_addr* proxy_addr) + struct atalk_addr *proxy_addr) { int netrange = ntohs(atif->nets.nr_lastnet) - ntohs(atif->nets.nr_firstnet) + 1; @@ -581,7 +581,7 @@ out: } /* Delete a route. Find it and discard it */ -static int atrtr_delete(struct atalk_addr * addr) +static int atrtr_delete(struct atalk_addr *addr) { struct atalk_route **r = &atalk_routes; int retval = 0; @@ -936,11 +936,11 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, int i, copy; /* checksum stuff in header space */ - if ( (copy = start - offset) > 0) { + if ((copy = start - offset) > 0) { if (copy > len) copy = len; sum = atalk_sum_partial(skb->data + offset, copy, sum); - if ( (len -= copy) == 0) + if ((len -= copy) == 0) return sum; offset += copy; @@ -1151,7 +1151,7 @@ static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; at->src_net = addr->sat_addr.s_net = ap->s_net; - at->src_node = addr->sat_addr.s_node= ap->s_node; + at->src_node = addr->sat_addr.s_node = ap->s_node; } else { err = -EADDRNOTAVAIL; if (!atalk_find_interface(addr->sat_addr.s_net, @@ -1790,53 +1790,53 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) void __user *argp = (void __user *)arg; switch (cmd) { - /* Protocol layer */ - case TIOCOUTQ: { - long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); + /* Protocol layer */ + case TIOCOUTQ: { + long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); - if (amount < 0) - amount = 0; - rc = put_user(amount, (int __user *)argp); - break; - } - case TIOCINQ: { - /* - * These two are safe on a single CPU system as only - * user tasks fiddle here - */ - struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); - long amount = 0; + if (amount < 0) + amount = 0; + rc = put_user(amount, (int __user *)argp); + break; + } + case TIOCINQ: { + /* + * These two are safe on a single CPU system as only + * user tasks fiddle here + */ + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + long amount = 0; - if (skb) - amount = skb->len - sizeof(struct ddpehdr); - rc = put_user(amount, (int __user *)argp); - break; - } - case SIOCGSTAMP: - rc = sock_get_timestamp(sk, argp); - break; - case SIOCGSTAMPNS: - rc = sock_get_timestampns(sk, argp); - break; - /* Routing */ - case SIOCADDRT: - case SIOCDELRT: - rc = -EPERM; - if (capable(CAP_NET_ADMIN)) - rc = atrtr_ioctl(cmd, argp); - break; - /* Interface */ - case SIOCGIFADDR: - case SIOCSIFADDR: - case SIOCGIFBRDADDR: - case SIOCATALKDIFADDR: - case SIOCDIFADDR: - case SIOCSARP: /* proxy AARP */ - case SIOCDARP: /* proxy AARP */ - rtnl_lock(); - rc = atif_ioctl(cmd, argp); - rtnl_unlock(); - break; + if (skb) + amount = skb->len - sizeof(struct ddpehdr); + rc = put_user(amount, (int __user *)argp); + break; + } + case SIOCGSTAMP: + rc = sock_get_timestamp(sk, argp); + break; + case SIOCGSTAMPNS: + rc = sock_get_timestampns(sk, argp); + break; + /* Routing */ + case SIOCADDRT: + case SIOCDELRT: + rc = -EPERM; + if (capable(CAP_NET_ADMIN)) + rc = atrtr_ioctl(cmd, argp); + break; + /* Interface */ + case SIOCGIFADDR: + case SIOCSIFADDR: + case SIOCGIFBRDADDR: + case SIOCATALKDIFADDR: + case SIOCDIFADDR: + case SIOCSARP: /* proxy AARP */ + case SIOCDARP: /* proxy AARP */ + rtnl_lock(); + rc = atif_ioctl(cmd, argp); + rtnl_unlock(); + break; } return rc; diff --git a/net/atm/mpc.c b/net/atm/mpc.c index b71ff6b234f2..91dc58f1124d 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -1492,7 +1492,7 @@ static void __exit atm_mpoa_cleanup(void) mpc_proc_clean(); - del_timer(&mpc_timer); + del_timer_sync(&mpc_timer); unregister_netdevice_notifier(&mpoa_notifier); deregister_atm_ioctl(&atm_ioctl_ops); diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index fa780b76630e..11660a3aab5a 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -50,6 +50,15 @@ config BATMAN_ADV_NC If you think that your network does not need this feature you can safely disable it and save some space. +config BATMAN_ADV_MCAST + bool "Multicast optimisation" + depends on BATMAN_ADV + default n + help + This option enables the multicast optimisation which aims to + reduce the air overhead while improving the reliability of + multicast messages. + config BATMAN_ADV_DEBUG bool "B.A.T.M.A.N. debugging" depends on BATMAN_ADV diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 42df18f877e9..eb7d8c0388e4 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -36,3 +36,4 @@ batman-adv-y += send.o batman-adv-y += soft-interface.o batman-adv-y += sysfs.o batman-adv-y += translation-table.o +batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 8323bced8e5b..b3bd4ec3fd94 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -347,10 +347,10 @@ static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface) unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; - memcpy(batadv_ogm_packet->orig, - hard_iface->net_dev->dev_addr, ETH_ALEN); - memcpy(batadv_ogm_packet->prev_sender, - hard_iface->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(batadv_ogm_packet->orig, + hard_iface->net_dev->dev_addr); + ether_addr_copy(batadv_ogm_packet->prev_sender, + hard_iface->net_dev->dev_addr); } static void @@ -830,7 +830,7 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node, tvlv_len = ntohs(batadv_ogm_packet->tvlv_len); batadv_ogm_packet->ttl--; - memcpy(batadv_ogm_packet->prev_sender, ethhdr->h_source, ETH_ALEN); + ether_addr_copy(batadv_ogm_packet->prev_sender, ethhdr->h_source); /* apply hop penalty */ batadv_ogm_packet->tq = batadv_hop_penalty(batadv_ogm_packet->tq, diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 05f0712be5e7..6f0d9ec37950 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -191,7 +191,7 @@ batadv_backbone_hash_find(struct batadv_priv *bat_priv, if (!hash) return NULL; - memcpy(search_entry.orig, addr, ETH_ALEN); + ether_addr_copy(search_entry.orig, addr); search_entry.vid = vid; index = batadv_choose_backbone_gw(&search_entry, hash->size); @@ -305,7 +305,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, /* normal claim frame * set Ethernet SRC to the clients mac */ - memcpy(ethhdr->h_source, mac, ETH_ALEN); + ether_addr_copy(ethhdr->h_source, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_send_claim(): CLAIM %pM on vid %d\n", mac, BATADV_PRINT_VID(vid)); @@ -314,7 +314,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, /* unclaim frame * set HW SRC to the clients mac */ - memcpy(hw_src, mac, ETH_ALEN); + ether_addr_copy(hw_src, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_send_claim(): UNCLAIM %pM on vid %d\n", mac, BATADV_PRINT_VID(vid)); @@ -323,7 +323,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, /* announcement frame * set HW SRC to the special mac containg the crc */ - memcpy(hw_src, mac, ETH_ALEN); + ether_addr_copy(hw_src, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_send_claim(): ANNOUNCE of %pM on vid %d\n", ethhdr->h_source, BATADV_PRINT_VID(vid)); @@ -333,8 +333,8 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, * set HW SRC and header destination to the receiving backbone * gws mac */ - memcpy(hw_src, mac, ETH_ALEN); - memcpy(ethhdr->h_dest, mac, ETH_ALEN); + ether_addr_copy(hw_src, mac); + ether_addr_copy(ethhdr->h_dest, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla_send_claim(): REQUEST of %pM to %pM on vid %d\n", ethhdr->h_source, ethhdr->h_dest, @@ -395,7 +395,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, entry->bat_priv = bat_priv; atomic_set(&entry->request_sent, 0); atomic_set(&entry->wait_periods, 0); - memcpy(entry->orig, orig, ETH_ALEN); + ether_addr_copy(entry->orig, orig); /* one for the hash, one for returning */ atomic_set(&entry->refcount, 2); @@ -563,7 +563,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, struct batadv_bla_claim search_claim; int hash_added; - memcpy(search_claim.addr, mac, ETH_ALEN); + ether_addr_copy(search_claim.addr, mac); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); @@ -573,7 +573,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, if (!claim) return; - memcpy(claim->addr, mac, ETH_ALEN); + ether_addr_copy(claim->addr, mac); claim->vid = vid; claim->lasttime = jiffies; claim->backbone_gw = backbone_gw; @@ -624,7 +624,7 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, { struct batadv_bla_claim search_claim, *claim; - memcpy(search_claim.addr, mac, ETH_ALEN); + ether_addr_copy(search_claim.addr, mac); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); if (!claim) @@ -882,7 +882,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, proto = ethhdr->h_proto; headlen = ETH_HLEN; if (vid & BATADV_VLAN_HAS_TAG) { - vhdr = (struct vlan_ethhdr *)ethhdr; + vhdr = vlan_eth_hdr(skb); proto = vhdr->h_vlan_encapsulated_proto; headlen += VLAN_HLEN; } @@ -1103,8 +1103,8 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, oldif->net_dev->dev_addr)) continue; - memcpy(backbone_gw->orig, - primary_if->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(backbone_gw->orig, + primary_if->net_dev->dev_addr); /* send an announce frame so others will ask for our * claims and update their tables. */ @@ -1310,7 +1310,7 @@ int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, entry = &bat_priv->bla.bcast_duplist[curr]; entry->crc = crc; entry->entrytime = jiffies; - memcpy(entry->orig, bcast_packet->orig, ETH_ALEN); + ether_addr_copy(entry->orig, bcast_packet->orig); bat_priv->bla.bcast_duplist_curr = curr; out: @@ -1458,7 +1458,7 @@ int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) goto handled; - memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN); + ether_addr_copy(search_claim.addr, ethhdr->h_source); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); @@ -1547,9 +1547,6 @@ int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, if (!atomic_read(&bat_priv->bridge_loop_avoidance)) goto allow; - /* in VLAN case, the mac header might not be set. */ - skb_reset_mac_header(skb); - if (batadv_bla_process_claim(bat_priv, primary_if, skb)) goto handled; @@ -1560,7 +1557,7 @@ int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, if (is_multicast_ether_addr(ethhdr->h_dest)) goto handled; - memcpy(search_claim.addr, ethhdr->h_source, ETH_ALEN); + ether_addr_copy(search_claim.addr, ethhdr->h_source); search_claim.vid = vid; claim = batadv_claim_hash_find(bat_priv, &search_claim); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index edee50411892..b25fd64d727b 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -277,7 +277,7 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip, /* if this entry is already known, just update it */ if (dat_entry) { if (!batadv_compare_eth(dat_entry->mac_addr, mac_addr)) - memcpy(dat_entry->mac_addr, mac_addr, ETH_ALEN); + ether_addr_copy(dat_entry->mac_addr, mac_addr); dat_entry->last_update = jiffies; batadv_dbg(BATADV_DBG_DAT, bat_priv, "Entry updated: %pI4 %pM (vid: %d)\n", @@ -292,7 +292,7 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip, dat_entry->ip = ip; dat_entry->vid = vid; - memcpy(dat_entry->mac_addr, mac_addr, ETH_ALEN); + ether_addr_copy(dat_entry->mac_addr, mac_addr); dat_entry->last_update = jiffies; atomic_set(&dat_entry->refcount, 2); @@ -1027,6 +1027,11 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, if (!skb_new) goto out; + /* the rest of the TX path assumes that the mac_header offset pointing + * to the inner Ethernet header has been set, therefore reset it now. + */ + skb_reset_mac_header(skb_new); + if (vid & BATADV_VLAN_HAS_TAG) skb_new = vlan_insert_tag(skb_new, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index ac9be9b67a25..d76e1d06c5b5 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -25,6 +25,9 @@ #include <linux/if_arp.h> +/** + * BATADV_DAT_ADDR_MAX - maximum address value in the DHT space + */ #define BATADV_DAT_ADDR_MAX ((batadv_dat_addr_t)~(batadv_dat_addr_t)0) void batadv_dat_status_update(struct net_device *net_dev); diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 88df9b1d552d..bcc4bea632fa 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -449,8 +449,8 @@ bool batadv_frag_send_packet(struct sk_buff *skb, frag_header.reserved = 0; frag_header.no = 0; frag_header.total_size = htons(skb->len); - memcpy(frag_header.orig, primary_if->net_dev->dev_addr, ETH_ALEN); - memcpy(frag_header.dest, orig_node->orig, ETH_ALEN); + ether_addr_copy(frag_header.orig, primary_if->net_dev->dev_addr); + ether_addr_copy(frag_header.dest, orig_node->orig); /* Eat and send fragments from the tail of skb */ while (skb->len > max_fragment_size) { diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 55cf2260d295..c835e137423b 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -389,8 +389,6 @@ out: batadv_neigh_ifinfo_free_ref(router_gw_tq); if (router_orig_tq) batadv_neigh_ifinfo_free_ref(router_orig_tq); - - return; } /** @@ -680,7 +678,7 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, if (!pskb_may_pull(skb, *header_len + ETH_HLEN)) return BATADV_DHCP_NO; - ethhdr = (struct ethhdr *)skb->data; + ethhdr = eth_hdr(skb); proto = ethhdr->h_proto; *header_len += ETH_HLEN; @@ -689,7 +687,7 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, if (!pskb_may_pull(skb, *header_len + VLAN_HLEN)) return BATADV_DHCP_NO; - vhdr = (struct vlan_ethhdr *)skb->data; + vhdr = vlan_eth_hdr(skb); proto = vhdr->h_vlan_encapsulated_proto; *header_len += VLAN_HLEN; } @@ -728,7 +726,7 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, return BATADV_DHCP_NO; /* skb->data might have been reallocated by pskb_may_pull() */ - ethhdr = (struct ethhdr *)skb->data; + ethhdr = eth_hdr(skb); if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) ethhdr = (struct ethhdr *)(skb->data + VLAN_HLEN); @@ -765,7 +763,7 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, if (*p != ETH_ALEN) return BATADV_DHCP_NO; - memcpy(chaddr, skb->data + chaddr_offset, ETH_ALEN); + ether_addr_copy(chaddr, skb->data + chaddr_offset); } return ret; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index abb9d6e0388b..161ef8f17d2e 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -158,6 +158,7 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, struct batadv_orig_node *orig_node = NULL; struct batadv_neigh_node *neigh_node = NULL; size_t packet_len = sizeof(struct batadv_icmp_packet); + uint8_t *addr; if (len < sizeof(struct batadv_icmp_header)) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, @@ -227,10 +228,10 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, goto dst_unreach; icmp_packet_rr = (struct batadv_icmp_packet_rr *)icmp_header; - if (packet_len == sizeof(*icmp_packet_rr)) - memcpy(icmp_packet_rr->rr, - neigh_node->if_incoming->net_dev->dev_addr, - ETH_ALEN); + if (packet_len == sizeof(*icmp_packet_rr)) { + addr = neigh_node->if_incoming->net_dev->dev_addr; + ether_addr_copy(icmp_packet_rr->rr[0], addr); + } break; default: @@ -250,7 +251,7 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff, goto free_skb; } - memcpy(icmp_header->orig, primary_if->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(icmp_header->orig, primary_if->net_dev->dev_addr); batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); goto out; diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 66ae135b9f27..d1183e882167 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -34,6 +34,7 @@ #include "gateway_client.h" #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" +#include "multicast.h" #include "gateway_common.h" #include "hash.h" #include "bat_algo.h" @@ -110,6 +111,9 @@ int batadv_mesh_init(struct net_device *soft_iface) spin_lock_init(&bat_priv->tt.last_changeset_lock); spin_lock_init(&bat_priv->tt.commit_lock); spin_lock_init(&bat_priv->gw.list_lock); +#ifdef CONFIG_BATMAN_ADV_MCAST + spin_lock_init(&bat_priv->mcast.want_lists_lock); +#endif spin_lock_init(&bat_priv->tvlv.container_list_lock); spin_lock_init(&bat_priv->tvlv.handler_list_lock); spin_lock_init(&bat_priv->softif_vlan_list_lock); @@ -117,9 +121,17 @@ int batadv_mesh_init(struct net_device *soft_iface) INIT_HLIST_HEAD(&bat_priv->forw_bat_list); INIT_HLIST_HEAD(&bat_priv->forw_bcast_list); INIT_HLIST_HEAD(&bat_priv->gw.list); +#ifdef CONFIG_BATMAN_ADV_MCAST + INIT_HLIST_HEAD(&bat_priv->mcast.want_all_unsnoopables_list); + INIT_HLIST_HEAD(&bat_priv->mcast.want_all_ipv4_list); + INIT_HLIST_HEAD(&bat_priv->mcast.want_all_ipv6_list); +#endif INIT_LIST_HEAD(&bat_priv->tt.changes_list); INIT_LIST_HEAD(&bat_priv->tt.req_list); INIT_LIST_HEAD(&bat_priv->tt.roam_list); +#ifdef CONFIG_BATMAN_ADV_MCAST + INIT_HLIST_HEAD(&bat_priv->mcast.mla_list); +#endif INIT_HLIST_HEAD(&bat_priv->tvlv.container_list); INIT_HLIST_HEAD(&bat_priv->tvlv.handler_list); INIT_HLIST_HEAD(&bat_priv->softif_vlan_list); @@ -145,6 +157,7 @@ int batadv_mesh_init(struct net_device *soft_iface) goto err; batadv_gw_init(bat_priv); + batadv_mcast_init(bat_priv); atomic_set(&bat_priv->gw.reselect, 0); atomic_set(&bat_priv->mesh_state, BATADV_MESH_ACTIVE); @@ -169,6 +182,8 @@ void batadv_mesh_free(struct net_device *soft_iface) batadv_dat_free(bat_priv); batadv_bla_free(bat_priv); + batadv_mcast_free(bat_priv); + /* Free the TT and the originator tables only after having terminated * all the other depending components which may use these structures for * their purposes. @@ -1133,8 +1148,8 @@ void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, uint8_t *src, unicast_tvlv_packet->reserved = 0; unicast_tvlv_packet->tvlv_len = htons(tvlv_len); unicast_tvlv_packet->align = 0; - memcpy(unicast_tvlv_packet->src, src, ETH_ALEN); - memcpy(unicast_tvlv_packet->dst, dst, ETH_ALEN); + ether_addr_copy(unicast_tvlv_packet->src, src); + ether_addr_copy(unicast_tvlv_packet->dst, dst); tvlv_buff = (unsigned char *)(unicast_tvlv_packet + 1); tvlv_hdr = (struct batadv_tvlv_hdr *)tvlv_buff; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 9374f1a51348..770dc890ceef 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -24,7 +24,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2014.1.0" +#define BATADV_SOURCE_VERSION "2014.2.0" #endif /* B.A.T.M.A.N. parameters */ @@ -176,6 +176,8 @@ enum batadv_uev_type { #include <linux/percpu.h> #include <linux/slab.h> #include <net/sock.h> /* struct sock */ +#include <net/addrconf.h> /* ipv6 address stuff */ +#include <linux/ip.h> #include <net/rtnetlink.h> #include <linux/jiffies.h> #include <linux/seq_file.h> diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c new file mode 100644 index 000000000000..8c7ca811de6e --- /dev/null +++ b/net/batman-adv/multicast.c @@ -0,0 +1,748 @@ +/* Copyright (C) 2014 B.A.T.M.A.N. contributors: + * + * Linus Lüssing + * + * 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. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "main.h" +#include "multicast.h" +#include "originator.h" +#include "hard-interface.h" +#include "translation-table.h" +#include "multicast.h" + +/** + * batadv_mcast_mla_softif_get - get softif multicast listeners + * @dev: the device to collect multicast addresses from + * @mcast_list: a list to put found addresses into + * + * Collect multicast addresses of the local multicast listeners + * on the given soft interface, dev, in the given mcast_list. + * + * Returns -ENOMEM on memory allocation error or the number of + * items added to the mcast_list otherwise. + */ +static int batadv_mcast_mla_softif_get(struct net_device *dev, + struct hlist_head *mcast_list) +{ + struct netdev_hw_addr *mc_list_entry; + struct batadv_hw_addr *new; + int ret = 0; + + netif_addr_lock_bh(dev); + netdev_for_each_mc_addr(mc_list_entry, dev) { + new = kmalloc(sizeof(*new), GFP_ATOMIC); + if (!new) { + ret = -ENOMEM; + break; + } + + ether_addr_copy(new->addr, mc_list_entry->addr); + hlist_add_head(&new->list, mcast_list); + ret++; + } + netif_addr_unlock_bh(dev); + + return ret; +} + +/** + * batadv_mcast_mla_is_duplicate - check whether an address is in a list + * @mcast_addr: the multicast address to check + * @mcast_list: the list with multicast addresses to search in + * + * Returns true if the given address is already in the given list. + * Otherwise returns false. + */ +static bool batadv_mcast_mla_is_duplicate(uint8_t *mcast_addr, + struct hlist_head *mcast_list) +{ + struct batadv_hw_addr *mcast_entry; + + hlist_for_each_entry(mcast_entry, mcast_list, list) + if (batadv_compare_eth(mcast_entry->addr, mcast_addr)) + return true; + + return false; +} + +/** + * batadv_mcast_mla_list_free - free a list of multicast addresses + * @mcast_list: the list to free + * + * Removes and frees all items in the given mcast_list. + */ +static void batadv_mcast_mla_list_free(struct hlist_head *mcast_list) +{ + struct batadv_hw_addr *mcast_entry; + struct hlist_node *tmp; + + hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) { + hlist_del(&mcast_entry->list); + kfree(mcast_entry); + } +} + +/** + * batadv_mcast_mla_tt_retract - clean up multicast listener announcements + * @bat_priv: the bat priv with all the soft interface information + * @mcast_list: a list of addresses which should _not_ be removed + * + * Retracts the announcement of any multicast listener from the + * translation table except the ones listed in the given mcast_list. + * + * If mcast_list is NULL then all are retracted. + */ +static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv, + struct hlist_head *mcast_list) +{ + struct batadv_hw_addr *mcast_entry; + struct hlist_node *tmp; + + hlist_for_each_entry_safe(mcast_entry, tmp, &bat_priv->mcast.mla_list, + list) { + if (mcast_list && + batadv_mcast_mla_is_duplicate(mcast_entry->addr, + mcast_list)) + continue; + + batadv_tt_local_remove(bat_priv, mcast_entry->addr, + BATADV_NO_FLAGS, + "mcast TT outdated", false); + + hlist_del(&mcast_entry->list); + kfree(mcast_entry); + } +} + +/** + * batadv_mcast_mla_tt_add - add multicast listener announcements + * @bat_priv: the bat priv with all the soft interface information + * @mcast_list: a list of addresses which are going to get added + * + * Adds multicast listener announcements from the given mcast_list to the + * translation table if they have not been added yet. + */ +static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv, + struct hlist_head *mcast_list) +{ + struct batadv_hw_addr *mcast_entry; + struct hlist_node *tmp; + + if (!mcast_list) + return; + + hlist_for_each_entry_safe(mcast_entry, tmp, mcast_list, list) { + if (batadv_mcast_mla_is_duplicate(mcast_entry->addr, + &bat_priv->mcast.mla_list)) + continue; + + if (!batadv_tt_local_add(bat_priv->soft_iface, + mcast_entry->addr, BATADV_NO_FLAGS, + BATADV_NULL_IFINDEX, BATADV_NO_MARK)) + continue; + + hlist_del(&mcast_entry->list); + hlist_add_head(&mcast_entry->list, &bat_priv->mcast.mla_list); + } +} + +/** + * batadv_mcast_has_bridge - check whether the soft-iface is bridged + * @bat_priv: the bat priv with all the soft interface information + * + * Checks whether there is a bridge on top of our soft interface. Returns + * true if so, false otherwise. + */ +static bool batadv_mcast_has_bridge(struct batadv_priv *bat_priv) +{ + struct net_device *upper = bat_priv->soft_iface; + + rcu_read_lock(); + do { + upper = netdev_master_upper_dev_get_rcu(upper); + } while (upper && !(upper->priv_flags & IFF_EBRIDGE)); + rcu_read_unlock(); + + return upper; +} + +/** + * batadv_mcast_mla_tvlv_update - update multicast tvlv + * @bat_priv: the bat priv with all the soft interface information + * + * Updates the own multicast tvlv with our current multicast related settings, + * capabilities and inabilities. + * + * Returns true if the tvlv container is registered afterwards. Otherwise + * returns false. + */ +static bool batadv_mcast_mla_tvlv_update(struct batadv_priv *bat_priv) +{ + struct batadv_tvlv_mcast_data mcast_data; + + mcast_data.flags = BATADV_NO_FLAGS; + memset(mcast_data.reserved, 0, sizeof(mcast_data.reserved)); + + /* Avoid attaching MLAs, if there is a bridge on top of our soft + * interface, we don't support that yet (TODO) + */ + if (batadv_mcast_has_bridge(bat_priv)) { + if (bat_priv->mcast.enabled) { + batadv_tvlv_container_unregister(bat_priv, + BATADV_TVLV_MCAST, 1); + bat_priv->mcast.enabled = false; + } + + return false; + } + + if (!bat_priv->mcast.enabled || + mcast_data.flags != bat_priv->mcast.flags) { + batadv_tvlv_container_register(bat_priv, BATADV_TVLV_MCAST, 1, + &mcast_data, sizeof(mcast_data)); + bat_priv->mcast.flags = mcast_data.flags; + bat_priv->mcast.enabled = true; + } + + return true; +} + +/** + * batadv_mcast_mla_update - update the own MLAs + * @bat_priv: the bat priv with all the soft interface information + * + * Updates the own multicast listener announcements in the translation + * table as well as the own, announced multicast tvlv container. + */ +void batadv_mcast_mla_update(struct batadv_priv *bat_priv) +{ + struct net_device *soft_iface = bat_priv->soft_iface; + struct hlist_head mcast_list = HLIST_HEAD_INIT; + int ret; + + if (!batadv_mcast_mla_tvlv_update(bat_priv)) + goto update; + + ret = batadv_mcast_mla_softif_get(soft_iface, &mcast_list); + if (ret < 0) + goto out; + +update: + batadv_mcast_mla_tt_retract(bat_priv, &mcast_list); + batadv_mcast_mla_tt_add(bat_priv, &mcast_list); + +out: + batadv_mcast_mla_list_free(&mcast_list); +} + +/** + * batadv_mcast_forw_mode_check_ipv4 - check for optimized forwarding potential + * @bat_priv: the bat priv with all the soft interface information + * @skb: the IPv4 packet to check + * @is_unsnoopable: stores whether the destination is snoopable + * + * Checks whether the given IPv4 packet has the potential to be forwarded with a + * mode more optimal than classic flooding. + * + * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM in case of + * memory allocation failure. + */ +static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv, + struct sk_buff *skb, + bool *is_unsnoopable) +{ + struct iphdr *iphdr; + + /* We might fail due to out-of-memory -> drop it */ + if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*iphdr))) + return -ENOMEM; + + iphdr = ip_hdr(skb); + + /* TODO: Implement Multicast Router Discovery (RFC4286), + * then allow scope > link local, too + */ + if (!ipv4_is_local_multicast(iphdr->daddr)) + return -EINVAL; + + /* link-local multicast listeners behind a bridge are + * not snoopable (see RFC4541, section 2.1.2.2) + */ + *is_unsnoopable = true; + + return 0; +} + +/** + * batadv_mcast_forw_mode_check_ipv6 - check for optimized forwarding potential + * @bat_priv: the bat priv with all the soft interface information + * @skb: the IPv6 packet to check + * @is_unsnoopable: stores whether the destination is snoopable + * + * Checks whether the given IPv6 packet has the potential to be forwarded with a + * mode more optimal than classic flooding. + * + * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM if we are out + * of memory. + */ +static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv, + struct sk_buff *skb, + bool *is_unsnoopable) +{ + struct ipv6hdr *ip6hdr; + + /* We might fail due to out-of-memory -> drop it */ + if (!pskb_may_pull(skb, sizeof(struct ethhdr) + sizeof(*ip6hdr))) + return -ENOMEM; + + ip6hdr = ipv6_hdr(skb); + + /* TODO: Implement Multicast Router Discovery (RFC4286), + * then allow scope > link local, too + */ + if (IPV6_ADDR_MC_SCOPE(&ip6hdr->daddr) != IPV6_ADDR_SCOPE_LINKLOCAL) + return -EINVAL; + + /* link-local-all-nodes multicast listeners behind a bridge are + * not snoopable (see RFC4541, section 3, paragraph 3) + */ + if (ipv6_addr_is_ll_all_nodes(&ip6hdr->daddr)) + *is_unsnoopable = true; + + return 0; +} + +/** + * batadv_mcast_forw_mode_check - check for optimized forwarding potential + * @bat_priv: the bat priv with all the soft interface information + * @skb: the multicast frame to check + * @is_unsnoopable: stores whether the destination is snoopable + * + * Checks whether the given multicast ethernet frame has the potential to be + * forwarded with a mode more optimal than classic flooding. + * + * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM if we are out + * of memory. + */ +static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv, + struct sk_buff *skb, + bool *is_unsnoopable) +{ + struct ethhdr *ethhdr = eth_hdr(skb); + + if (!atomic_read(&bat_priv->multicast_mode)) + return -EINVAL; + + if (atomic_read(&bat_priv->mcast.num_disabled)) + return -EINVAL; + + switch (ntohs(ethhdr->h_proto)) { + case ETH_P_IP: + return batadv_mcast_forw_mode_check_ipv4(bat_priv, skb, + is_unsnoopable); + case ETH_P_IPV6: + return batadv_mcast_forw_mode_check_ipv6(bat_priv, skb, + is_unsnoopable); + default: + return -EINVAL; + } +} + +/** + * batadv_mcast_want_all_ip_count - count nodes with unspecific mcast interest + * @bat_priv: the bat priv with all the soft interface information + * @ethhdr: ethernet header of a packet + * + * Returns the number of nodes which want all IPv4 multicast traffic if the + * given ethhdr is from an IPv4 packet or the number of nodes which want all + * IPv6 traffic if it matches an IPv6 packet. + */ +static int batadv_mcast_forw_want_all_ip_count(struct batadv_priv *bat_priv, + struct ethhdr *ethhdr) +{ + switch (ntohs(ethhdr->h_proto)) { + case ETH_P_IP: + return atomic_read(&bat_priv->mcast.num_want_all_ipv4); + case ETH_P_IPV6: + return atomic_read(&bat_priv->mcast.num_want_all_ipv6); + default: + /* we shouldn't be here... */ + return 0; + } +} + +/** + * batadv_mcast_forw_tt_node_get - get a multicast tt node + * @bat_priv: the bat priv with all the soft interface information + * @ethhdr: the ether header containing the multicast destination + * + * Returns an orig_node matching the multicast address provided by ethhdr + * via a translation table lookup. This increases the returned nodes refcount. + */ +static struct batadv_orig_node * +batadv_mcast_forw_tt_node_get(struct batadv_priv *bat_priv, + struct ethhdr *ethhdr) +{ + return batadv_transtable_search(bat_priv, ethhdr->h_source, + ethhdr->h_dest, BATADV_NO_FLAGS); +} + +/** + * batadv_mcast_want_forw_ipv4_node_get - get a node with an ipv4 flag + * @bat_priv: the bat priv with all the soft interface information + * + * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 flag set and + * increases its refcount. + */ +static struct batadv_orig_node * +batadv_mcast_forw_ipv4_node_get(struct batadv_priv *bat_priv) +{ + struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_orig_node, + &bat_priv->mcast.want_all_ipv4_list, + mcast_want_all_ipv4_node) { + if (!atomic_inc_not_zero(&orig_node->refcount)) + continue; + + orig_node = tmp_orig_node; + break; + } + rcu_read_unlock(); + + return orig_node; +} + +/** + * batadv_mcast_want_forw_ipv6_node_get - get a node with an ipv6 flag + * @bat_priv: the bat priv with all the soft interface information + * + * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV6 flag set + * and increases its refcount. + */ +static struct batadv_orig_node * +batadv_mcast_forw_ipv6_node_get(struct batadv_priv *bat_priv) +{ + struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_orig_node, + &bat_priv->mcast.want_all_ipv6_list, + mcast_want_all_ipv6_node) { + if (!atomic_inc_not_zero(&orig_node->refcount)) + continue; + + orig_node = tmp_orig_node; + break; + } + rcu_read_unlock(); + + return orig_node; +} + +/** + * batadv_mcast_want_forw_ip_node_get - get a node with an ipv4/ipv6 flag + * @bat_priv: the bat priv with all the soft interface information + * @ethhdr: an ethernet header to determine the protocol family from + * + * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 or + * BATADV_MCAST_WANT_ALL_IPV6 flag, depending on the provided ethhdr, set and + * increases its refcount. + */ +static struct batadv_orig_node * +batadv_mcast_forw_ip_node_get(struct batadv_priv *bat_priv, + struct ethhdr *ethhdr) +{ + switch (ntohs(ethhdr->h_proto)) { + case ETH_P_IP: + return batadv_mcast_forw_ipv4_node_get(bat_priv); + case ETH_P_IPV6: + return batadv_mcast_forw_ipv6_node_get(bat_priv); + default: + /* we shouldn't be here... */ + return NULL; + } +} + +/** + * batadv_mcast_want_forw_unsnoop_node_get - get a node with an unsnoopable flag + * @bat_priv: the bat priv with all the soft interface information + * + * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag + * set and increases its refcount. + */ +static struct batadv_orig_node * +batadv_mcast_forw_unsnoop_node_get(struct batadv_priv *bat_priv) +{ + struct batadv_orig_node *tmp_orig_node, *orig_node = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_orig_node, + &bat_priv->mcast.want_all_unsnoopables_list, + mcast_want_all_unsnoopables_node) { + if (!atomic_inc_not_zero(&orig_node->refcount)) + continue; + + orig_node = tmp_orig_node; + break; + } + rcu_read_unlock(); + + return orig_node; +} + +/** + * batadv_mcast_forw_mode - check on how to forward a multicast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: The multicast packet to check + * @orig: an originator to be set to forward the skb to + * + * Returns the forwarding mode as enum batadv_forw_mode and in case of + * BATADV_FORW_SINGLE set the orig to the single originator the skb + * should be forwarded to. + */ +enum batadv_forw_mode +batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, + struct batadv_orig_node **orig) +{ + int ret, tt_count, ip_count, unsnoop_count, total_count; + bool is_unsnoopable = false; + struct ethhdr *ethhdr; + + ret = batadv_mcast_forw_mode_check(bat_priv, skb, &is_unsnoopable); + if (ret == -ENOMEM) + return BATADV_FORW_NONE; + else if (ret < 0) + return BATADV_FORW_ALL; + + ethhdr = eth_hdr(skb); + + tt_count = batadv_tt_global_hash_count(bat_priv, ethhdr->h_dest, + BATADV_NO_FLAGS); + ip_count = batadv_mcast_forw_want_all_ip_count(bat_priv, ethhdr); + unsnoop_count = !is_unsnoopable ? 0 : + atomic_read(&bat_priv->mcast.num_want_all_unsnoopables); + + total_count = tt_count + ip_count + unsnoop_count; + + switch (total_count) { + case 1: + if (tt_count) + *orig = batadv_mcast_forw_tt_node_get(bat_priv, ethhdr); + else if (ip_count) + *orig = batadv_mcast_forw_ip_node_get(bat_priv, ethhdr); + else if (unsnoop_count) + *orig = batadv_mcast_forw_unsnoop_node_get(bat_priv); + + if (*orig) + return BATADV_FORW_SINGLE; + + /* fall through */ + case 0: + return BATADV_FORW_NONE; + default: + return BATADV_FORW_ALL; + } +} + +/** + * batadv_mcast_want_unsnoop_update - update unsnoop counter and list + * @bat_priv: the bat priv with all the soft interface information + * @orig: the orig_node which multicast state might have changed of + * @mcast_flags: flags indicating the new multicast state + * + * If the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag of this originator, + * orig, has toggled then this method updates counter and list accordingly. + */ +static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig, + uint8_t mcast_flags) +{ + /* switched from flag unset to set */ + if (mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES && + !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)) { + atomic_inc(&bat_priv->mcast.num_want_all_unsnoopables); + + spin_lock_bh(&bat_priv->mcast.want_lists_lock); + hlist_add_head_rcu(&orig->mcast_want_all_unsnoopables_node, + &bat_priv->mcast.want_all_unsnoopables_list); + spin_unlock_bh(&bat_priv->mcast.want_lists_lock); + /* switched from flag set to unset */ + } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) && + orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) { + atomic_dec(&bat_priv->mcast.num_want_all_unsnoopables); + + spin_lock_bh(&bat_priv->mcast.want_lists_lock); + hlist_del_rcu(&orig->mcast_want_all_unsnoopables_node); + spin_unlock_bh(&bat_priv->mcast.want_lists_lock); + } +} + +/** + * batadv_mcast_want_ipv4_update - update want-all-ipv4 counter and list + * @bat_priv: the bat priv with all the soft interface information + * @orig: the orig_node which multicast state might have changed of + * @mcast_flags: flags indicating the new multicast state + * + * If the BATADV_MCAST_WANT_ALL_IPV4 flag of this originator, orig, has + * toggled then this method updates counter and list accordingly. + */ +static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig, + uint8_t mcast_flags) +{ + /* switched from flag unset to set */ + if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV4 && + !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4)) { + atomic_inc(&bat_priv->mcast.num_want_all_ipv4); + + spin_lock_bh(&bat_priv->mcast.want_lists_lock); + hlist_add_head_rcu(&orig->mcast_want_all_ipv4_node, + &bat_priv->mcast.want_all_ipv4_list); + spin_unlock_bh(&bat_priv->mcast.want_lists_lock); + /* switched from flag set to unset */ + } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) && + orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) { + atomic_dec(&bat_priv->mcast.num_want_all_ipv4); + + spin_lock_bh(&bat_priv->mcast.want_lists_lock); + hlist_del_rcu(&orig->mcast_want_all_ipv4_node); + spin_unlock_bh(&bat_priv->mcast.want_lists_lock); + } +} + +/** + * batadv_mcast_want_ipv6_update - update want-all-ipv6 counter and list + * @bat_priv: the bat priv with all the soft interface information + * @orig: the orig_node which multicast state might have changed of + * @mcast_flags: flags indicating the new multicast state + * + * If the BATADV_MCAST_WANT_ALL_IPV6 flag of this originator, orig, has + * toggled then this method updates counter and list accordingly. + */ +static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig, + uint8_t mcast_flags) +{ + /* switched from flag unset to set */ + if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV6 && + !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6)) { + atomic_inc(&bat_priv->mcast.num_want_all_ipv6); + + spin_lock_bh(&bat_priv->mcast.want_lists_lock); + hlist_add_head_rcu(&orig->mcast_want_all_ipv6_node, + &bat_priv->mcast.want_all_ipv6_list); + spin_unlock_bh(&bat_priv->mcast.want_lists_lock); + /* switched from flag set to unset */ + } else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) && + orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) { + atomic_dec(&bat_priv->mcast.num_want_all_ipv6); + + spin_lock_bh(&bat_priv->mcast.want_lists_lock); + hlist_del_rcu(&orig->mcast_want_all_ipv6_node); + spin_unlock_bh(&bat_priv->mcast.want_lists_lock); + } +} + +/** + * batadv_mcast_tvlv_ogm_handler_v1 - process incoming multicast tvlv container + * @bat_priv: the bat priv with all the soft interface information + * @orig: the orig_node of the ogm + * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags) + * @tvlv_value: tvlv buffer containing the multicast data + * @tvlv_value_len: tvlv buffer length + */ +static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig, + uint8_t flags, + void *tvlv_value, + uint16_t tvlv_value_len) +{ + bool orig_mcast_enabled = !(flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND); + uint8_t mcast_flags = BATADV_NO_FLAGS; + bool orig_initialized; + + orig_initialized = orig->capa_initialized & BATADV_ORIG_CAPA_HAS_MCAST; + + /* If mcast support is turned on decrease the disabled mcast node + * counter only if we had increased it for this node before. If this + * is a completely new orig_node no need to decrease the counter. + */ + if (orig_mcast_enabled && + !(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST)) { + if (orig_initialized) + atomic_dec(&bat_priv->mcast.num_disabled); + orig->capabilities |= BATADV_ORIG_CAPA_HAS_MCAST; + /* If mcast support is being switched off increase the disabled + * mcast node counter. + */ + } else if (!orig_mcast_enabled && + orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST) { + atomic_inc(&bat_priv->mcast.num_disabled); + orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_MCAST; + } + + orig->capa_initialized |= BATADV_ORIG_CAPA_HAS_MCAST; + + if (orig_mcast_enabled && tvlv_value && + (tvlv_value_len >= sizeof(mcast_flags))) + mcast_flags = *(uint8_t *)tvlv_value; + + batadv_mcast_want_unsnoop_update(bat_priv, orig, mcast_flags); + batadv_mcast_want_ipv4_update(bat_priv, orig, mcast_flags); + batadv_mcast_want_ipv6_update(bat_priv, orig, mcast_flags); + + orig->mcast_flags = mcast_flags; +} + +/** + * batadv_mcast_init - initialize the multicast optimizations structures + * @bat_priv: the bat priv with all the soft interface information + */ +void batadv_mcast_init(struct batadv_priv *bat_priv) +{ + batadv_tvlv_handler_register(bat_priv, batadv_mcast_tvlv_ogm_handler_v1, + NULL, BATADV_TVLV_MCAST, 1, + BATADV_TVLV_HANDLER_OGM_CIFNOTFND); +} + +/** + * batadv_mcast_free - free the multicast optimizations structures + * @bat_priv: the bat priv with all the soft interface information + */ +void batadv_mcast_free(struct batadv_priv *bat_priv) +{ + batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 1); + batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 1); + + batadv_mcast_mla_tt_retract(bat_priv, NULL); +} + +/** + * batadv_mcast_purge_orig - reset originator global mcast state modifications + * @orig: the originator which is going to get purged + */ +void batadv_mcast_purge_orig(struct batadv_orig_node *orig) +{ + struct batadv_priv *bat_priv = orig->bat_priv; + + if (!(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST)) + atomic_dec(&bat_priv->mcast.num_disabled); + + batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS); + batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS); + batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS); +} diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h new file mode 100644 index 000000000000..73b5d45819c1 --- /dev/null +++ b/net/batman-adv/multicast.h @@ -0,0 +1,80 @@ +/* Copyright (C) 2014 B.A.T.M.A.N. contributors: + * + * Linus Lüssing + * + * 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. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _NET_BATMAN_ADV_MULTICAST_H_ +#define _NET_BATMAN_ADV_MULTICAST_H_ + +/** + * batadv_forw_mode - the way a packet should be forwarded as + * @BATADV_FORW_ALL: forward the packet to all nodes (currently via classic + * flooding) + * @BATADV_FORW_SINGLE: forward the packet to a single node (currently via the + * BATMAN unicast routing protocol) + * @BATADV_FORW_NONE: don't forward, drop it + */ +enum batadv_forw_mode { + BATADV_FORW_ALL, + BATADV_FORW_SINGLE, + BATADV_FORW_NONE, +}; + +#ifdef CONFIG_BATMAN_ADV_MCAST + +void batadv_mcast_mla_update(struct batadv_priv *bat_priv); + +enum batadv_forw_mode +batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, + struct batadv_orig_node **mcast_single_orig); + +void batadv_mcast_init(struct batadv_priv *bat_priv); + +void batadv_mcast_free(struct batadv_priv *bat_priv); + +void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node); + +#else + +static inline void batadv_mcast_mla_update(struct batadv_priv *bat_priv) +{ + return; +} + +static inline enum batadv_forw_mode +batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, + struct batadv_orig_node **mcast_single_orig) +{ + return BATADV_FORW_ALL; +} + +static inline int batadv_mcast_init(struct batadv_priv *bat_priv) +{ + return 0; +} + +static inline void batadv_mcast_free(struct batadv_priv *bat_priv) +{ + return; +} + +static inline void batadv_mcast_purge_orig(struct batadv_orig_node *orig_node) +{ + return; +} + +#endif /* CONFIG_BATMAN_ADV_MCAST */ + +#endif /* _NET_BATMAN_ADV_MULTICAST_H_ */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index f1b604d88dc3..a9546fe541eb 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -819,7 +819,7 @@ static struct batadv_nc_node /* Initialize nc_node */ INIT_LIST_HEAD(&nc_node->list); - memcpy(nc_node->addr, orig_node->orig, ETH_ALEN); + ether_addr_copy(nc_node->addr, orig_node->orig); nc_node->orig_node = orig_neigh_node; atomic_set(&nc_node->refcount, 2); @@ -941,8 +941,8 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, spin_lock_init(&nc_path->packet_list_lock); atomic_set(&nc_path->refcount, 2); nc_path->last_valid = jiffies; - memcpy(nc_path->next_hop, dst, ETH_ALEN); - memcpy(nc_path->prev_hop, src, ETH_ALEN); + ether_addr_copy(nc_path->next_hop, dst); + ether_addr_copy(nc_path->prev_hop, src); batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_path %pM -> %pM\n", nc_path->prev_hop, @@ -1114,15 +1114,15 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, coded_packet->ttl = packet1->ttl; /* Info about first unicast packet */ - memcpy(coded_packet->first_source, first_source, ETH_ALEN); - memcpy(coded_packet->first_orig_dest, packet1->dest, ETH_ALEN); + ether_addr_copy(coded_packet->first_source, first_source); + ether_addr_copy(coded_packet->first_orig_dest, packet1->dest); coded_packet->first_crc = packet_id1; coded_packet->first_ttvn = packet1->ttvn; /* Info about second unicast packet */ - memcpy(coded_packet->second_dest, second_dest, ETH_ALEN); - memcpy(coded_packet->second_source, second_source, ETH_ALEN); - memcpy(coded_packet->second_orig_dest, packet2->dest, ETH_ALEN); + ether_addr_copy(coded_packet->second_dest, second_dest); + ether_addr_copy(coded_packet->second_source, second_source); + ether_addr_copy(coded_packet->second_orig_dest, packet2->dest); coded_packet->second_crc = packet_id2; coded_packet->second_ttl = packet2->ttl; coded_packet->second_ttvn = packet2->ttvn; @@ -1349,8 +1349,8 @@ static void batadv_nc_skb_store_before_coding(struct batadv_priv *bat_priv, /* Set the mac header as if we actually sent the packet uncoded */ ethhdr = eth_hdr(skb); - memcpy(ethhdr->h_source, ethhdr->h_dest, ETH_ALEN); - memcpy(ethhdr->h_dest, eth_dst_new, ETH_ALEN); + ether_addr_copy(ethhdr->h_source, ethhdr->h_dest); + ether_addr_copy(ethhdr->h_dest, eth_dst_new); /* Set data pointer to MAC header to mimic packets from our tx path */ skb_push(skb, ETH_HLEN); @@ -1636,7 +1636,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, /* Reconstruct original mac header */ ethhdr = eth_hdr(skb); - memcpy(ethhdr, ðhdr_tmp, sizeof(*ethhdr)); + *ethhdr = ethhdr_tmp; /* Select the correct unicast header information based on the location * of our mac address in the coded_packet header @@ -1646,7 +1646,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, * so the Ethernet address must be copied to h_dest and * pkt_type changed from PACKET_OTHERHOST to PACKET_HOST */ - memcpy(ethhdr->h_dest, coded_packet_tmp.second_dest, ETH_ALEN); + ether_addr_copy(ethhdr->h_dest, coded_packet_tmp.second_dest); skb->pkt_type = PACKET_HOST; orig_dest = coded_packet_tmp.second_orig_dest; @@ -1682,7 +1682,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unicast_packet->packet_type = BATADV_UNICAST; unicast_packet->version = BATADV_COMPAT_VERSION; unicast_packet->ttl = ttl; - memcpy(unicast_packet->dest, orig_dest, ETH_ALEN); + ether_addr_copy(unicast_packet->dest, orig_dest); unicast_packet->ttvn = ttvn; batadv_nc_packet_free(nc_packet); diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 853941629dc1..ffd9dfbd9b0e 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -27,6 +27,7 @@ #include "bridge_loop_avoidance.h" #include "network-coding.h" #include "fragmentation.h" +#include "multicast.h" /* hash class keys */ static struct lock_class_key batadv_orig_hash_lock_class_key; @@ -446,7 +447,7 @@ batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, INIT_HLIST_HEAD(&neigh_node->ifinfo_list); spin_lock_init(&neigh_node->ifinfo_lock); - memcpy(neigh_node->addr, neigh_addr, ETH_ALEN); + ether_addr_copy(neigh_node->addr, neigh_addr); neigh_node->if_incoming = hard_iface; neigh_node->orig_node = orig_node; @@ -557,6 +558,8 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) } spin_unlock_bh(&orig_node->neigh_list_lock); + batadv_mcast_purge_orig(orig_node); + /* Free nc_nodes */ batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); @@ -664,15 +667,17 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, /* extra reference for return */ atomic_set(&orig_node->refcount, 2); - orig_node->tt_initialised = false; orig_node->bat_priv = bat_priv; - memcpy(orig_node->orig, addr, ETH_ALEN); + ether_addr_copy(orig_node->orig, addr); batadv_dat_init_orig_node_addr(orig_node); atomic_set(&orig_node->last_ttvn, 0); orig_node->tt_buff = NULL; orig_node->tt_buff_len = 0; reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); orig_node->bcast_seqno_reset = reset_time; +#ifdef CONFIG_BATMAN_ADV_MCAST + orig_node->mcast_flags = BATADV_NO_FLAGS; +#endif /* create a vlan object for the "untagged" LAN */ vlan = batadv_orig_node_vlan_new(orig_node, BATADV_NO_FLAGS); diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 0a381d1174c1..34e096d2dce1 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -89,6 +89,19 @@ enum batadv_icmp_packettype { BATADV_PARAMETER_PROBLEM = 12, }; +/** + * enum batadv_mcast_flags - flags for multicast capabilities and settings + * @BATADV_MCAST_WANT_ALL_UNSNOOPABLES: we want all packets destined for + * 224.0.0.0/24 or ff02::1 + * @BATADV_MCAST_WANT_ALL_IPV4: we want all IPv4 multicast packets + * @BATADV_MCAST_WANT_ALL_IPV6: we want all IPv6 multicast packets + */ +enum batadv_mcast_flags { + BATADV_MCAST_WANT_ALL_UNSNOOPABLES = BIT(0), + BATADV_MCAST_WANT_ALL_IPV4 = BIT(1), + BATADV_MCAST_WANT_ALL_IPV6 = BIT(2), +}; + /* tt data subtypes */ #define BATADV_TT_DATA_TYPE_MASK 0x0F @@ -106,10 +119,30 @@ enum batadv_tt_data_flags { BATADV_TT_FULL_TABLE = BIT(4), }; -/* BATADV_TT_CLIENT flags. - * Flags from BIT(0) to BIT(7) are sent on the wire, while flags from BIT(8) to - * BIT(15) are used for local computation only. - * Flags from BIT(4) to BIT(7) are kept in sync with the rest of the network. +/** + * enum batadv_tt_client_flags - TT client specific flags + * @BATADV_TT_CLIENT_DEL: the client has to be deleted from the table + * @BATADV_TT_CLIENT_ROAM: the client roamed to/from another node and the new + * update telling its new real location has not been received/sent yet + * @BATADV_TT_CLIENT_WIFI: this client is connected through a wifi interface. + * This information is used by the "AP Isolation" feature + * @BATADV_TT_CLIENT_ISOLA: this client is considered "isolated". This + * information is used by the Extended Isolation feature + * @BATADV_TT_CLIENT_NOPURGE: this client should never be removed from the table + * @BATADV_TT_CLIENT_NEW: this client has been added to the local table but has + * not been announced yet + * @BATADV_TT_CLIENT_PENDING: this client is marked for removal but it is kept + * in the table for one more originator interval for consistency purposes + * @BATADV_TT_CLIENT_TEMP: this global client has been detected to be part of + * the network but no nnode has already announced it + * + * Bits from 0 to 7 are called _remote flags_ because they are sent on the wire. + * Bits from 8 to 15 are called _local flags_ because they are used for local + * computations only. + * + * Bits from 4 to 7 - a subset of remote flags - are ensured to be in sync with + * the other nodes in the network. To achieve this goal these flags are included + * in the TT CRC computation. */ enum batadv_tt_client_flags { BATADV_TT_CLIENT_DEL = BIT(0), @@ -145,6 +178,7 @@ enum batadv_bla_claimframe { * @BATADV_TVLV_NC: network coding tvlv * @BATADV_TVLV_TT: translation table tvlv * @BATADV_TVLV_ROAM: roaming advertisement tvlv + * @BATADV_TVLV_MCAST: multicast capability tvlv */ enum batadv_tvlv_type { BATADV_TVLV_GW = 0x01, @@ -152,6 +186,7 @@ enum batadv_tvlv_type { BATADV_TVLV_NC = 0x03, BATADV_TVLV_TT = 0x04, BATADV_TVLV_ROAM = 0x05, + BATADV_TVLV_MCAST = 0x06, }; #pragma pack(2) @@ -504,4 +539,14 @@ struct batadv_tvlv_roam_adv { __be16 vid; }; +/** + * struct batadv_tvlv_mcast_data - payload of a multicast tvlv + * @flags: multicast flags announced by the orig node + * @reserved: reserved field + */ +struct batadv_tvlv_mcast_data { + uint8_t flags; + uint8_t reserved[3]; +}; + #endif /* _NET_BATMAN_ADV_PACKET_H_ */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index a953d5b196a3..35141534938e 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -222,8 +222,8 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv, icmph = (struct batadv_icmp_header *)skb->data; - memcpy(icmph->dst, icmph->orig, ETH_ALEN); - memcpy(icmph->orig, primary_if->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(icmph->dst, icmph->orig); + ether_addr_copy(icmph->orig, primary_if->net_dev->dev_addr); icmph->msg_type = BATADV_ECHO_REPLY; icmph->ttl = BATADV_TTL; @@ -276,9 +276,8 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv, icmp_packet = (struct batadv_icmp_packet *)skb->data; - memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN); - memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr, - ETH_ALEN); + ether_addr_copy(icmp_packet->dst, icmp_packet->orig); + ether_addr_copy(icmp_packet->orig, primary_if->net_dev->dev_addr); icmp_packet->msg_type = BATADV_TTL_EXCEEDED; icmp_packet->ttl = BATADV_TTL; @@ -341,8 +340,8 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, if (icmp_packet_rr->rr_cur >= BATADV_RR_LEN) goto out; - memcpy(&(icmp_packet_rr->rr[icmp_packet_rr->rr_cur]), - ethhdr->h_dest, ETH_ALEN); + ether_addr_copy(icmp_packet_rr->rr[icmp_packet_rr->rr_cur], + ethhdr->h_dest); icmp_packet_rr->rr_cur++; } @@ -664,7 +663,7 @@ batadv_reroute_unicast_packet(struct batadv_priv *bat_priv, } /* update the packet header */ - memcpy(unicast_packet->dest, orig_addr, ETH_ALEN); + ether_addr_copy(unicast_packet->dest, orig_addr); unicast_packet->ttvn = orig_ttvn; ret = true; @@ -774,7 +773,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, if (!primary_if) return 0; - memcpy(unicast_packet->dest, primary_if->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(unicast_packet->dest, primary_if->net_dev->dev_addr); batadv_hardif_free_ref(primary_if); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 843febd1e519..3d64ed20c393 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -27,6 +27,7 @@ #include "originator.h" #include "network-coding.h" #include "fragmentation.h" +#include "multicast.h" static void batadv_send_outstanding_bcast_packet(struct work_struct *work); @@ -59,8 +60,8 @@ int batadv_send_skb_packet(struct sk_buff *skb, skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); - memcpy(ethhdr->h_source, hard_iface->net_dev->dev_addr, ETH_ALEN); - memcpy(ethhdr->h_dest, dst_addr, ETH_ALEN); + ether_addr_copy(ethhdr->h_source, hard_iface->net_dev->dev_addr); + ether_addr_copy(ethhdr->h_dest, dst_addr); ethhdr->h_proto = htons(ETH_P_BATMAN); skb_set_network_header(skb, ETH_HLEN); @@ -165,7 +166,7 @@ batadv_send_skb_push_fill_unicast(struct sk_buff *skb, int hdr_size, /* set unicast ttl */ unicast_packet->ttl = BATADV_TTL; /* copy the destination for faster routing */ - memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN); + ether_addr_copy(unicast_packet->dest, orig_node->orig); /* set the destination tt version number */ unicast_packet->ttvn = ttvn; @@ -220,7 +221,7 @@ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv, uc_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; uc_4addr_packet->u.packet_type = BATADV_UNICAST_4ADDR; - memcpy(uc_4addr_packet->src, primary_if->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(uc_4addr_packet->src, primary_if->net_dev->dev_addr); uc_4addr_packet->subtype = packet_subtype; uc_4addr_packet->reserved = 0; @@ -248,15 +249,15 @@ out: * * Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ -static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, - struct sk_buff *skb, int packet_type, - int packet_subtype, - struct batadv_orig_node *orig_node, - unsigned short vid) +int batadv_send_skb_unicast(struct batadv_priv *bat_priv, + struct sk_buff *skb, int packet_type, + int packet_subtype, + struct batadv_orig_node *orig_node, + unsigned short vid) { struct ethhdr *ethhdr; struct batadv_unicast_packet *unicast_packet; - int ret = NET_XMIT_DROP, hdr_size; + int ret = NET_XMIT_DROP; if (!orig_node) goto out; @@ -265,16 +266,12 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, case BATADV_UNICAST: if (!batadv_send_skb_prepare_unicast(skb, orig_node)) goto out; - - hdr_size = sizeof(*unicast_packet); break; case BATADV_UNICAST_4ADDR: if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb, orig_node, packet_subtype)) goto out; - - hdr_size = sizeof(struct batadv_unicast_4addr_packet); break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It @@ -283,7 +280,10 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, goto out; } - ethhdr = (struct ethhdr *)(skb->data + hdr_size); + /* skb->data might have been reallocated by + * batadv_send_skb_prepare_unicast{,_4addr}() + */ + ethhdr = eth_hdr(skb); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route @@ -312,6 +312,7 @@ out: * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) + * @dst_hint: can be used to override the destination contained in the skb * @vid: the vid to be used to search the translation table * * Look up the recipient node for the destination address in the ethernet diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index aaddaa9661ce..38d0ec1833ae 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -36,6 +36,11 @@ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node *orig_node, int packet_subtype); +int batadv_send_skb_unicast(struct batadv_priv *bat_priv, + struct sk_buff *skb, int packet_type, + int packet_subtype, + struct batadv_orig_node *orig_node, + unsigned short vid); int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, uint8_t *dst_hint, @@ -47,6 +52,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, * batadv_send_skb_via_tt - send an skb via TT lookup * @bat_priv: the bat priv with all the soft interface information * @skb: the payload to send + * @dst_hint: can be used to override the destination contained in the skb * @vid: the vid to be used to search the translation table * * Look up the recipient node for the destination address in the ethernet @@ -68,6 +74,7 @@ static inline int batadv_send_skb_via_tt(struct batadv_priv *bat_priv, * @bat_priv: the bat priv with all the soft interface information * @skb: the payload to send * @packet_subtype: the unicast 4addr packet subtype to use + * @dst_hint: can be used to override the destination contained in the skb * @vid: the vid to be used to search the translation table * * Look up the recipient node for the destination address in the ethernet diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index f82c267e1886..744a59b85e15 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -32,6 +32,7 @@ #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/if_vlan.h> +#include "multicast.h" #include "bridge_loop_avoidance.h" #include "network-coding.h" @@ -111,8 +112,8 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - memcpy(old_addr, dev->dev_addr, ETH_ALEN); - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); + ether_addr_copy(old_addr, dev->dev_addr); + ether_addr_copy(dev->dev_addr, addr->sa_data); /* only modify transtable if it has been initialized before */ if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE) { @@ -170,17 +171,19 @@ static int batadv_interface_tx(struct sk_buff *skb, unsigned short vid; uint32_t seqno; int gw_mode; + enum batadv_forw_mode forw_mode; + struct batadv_orig_node *mcast_single_orig = NULL; if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto dropped; soft_iface->trans_start = jiffies; vid = batadv_get_vid(skb, 0); - ethhdr = (struct ethhdr *)skb->data; + ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { case ETH_P_8021Q: - vhdr = (struct vlan_ethhdr *)skb->data; + vhdr = vlan_eth_hdr(skb); if (vhdr->h_vlan_encapsulated_proto != ethertype) break; @@ -194,7 +197,7 @@ static int batadv_interface_tx(struct sk_buff *skb, goto dropped; /* skb->data might have been reallocated by batadv_bla_tx() */ - ethhdr = (struct ethhdr *)skb->data; + ethhdr = eth_hdr(skb); /* Register the client MAC in the transtable */ if (!is_multicast_ether_addr(ethhdr->h_source)) { @@ -230,7 +233,7 @@ static int batadv_interface_tx(struct sk_buff *skb, /* skb->data may have been modified by * batadv_gw_dhcp_recipient_get() */ - ethhdr = (struct ethhdr *)skb->data; + ethhdr = eth_hdr(skb); /* if gw_mode is on, broadcast any non-DHCP message. * All the DHCP packets are going to be sent as unicast */ @@ -247,9 +250,19 @@ static int batadv_interface_tx(struct sk_buff *skb, * directed to a DHCP server */ goto dropped; - } send: + if (do_bcast && !is_broadcast_ether_addr(ethhdr->h_dest)) { + forw_mode = batadv_mcast_forw_mode(bat_priv, skb, + &mcast_single_orig); + if (forw_mode == BATADV_FORW_NONE) + goto dropped; + + if (forw_mode == BATADV_FORW_SINGLE) + do_bcast = false; + } + } + batadv_skb_set_priority(skb, 0); /* ethernet packet should be broadcasted */ @@ -279,8 +292,8 @@ send: /* hw address of first interface is the orig mac because only * this mac is known throughout the mesh */ - memcpy(bcast_packet->orig, - primary_if->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(bcast_packet->orig, + primary_if->net_dev->dev_addr); /* set broadcast sequence number */ seqno = atomic_inc_return(&bat_priv->bcast_seqno); @@ -301,6 +314,10 @@ send: if (ret) goto dropped; ret = batadv_send_skb_via_gw(bat_priv, skb, vid); + } else if (mcast_single_orig) { + ret = batadv_send_skb_unicast(bat_priv, skb, + BATADV_UNICAST, 0, + mcast_single_orig, vid); } else { if (batadv_dat_snoop_outgoing_arp_request(bat_priv, skb)) @@ -652,10 +669,7 @@ static void batadv_softif_destroy_finish(struct work_struct *work) } batadv_sysfs_del_meshif(soft_iface); - - rtnl_lock(); - unregister_netdevice(soft_iface); - rtnl_unlock(); + unregister_netdev(soft_iface); } /** @@ -692,6 +706,14 @@ static int batadv_softif_init_late(struct net_device *dev) #ifdef CONFIG_BATMAN_ADV_DAT atomic_set(&bat_priv->distributed_arp_table, 1); #endif +#ifdef CONFIG_BATMAN_ADV_MCAST + bat_priv->mcast.flags = BATADV_NO_FLAGS; + atomic_set(&bat_priv->multicast_mode, 1); + atomic_set(&bat_priv->mcast.num_disabled, 0); + atomic_set(&bat_priv->mcast.num_want_all_unsnoopables, 0); + atomic_set(&bat_priv->mcast.num_want_all_ipv4, 0); + atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0); +#endif atomic_set(&bat_priv->gw_mode, BATADV_GW_MODE_OFF); atomic_set(&bat_priv->gw_sel_class, 20); atomic_set(&bat_priv->gw.bandwidth_down, 100); diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index e456bf6bb284..1ebb0d9e2ea5 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -539,6 +539,9 @@ BATADV_ATTR_SIF_UINT(gw_sel_class, S_IRUGO | S_IWUSR, 1, BATADV_TQ_MAX_VALUE, batadv_post_gw_reselect); static BATADV_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, batadv_show_gw_bwidth, batadv_store_gw_bwidth); +#ifdef CONFIG_BATMAN_ADV_MCAST +BATADV_ATTR_SIF_BOOL(multicast_mode, S_IRUGO | S_IWUSR, NULL); +#endif #ifdef CONFIG_BATMAN_ADV_DEBUG BATADV_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, BATADV_DBG_ALL, NULL); #endif @@ -558,6 +561,9 @@ static struct batadv_attribute *batadv_mesh_attrs[] = { #ifdef CONFIG_BATMAN_ADV_DAT &batadv_attr_distributed_arp_table, #endif +#ifdef CONFIG_BATMAN_ADV_MCAST + &batadv_attr_multicast_mode, +#endif &batadv_attr_fragmentation, &batadv_attr_routing_algo, &batadv_attr_gw_mode, diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 959dde721c46..d636bde72c9a 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -24,6 +24,7 @@ #include "originator.h" #include "routing.h" #include "bridge_loop_avoidance.h" +#include "multicast.h" #include <linux/crc32c.h> @@ -96,7 +97,7 @@ batadv_tt_hash_find(struct batadv_hashtable *hash, const uint8_t *addr, if (!hash) return NULL; - memcpy(to_search.addr, addr, ETH_ALEN); + ether_addr_copy(to_search.addr, addr); to_search.vid = vid; index = batadv_choose_tt(&to_search, hash->size); @@ -192,6 +193,31 @@ batadv_tt_global_entry_free_ref(struct batadv_tt_global_entry *tt_global_entry) } } +/** + * batadv_tt_global_hash_count - count the number of orig entries + * @hash: hash table containing the tt entries + * @addr: the mac address of the client to count entries for + * @vid: VLAN identifier + * + * Return the number of originators advertising the given address/data + * (excluding ourself). + */ +int batadv_tt_global_hash_count(struct batadv_priv *bat_priv, + const uint8_t *addr, unsigned short vid) +{ + struct batadv_tt_global_entry *tt_global_entry; + int count; + + tt_global_entry = batadv_tt_global_hash_find(bat_priv, addr, vid); + if (!tt_global_entry) + return 0; + + count = atomic_read(&tt_global_entry->orig_list_count); + batadv_tt_global_entry_free_ref(tt_global_entry); + + return count; +} + static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu) { struct batadv_tt_orig_list_entry *orig_entry; @@ -333,7 +359,7 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv, tt_change_node->change.flags = flags; memset(tt_change_node->change.reserved, 0, sizeof(tt_change_node->change.reserved)); - memcpy(tt_change_node->change.addr, common->addr, ETH_ALEN); + ether_addr_copy(tt_change_node->change.addr, common->addr); tt_change_node->change.vid = htons(common->vid); del_op_requested = flags & BATADV_TT_CLIENT_DEL; @@ -484,7 +510,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, { struct batadv_priv *bat_priv = netdev_priv(soft_iface); struct batadv_tt_local_entry *tt_local; - struct batadv_tt_global_entry *tt_global; + struct batadv_tt_global_entry *tt_global = NULL; struct net_device *in_dev = NULL; struct hlist_head *head; struct batadv_tt_orig_list_entry *orig_entry; @@ -497,7 +523,9 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, in_dev = dev_get_by_index(&init_net, ifindex); tt_local = batadv_tt_local_hash_find(bat_priv, addr, vid); - tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid); + + if (!is_multicast_ether_addr(addr)) + tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid); if (tt_local) { tt_local->last_seen = jiffies; @@ -549,7 +577,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, addr, BATADV_PRINT_VID(vid), (uint8_t)atomic_read(&bat_priv->tt.vn)); - memcpy(tt_local->common.addr, addr, ETH_ALEN); + ether_addr_copy(tt_local->common.addr, addr); /* The local entry has to be marked as NEW to avoid to send it in * a full table response going out before the next ttvn increment * (consistency check) @@ -562,8 +590,11 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, tt_local->last_seen = jiffies; tt_local->common.added_at = tt_local->last_seen; - /* the batman interface mac address should never be purged */ - if (batadv_compare_eth(addr, soft_iface->dev_addr)) + /* the batman interface mac and multicast addresses should never be + * purged + */ + if (batadv_compare_eth(addr, soft_iface->dev_addr) || + is_multicast_ether_addr(addr)) tt_local->common.flags |= BATADV_TT_CLIENT_NOPURGE; hash_added = batadv_hash_add(bat_priv->tt.local_hash, batadv_compare_tt, @@ -1219,6 +1250,8 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global, hlist_add_head_rcu(&orig_entry->list, &tt_global->orig_list); spin_unlock_bh(&tt_global->list_lock); + atomic_inc(&tt_global->orig_list_count); + out: if (orig_entry) batadv_tt_orig_list_entry_free_ref(orig_entry); @@ -1277,7 +1310,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, goto out; common = &tt_global_entry->common; - memcpy(common->addr, tt_addr, ETH_ALEN); + ether_addr_copy(common->addr, tt_addr); common->vid = vid; common->flags = flags; @@ -1292,6 +1325,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, common->added_at = jiffies; INIT_HLIST_HEAD(&tt_global_entry->orig_list); + atomic_set(&tt_global_entry->orig_list_count, 0); spin_lock_init(&tt_global_entry->list_lock); hash_added = batadv_hash_add(bat_priv->tt.global_hash, @@ -1361,6 +1395,11 @@ add_orig_entry: ret = true; out_remove: + /* Do not remove multicast addresses from the local hash on + * global additions + */ + if (is_multicast_ether_addr(tt_addr)) + goto out; /* remove address from local hash if present */ local_flags = batadv_tt_local_remove(bat_priv, tt_addr, vid, @@ -1552,6 +1591,25 @@ out: return 0; } +/** + * batadv_tt_global_del_orig_entry - remove and free an orig_entry + * @tt_global_entry: the global entry to remove the orig_entry from + * @orig_entry: the orig entry to remove and free + * + * Remove an orig_entry from its list in the given tt_global_entry and + * free this orig_entry afterwards. + */ +static void +batadv_tt_global_del_orig_entry(struct batadv_tt_global_entry *tt_global_entry, + struct batadv_tt_orig_list_entry *orig_entry) +{ + batadv_tt_global_size_dec(orig_entry->orig_node, + tt_global_entry->common.vid); + atomic_dec(&tt_global_entry->orig_list_count); + hlist_del_rcu(&orig_entry->list); + batadv_tt_orig_list_entry_free_ref(orig_entry); +} + /* deletes the orig list of a tt_global_entry */ static void batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry) @@ -1562,20 +1620,26 @@ batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry) spin_lock_bh(&tt_global_entry->list_lock); head = &tt_global_entry->orig_list; - hlist_for_each_entry_safe(orig_entry, safe, head, list) { - hlist_del_rcu(&orig_entry->list); - batadv_tt_global_size_dec(orig_entry->orig_node, - tt_global_entry->common.vid); - batadv_tt_orig_list_entry_free_ref(orig_entry); - } + hlist_for_each_entry_safe(orig_entry, safe, head, list) + batadv_tt_global_del_orig_entry(tt_global_entry, orig_entry); spin_unlock_bh(&tt_global_entry->list_lock); } +/** + * batadv_tt_global_del_orig_node - remove orig_node from a global tt entry + * @bat_priv: the bat priv with all the soft interface information + * @tt_global_entry: the global entry to remove the orig_node from + * @orig_node: the originator announcing the client + * @message: message to append to the log on deletion + * + * Remove the given orig_node and its according orig_entry from the given + * global tt entry. + */ static void -batadv_tt_global_del_orig_entry(struct batadv_priv *bat_priv, - struct batadv_tt_global_entry *tt_global_entry, - struct batadv_orig_node *orig_node, - const char *message) +batadv_tt_global_del_orig_node(struct batadv_priv *bat_priv, + struct batadv_tt_global_entry *tt_global_entry, + struct batadv_orig_node *orig_node, + const char *message) { struct hlist_head *head; struct hlist_node *safe; @@ -1592,10 +1656,8 @@ batadv_tt_global_del_orig_entry(struct batadv_priv *bat_priv, orig_node->orig, tt_global_entry->common.addr, BATADV_PRINT_VID(vid), message); - hlist_del_rcu(&orig_entry->list); - batadv_tt_global_size_dec(orig_node, - tt_global_entry->common.vid); - batadv_tt_orig_list_entry_free_ref(orig_entry); + batadv_tt_global_del_orig_entry(tt_global_entry, + orig_entry); } } spin_unlock_bh(&tt_global_entry->list_lock); @@ -1637,8 +1699,8 @@ batadv_tt_global_del_roaming(struct batadv_priv *bat_priv, /* there is another entry, we can simply delete this * one and can still use the other one. */ - batadv_tt_global_del_orig_entry(bat_priv, tt_global_entry, - orig_node, message); + batadv_tt_global_del_orig_node(bat_priv, tt_global_entry, + orig_node, message); } /** @@ -1664,8 +1726,8 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv, goto out; if (!roaming) { - batadv_tt_global_del_orig_entry(bat_priv, tt_global_entry, - orig_node, message); + batadv_tt_global_del_orig_node(bat_priv, tt_global_entry, + orig_node, message); if (hlist_empty(&tt_global_entry->orig_list)) batadv_tt_global_free(bat_priv, tt_global_entry, @@ -1748,8 +1810,8 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, struct batadv_tt_global_entry, common); - batadv_tt_global_del_orig_entry(bat_priv, tt_global, - orig_node, message); + batadv_tt_global_del_orig_node(bat_priv, tt_global, + orig_node, message); if (hlist_empty(&tt_global->orig_list)) { vid = tt_global->common.vid; @@ -1763,7 +1825,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, } spin_unlock_bh(list_lock); } - orig_node->tt_initialised = false; + orig_node->capa_initialized &= ~BATADV_ORIG_CAPA_HAS_TT; } static bool batadv_tt_global_to_purge(struct batadv_tt_global_entry *tt_global, @@ -2160,7 +2222,7 @@ batadv_new_tt_req_node(struct batadv_priv *bat_priv, if (!tt_req_node) goto unlock; - memcpy(tt_req_node->addr, orig_node->orig, ETH_ALEN); + ether_addr_copy(tt_req_node->addr, orig_node->orig); tt_req_node->issued_at = jiffies; list_add(&tt_req_node->list, &bat_priv->tt.req_list); @@ -2240,8 +2302,7 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, if ((valid_cb) && (!valid_cb(tt_common_entry, cb_data))) continue; - memcpy(tt_change->addr, tt_common_entry->addr, - ETH_ALEN); + ether_addr_copy(tt_change->addr, tt_common_entry->addr); tt_change->flags = tt_common_entry->flags; tt_change->vid = htons(tt_common_entry->vid); memset(tt_change->reserved, 0, @@ -2724,7 +2785,7 @@ static void _batadv_tt_update_changes(struct batadv_priv *bat_priv, return; } } - orig_node->tt_initialised = true; + orig_node->capa_initialized |= BATADV_ORIG_CAPA_HAS_TT; } static void batadv_tt_fill_gtable(struct batadv_priv *bat_priv, @@ -2932,7 +2993,7 @@ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, tt_roam_node->first_time = jiffies; atomic_set(&tt_roam_node->counter, BATADV_ROAMING_MAX_COUNT - 1); - memcpy(tt_roam_node->addr, client, ETH_ALEN); + ether_addr_copy(tt_roam_node->addr, client); list_add(&tt_roam_node->list, &bat_priv->tt.roam_list); ret = true; @@ -3121,6 +3182,9 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) */ static void batadv_tt_local_commit_changes_nolock(struct batadv_priv *bat_priv) { + /* Update multicast addresses in local translation table */ + batadv_mcast_mla_update(bat_priv); + if (atomic_read(&bat_priv->tt.local_changes) < 1) { if (!batadv_atomic_dec_not_zero(&bat_priv->tt.ogm_append_cnt)) batadv_tt_tvlv_container_update(bat_priv); @@ -3211,13 +3275,15 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv, uint8_t orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); struct batadv_tvlv_tt_vlan_data *tt_vlan; bool full_table = true; + bool has_tt_init; tt_vlan = (struct batadv_tvlv_tt_vlan_data *)tt_buff; + has_tt_init = orig_node->capa_initialized & BATADV_ORIG_CAPA_HAS_TT; + /* orig table not initialised AND first diff is in the OGM OR the ttvn * increased by one -> we can apply the attached changes */ - if ((!orig_node->tt_initialised && ttvn == 1) || - ttvn - orig_ttvn == 1) { + if ((!has_tt_init && ttvn == 1) || ttvn - orig_ttvn == 1) { /* the OGM could not contain the changes due to their size or * because they have already been sent BATADV_TT_OGM_APPEND_MAX * times. @@ -3257,7 +3323,7 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv, /* if we missed more than one change or our tables are not * in sync anymore -> request fresh tt data */ - if (!orig_node->tt_initialised || ttvn != orig_ttvn || + if (!has_tt_init || ttvn != orig_ttvn || !batadv_tt_global_check_crc(orig_node, tt_vlan, tt_num_vlan)) { request_table: diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 20a1d7861ded..ad84d7b89e39 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -29,6 +29,8 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset); void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, int32_t match_vid, const char *message); +int batadv_tt_global_hash_count(struct batadv_priv *bat_priv, + const uint8_t *addr, unsigned short vid); struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv, const uint8_t *src, const uint8_t *addr, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 78370ab31f9c..34891a56773f 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -24,8 +24,9 @@ #ifdef CONFIG_BATMAN_ADV_DAT -/* batadv_dat_addr_t is the type used for all DHT addresses. If it is changed, - * BATADV_DAT_ADDR_MAX is changed as well. +/** + * batadv_dat_addr_t - it is the type used for all DHT addresses. If it is + * changed, BATADV_DAT_ADDR_MAX is changed as well. * * *Please be careful: batadv_dat_addr_t must be UNSIGNED* */ @@ -163,7 +164,7 @@ struct batadv_vlan_tt { }; /** - * batadv_orig_node_vlan - VLAN specific data per orig_node + * struct batadv_orig_node_vlan - VLAN specific data per orig_node * @vid: the VLAN identifier * @tt: VLAN specific TT attributes * @list: list node for orig_node::vlan_list @@ -204,14 +205,18 @@ struct batadv_orig_bat_iv { * @batadv_dat_addr_t: address of the orig node in the distributed hash * @last_seen: time when last packet from this node was received * @bcast_seqno_reset: time when the broadcast seqno window was reset + * @mcast_flags: multicast flags announced by the orig node + * @mcast_want_all_unsnoop_node: a list node for the + * mcast.want_all_unsnoopables list + * @mcast_want_all_ipv4_node: a list node for the mcast.want_all_ipv4 list + * @mcast_want_all_ipv6_node: a list node for the mcast.want_all_ipv6 list * @capabilities: announced capabilities of this originator + * @capa_initialized: bitfield to remember whether a capability was initialized * @last_ttvn: last seen translation table version number * @tt_buff: last tt changeset this node received from the orig node * @tt_buff_len: length of the last tt changeset this node received from the * orig node * @tt_buff_lock: lock that protects tt_buff and tt_buff_len - * @tt_initialised: bool keeping track of whether or not this node have received - * any translation table information from the orig node yet * @tt_lock: prevents from updating the table while reading it. Table update is * made up by two operations (data structure update and metdata -CRC/TTVN- * recalculation) and they have to be executed atomically in order to avoid @@ -247,12 +252,18 @@ struct batadv_orig_node { #endif unsigned long last_seen; unsigned long bcast_seqno_reset; +#ifdef CONFIG_BATMAN_ADV_MCAST + uint8_t mcast_flags; + struct hlist_node mcast_want_all_unsnoopables_node; + struct hlist_node mcast_want_all_ipv4_node; + struct hlist_node mcast_want_all_ipv6_node; +#endif uint8_t capabilities; + uint8_t capa_initialized; atomic_t last_ttvn; unsigned char *tt_buff; int16_t tt_buff_len; spinlock_t tt_buff_lock; /* protects tt_buff & tt_buff_len */ - bool tt_initialised; /* prevents from changing the table while reading it */ spinlock_t tt_lock; DECLARE_BITMAP(bcast_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); @@ -282,10 +293,15 @@ struct batadv_orig_node { * enum batadv_orig_capabilities - orig node capabilities * @BATADV_ORIG_CAPA_HAS_DAT: orig node has distributed arp table enabled * @BATADV_ORIG_CAPA_HAS_NC: orig node has network coding enabled + * @BATADV_ORIG_CAPA_HAS_TT: orig node has tt capability + * @BATADV_ORIG_CAPA_HAS_MCAST: orig node has some multicast capability + * (= orig node announces a tvlv of type BATADV_TVLV_MCAST) */ enum batadv_orig_capabilities { BATADV_ORIG_CAPA_HAS_DAT = BIT(0), BATADV_ORIG_CAPA_HAS_NC = BIT(1), + BATADV_ORIG_CAPA_HAS_TT = BIT(2), + BATADV_ORIG_CAPA_HAS_MCAST = BIT(3), }; /** @@ -334,7 +350,7 @@ struct batadv_neigh_node { }; /** - * struct batadv_neigh_node_bat_iv - neighbor information per outgoing + * struct batadv_neigh_ifinfo_bat_iv - neighbor information per outgoing * interface for BATMAN IV * @tq_recv: ring buffer of received TQ values from this neigh node * @tq_index: ring buffer index @@ -544,7 +560,7 @@ struct batadv_priv_bla { #endif /** - * struct batadv_debug_log - debug logging data + * struct batadv_priv_debug_log - debug logging data * @log_buff: buffer holding the logs (ring bufer) * @log_start: index of next character to read * @log_end: index of next character to write @@ -607,6 +623,39 @@ struct batadv_priv_dat { }; #endif +#ifdef CONFIG_BATMAN_ADV_MCAST +/** + * struct batadv_priv_mcast - per mesh interface mcast data + * @mla_list: list of multicast addresses we are currently announcing via TT + * @want_all_unsnoopables_list: a list of orig_nodes wanting all unsnoopable + * multicast traffic + * @want_all_ipv4_list: a list of orig_nodes wanting all IPv4 multicast traffic + * @want_all_ipv6_list: a list of orig_nodes wanting all IPv6 multicast traffic + * @flags: the flags we have last sent in our mcast tvlv + * @enabled: whether the multicast tvlv is currently enabled + * @num_disabled: number of nodes that have no mcast tvlv + * @num_want_all_unsnoopables: number of nodes wanting unsnoopable IP traffic + * @num_want_all_ipv4: counter for items in want_all_ipv4_list + * @num_want_all_ipv6: counter for items in want_all_ipv6_list + * @want_lists_lock: lock for protecting modifications to mcast want lists + * (traversals are rcu-locked) + */ +struct batadv_priv_mcast { + struct hlist_head mla_list; + struct hlist_head want_all_unsnoopables_list; + struct hlist_head want_all_ipv4_list; + struct hlist_head want_all_ipv6_list; + uint8_t flags; + bool enabled; + atomic_t num_disabled; + atomic_t num_want_all_unsnoopables; + atomic_t num_want_all_ipv4; + atomic_t num_want_all_ipv6; + /* protects want_all_{unsnoopables,ipv4,ipv6}_list */ + spinlock_t want_lists_lock; +}; +#endif + /** * struct batadv_priv_nc - per mesh interface network coding private data * @work: work queue callback item for cleanup @@ -672,6 +721,8 @@ struct batadv_softif_vlan { * enabled * @distributed_arp_table: bool indicating whether distributed ARP table is * enabled + * @multicast_mode: Enable or disable multicast optimizations on this node's + * sender/originating side * @gw_mode: gateway operation: off, client or server (see batadv_gw_modes) * @gw_sel_class: gateway selection class (applies if gw_mode client) * @orig_interval: OGM broadcast interval in milliseconds @@ -702,6 +753,7 @@ struct batadv_softif_vlan { * @tt: translation table data * @tvlv: type-version-length-value data * @dat: distributed arp table data + * @mcast: multicast data * @network_coding: bool indicating whether network coding is enabled * @batadv_priv_nc: network coding data */ @@ -721,6 +773,9 @@ struct batadv_priv { #ifdef CONFIG_BATMAN_ADV_DAT atomic_t distributed_arp_table; #endif +#ifdef CONFIG_BATMAN_ADV_MCAST + atomic_t multicast_mode; +#endif atomic_t gw_mode; atomic_t gw_sel_class; atomic_t orig_interval; @@ -759,6 +814,9 @@ struct batadv_priv { #ifdef CONFIG_BATMAN_ADV_DAT struct batadv_priv_dat dat; #endif +#ifdef CONFIG_BATMAN_ADV_MCAST + struct batadv_priv_mcast mcast; +#endif #ifdef CONFIG_BATMAN_ADV_NC atomic_t network_coding; struct batadv_priv_nc nc; @@ -881,12 +939,14 @@ struct batadv_tt_local_entry { * struct batadv_tt_global_entry - translation table global entry data * @common: general translation table data * @orig_list: list of orig nodes announcing this non-mesh client + * @orig_list_count: number of items in the orig_list * @list_lock: lock protecting orig_list * @roam_at: time at which TT_GLOBAL_ROAM was set */ struct batadv_tt_global_entry { struct batadv_tt_common_entry common; struct hlist_head orig_list; + atomic_t orig_list_count; spinlock_t list_lock; /* protects orig_list */ unsigned long roam_at; }; @@ -1004,8 +1064,8 @@ struct batadv_nc_packet { }; /** - * batadv_skb_cb - control buffer structure used to store private data relevant - * to batman-adv in the skb->cb buffer in skbs. + * struct batadv_skb_cb - control buffer structure used to store private data + * relevant to batman-adv in the skb->cb buffer in skbs. * @decoded: Marks a skb as decoded, which is checked when searching for coding * opportunities in network-coding.c */ @@ -1116,6 +1176,16 @@ struct batadv_dat_entry { }; /** + * struct batadv_hw_addr - a list entry for a MAC address + * @list: list node for the linking of entries + * @addr: the MAC address of this list entry + */ +struct batadv_hw_addr { + struct hlist_node list; + unsigned char addr[ETH_ALEN]; +}; + +/** * struct batadv_dat_candidate - candidate destination for DAT operations * @type: the type of the selected candidate. It can one of the following: * - BATADV_DAT_CANDIDATE_NOT_FOUND diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index adb3ea04adaa..73492b91105a 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -27,7 +27,7 @@ #include "6lowpan.h" -#include "../ieee802154/6lowpan.h" /* for the compression support */ +#include <net/6lowpan.h> /* for the compression support */ #define IFACE_NAME_TEMPLATE "bt%d" #define EUI64_ADDR_LEN 8 diff --git a/net/bluetooth/6lowpan.h b/net/bluetooth/6lowpan.h index 680eac808d74..5d281f1eaf55 100644 --- a/net/bluetooth/6lowpan.h +++ b/net/bluetooth/6lowpan.h @@ -14,13 +14,34 @@ #ifndef __6LOWPAN_H #define __6LOWPAN_H +#include <linux/errno.h> #include <linux/skbuff.h> #include <net/bluetooth/l2cap.h> +#if IS_ENABLED(CONFIG_BT_6LOWPAN) int bt_6lowpan_recv(struct l2cap_conn *conn, struct sk_buff *skb); int bt_6lowpan_add_conn(struct l2cap_conn *conn); int bt_6lowpan_del_conn(struct l2cap_conn *conn); int bt_6lowpan_init(void); void bt_6lowpan_cleanup(void); +#else +static int bt_6lowpan_recv(struct l2cap_conn *conn, struct sk_buff *skb) +{ + return -EOPNOTSUPP; +} +static int bt_6lowpan_add_conn(struct l2cap_conn *conn) +{ + return -EOPNOTSUPP; +} +int bt_6lowpan_del_conn(struct l2cap_conn *conn) +{ + return -EOPNOTSUPP; +} +static int bt_6lowpan_init(void) +{ + return -EOPNOTSUPP; +} +static void bt_6lowpan_cleanup(void) { } +#endif #endif /* __6LOWPAN_H */ diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 985b56070d26..06ec14499ca1 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -6,13 +6,13 @@ menuconfig BT tristate "Bluetooth subsystem support" depends on NET && !S390 depends on RFKILL || !RFKILL + select 6LOWPAN_IPHC if BT_6LOWPAN select CRC16 select CRYPTO select CRYPTO_BLKCIPHER select CRYPTO_AES select CRYPTO_ECB select CRYPTO_SHA256 - select 6LOWPAN_IPHC help Bluetooth is low-cost, low-power, short-range wireless technology. It was designed as a replacement for cables and other short-range @@ -40,6 +40,12 @@ menuconfig BT to Bluetooth kernel modules are provided in the BlueZ packages. For more information, see <http://www.bluez.org/>. +config BT_6LOWPAN + bool "Bluetooth 6LoWPAN support" + depends on BT && IPV6 + help + IPv6 compression over Bluetooth. + source "net/bluetooth/rfcomm/Kconfig" source "net/bluetooth/bnep/Kconfig" diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 80cb215826e8..ca51246b1016 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -10,6 +10,7 @@ obj-$(CONFIG_BT_HIDP) += hidp/ bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o sco.o lib.o \ - a2mp.o amp.o 6lowpan.o + a2mp.o amp.o +bluetooth-$(CONFIG_BT_6LOWPAN) += 6lowpan.o subdir-ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index efcd108822c4..9514cc9e850c 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -162,7 +162,7 @@ static int a2mp_discover_req(struct amp_mgr *mgr, struct sk_buff *skb, return -ENOMEM; } - rsp->mtu = __constant_cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); + rsp->mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); rsp->ext_feat = 0; __a2mp_add_cl(mgr, rsp->cl); @@ -235,7 +235,7 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); - if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) + if (chan->scid == L2CAP_CID_A2MP) continue; l2cap_chan_lock(chan); @@ -649,7 +649,7 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) if (err) { struct a2mp_cmd_rej rej; - rej.reason = __constant_cpu_to_le16(0); + rej.reason = cpu_to_le16(0); hdr = (void *) skb->data; BT_DBG("Send A2MP Rej: cmd 0x%2.2x err %d", hdr->code, err); @@ -695,7 +695,13 @@ static void a2mp_chan_state_change_cb(struct l2cap_chan *chan, int state, static struct sk_buff *a2mp_chan_alloc_skb_cb(struct l2cap_chan *chan, unsigned long len, int nb) { - return bt_skb_alloc(len, GFP_KERNEL); + struct sk_buff *skb; + + skb = bt_skb_alloc(len, GFP_KERNEL); + if (!skb) + return ERR_PTR(-ENOMEM); + + return skb; } static struct l2cap_ops a2mp_chan_ops = { @@ -726,7 +732,11 @@ static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked) BT_DBG("chan %p", chan); - chan->chan_type = L2CAP_CHAN_CONN_FIX_A2MP; + chan->chan_type = L2CAP_CHAN_FIXED; + chan->scid = L2CAP_CID_A2MP; + chan->dcid = L2CAP_CID_A2MP; + chan->omtu = L2CAP_A2MP_DEFAULT_MTU; + chan->imtu = L2CAP_A2MP_DEFAULT_MTU; chan->flush_to = L2CAP_DEFAULT_FLUSH_TO; chan->ops = &a2mp_chan_ops; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 0c5866bb49b6..2021c481cdb6 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -31,7 +31,7 @@ #include <net/bluetooth/bluetooth.h> #include <linux/proc_fs.h> -#define VERSION "2.18" +#define VERSION "2.19" /* Bluetooth sockets */ #define BT_MAX_PROTO 8 diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index ba5366c320da..d958e2dca52f 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -82,7 +82,7 @@ static void hci_acl_create_connection(struct hci_conn *conn) cp.pscan_rep_mode = ie->data.pscan_rep_mode; cp.pscan_mode = ie->data.pscan_mode; cp.clock_offset = ie->data.clock_offset | - __constant_cpu_to_le16(0x8000); + cpu_to_le16(0x8000); } memcpy(conn->dev_class, ie->data.dev_class, 3); @@ -182,8 +182,8 @@ bool hci_setup_sync(struct hci_conn *conn, __u16 handle) cp.handle = cpu_to_le16(handle); - cp.tx_bandwidth = __constant_cpu_to_le32(0x00001f40); - cp.rx_bandwidth = __constant_cpu_to_le32(0x00001f40); + cp.tx_bandwidth = cpu_to_le32(0x00001f40); + cp.rx_bandwidth = cpu_to_le32(0x00001f40); cp.voice_setting = cpu_to_le16(conn->setting); switch (conn->setting & SCO_AIRMODE_MASK) { @@ -225,13 +225,13 @@ void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, cp.conn_interval_max = cpu_to_le16(max); cp.conn_latency = cpu_to_le16(latency); cp.supervision_timeout = cpu_to_le16(to_multiplier); - cp.min_ce_len = __constant_cpu_to_le16(0x0001); - cp.max_ce_len = __constant_cpu_to_le16(0x0001); + cp.min_ce_len = cpu_to_le16(0x0000); + cp.max_ce_len = cpu_to_le16(0x0000); hci_send_cmd(hdev, HCI_OP_LE_CONN_UPDATE, sizeof(cp), &cp); } -void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8], +void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, __u8 ltk[16]) { struct hci_dev *hdev = conn->hdev; @@ -242,9 +242,9 @@ void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8], memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); - memcpy(cp.ltk, ltk, sizeof(cp.ltk)); + cp.rand = rand; cp.ediv = ediv; - memcpy(cp.rand, rand, sizeof(cp.rand)); + memcpy(cp.ltk, ltk, sizeof(cp.ltk)); hci_send_cmd(hdev, HCI_OP_LE_START_ENC, sizeof(cp), &cp); } @@ -337,9 +337,9 @@ static void hci_conn_idle(struct work_struct *work) if (lmp_sniffsubr_capable(hdev) && lmp_sniffsubr_capable(conn)) { struct hci_cp_sniff_subrate cp; cp.handle = cpu_to_le16(conn->handle); - cp.max_latency = __constant_cpu_to_le16(0); - cp.min_remote_timeout = __constant_cpu_to_le16(0); - cp.min_local_timeout = __constant_cpu_to_le16(0); + cp.max_latency = cpu_to_le16(0); + cp.min_remote_timeout = cpu_to_le16(0); + cp.min_local_timeout = cpu_to_le16(0); hci_send_cmd(hdev, HCI_OP_SNIFF_SUBRATE, sizeof(cp), &cp); } @@ -348,8 +348,8 @@ static void hci_conn_idle(struct work_struct *work) cp.handle = cpu_to_le16(conn->handle); cp.max_interval = cpu_to_le16(hdev->sniff_max_interval); cp.min_interval = cpu_to_le16(hdev->sniff_min_interval); - cp.attempt = __constant_cpu_to_le16(4); - cp.timeout = __constant_cpu_to_le16(1); + cp.attempt = cpu_to_le16(4); + cp.timeout = cpu_to_le16(1); hci_send_cmd(hdev, HCI_OP_SNIFF_MODE, sizeof(cp), &cp); } } @@ -363,6 +363,16 @@ static void hci_conn_auto_accept(struct work_struct *work) &conn->dst); } +static void le_conn_timeout(struct work_struct *work) +{ + struct hci_conn *conn = container_of(work, struct hci_conn, + le_conn_timeout.work); + + BT_DBG(""); + + hci_le_create_connection_cancel(conn); +} + struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) { struct hci_conn *conn; @@ -410,6 +420,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst) INIT_DELAYED_WORK(&conn->disc_work, hci_conn_timeout); INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept); INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle); + INIT_DELAYED_WORK(&conn->le_conn_timeout, le_conn_timeout); atomic_set(&conn->refcnt, 0); @@ -442,6 +453,8 @@ int hci_conn_del(struct hci_conn *conn) /* Unacked frames */ hdev->acl_cnt += conn->sent; } else if (conn->type == LE_LINK) { + cancel_delayed_work_sync(&conn->le_conn_timeout); + if (hdev->le_pkts) hdev->le_cnt += conn->sent; else @@ -514,6 +527,26 @@ struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src) } EXPORT_SYMBOL(hci_get_route); +/* This function requires the caller holds hdev->lock */ +void hci_le_conn_failed(struct hci_conn *conn, u8 status) +{ + struct hci_dev *hdev = conn->hdev; + + conn->state = BT_CLOSED; + + mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, + status); + + hci_proto_connect_cfm(conn, status); + + hci_conn_del(conn); + + /* Since we may have temporarily stopped the background scanning in + * favor of connection establishment, we should restart it. + */ + hci_update_background_scan(hdev); +} + static void create_le_conn_complete(struct hci_dev *hdev, u8 status) { struct hci_conn *conn; @@ -530,55 +563,55 @@ static void create_le_conn_complete(struct hci_dev *hdev, u8 status) if (!conn) goto done; - conn->state = BT_CLOSED; - - mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, - status); - - hci_proto_connect_cfm(conn, status); - - hci_conn_del(conn); + hci_le_conn_failed(conn, status); done: hci_dev_unlock(hdev); } -static int hci_create_le_conn(struct hci_conn *conn) +static void hci_req_add_le_create_conn(struct hci_request *req, + struct hci_conn *conn) { - struct hci_dev *hdev = conn->hdev; struct hci_cp_le_create_conn cp; - struct hci_request req; - int err; - - hci_req_init(&req, hdev); + struct hci_dev *hdev = conn->hdev; + u8 own_addr_type; memset(&cp, 0, sizeof(cp)); + + /* Update random address, but set require_privacy to false so + * that we never connect with an unresolvable address. + */ + if (hci_update_random_address(req, false, &own_addr_type)) + return; + + /* Save the address type used for this connnection attempt so we able + * to retrieve this information if we need it. + */ + conn->src_type = own_addr_type; + cp.scan_interval = cpu_to_le16(hdev->le_scan_interval); cp.scan_window = cpu_to_le16(hdev->le_scan_window); bacpy(&cp.peer_addr, &conn->dst); cp.peer_addr_type = conn->dst_type; - cp.own_address_type = conn->src_type; - cp.conn_interval_min = cpu_to_le16(hdev->le_conn_min_interval); - cp.conn_interval_max = cpu_to_le16(hdev->le_conn_max_interval); - cp.supervision_timeout = __constant_cpu_to_le16(0x002a); - cp.min_ce_len = __constant_cpu_to_le16(0x0000); - cp.max_ce_len = __constant_cpu_to_le16(0x0000); + cp.own_address_type = own_addr_type; + cp.conn_interval_min = cpu_to_le16(conn->le_conn_min_interval); + cp.conn_interval_max = cpu_to_le16(conn->le_conn_max_interval); + cp.supervision_timeout = cpu_to_le16(0x002a); + cp.min_ce_len = cpu_to_le16(0x0000); + cp.max_ce_len = cpu_to_le16(0x0000); - hci_req_add(&req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); + hci_req_add(req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp); - err = hci_req_run(&req, create_le_conn_complete); - if (err) { - hci_conn_del(conn); - return err; - } - - return 0; + conn->state = BT_CONNECT; } -static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, - u8 dst_type, u8 sec_level, u8 auth_type) +struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, + u8 dst_type, u8 sec_level, u8 auth_type) { + struct hci_conn_params *params; struct hci_conn *conn; + struct smp_irk *irk; + struct hci_request req; int err; if (test_bit(HCI_ADVERTISING, &hdev->flags)) @@ -607,35 +640,74 @@ static struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, if (conn) return ERR_PTR(-EBUSY); + /* When given an identity address with existing identity + * resolving key, the connection needs to be established + * to a resolvable random address. + * + * This uses the cached random resolvable address from + * a previous scan. When no cached address is available, + * try connecting to the identity address instead. + * + * Storing the resolvable random address is required here + * to handle connection failures. The address will later + * be resolved back into the original identity address + * from the connect request. + */ + irk = hci_find_irk_by_addr(hdev, dst, dst_type); + if (irk && bacmp(&irk->rpa, BDADDR_ANY)) { + dst = &irk->rpa; + dst_type = ADDR_LE_DEV_RANDOM; + } + conn = hci_conn_add(hdev, LE_LINK, dst); if (!conn) return ERR_PTR(-ENOMEM); - if (dst_type == BDADDR_LE_PUBLIC) - conn->dst_type = ADDR_LE_DEV_PUBLIC; - else - conn->dst_type = ADDR_LE_DEV_RANDOM; - - conn->src_type = hdev->own_addr_type; + conn->dst_type = dst_type; - conn->state = BT_CONNECT; conn->out = true; conn->link_mode |= HCI_LM_MASTER; conn->sec_level = BT_SECURITY_LOW; conn->pending_sec_level = sec_level; conn->auth_type = auth_type; - err = hci_create_le_conn(conn); - if (err) + params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); + if (params) { + conn->le_conn_min_interval = params->conn_min_interval; + conn->le_conn_max_interval = params->conn_max_interval; + } else { + conn->le_conn_min_interval = hdev->le_conn_min_interval; + conn->le_conn_max_interval = hdev->le_conn_max_interval; + } + + hci_req_init(&req, hdev); + + /* If controller is scanning, we stop it since some controllers are + * not able to scan and connect at the same time. Also set the + * HCI_LE_SCAN_INTERRUPTED flag so that the command complete + * handler for scan disabling knows to set the correct discovery + * state. + */ + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) { + hci_req_add_le_scan_disable(&req); + set_bit(HCI_LE_SCAN_INTERRUPTED, &hdev->dev_flags); + } + + hci_req_add_le_create_conn(&req, conn); + + err = hci_req_run(&req, create_le_conn_complete); + if (err) { + hci_conn_del(conn); return ERR_PTR(err); + } done: hci_conn_hold(conn); return conn; } -static struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, - u8 sec_level, u8 auth_type) +struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, + u8 sec_level, u8 auth_type) { struct hci_conn *acl; @@ -704,27 +776,22 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, return sco; } -/* Create SCO, ACL or LE connection. */ -struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, - __u8 dst_type, __u8 sec_level, __u8 auth_type) -{ - BT_DBG("%s dst %pMR type 0x%x", hdev->name, dst, type); - - switch (type) { - case LE_LINK: - return hci_connect_le(hdev, dst, dst_type, sec_level, auth_type); - case ACL_LINK: - return hci_connect_acl(hdev, dst, sec_level, auth_type); - } - - return ERR_PTR(-EINVAL); -} - /* Check link security requirement */ int hci_conn_check_link_mode(struct hci_conn *conn) { BT_DBG("hcon %p", conn); + /* In Secure Connections Only mode, it is required that Secure + * Connections is used and the link is encrypted with AES-CCM + * using a P-256 authenticated combination key. + */ + if (test_bit(HCI_SC_ONLY, &conn->hdev->flags)) { + if (!hci_conn_sc_enabled(conn) || + !test_bit(HCI_CONN_AES_CCM, &conn->flags) || + conn->key_type != HCI_LK_AUTH_COMBINATION_P256) + return 0; + } + if (hci_conn_ssp_enabled(conn) && !(conn->link_mode & HCI_LM_ENCRYPT)) return 0; @@ -800,14 +867,23 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) if (!(conn->link_mode & HCI_LM_AUTH)) goto auth; - /* An authenticated combination key has sufficient security for any - security level. */ - if (conn->key_type == HCI_LK_AUTH_COMBINATION) + /* An authenticated FIPS approved combination key has sufficient + * security for security level 4. */ + if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256 && + sec_level == BT_SECURITY_FIPS) + goto encrypt; + + /* An authenticated combination key has sufficient security for + security level 3. */ + if ((conn->key_type == HCI_LK_AUTH_COMBINATION_P192 || + conn->key_type == HCI_LK_AUTH_COMBINATION_P256) && + sec_level == BT_SECURITY_HIGH) goto encrypt; /* An unauthenticated combination key has sufficient security for security level 1 and 2. */ - if (conn->key_type == HCI_LK_UNAUTH_COMBINATION && + if ((conn->key_type == HCI_LK_UNAUTH_COMBINATION_P192 || + conn->key_type == HCI_LK_UNAUTH_COMBINATION_P256) && (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW)) goto encrypt; @@ -816,7 +892,8 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) is generated using maximum PIN code length (16). For pre 2.1 units. */ if (conn->key_type == HCI_LK_COMBINATION && - (sec_level != BT_SECURITY_HIGH || conn->pin_length == 16)) + (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW || + conn->pin_length == 16)) goto encrypt; auth: @@ -840,13 +917,17 @@ int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level) { BT_DBG("hcon %p", conn); - if (sec_level != BT_SECURITY_HIGH) - return 1; /* Accept if non-secure is required */ + /* Accept if non-secure or higher security level is required */ + if (sec_level != BT_SECURITY_HIGH && sec_level != BT_SECURITY_FIPS) + return 1; - if (conn->sec_level == BT_SECURITY_HIGH) + /* Accept if secure or higher security level is already present */ + if (conn->sec_level == BT_SECURITY_HIGH || + conn->sec_level == BT_SECURITY_FIPS) return 1; - return 0; /* Reject not secure link */ + /* Reject not secure link */ + return 0; } EXPORT_SYMBOL(hci_conn_check_secure); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 5e8663c194c1..1c6ffaa8902f 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -29,11 +29,14 @@ #include <linux/idr.h> #include <linux/rfkill.h> #include <linux/debugfs.h> +#include <linux/crypto.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +#include "smp.h" + static void hci_rx_work(struct work_struct *work); static void hci_cmd_work(struct work_struct *work); static void hci_tx_work(struct work_struct *work); @@ -285,24 +288,6 @@ static const struct file_operations link_keys_fops = { .release = single_release, }; -static ssize_t use_debug_keys_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct hci_dev *hdev = file->private_data; - char buf[3]; - - buf[0] = test_bit(HCI_DEBUG_KEYS, &hdev->dev_flags) ? 'Y': 'N'; - buf[1] = '\n'; - buf[2] = '\0'; - return simple_read_from_buffer(user_buf, count, ppos, buf, 2); -} - -static const struct file_operations use_debug_keys_fops = { - .open = simple_open, - .read = use_debug_keys_read, - .llseek = default_llseek, -}; - static int dev_class_show(struct seq_file *f, void *ptr) { struct hci_dev *hdev = f->private; @@ -415,6 +400,70 @@ static int ssp_debug_mode_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(ssp_debug_mode_fops, ssp_debug_mode_get, ssp_debug_mode_set, "%llu\n"); +static ssize_t force_sc_support_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[3]; + + buf[0] = test_bit(HCI_FORCE_SC, &hdev->dev_flags) ? 'Y': 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t force_sc_support_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[32]; + size_t buf_size = min(count, (sizeof(buf)-1)); + bool enable; + + if (test_bit(HCI_UP, &hdev->flags)) + return -EBUSY; + + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + if (strtobool(buf, &enable)) + return -EINVAL; + + if (enable == test_bit(HCI_FORCE_SC, &hdev->dev_flags)) + return -EALREADY; + + change_bit(HCI_FORCE_SC, &hdev->dev_flags); + + return count; +} + +static const struct file_operations force_sc_support_fops = { + .open = simple_open, + .read = force_sc_support_read, + .write = force_sc_support_write, + .llseek = default_llseek, +}; + +static ssize_t sc_only_mode_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[3]; + + buf[0] = test_bit(HCI_SC_ONLY, &hdev->dev_flags) ? 'Y': 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static const struct file_operations sc_only_mode_fops = { + .open = simple_open, + .read = sc_only_mode_read, + .llseek = default_llseek, +}; + static int idle_timeout_set(void *data, u64 val) { struct hci_dev *hdev = data; @@ -443,6 +492,37 @@ static int idle_timeout_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(idle_timeout_fops, idle_timeout_get, idle_timeout_set, "%llu\n"); +static int rpa_timeout_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; + + /* Require the RPA timeout to be at least 30 seconds and at most + * 24 hours. + */ + if (val < 30 || val > (60 * 60 * 24)) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->rpa_timeout = val; + hci_dev_unlock(hdev); + + return 0; +} + +static int rpa_timeout_get(void *data, u64 *val) +{ + struct hci_dev *hdev = data; + + hci_dev_lock(hdev); + *val = hdev->rpa_timeout; + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(rpa_timeout_fops, rpa_timeout_get, + rpa_timeout_set, "%llu\n"); + static int sniff_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; @@ -499,6 +579,59 @@ static int sniff_max_interval_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(sniff_max_interval_fops, sniff_max_interval_get, sniff_max_interval_set, "%llu\n"); +static int identity_show(struct seq_file *f, void *p) +{ + struct hci_dev *hdev = f->private; + bdaddr_t addr; + u8 addr_type; + + hci_dev_lock(hdev); + + hci_copy_identity_address(hdev, &addr, &addr_type); + + seq_printf(f, "%pMR (type %u) %*phN %pMR\n", &addr, addr_type, + 16, hdev->irk, &hdev->rpa); + + hci_dev_unlock(hdev); + + return 0; +} + +static int identity_open(struct inode *inode, struct file *file) +{ + return single_open(file, identity_show, inode->i_private); +} + +static const struct file_operations identity_fops = { + .open = identity_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int random_address_show(struct seq_file *f, void *p) +{ + struct hci_dev *hdev = f->private; + + hci_dev_lock(hdev); + seq_printf(f, "%pMR\n", &hdev->random_addr); + hci_dev_unlock(hdev); + + return 0; +} + +static int random_address_open(struct inode *inode, struct file *file) +{ + return single_open(file, random_address_show, inode->i_private); +} + +static const struct file_operations random_address_fops = { + .open = random_address_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int static_address_show(struct seq_file *f, void *p) { struct hci_dev *hdev = f->private; @@ -522,33 +655,107 @@ static const struct file_operations static_address_fops = { .release = single_release, }; -static int own_address_type_set(void *data, u64 val) +static ssize_t force_static_address_read(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) { - struct hci_dev *hdev = data; + struct hci_dev *hdev = file->private_data; + char buf[3]; - if (val != 0 && val != 1) + buf[0] = test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) ? 'Y': 'N'; + buf[1] = '\n'; + buf[2] = '\0'; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t force_static_address_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct hci_dev *hdev = file->private_data; + char buf[32]; + size_t buf_size = min(count, (sizeof(buf)-1)); + bool enable; + + if (test_bit(HCI_UP, &hdev->flags)) + return -EBUSY; + + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size] = '\0'; + if (strtobool(buf, &enable)) return -EINVAL; + if (enable == test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags)) + return -EALREADY; + + change_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags); + + return count; +} + +static const struct file_operations force_static_address_fops = { + .open = simple_open, + .read = force_static_address_read, + .write = force_static_address_write, + .llseek = default_llseek, +}; + +static int white_list_show(struct seq_file *f, void *ptr) +{ + struct hci_dev *hdev = f->private; + struct bdaddr_list *b; + hci_dev_lock(hdev); - hdev->own_addr_type = val; + list_for_each_entry(b, &hdev->le_white_list, list) + seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); hci_dev_unlock(hdev); return 0; } -static int own_address_type_get(void *data, u64 *val) +static int white_list_open(struct inode *inode, struct file *file) { - struct hci_dev *hdev = data; + return single_open(file, white_list_show, inode->i_private); +} + +static const struct file_operations white_list_fops = { + .open = white_list_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int identity_resolving_keys_show(struct seq_file *f, void *ptr) +{ + struct hci_dev *hdev = f->private; + struct list_head *p, *n; hci_dev_lock(hdev); - *val = hdev->own_addr_type; + list_for_each_safe(p, n, &hdev->identity_resolving_keys) { + struct smp_irk *irk = list_entry(p, struct smp_irk, list); + seq_printf(f, "%pMR (type %u) %*phN %pMR\n", + &irk->bdaddr, irk->addr_type, + 16, irk->val, &irk->rpa); + } hci_dev_unlock(hdev); return 0; } -DEFINE_SIMPLE_ATTRIBUTE(own_address_type_fops, own_address_type_get, - own_address_type_set, "%llu\n"); +static int identity_resolving_keys_open(struct inode *inode, struct file *file) +{ + return single_open(file, identity_resolving_keys_show, + inode->i_private); +} + +static const struct file_operations identity_resolving_keys_fops = { + .open = identity_resolving_keys_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; static int long_term_keys_show(struct seq_file *f, void *ptr) { @@ -556,12 +763,12 @@ static int long_term_keys_show(struct seq_file *f, void *ptr) struct list_head *p, *n; hci_dev_lock(hdev); - list_for_each_safe(p, n, &hdev->link_keys) { + list_for_each_safe(p, n, &hdev->long_term_keys) { struct smp_ltk *ltk = list_entry(p, struct smp_ltk, list); - seq_printf(f, "%pMR (type %u) %u %u %u %.4x %*phN %*phN\\n", + seq_printf(f, "%pMR (type %u) %u 0x%02x %u %.4x %.16llx %*phN\n", <k->bdaddr, ltk->bdaddr_type, ltk->authenticated, ltk->type, ltk->enc_size, __le16_to_cpu(ltk->ediv), - 8, ltk->rand, 16, ltk->val); + __le64_to_cpu(ltk->rand), 16, ltk->val); } hci_dev_unlock(hdev); @@ -636,6 +843,34 @@ static int conn_max_interval_get(void *data, u64 *val) DEFINE_SIMPLE_ATTRIBUTE(conn_max_interval_fops, conn_max_interval_get, conn_max_interval_set, "%llu\n"); +static int adv_channel_map_set(void *data, u64 val) +{ + struct hci_dev *hdev = data; + + if (val < 0x01 || val > 0x07) + return -EINVAL; + + hci_dev_lock(hdev); + hdev->le_adv_channel_map = val; + hci_dev_unlock(hdev); + + return 0; +} + +static int adv_channel_map_get(void *data, u64 *val) +{ + struct hci_dev *hdev = data; + + hci_dev_lock(hdev); + *val = hdev->le_adv_channel_map; + hci_dev_unlock(hdev); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(adv_channel_map_fops, adv_channel_map_get, + adv_channel_map_set, "%llu\n"); + static ssize_t lowpan_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -679,6 +914,115 @@ static const struct file_operations lowpan_debugfs_fops = { .llseek = default_llseek, }; +static int le_auto_conn_show(struct seq_file *sf, void *ptr) +{ + struct hci_dev *hdev = sf->private; + struct hci_conn_params *p; + + hci_dev_lock(hdev); + + list_for_each_entry(p, &hdev->le_conn_params, list) { + seq_printf(sf, "%pMR %u %u\n", &p->addr, p->addr_type, + p->auto_connect); + } + + hci_dev_unlock(hdev); + + return 0; +} + +static int le_auto_conn_open(struct inode *inode, struct file *file) +{ + return single_open(file, le_auto_conn_show, inode->i_private); +} + +static ssize_t le_auto_conn_write(struct file *file, const char __user *data, + size_t count, loff_t *offset) +{ + struct seq_file *sf = file->private_data; + struct hci_dev *hdev = sf->private; + u8 auto_connect = 0; + bdaddr_t addr; + u8 addr_type; + char *buf; + int err = 0; + int n; + + /* Don't allow partial write */ + if (*offset != 0) + return -EINVAL; + + if (count < 3) + return -EINVAL; + + buf = kzalloc(count, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + if (copy_from_user(buf, data, count)) { + err = -EFAULT; + goto done; + } + + if (memcmp(buf, "add", 3) == 0) { + n = sscanf(&buf[4], "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu %hhu", + &addr.b[5], &addr.b[4], &addr.b[3], &addr.b[2], + &addr.b[1], &addr.b[0], &addr_type, + &auto_connect); + + if (n < 7) { + err = -EINVAL; + goto done; + } + + hci_dev_lock(hdev); + err = hci_conn_params_add(hdev, &addr, addr_type, auto_connect, + hdev->le_conn_min_interval, + hdev->le_conn_max_interval); + hci_dev_unlock(hdev); + + if (err) + goto done; + } else if (memcmp(buf, "del", 3) == 0) { + n = sscanf(&buf[4], "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu", + &addr.b[5], &addr.b[4], &addr.b[3], &addr.b[2], + &addr.b[1], &addr.b[0], &addr_type); + + if (n < 7) { + err = -EINVAL; + goto done; + } + + hci_dev_lock(hdev); + hci_conn_params_del(hdev, &addr, addr_type); + hci_dev_unlock(hdev); + } else if (memcmp(buf, "clr", 3) == 0) { + hci_dev_lock(hdev); + hci_conn_params_clear(hdev); + hci_pend_le_conns_clear(hdev); + hci_update_background_scan(hdev); + hci_dev_unlock(hdev); + } else { + err = -EINVAL; + } + +done: + kfree(buf); + + if (err) + return err; + else + return count; +} + +static const struct file_operations le_auto_conn_fops = { + .open = le_auto_conn_open, + .read = seq_read, + .write = le_auto_conn_write, + .llseek = seq_lseek, + .release = single_release, +}; + /* ---- HCI requests ---- */ static void hci_req_sync_complete(struct hci_dev *hdev, u8 result) @@ -1005,7 +1349,7 @@ static void bredr_setup(struct hci_request *req) hci_req_add(req, HCI_OP_SET_EVENT_FLT, 1, &flt_type); /* Connection accept timeout ~20 secs */ - param = __constant_cpu_to_le16(0x7d00); + param = cpu_to_le16(0x7d00); hci_req_add(req, HCI_OP_WRITE_CA_TIMEOUT, 2, ¶m); /* AVM Berlin (31), aka "BlueFRITZ!", reports version 1.2, @@ -1027,14 +1371,17 @@ static void le_setup(struct hci_request *req) /* Read LE Local Supported Features */ hci_req_add(req, HCI_OP_LE_READ_LOCAL_FEATURES, 0, NULL); + /* Read LE Supported States */ + hci_req_add(req, HCI_OP_LE_READ_SUPPORTED_STATES, 0, NULL); + /* Read LE Advertising Channel TX Power */ hci_req_add(req, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL); /* Read LE White List Size */ hci_req_add(req, HCI_OP_LE_READ_WHITE_LIST_SIZE, 0, NULL); - /* Read LE Supported States */ - hci_req_add(req, HCI_OP_LE_READ_SUPPORTED_STATES, 0, NULL); + /* Clear LE White List */ + hci_req_add(req, HCI_OP_LE_CLEAR_WHITE_LIST, 0, NULL); /* LE-only controllers have LE implicitly enabled */ if (!lmp_bredr_capable(hdev)) @@ -1288,6 +1635,10 @@ static void hci_set_event_mask_page_2(struct hci_request *req) events[2] |= 0x08; /* Truncated Page Complete */ } + /* Enable Authenticated Payload Timeout Expired event if supported */ + if (lmp_ping_capable(hdev)) + events[2] |= 0x80; + hci_req_add(req, HCI_OP_SET_EVENT_MASK_PAGE_2, sizeof(events), events); } @@ -1322,21 +1673,8 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt) if (hdev->commands[5] & 0x10) hci_setup_link_policy(req); - if (lmp_le_capable(hdev)) { - if (test_bit(HCI_SETUP, &hdev->dev_flags)) { - /* If the controller has a public BD_ADDR, then - * by default use that one. If this is a LE only - * controller without a public address, default - * to the random address. - */ - if (bacmp(&hdev->bdaddr, BDADDR_ANY)) - hdev->own_addr_type = ADDR_LE_DEV_PUBLIC; - else - hdev->own_addr_type = ADDR_LE_DEV_RANDOM; - } - + if (lmp_le_capable(hdev)) hci_set_le_support(req); - } /* Read features beyond page 1 if available */ for (p = 2; p < HCI_MAX_PAGES && p <= hdev->max_page; p++) { @@ -1359,6 +1697,15 @@ static void hci_init4_req(struct hci_request *req, unsigned long opt) /* Check for Synchronization Train support */ if (lmp_sync_train_capable(hdev)) hci_req_add(req, HCI_OP_READ_SYNC_TRAIN_PARAMS, 0, NULL); + + /* Enable Secure Connections if supported and configured */ + if ((lmp_sc_capable(hdev) || + test_bit(HCI_FORCE_SC, &hdev->dev_flags)) && + test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) { + u8 support = 0x01; + hci_req_add(req, HCI_OP_WRITE_SC_SUPPORT, + sizeof(support), &support); + } } static int __hci_init(struct hci_dev *hdev) @@ -1417,8 +1764,6 @@ static int __hci_init(struct hci_dev *hdev) hdev, &inquiry_cache_fops); debugfs_create_file("link_keys", 0400, hdev->debugfs, hdev, &link_keys_fops); - debugfs_create_file("use_debug_keys", 0444, hdev->debugfs, - hdev, &use_debug_keys_fops); debugfs_create_file("dev_class", 0444, hdev->debugfs, hdev, &dev_class_fops); debugfs_create_file("voice_setting", 0444, hdev->debugfs, @@ -1430,6 +1775,10 @@ static int __hci_init(struct hci_dev *hdev) hdev, &auto_accept_delay_fops); debugfs_create_file("ssp_debug_mode", 0644, hdev->debugfs, hdev, &ssp_debug_mode_fops); + debugfs_create_file("force_sc_support", 0644, hdev->debugfs, + hdev, &force_sc_support_fops); + debugfs_create_file("sc_only_mode", 0444, hdev->debugfs, + hdev, &sc_only_mode_fops); } if (lmp_sniff_capable(hdev)) { @@ -1442,20 +1791,43 @@ static int __hci_init(struct hci_dev *hdev) } if (lmp_le_capable(hdev)) { + debugfs_create_file("identity", 0400, hdev->debugfs, + hdev, &identity_fops); + debugfs_create_file("rpa_timeout", 0644, hdev->debugfs, + hdev, &rpa_timeout_fops); + debugfs_create_file("random_address", 0444, hdev->debugfs, + hdev, &random_address_fops); + debugfs_create_file("static_address", 0444, hdev->debugfs, + hdev, &static_address_fops); + + /* For controllers with a public address, provide a debug + * option to force the usage of the configured static + * address. By default the public address is used. + */ + if (bacmp(&hdev->bdaddr, BDADDR_ANY)) + debugfs_create_file("force_static_address", 0644, + hdev->debugfs, hdev, + &force_static_address_fops); + debugfs_create_u8("white_list_size", 0444, hdev->debugfs, &hdev->le_white_list_size); - debugfs_create_file("static_address", 0444, hdev->debugfs, - hdev, &static_address_fops); - debugfs_create_file("own_address_type", 0644, hdev->debugfs, - hdev, &own_address_type_fops); + debugfs_create_file("white_list", 0444, hdev->debugfs, hdev, + &white_list_fops); + debugfs_create_file("identity_resolving_keys", 0400, + hdev->debugfs, hdev, + &identity_resolving_keys_fops); debugfs_create_file("long_term_keys", 0400, hdev->debugfs, hdev, &long_term_keys_fops); debugfs_create_file("conn_min_interval", 0644, hdev->debugfs, hdev, &conn_min_interval_fops); debugfs_create_file("conn_max_interval", 0644, hdev->debugfs, hdev, &conn_max_interval_fops); + debugfs_create_file("adv_channel_map", 0644, hdev->debugfs, + hdev, &adv_channel_map_fops); debugfs_create_file("6lowpan", 0644, hdev->debugfs, hdev, &lowpan_debugfs_fops); + debugfs_create_file("le_auto_conn", 0644, hdev->debugfs, hdev, + &le_auto_conn_fops); } return 0; @@ -1548,6 +1920,8 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state) switch (state) { case DISCOVERY_STOPPED: + hci_update_background_scan(hdev); + if (hdev->discovery.state != DISCOVERY_STARTING) mgmt_discovering(hdev, 0); break; @@ -1876,10 +2250,15 @@ static int hci_dev_do_open(struct hci_dev *hdev) * be able to determine if there is a public address * or not. * + * In case of user channel usage, it is not important + * if a public address or static random address is + * available. + * * This check is only valid for BR/EDR controllers * since AMP controllers do not have an address. */ - if (hdev->dev_type == HCI_BREDR && + if (!test_bit(HCI_USER_CHANNEL, &hdev->dev_flags) && + hdev->dev_type == HCI_BREDR && !bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY)) { ret = -EADDRNOTAVAIL; @@ -1916,6 +2295,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) if (!ret) { hci_dev_hold(hdev); + set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); set_bit(HCI_UP, &hdev->flags); hci_notify(hdev, HCI_DEV_UP); if (!test_bit(HCI_SETUP, &hdev->dev_flags) && @@ -2014,9 +2394,13 @@ static int hci_dev_do_close(struct hci_dev *hdev) cancel_delayed_work_sync(&hdev->le_scan_disable); + if (test_bit(HCI_MGMT, &hdev->dev_flags)) + cancel_delayed_work_sync(&hdev->rpa_expired); + hci_dev_lock(hdev); hci_inquiry_cache_flush(hdev); hci_conn_hash_flush(hdev); + hci_pend_le_conns_clear(hdev); hci_dev_unlock(hdev); hci_notify(hdev, HCI_DEV_DOWN); @@ -2074,6 +2458,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) memset(hdev->eir, 0, sizeof(hdev->eir)); memset(hdev->dev_class, 0, sizeof(hdev->dev_class)); + bacpy(&hdev->random_addr, BDADDR_ANY); hci_req_unlock(hdev); @@ -2437,7 +2822,7 @@ static void hci_discov_off(struct work_struct *work) mgmt_discoverable_timeout(hdev); } -int hci_uuids_clear(struct hci_dev *hdev) +void hci_uuids_clear(struct hci_dev *hdev) { struct bt_uuid *uuid, *tmp; @@ -2445,11 +2830,9 @@ int hci_uuids_clear(struct hci_dev *hdev) list_del(&uuid->list); kfree(uuid); } - - return 0; } -int hci_link_keys_clear(struct hci_dev *hdev) +void hci_link_keys_clear(struct hci_dev *hdev) { struct list_head *p, *n; @@ -2461,11 +2844,9 @@ int hci_link_keys_clear(struct hci_dev *hdev) list_del(p); kfree(key); } - - return 0; } -int hci_smp_ltks_clear(struct hci_dev *hdev) +void hci_smp_ltks_clear(struct hci_dev *hdev) { struct smp_ltk *k, *tmp; @@ -2473,8 +2854,16 @@ int hci_smp_ltks_clear(struct hci_dev *hdev) list_del(&k->list); kfree(k); } +} - return 0; +void hci_smp_irks_clear(struct hci_dev *hdev) +{ + struct smp_irk *k, *tmp; + + list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { + list_del(&k->list); + kfree(k); + } } struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) @@ -2524,13 +2913,24 @@ static bool hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn, return false; } -struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, u8 rand[8]) +static bool ltk_type_master(u8 type) +{ + if (type == HCI_SMP_STK || type == HCI_SMP_LTK) + return true; + + return false; +} + +struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, __le64 rand, + bool master) { struct smp_ltk *k; list_for_each_entry(k, &hdev->long_term_keys, list) { - if (k->ediv != ediv || - memcmp(rand, k->rand, sizeof(k->rand))) + if (k->ediv != ediv || k->rand != rand) + continue; + + if (ltk_type_master(k->type) != master) continue; return k; @@ -2540,18 +2940,56 @@ struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, u8 rand[8]) } struct smp_ltk *hci_find_ltk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, - u8 addr_type) + u8 addr_type, bool master) { struct smp_ltk *k; list_for_each_entry(k, &hdev->long_term_keys, list) if (addr_type == k->bdaddr_type && - bacmp(bdaddr, &k->bdaddr) == 0) + bacmp(bdaddr, &k->bdaddr) == 0 && + ltk_type_master(k->type) == master) return k; return NULL; } +struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa) +{ + struct smp_irk *irk; + + list_for_each_entry(irk, &hdev->identity_resolving_keys, list) { + if (!bacmp(&irk->rpa, rpa)) + return irk; + } + + list_for_each_entry(irk, &hdev->identity_resolving_keys, list) { + if (smp_irk_matches(hdev->tfm_aes, irk->val, rpa)) { + bacpy(&irk->rpa, rpa); + return irk; + } + } + + return NULL; +} + +struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type) +{ + struct smp_irk *irk; + + /* Identity Address must be public or static random */ + if (addr_type == ADDR_LE_DEV_RANDOM && (bdaddr->b[5] & 0xc0) != 0xc0) + return NULL; + + list_for_each_entry(irk, &hdev->identity_resolving_keys, list) { + if (addr_type == irk->addr_type && + bacmp(bdaddr, &irk->bdaddr) == 0) + return irk; + } + + return NULL; +} + int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len) { @@ -2565,7 +3003,7 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, key = old_key; } else { old_key_type = conn ? conn->key_type : 0xff; - key = kzalloc(sizeof(*key), GFP_ATOMIC); + key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) return -ENOMEM; list_add(&key->list, &hdev->link_keys); @@ -2605,22 +3043,20 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, return 0; } -int hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type, - int new_key, u8 authenticated, u8 tk[16], u8 enc_size, __le16 - ediv, u8 rand[8]) +struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type, u8 type, u8 authenticated, + u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand) { struct smp_ltk *key, *old_key; + bool master = ltk_type_master(type); - if (!(type & HCI_SMP_STK) && !(type & HCI_SMP_LTK)) - return 0; - - old_key = hci_find_ltk_by_addr(hdev, bdaddr, addr_type); + old_key = hci_find_ltk_by_addr(hdev, bdaddr, addr_type, master); if (old_key) key = old_key; else { - key = kzalloc(sizeof(*key), GFP_ATOMIC); + key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) - return -ENOMEM; + return NULL; list_add(&key->list, &hdev->long_term_keys); } @@ -2629,17 +3065,34 @@ int hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type, memcpy(key->val, tk, sizeof(key->val)); key->authenticated = authenticated; key->ediv = ediv; + key->rand = rand; key->enc_size = enc_size; key->type = type; - memcpy(key->rand, rand, sizeof(key->rand)); - if (!new_key) - return 0; + return key; +} + +struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 addr_type, u8 val[16], bdaddr_t *rpa) +{ + struct smp_irk *irk; - if (type & HCI_SMP_LTK) - mgmt_new_ltk(hdev, key, 1); + irk = hci_find_irk_by_addr(hdev, bdaddr, addr_type); + if (!irk) { + irk = kzalloc(sizeof(*irk), GFP_KERNEL); + if (!irk) + return NULL; - return 0; + bacpy(&irk->bdaddr, bdaddr); + irk->addr_type = addr_type; + + list_add(&irk->list, &hdev->identity_resolving_keys); + } + + memcpy(irk->val, val, 16); + bacpy(&irk->rpa, rpa); + + return irk; } int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) @@ -2658,21 +3111,38 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) return 0; } -int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr) +int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct smp_ltk *k, *tmp; + int removed = 0; list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { - if (bacmp(bdaddr, &k->bdaddr)) + if (bacmp(bdaddr, &k->bdaddr) || k->bdaddr_type != bdaddr_type) continue; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del(&k->list); kfree(k); + removed++; } - return 0; + return removed ? 0 : -ENOENT; +} + +void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) +{ + struct smp_irk *k, *tmp; + + list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { + if (bacmp(bdaddr, &k->bdaddr) || k->addr_type != addr_type) + continue; + + BT_DBG("%s removing %pMR", hdev->name, bdaddr); + + list_del(&k->list); + kfree(k); + } } /* HCI command timer function */ @@ -2721,7 +3191,7 @@ int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr) return 0; } -int hci_remote_oob_data_clear(struct hci_dev *hdev) +void hci_remote_oob_data_clear(struct hci_dev *hdev) { struct oob_data *data, *n; @@ -2729,19 +3199,43 @@ int hci_remote_oob_data_clear(struct hci_dev *hdev) list_del(&data->list); kfree(data); } +} + +int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 *hash, u8 *randomizer) +{ + struct oob_data *data; + + data = hci_find_remote_oob_data(hdev, bdaddr); + if (!data) { + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + bacpy(&data->bdaddr, bdaddr); + list_add(&data->list, &hdev->remote_oob_data); + } + + memcpy(data->hash192, hash, sizeof(data->hash192)); + memcpy(data->randomizer192, randomizer, sizeof(data->randomizer192)); + + memset(data->hash256, 0, sizeof(data->hash256)); + memset(data->randomizer256, 0, sizeof(data->randomizer256)); + + BT_DBG("%s for %pMR", hdev->name, bdaddr); return 0; } -int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash, - u8 *randomizer) +int hci_add_remote_oob_ext_data(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 *hash192, u8 *randomizer192, + u8 *hash256, u8 *randomizer256) { struct oob_data *data; data = hci_find_remote_oob_data(hdev, bdaddr); - if (!data) { - data = kmalloc(sizeof(*data), GFP_ATOMIC); + data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; @@ -2749,8 +3243,11 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash, list_add(&data->list, &hdev->remote_oob_data); } - memcpy(data->hash, hash, sizeof(data->hash)); - memcpy(data->randomizer, randomizer, sizeof(data->randomizer)); + memcpy(data->hash192, hash192, sizeof(data->hash192)); + memcpy(data->randomizer192, randomizer192, sizeof(data->randomizer192)); + + memcpy(data->hash256, hash256, sizeof(data->hash256)); + memcpy(data->randomizer256, randomizer256, sizeof(data->randomizer256)); BT_DBG("%s for %pMR", hdev->name, bdaddr); @@ -2770,7 +3267,7 @@ struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, return NULL; } -int hci_blacklist_clear(struct hci_dev *hdev) +static void hci_blacklist_clear(struct hci_dev *hdev) { struct list_head *p, *n; @@ -2780,8 +3277,6 @@ int hci_blacklist_clear(struct hci_dev *hdev) list_del(p); kfree(b); } - - return 0; } int hci_blacklist_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) @@ -2810,8 +3305,10 @@ int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; - if (!bacmp(bdaddr, BDADDR_ANY)) - return hci_blacklist_clear(hdev); + if (!bacmp(bdaddr, BDADDR_ANY)) { + hci_blacklist_clear(hdev); + return 0; + } entry = hci_blacklist_lookup(hdev, bdaddr, type); if (!entry) @@ -2823,6 +3320,262 @@ int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) return mgmt_device_unblocked(hdev, bdaddr, type); } +struct bdaddr_list *hci_white_list_lookup(struct hci_dev *hdev, + bdaddr_t *bdaddr, u8 type) +{ + struct bdaddr_list *b; + + list_for_each_entry(b, &hdev->le_white_list, list) { + if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) + return b; + } + + return NULL; +} + +void hci_white_list_clear(struct hci_dev *hdev) +{ + struct list_head *p, *n; + + list_for_each_safe(p, n, &hdev->le_white_list) { + struct bdaddr_list *b = list_entry(p, struct bdaddr_list, list); + + list_del(p); + kfree(b); + } +} + +int hci_white_list_add(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) +{ + struct bdaddr_list *entry; + + if (!bacmp(bdaddr, BDADDR_ANY)) + return -EBADF; + + entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + bacpy(&entry->bdaddr, bdaddr); + entry->bdaddr_type = type; + + list_add(&entry->list, &hdev->le_white_list); + + return 0; +} + +int hci_white_list_del(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) +{ + struct bdaddr_list *entry; + + if (!bacmp(bdaddr, BDADDR_ANY)) + return -EBADF; + + entry = hci_white_list_lookup(hdev, bdaddr, type); + if (!entry) + return -ENOENT; + + list_del(&entry->list); + kfree(entry); + + return 0; +} + +/* This function requires the caller holds hdev->lock */ +struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, + bdaddr_t *addr, u8 addr_type) +{ + struct hci_conn_params *params; + + list_for_each_entry(params, &hdev->le_conn_params, list) { + if (bacmp(¶ms->addr, addr) == 0 && + params->addr_type == addr_type) { + return params; + } + } + + return NULL; +} + +static bool is_connected(struct hci_dev *hdev, bdaddr_t *addr, u8 type) +{ + struct hci_conn *conn; + + conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, addr); + if (!conn) + return false; + + if (conn->dst_type != type) + return false; + + if (conn->state != BT_CONNECTED) + return false; + + return true; +} + +static bool is_identity_address(bdaddr_t *addr, u8 addr_type) +{ + if (addr_type == ADDR_LE_DEV_PUBLIC) + return true; + + /* Check for Random Static address type */ + if ((addr->b[5] & 0xc0) == 0xc0) + return true; + + return false; +} + +/* This function requires the caller holds hdev->lock */ +int hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type, + u8 auto_connect, u16 conn_min_interval, + u16 conn_max_interval) +{ + struct hci_conn_params *params; + + if (!is_identity_address(addr, addr_type)) + return -EINVAL; + + params = hci_conn_params_lookup(hdev, addr, addr_type); + if (params) + goto update; + + params = kzalloc(sizeof(*params), GFP_KERNEL); + if (!params) { + BT_ERR("Out of memory"); + return -ENOMEM; + } + + bacpy(¶ms->addr, addr); + params->addr_type = addr_type; + + list_add(¶ms->list, &hdev->le_conn_params); + +update: + params->conn_min_interval = conn_min_interval; + params->conn_max_interval = conn_max_interval; + params->auto_connect = auto_connect; + + switch (auto_connect) { + case HCI_AUTO_CONN_DISABLED: + case HCI_AUTO_CONN_LINK_LOSS: + hci_pend_le_conn_del(hdev, addr, addr_type); + break; + case HCI_AUTO_CONN_ALWAYS: + if (!is_connected(hdev, addr, addr_type)) + hci_pend_le_conn_add(hdev, addr, addr_type); + break; + } + + BT_DBG("addr %pMR (type %u) auto_connect %u conn_min_interval 0x%.4x " + "conn_max_interval 0x%.4x", addr, addr_type, auto_connect, + conn_min_interval, conn_max_interval); + + return 0; +} + +/* This function requires the caller holds hdev->lock */ +void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) +{ + struct hci_conn_params *params; + + params = hci_conn_params_lookup(hdev, addr, addr_type); + if (!params) + return; + + hci_pend_le_conn_del(hdev, addr, addr_type); + + list_del(¶ms->list); + kfree(params); + + BT_DBG("addr %pMR (type %u)", addr, addr_type); +} + +/* This function requires the caller holds hdev->lock */ +void hci_conn_params_clear(struct hci_dev *hdev) +{ + struct hci_conn_params *params, *tmp; + + list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) { + list_del(¶ms->list); + kfree(params); + } + + BT_DBG("All LE connection parameters were removed"); +} + +/* This function requires the caller holds hdev->lock */ +struct bdaddr_list *hci_pend_le_conn_lookup(struct hci_dev *hdev, + bdaddr_t *addr, u8 addr_type) +{ + struct bdaddr_list *entry; + + list_for_each_entry(entry, &hdev->pend_le_conns, list) { + if (bacmp(&entry->bdaddr, addr) == 0 && + entry->bdaddr_type == addr_type) + return entry; + } + + return NULL; +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_conn_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) +{ + struct bdaddr_list *entry; + + entry = hci_pend_le_conn_lookup(hdev, addr, addr_type); + if (entry) + goto done; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + BT_ERR("Out of memory"); + return; + } + + bacpy(&entry->bdaddr, addr); + entry->bdaddr_type = addr_type; + + list_add(&entry->list, &hdev->pend_le_conns); + + BT_DBG("addr %pMR (type %u)", addr, addr_type); + +done: + hci_update_background_scan(hdev); +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_conn_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) +{ + struct bdaddr_list *entry; + + entry = hci_pend_le_conn_lookup(hdev, addr, addr_type); + if (!entry) + goto done; + + list_del(&entry->list); + kfree(entry); + + BT_DBG("addr %pMR (type %u)", addr, addr_type); + +done: + hci_update_background_scan(hdev); +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_conns_clear(struct hci_dev *hdev) +{ + struct bdaddr_list *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &hdev->pend_le_conns, list) { + list_del(&entry->list); + kfree(entry); + } + + BT_DBG("All LE pending connections cleared"); +} + static void inquiry_complete(struct hci_dev *hdev, u8 status) { if (status) { @@ -2882,7 +3635,6 @@ static void le_scan_disable_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, le_scan_disable.work); - struct hci_cp_le_set_scan_enable cp; struct hci_request req; int err; @@ -2890,15 +3642,128 @@ static void le_scan_disable_work(struct work_struct *work) hci_req_init(&req, hdev); - memset(&cp, 0, sizeof(cp)); - cp.enable = LE_SCAN_DISABLE; - hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); + hci_req_add_le_scan_disable(&req); err = hci_req_run(&req, le_scan_disable_work_complete); if (err) BT_ERR("Disable LE scanning request failed: err %d", err); } +static void set_random_addr(struct hci_request *req, bdaddr_t *rpa) +{ + struct hci_dev *hdev = req->hdev; + + /* If we're advertising or initiating an LE connection we can't + * go ahead and change the random address at this time. This is + * because the eventual initiator address used for the + * subsequently created connection will be undefined (some + * controllers use the new address and others the one we had + * when the operation started). + * + * In this kind of scenario skip the update and let the random + * address be updated at the next cycle. + */ + if (test_bit(HCI_ADVERTISING, &hdev->dev_flags) || + hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) { + BT_DBG("Deferring random address update"); + return; + } + + hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, rpa); +} + +int hci_update_random_address(struct hci_request *req, bool require_privacy, + u8 *own_addr_type) +{ + struct hci_dev *hdev = req->hdev; + int err; + + /* If privacy is enabled use a resolvable private address. If + * current RPA has expired or there is something else than + * the current RPA in use, then generate a new one. + */ + if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) { + int to; + + *own_addr_type = ADDR_LE_DEV_RANDOM; + + if (!test_and_clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags) && + !bacmp(&hdev->random_addr, &hdev->rpa)) + return 0; + + err = smp_generate_rpa(hdev->tfm_aes, hdev->irk, &hdev->rpa); + if (err < 0) { + BT_ERR("%s failed to generate new RPA", hdev->name); + return err; + } + + set_random_addr(req, &hdev->rpa); + + to = msecs_to_jiffies(hdev->rpa_timeout * 1000); + queue_delayed_work(hdev->workqueue, &hdev->rpa_expired, to); + + return 0; + } + + /* In case of required privacy without resolvable private address, + * use an unresolvable private address. This is useful for active + * scanning and non-connectable advertising. + */ + if (require_privacy) { + bdaddr_t urpa; + + get_random_bytes(&urpa, 6); + urpa.b[5] &= 0x3f; /* Clear two most significant bits */ + + *own_addr_type = ADDR_LE_DEV_RANDOM; + set_random_addr(req, &urpa); + return 0; + } + + /* If forcing static address is in use or there is no public + * address use the static address as random address (but skip + * the HCI command if the current random address is already the + * static one. + */ + if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) || + !bacmp(&hdev->bdaddr, BDADDR_ANY)) { + *own_addr_type = ADDR_LE_DEV_RANDOM; + if (bacmp(&hdev->static_addr, &hdev->random_addr)) + hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, + &hdev->static_addr); + return 0; + } + + /* Neither privacy nor static address is being used so use a + * public address. + */ + *own_addr_type = ADDR_LE_DEV_PUBLIC; + + return 0; +} + +/* Copy the Identity Address of the controller. + * + * If the controller has a public BD_ADDR, then by default use that one. + * If this is a LE only controller without a public address, default to + * the static random address. + * + * For debugging purposes it is possible to force controllers with a + * public address to use the static random address instead. + */ +void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, + u8 *bdaddr_type) +{ + if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dev_flags) || + !bacmp(&hdev->bdaddr, BDADDR_ANY)) { + bacpy(bdaddr, &hdev->static_addr); + *bdaddr_type = ADDR_LE_DEV_RANDOM; + } else { + bacpy(bdaddr, &hdev->bdaddr); + *bdaddr_type = ADDR_LE_DEV_PUBLIC; + } +} + /* Alloc HCI device */ struct hci_dev *hci_alloc_dev(void) { @@ -2919,11 +3784,14 @@ struct hci_dev *hci_alloc_dev(void) hdev->sniff_max_interval = 800; hdev->sniff_min_interval = 80; + hdev->le_adv_channel_map = 0x07; hdev->le_scan_interval = 0x0060; hdev->le_scan_window = 0x0030; hdev->le_conn_min_interval = 0x0028; hdev->le_conn_max_interval = 0x0038; + hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT; + mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); @@ -2932,7 +3800,11 @@ struct hci_dev *hci_alloc_dev(void) INIT_LIST_HEAD(&hdev->uuids); INIT_LIST_HEAD(&hdev->link_keys); INIT_LIST_HEAD(&hdev->long_term_keys); + INIT_LIST_HEAD(&hdev->identity_resolving_keys); INIT_LIST_HEAD(&hdev->remote_oob_data); + INIT_LIST_HEAD(&hdev->le_white_list); + INIT_LIST_HEAD(&hdev->le_conn_params); + INIT_LIST_HEAD(&hdev->pend_le_conns); INIT_LIST_HEAD(&hdev->conn_hash.list); INIT_WORK(&hdev->rx_work, hci_rx_work); @@ -3017,9 +3889,18 @@ int hci_register_dev(struct hci_dev *hdev) dev_set_name(&hdev->dev, "%s", hdev->name); + hdev->tfm_aes = crypto_alloc_blkcipher("ecb(aes)", 0, + CRYPTO_ALG_ASYNC); + if (IS_ERR(hdev->tfm_aes)) { + BT_ERR("Unable to create crypto context"); + error = PTR_ERR(hdev->tfm_aes); + hdev->tfm_aes = NULL; + goto err_wqueue; + } + error = device_add(&hdev->dev); if (error < 0) - goto err_wqueue; + goto err_tfm; hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, RFKILL_TYPE_BLUETOOTH, &hci_rfkill_ops, @@ -3055,6 +3936,8 @@ int hci_register_dev(struct hci_dev *hdev) return id; +err_tfm: + crypto_free_blkcipher(hdev->tfm_aes); err_wqueue: destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); @@ -3105,6 +3988,9 @@ void hci_unregister_dev(struct hci_dev *hdev) rfkill_destroy(hdev->rfkill); } + if (hdev->tfm_aes) + crypto_free_blkcipher(hdev->tfm_aes); + device_del(&hdev->dev); debugfs_remove_recursive(hdev->debugfs); @@ -3117,7 +4003,11 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_uuids_clear(hdev); hci_link_keys_clear(hdev); hci_smp_ltks_clear(hdev); + hci_smp_irks_clear(hdev); hci_remote_oob_data_clear(hdev); + hci_white_list_clear(hdev); + hci_conn_params_clear(hdev); + hci_pend_le_conns_clear(hdev); hci_dev_unlock(hdev); hci_dev_put(hdev); @@ -4345,3 +5235,104 @@ static void hci_cmd_work(struct work_struct *work) } } } + +void hci_req_add_le_scan_disable(struct hci_request *req) +{ + struct hci_cp_le_set_scan_enable cp; + + memset(&cp, 0, sizeof(cp)); + cp.enable = LE_SCAN_DISABLE; + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); +} + +void hci_req_add_le_passive_scan(struct hci_request *req) +{ + struct hci_cp_le_set_scan_param param_cp; + struct hci_cp_le_set_scan_enable enable_cp; + struct hci_dev *hdev = req->hdev; + u8 own_addr_type; + + /* Set require_privacy to true to avoid identification from + * unknown peer devices. Since this is passive scanning, no + * SCAN_REQ using the local identity should be sent. Mandating + * privacy is just an extra precaution. + */ + if (hci_update_random_address(req, true, &own_addr_type)) + return; + + memset(¶m_cp, 0, sizeof(param_cp)); + param_cp.type = LE_SCAN_PASSIVE; + param_cp.interval = cpu_to_le16(hdev->le_scan_interval); + param_cp.window = cpu_to_le16(hdev->le_scan_window); + param_cp.own_address_type = own_addr_type; + hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), + ¶m_cp); + + memset(&enable_cp, 0, sizeof(enable_cp)); + enable_cp.enable = LE_SCAN_ENABLE; + enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), + &enable_cp); +} + +static void update_background_scan_complete(struct hci_dev *hdev, u8 status) +{ + if (status) + BT_DBG("HCI request failed to update background scanning: " + "status 0x%2.2x", status); +} + +/* This function controls the background scanning based on hdev->pend_le_conns + * list. If there are pending LE connection we start the background scanning, + * otherwise we stop it. + * + * This function requires the caller holds hdev->lock. + */ +void hci_update_background_scan(struct hci_dev *hdev) +{ + struct hci_request req; + struct hci_conn *conn; + int err; + + hci_req_init(&req, hdev); + + if (list_empty(&hdev->pend_le_conns)) { + /* If there is no pending LE connections, we should stop + * the background scanning. + */ + + /* If controller is not scanning we are done. */ + if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + return; + + hci_req_add_le_scan_disable(&req); + + BT_DBG("%s stopping background scanning", hdev->name); + } else { + /* If there is at least one pending LE connection, we should + * keep the background scan running. + */ + + /* If controller is connecting, we should not start scanning + * since some controllers are not able to scan and connect at + * the same time. + */ + conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT); + if (conn) + return; + + /* If controller is currently scanning, we stop it to ensure we + * don't miss any advertising (due to duplicates filter). + */ + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + hci_req_add_le_scan_disable(&req); + + hci_req_add_le_passive_scan(&req); + + BT_DBG("%s starting background scanning", hdev->name); + } + + err = hci_req_run(&req, update_background_scan_complete); + if (err) + BT_ERR("Failed to run HCI request: err %d", err); +} diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 5f812455a450..49774912cb01 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -199,6 +199,8 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) memset(hdev->scan_rsp_data, 0, sizeof(hdev->scan_rsp_data)); hdev->scan_rsp_data_len = 0; + hdev->le_scan_type = LE_SCAN_PASSIVE; + hdev->ssp_debug_mode = 0; } @@ -461,6 +463,34 @@ static void hci_cc_write_ssp_mode(struct hci_dev *hdev, struct sk_buff *skb) } } +static void hci_cc_write_sc_support(struct hci_dev *hdev, struct sk_buff *skb) +{ + u8 status = *((u8 *) skb->data); + struct hci_cp_write_sc_support *sent; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + sent = hci_sent_cmd_data(hdev, HCI_OP_WRITE_SC_SUPPORT); + if (!sent) + return; + + if (!status) { + if (sent->support) + hdev->features[1][0] |= LMP_HOST_SC; + else + hdev->features[1][0] &= ~LMP_HOST_SC; + } + + if (test_bit(HCI_MGMT, &hdev->dev_flags)) + mgmt_sc_enable_complete(hdev, sent->support, status); + else if (!status) { + if (sent->support) + set_bit(HCI_SC_ENABLED, &hdev->dev_flags); + else + clear_bit(HCI_SC_ENABLED, &hdev->dev_flags); + } +} + static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_local_version *rp = (void *) skb->data; @@ -904,16 +934,50 @@ static void hci_cc_user_passkey_neg_reply(struct hci_dev *hdev, hci_dev_unlock(hdev); } -static void hci_cc_read_local_oob_data_reply(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_cc_read_local_oob_data(struct hci_dev *hdev, + struct sk_buff *skb) { struct hci_rp_read_local_oob_data *rp = (void *) skb->data; BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); hci_dev_lock(hdev); - mgmt_read_local_oob_data_reply_complete(hdev, rp->hash, - rp->randomizer, rp->status); + mgmt_read_local_oob_data_complete(hdev, rp->hash, rp->randomizer, + NULL, NULL, rp->status); + hci_dev_unlock(hdev); +} + +static void hci_cc_read_local_oob_ext_data(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_read_local_oob_ext_data *rp = (void *) skb->data; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + hci_dev_lock(hdev); + mgmt_read_local_oob_data_complete(hdev, rp->hash192, rp->randomizer192, + rp->hash256, rp->randomizer256, + rp->status); + hci_dev_unlock(hdev); +} + + +static void hci_cc_le_set_random_addr(struct hci_dev *hdev, struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + bdaddr_t *sent; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_RANDOM_ADDR); + if (!sent) + return; + + hci_dev_lock(hdev); + + if (!status) + bacpy(&hdev->random_addr, sent); + hci_dev_unlock(hdev); } @@ -929,12 +993,27 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); - if (!status) { - if (*sent) - set_bit(HCI_ADVERTISING, &hdev->dev_flags); - else - clear_bit(HCI_ADVERTISING, &hdev->dev_flags); - } + if (!status) + mgmt_advertising(hdev, *sent); + + hci_dev_unlock(hdev); +} + +static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_cp_le_set_scan_param *cp; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_PARAM); + if (!cp) + return; + + hci_dev_lock(hdev); + + if (!status) + hdev->le_scan_type = cp->type; hci_dev_unlock(hdev); } @@ -960,7 +1039,19 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, break; case LE_SCAN_DISABLE: + /* Cancel this timer so that we don't try to disable scanning + * when it's already disabled. + */ + cancel_delayed_work(&hdev->le_scan_disable); + clear_bit(HCI_LE_SCAN, &hdev->dev_flags); + /* The HCI_LE_SCAN_INTERRUPTED flag indicates that we + * interrupted scanning due to a connect request. Mark + * therefore discovery as stopped. + */ + if (test_and_clear_bit(HCI_LE_SCAN_INTERRUPTED, + &hdev->dev_flags)) + hci_discovery_set_state(hdev, DISCOVERY_STOPPED); break; default: @@ -980,6 +1071,49 @@ static void hci_cc_le_read_white_list_size(struct hci_dev *hdev, hdev->le_white_list_size = rp->size; } +static void hci_cc_le_clear_white_list(struct hci_dev *hdev, + struct sk_buff *skb) +{ + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (!status) + hci_white_list_clear(hdev); +} + +static void hci_cc_le_add_to_white_list(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_add_to_white_list *sent; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_WHITE_LIST); + if (!sent) + return; + + if (!status) + hci_white_list_add(hdev, &sent->bdaddr, sent->bdaddr_type); +} + +static void hci_cc_le_del_from_white_list(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_del_from_white_list *sent; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_DEL_FROM_WHITE_LIST); + if (!sent) + return; + + if (!status) + hci_white_list_del(hdev, &sent->bdaddr, sent->bdaddr_type); +} + static void hci_cc_le_read_supported_states(struct hci_dev *hdev, struct sk_buff *skb) { @@ -1020,6 +1154,25 @@ static void hci_cc_write_le_host_supported(struct hci_dev *hdev, } } +static void hci_cc_set_adv_param(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_cp_le_set_adv_param *cp; + u8 status = *((u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_PARAM); + if (!cp) + return; + + hci_dev_lock(hdev); + hdev->adv_addr_type = cp->own_address_type; + hci_dev_unlock(hdev); +} + static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev, struct sk_buff *skb) { @@ -1185,9 +1338,12 @@ static int hci_outgoing_auth_needed(struct hci_dev *hdev, return 0; /* Only request authentication for SSP connections or non-SSP - * devices with sec_level HIGH or if MITM protection is requested */ + * devices with sec_level MEDIUM or HIGH or if MITM protection + * is requested. + */ if (!hci_conn_ssp_enabled(conn) && !(conn->auth_type & 0x01) && - conn->pending_sec_level != BT_SECURITY_HIGH) + conn->pending_sec_level != BT_SECURITY_HIGH && + conn->pending_sec_level != BT_SECURITY_MEDIUM) return 0; return 1; @@ -1518,6 +1674,87 @@ static void hci_cs_accept_phylink(struct hci_dev *hdev, u8 status) amp_write_remote_assoc(hdev, cp->phy_handle); } +static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) +{ + struct hci_cp_le_create_conn *cp; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + /* All connection failure handling is taken care of by the + * hci_le_conn_failed function which is triggered by the HCI + * request completion callbacks used for connecting. + */ + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_CREATE_CONN); + if (!cp) + return; + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->peer_addr); + if (!conn) + goto unlock; + + /* Store the initiator and responder address information which + * is needed for SMP. These values will not change during the + * lifetime of the connection. + */ + conn->init_addr_type = cp->own_address_type; + if (cp->own_address_type == ADDR_LE_DEV_RANDOM) + bacpy(&conn->init_addr, &hdev->random_addr); + else + bacpy(&conn->init_addr, &hdev->bdaddr); + + conn->resp_addr_type = cp->peer_addr_type; + bacpy(&conn->resp_addr, &cp->peer_addr); + + /* We don't want the connection attempt to stick around + * indefinitely since LE doesn't have a page timeout concept + * like BR/EDR. Set a timer for any connection that doesn't use + * the white list for connecting. + */ + if (cp->filter_policy == HCI_LE_USE_PEER_ADDR) + queue_delayed_work(conn->hdev->workqueue, + &conn->le_conn_timeout, + HCI_LE_CONN_TIMEOUT); + +unlock: + hci_dev_unlock(hdev); +} + +static void hci_cs_le_start_enc(struct hci_dev *hdev, u8 status) +{ + struct hci_cp_le_start_enc *cp; + struct hci_conn *conn; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (!status) + return; + + hci_dev_lock(hdev); + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_START_ENC); + if (!cp) + goto unlock; + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(cp->handle)); + if (!conn) + goto unlock; + + if (conn->state != BT_CONNECTED) + goto unlock; + + hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); + hci_conn_drop(conn); + +unlock: + hci_dev_unlock(hdev); +} + static void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); @@ -1659,7 +1896,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) } else { conn->state = BT_CLOSED; if (conn->type == ACL_LINK) - mgmt_connect_failed(hdev, &ev->bdaddr, conn->type, + mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, ev->status); } @@ -1738,9 +1975,9 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) bacpy(&cp.bdaddr, &ev->bdaddr); cp.pkt_type = cpu_to_le16(conn->pkt_type); - cp.tx_bandwidth = __constant_cpu_to_le32(0x00001f40); - cp.rx_bandwidth = __constant_cpu_to_le32(0x00001f40); - cp.max_latency = __constant_cpu_to_le16(0xffff); + cp.tx_bandwidth = cpu_to_le32(0x00001f40); + cp.rx_bandwidth = cpu_to_le32(0x00001f40); + cp.max_latency = cpu_to_le16(0xffff); cp.content_format = cpu_to_le16(hdev->voice_setting); cp.retrans_effort = 0xff; @@ -1780,7 +2017,9 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_disconn_complete *ev = (void *) skb->data; u8 reason = hci_to_mgmt_reason(ev->reason); + struct hci_conn_params *params; struct hci_conn *conn; + bool mgmt_connected; u8 type; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); @@ -1799,13 +2038,30 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->state = BT_CLOSED; - if (test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_disconnected(hdev, &conn->dst, conn->type, - conn->dst_type, reason); + mgmt_connected = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags); + mgmt_device_disconnected(hdev, &conn->dst, conn->type, conn->dst_type, + reason, mgmt_connected); if (conn->type == ACL_LINK && conn->flush_key) hci_remove_link_key(hdev, &conn->dst); + params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); + if (params) { + switch (params->auto_connect) { + case HCI_AUTO_CONN_LINK_LOSS: + if (ev->reason != HCI_ERROR_CONNECTION_TIMEOUT) + break; + /* Fall through */ + + case HCI_AUTO_CONN_ALWAYS: + hci_pend_le_conn_add(hdev, &conn->dst, conn->dst_type); + break; + + default: + break; + } + } + type = conn->type; hci_proto_disconn_cfm(conn, ev->reason); @@ -1943,34 +2199,57 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); - if (conn) { - if (!ev->status) { - if (ev->encrypt) { - /* Encryption implies authentication */ - conn->link_mode |= HCI_LM_AUTH; - conn->link_mode |= HCI_LM_ENCRYPT; - conn->sec_level = conn->pending_sec_level; - } else - conn->link_mode &= ~HCI_LM_ENCRYPT; + if (!conn) + goto unlock; + + if (!ev->status) { + if (ev->encrypt) { + /* Encryption implies authentication */ + conn->link_mode |= HCI_LM_AUTH; + conn->link_mode |= HCI_LM_ENCRYPT; + conn->sec_level = conn->pending_sec_level; + + /* P-256 authentication key implies FIPS */ + if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256) + conn->link_mode |= HCI_LM_FIPS; + + if ((conn->type == ACL_LINK && ev->encrypt == 0x02) || + conn->type == LE_LINK) + set_bit(HCI_CONN_AES_CCM, &conn->flags); + } else { + conn->link_mode &= ~HCI_LM_ENCRYPT; + clear_bit(HCI_CONN_AES_CCM, &conn->flags); } + } - clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); + clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); - if (ev->status && conn->state == BT_CONNECTED) { - hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); + if (ev->status && conn->state == BT_CONNECTED) { + hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); + hci_conn_drop(conn); + goto unlock; + } + + if (conn->state == BT_CONFIG) { + if (!ev->status) + conn->state = BT_CONNECTED; + + /* In Secure Connections Only mode, do not allow any + * connections that are not encrypted with AES-CCM + * using a P-256 authenticated combination key. + */ + if (test_bit(HCI_SC_ONLY, &hdev->dev_flags) && + (!test_bit(HCI_CONN_AES_CCM, &conn->flags) || + conn->key_type != HCI_LK_AUTH_COMBINATION_P256)) { + hci_proto_connect_cfm(conn, HCI_ERROR_AUTH_FAILURE); hci_conn_drop(conn); goto unlock; } - if (conn->state == BT_CONFIG) { - if (!ev->status) - conn->state = BT_CONNECTED; - - hci_proto_connect_cfm(conn, ev->status); - hci_conn_drop(conn); - } else - hci_encrypt_cfm(conn, ev->status, ev->encrypt); - } + hci_proto_connect_cfm(conn, ev->status); + hci_conn_drop(conn); + } else + hci_encrypt_cfm(conn, ev->status, ev->encrypt); unlock: hci_dev_unlock(hdev); @@ -2144,6 +2423,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_write_ssp_mode(hdev, skb); break; + case HCI_OP_WRITE_SC_SUPPORT: + hci_cc_write_sc_support(hdev, skb); + break; + case HCI_OP_READ_LOCAL_VERSION: hci_cc_read_local_version(hdev, skb); break; @@ -2213,7 +2496,11 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) break; case HCI_OP_READ_LOCAL_OOB_DATA: - hci_cc_read_local_oob_data_reply(hdev, skb); + hci_cc_read_local_oob_data(hdev, skb); + break; + + case HCI_OP_READ_LOCAL_OOB_EXT_DATA: + hci_cc_read_local_oob_ext_data(hdev, skb); break; case HCI_OP_LE_READ_BUFFER_SIZE: @@ -2244,10 +2531,18 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_user_passkey_neg_reply(hdev, skb); break; + case HCI_OP_LE_SET_RANDOM_ADDR: + hci_cc_le_set_random_addr(hdev, skb); + break; + case HCI_OP_LE_SET_ADV_ENABLE: hci_cc_le_set_adv_enable(hdev, skb); break; + case HCI_OP_LE_SET_SCAN_PARAM: + hci_cc_le_set_scan_param(hdev, skb); + break; + case HCI_OP_LE_SET_SCAN_ENABLE: hci_cc_le_set_scan_enable(hdev, skb); break; @@ -2256,6 +2551,18 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_le_read_white_list_size(hdev, skb); break; + case HCI_OP_LE_CLEAR_WHITE_LIST: + hci_cc_le_clear_white_list(hdev, skb); + break; + + case HCI_OP_LE_ADD_TO_WHITE_LIST: + hci_cc_le_add_to_white_list(hdev, skb); + break; + + case HCI_OP_LE_DEL_FROM_WHITE_LIST: + hci_cc_le_del_from_white_list(hdev, skb); + break; + case HCI_OP_LE_READ_SUPPORTED_STATES: hci_cc_le_read_supported_states(hdev, skb); break; @@ -2264,6 +2571,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cc_write_le_host_supported(hdev, skb); break; + case HCI_OP_LE_SET_ADV_PARAM: + hci_cc_set_adv_param(hdev, skb); + break; + case HCI_OP_WRITE_REMOTE_AMP_ASSOC: hci_cc_write_remote_amp_assoc(hdev, skb); break; @@ -2351,6 +2662,14 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cs_accept_phylink(hdev, ev->status); break; + case HCI_OP_LE_CREATE_CONN: + hci_cs_le_create_conn(hdev, ev->status); + break; + + case HCI_OP_LE_START_ENC: + hci_cs_le_start_enc(hdev, ev->status); + break; + default: BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); break; @@ -2630,7 +2949,8 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb) conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); if (conn) { - if (key->type == HCI_LK_UNAUTH_COMBINATION && + if ((key->type == HCI_LK_UNAUTH_COMBINATION_P192 || + key->type == HCI_LK_UNAUTH_COMBINATION_P256) && conn->auth_type != 0xff && (conn->auth_type & 0x01)) { BT_DBG("%s ignoring unauthenticated key", hdev->name); goto not_found; @@ -2844,6 +3164,9 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev, * features do not indicate SSP support */ clear_bit(HCI_CONN_SSP_ENABLED, &conn->flags); } + + if (ev->features[0] & LMP_HOST_SC) + set_bit(HCI_CONN_SC_ENABLED, &conn->flags); } if (conn->state != BT_CONFIG) @@ -2905,6 +3228,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, case 0x1c: /* SCO interval rejected */ case 0x1a: /* Unsupported Remote Feature */ case 0x1f: /* Unspecified error */ + case 0x20: /* Unsupported LMP Parameter value */ if (conn->out) { conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) | (hdev->esco_type & EDR_ESCO_MASK); @@ -3194,8 +3518,8 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev, } confirm: - mgmt_user_confirm_request(hdev, &ev->bdaddr, ACL_LINK, 0, ev->passkey, - confirm_hint); + mgmt_user_confirm_request(hdev, &ev->bdaddr, ACL_LINK, 0, + le32_to_cpu(ev->passkey), confirm_hint); unlock: hci_dev_unlock(hdev); @@ -3337,20 +3661,36 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev, data = hci_find_remote_oob_data(hdev, &ev->bdaddr); if (data) { - struct hci_cp_remote_oob_data_reply cp; + if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) { + struct hci_cp_remote_oob_ext_data_reply cp; - bacpy(&cp.bdaddr, &ev->bdaddr); - memcpy(cp.hash, data->hash, sizeof(cp.hash)); - memcpy(cp.randomizer, data->randomizer, sizeof(cp.randomizer)); + bacpy(&cp.bdaddr, &ev->bdaddr); + memcpy(cp.hash192, data->hash192, sizeof(cp.hash192)); + memcpy(cp.randomizer192, data->randomizer192, + sizeof(cp.randomizer192)); + memcpy(cp.hash256, data->hash256, sizeof(cp.hash256)); + memcpy(cp.randomizer256, data->randomizer256, + sizeof(cp.randomizer256)); + + hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_EXT_DATA_REPLY, + sizeof(cp), &cp); + } else { + struct hci_cp_remote_oob_data_reply cp; + + bacpy(&cp.bdaddr, &ev->bdaddr); + memcpy(cp.hash, data->hash192, sizeof(cp.hash)); + memcpy(cp.randomizer, data->randomizer192, + sizeof(cp.randomizer)); - hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY, sizeof(cp), - &cp); + hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_REPLY, + sizeof(cp), &cp); + } } else { struct hci_cp_remote_oob_data_neg_reply cp; bacpy(&cp.bdaddr, &ev->bdaddr); - hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY, sizeof(cp), - &cp); + hci_send_cmd(hdev, HCI_OP_REMOTE_OOB_DATA_NEG_REPLY, + sizeof(cp), &cp); } unlock: @@ -3484,6 +3824,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_conn_complete *ev = (void *) skb->data; struct hci_conn *conn; + struct smp_irk *irk; BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); @@ -3514,19 +3855,70 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) conn->out = true; conn->link_mode |= HCI_LM_MASTER; } + + /* If we didn't have a hci_conn object previously + * but we're in master role this must be something + * initiated using a white list. Since white list based + * connections are not "first class citizens" we don't + * have full tracking of them. Therefore, we go ahead + * with a "best effort" approach of determining the + * initiator address based on the HCI_PRIVACY flag. + */ + if (conn->out) { + conn->resp_addr_type = ev->bdaddr_type; + bacpy(&conn->resp_addr, &ev->bdaddr); + if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) { + conn->init_addr_type = ADDR_LE_DEV_RANDOM; + bacpy(&conn->init_addr, &hdev->rpa); + } else { + hci_copy_identity_address(hdev, + &conn->init_addr, + &conn->init_addr_type); + } + } else { + /* Set the responder (our side) address type based on + * the advertising address type. + */ + conn->resp_addr_type = hdev->adv_addr_type; + if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) + bacpy(&conn->resp_addr, &hdev->random_addr); + else + bacpy(&conn->resp_addr, &hdev->bdaddr); + + conn->init_addr_type = ev->bdaddr_type; + bacpy(&conn->init_addr, &ev->bdaddr); + } + } else { + cancel_delayed_work(&conn->le_conn_timeout); + } + + /* Ensure that the hci_conn contains the identity address type + * regardless of which address the connection was made with. + */ + hci_copy_identity_address(hdev, &conn->src, &conn->src_type); + + /* Lookup the identity address from the stored connection + * address and address type. + * + * When establishing connections to an identity address, the + * connection procedure will store the resolvable random + * address first. Now if it can be converted back into the + * identity address, start using the identity address from + * now on. + */ + irk = hci_get_irk(hdev, &conn->dst, conn->dst_type); + if (irk) { + bacpy(&conn->dst, &irk->bdaddr); + conn->dst_type = irk->addr_type; } if (ev->status) { - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, ev->status); - hci_proto_connect_cfm(conn, ev->status); - conn->state = BT_CLOSED; - hci_conn_del(conn); + hci_le_conn_failed(conn, ev->status); goto unlock; } if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, &ev->bdaddr, conn->type, + mgmt_device_connected(hdev, &conn->dst, conn->type, conn->dst_type, 0, NULL, 0, NULL); conn->sec_level = BT_SECURITY_LOW; @@ -3540,25 +3932,73 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_proto_connect_cfm(conn, ev->status); + hci_pend_le_conn_del(hdev, &conn->dst, conn->dst_type); + unlock: hci_dev_unlock(hdev); } +/* This function requires the caller holds hdev->lock */ +static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr, + u8 addr_type) +{ + struct hci_conn *conn; + struct smp_irk *irk; + + /* If this is a resolvable address, we should resolve it and then + * update address and address type variables. + */ + irk = hci_get_irk(hdev, addr, addr_type); + if (irk) { + addr = &irk->bdaddr; + addr_type = irk->addr_type; + } + + if (!hci_pend_le_conn_lookup(hdev, addr, addr_type)) + return; + + conn = hci_connect_le(hdev, addr, addr_type, BT_SECURITY_LOW, + HCI_AT_NO_BONDING); + if (!IS_ERR(conn)) + return; + + switch (PTR_ERR(conn)) { + case -EBUSY: + /* If hci_connect() returns -EBUSY it means there is already + * an LE connection attempt going on. Since controllers don't + * support more than one connection attempt at the time, we + * don't consider this an error case. + */ + break; + default: + BT_DBG("Failed to connect: err %ld", PTR_ERR(conn)); + } +} + static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) { u8 num_reports = skb->data[0]; void *ptr = &skb->data[1]; s8 rssi; + hci_dev_lock(hdev); + while (num_reports--) { struct hci_ev_le_advertising_info *ev = ptr; + if (ev->evt_type == LE_ADV_IND || + ev->evt_type == LE_ADV_DIRECT_IND) + check_pending_le_conn(hdev, &ev->bdaddr, + ev->bdaddr_type); + rssi = ev->data[ev->length]; mgmt_device_found(hdev, &ev->bdaddr, LE_LINK, ev->bdaddr_type, NULL, rssi, 0, 1, ev->data, ev->length); ptr += sizeof(*ev) + ev->length + 1; } + + hci_dev_unlock(hdev); } static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) @@ -3577,7 +4017,7 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) if (conn == NULL) goto not_found; - ltk = hci_find_ltk(hdev, ev->ediv, ev->random); + ltk = hci_find_ltk(hdev, ev->ediv, ev->rand, conn->out); if (ltk == NULL) goto not_found; @@ -3593,7 +4033,13 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); - if (ltk->type & HCI_SMP_STK) { + /* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a + * temporary key used to encrypt a connection following + * pairing. It is used during the Encrypted Session Setup to + * distribute the keys. Later, security can be re-established + * using a distributed LTK. + */ + if (ltk->type == HCI_SMP_STK_SLAVE) { list_del(<k->list); kfree(ltk); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 7552f9e3089c..b9a418e578e0 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -211,22 +211,22 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) switch (bt_cb(skb)->pkt_type) { case HCI_COMMAND_PKT: - opcode = __constant_cpu_to_le16(HCI_MON_COMMAND_PKT); + opcode = cpu_to_le16(HCI_MON_COMMAND_PKT); break; case HCI_EVENT_PKT: - opcode = __constant_cpu_to_le16(HCI_MON_EVENT_PKT); + opcode = cpu_to_le16(HCI_MON_EVENT_PKT); break; case HCI_ACLDATA_PKT: if (bt_cb(skb)->incoming) - opcode = __constant_cpu_to_le16(HCI_MON_ACL_RX_PKT); + opcode = cpu_to_le16(HCI_MON_ACL_RX_PKT); else - opcode = __constant_cpu_to_le16(HCI_MON_ACL_TX_PKT); + opcode = cpu_to_le16(HCI_MON_ACL_TX_PKT); break; case HCI_SCODATA_PKT: if (bt_cb(skb)->incoming) - opcode = __constant_cpu_to_le16(HCI_MON_SCO_RX_PKT); + opcode = cpu_to_le16(HCI_MON_SCO_RX_PKT); else - opcode = __constant_cpu_to_le16(HCI_MON_SCO_TX_PKT); + opcode = cpu_to_le16(HCI_MON_SCO_TX_PKT); break; default: return; @@ -319,7 +319,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) bacpy(&ni->bdaddr, &hdev->bdaddr); memcpy(ni->name, hdev->name, 8); - opcode = __constant_cpu_to_le16(HCI_MON_NEW_INDEX); + opcode = cpu_to_le16(HCI_MON_NEW_INDEX); break; case HCI_DEV_UNREG: @@ -327,7 +327,7 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) if (!skb) return NULL; - opcode = __constant_cpu_to_le16(HCI_MON_DEL_INDEX); + opcode = cpu_to_le16(HCI_MON_DEL_INDEX); break; default: @@ -716,6 +716,7 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, err = hci_dev_open(hdev->id); if (err) { clear_bit(HCI_USER_CHANNEL, &hdev->dev_flags); + mgmt_index_added(hdev); hci_dev_put(hdev); goto done; } diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 0b61250cfdf9..555982a78a58 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -49,14 +49,7 @@ static struct attribute *bt_link_attrs[] = { NULL }; -static struct attribute_group bt_link_group = { - .attrs = bt_link_attrs, -}; - -static const struct attribute_group *bt_link_groups[] = { - &bt_link_group, - NULL -}; +ATTRIBUTE_GROUPS(bt_link); static void bt_link_release(struct device *dev) { @@ -182,14 +175,7 @@ static struct attribute *bt_host_attrs[] = { NULL }; -static struct attribute_group bt_host_group = { - .attrs = bt_host_attrs, -}; - -static const struct attribute_group *bt_host_groups[] = { - &bt_host_group, - NULL -}; +ATTRIBUTE_GROUPS(bt_host); static void bt_host_release(struct device *dev) { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b0ad2c752d73..a1e5bb7d06e8 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -42,6 +42,8 @@ #include "amp.h" #include "6lowpan.h" +#define LE_FLOWCTL_MAX_CREDITS 65535 + bool disable_ertm; static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN | L2CAP_FEAT_UCD; @@ -330,44 +332,20 @@ static inline bool l2cap_seq_list_contains(struct l2cap_seq_list *seq_list, return seq_list->list[seq & seq_list->mask] != L2CAP_SEQ_LIST_CLEAR; } -static u16 l2cap_seq_list_remove(struct l2cap_seq_list *seq_list, u16 seq) +static inline u16 l2cap_seq_list_pop(struct l2cap_seq_list *seq_list) { + u16 seq = seq_list->head; u16 mask = seq_list->mask; - if (seq_list->head == L2CAP_SEQ_LIST_CLEAR) { - /* In case someone tries to pop the head of an empty list */ - return L2CAP_SEQ_LIST_CLEAR; - } else if (seq_list->head == seq) { - /* Head can be removed in constant time */ - seq_list->head = seq_list->list[seq & mask]; - seq_list->list[seq & mask] = L2CAP_SEQ_LIST_CLEAR; - - if (seq_list->head == L2CAP_SEQ_LIST_TAIL) { - seq_list->head = L2CAP_SEQ_LIST_CLEAR; - seq_list->tail = L2CAP_SEQ_LIST_CLEAR; - } - } else { - /* Walk the list to find the sequence number */ - u16 prev = seq_list->head; - while (seq_list->list[prev & mask] != seq) { - prev = seq_list->list[prev & mask]; - if (prev == L2CAP_SEQ_LIST_TAIL) - return L2CAP_SEQ_LIST_CLEAR; - } + seq_list->head = seq_list->list[seq & mask]; + seq_list->list[seq & mask] = L2CAP_SEQ_LIST_CLEAR; - /* Unlink the number from the list and clear it */ - seq_list->list[prev & mask] = seq_list->list[seq & mask]; - seq_list->list[seq & mask] = L2CAP_SEQ_LIST_CLEAR; - if (seq_list->tail == seq) - seq_list->tail = prev; + if (seq_list->head == L2CAP_SEQ_LIST_TAIL) { + seq_list->head = L2CAP_SEQ_LIST_CLEAR; + seq_list->tail = L2CAP_SEQ_LIST_CLEAR; } - return seq; -} -static inline u16 l2cap_seq_list_pop(struct l2cap_seq_list *seq_list) -{ - /* Remove the head in constant time */ - return l2cap_seq_list_remove(seq_list, seq_list->head); + return seq; } static void l2cap_seq_list_clear(struct l2cap_seq_list *seq_list) @@ -506,7 +484,7 @@ static void l2cap_le_flowctl_init(struct l2cap_chan *chan) chan->sdu_len = 0; chan->tx_credits = 0; chan->rx_credits = le_max_credits; - chan->mps = min_t(u16, chan->imtu, L2CAP_LE_DEFAULT_MPS); + chan->mps = min_t(u16, chan->imtu, le_default_mps); skb_queue_head_init(&chan->tx_q); } @@ -522,18 +500,10 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) switch (chan->chan_type) { case L2CAP_CHAN_CONN_ORIENTED: - if (conn->hcon->type == LE_LINK) { - if (chan->dcid == L2CAP_CID_ATT) { - chan->omtu = L2CAP_DEFAULT_MTU; - chan->scid = L2CAP_CID_ATT; - } else { - chan->scid = l2cap_alloc_cid(conn); - } - } else { - /* Alloc CID for connection-oriented socket */ - chan->scid = l2cap_alloc_cid(conn); + /* Alloc CID for connection-oriented socket */ + chan->scid = l2cap_alloc_cid(conn); + if (conn->hcon->type == ACL_LINK) chan->omtu = L2CAP_DEFAULT_MTU; - } break; case L2CAP_CHAN_CONN_LESS: @@ -543,11 +513,8 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) chan->omtu = L2CAP_DEFAULT_MTU; break; - case L2CAP_CHAN_CONN_FIX_A2MP: - chan->scid = L2CAP_CID_A2MP; - chan->dcid = L2CAP_CID_A2MP; - chan->omtu = L2CAP_A2MP_DEFAULT_MTU; - chan->imtu = L2CAP_A2MP_DEFAULT_MTU; + case L2CAP_CHAN_FIXED: + /* Caller will set CID and CID specific MTU values */ break; default: @@ -595,7 +562,7 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) chan->conn = NULL; - if (chan->chan_type != L2CAP_CHAN_CONN_FIX_A2MP) + if (chan->scid != L2CAP_CID_A2MP) hci_conn_drop(conn->hcon); if (mgr && mgr->bredr_chan == chan) @@ -642,6 +609,23 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) return; } +void l2cap_conn_update_id_addr(struct hci_conn *hcon) +{ + struct l2cap_conn *conn = hcon->l2cap_data; + struct l2cap_chan *chan; + + mutex_lock(&conn->chan_lock); + + list_for_each_entry(chan, &conn->chan_l, list) { + l2cap_chan_lock(chan); + bacpy(&chan->dst, &hcon->dst); + chan->dst_type = bdaddr_type(hcon, hcon->dst_type); + l2cap_chan_unlock(chan); + } + + mutex_unlock(&conn->chan_lock); +} + static void l2cap_chan_le_connect_reject(struct l2cap_chan *chan) { struct l2cap_conn *conn = chan->conn; @@ -681,7 +665,7 @@ static void l2cap_chan_connect_reject(struct l2cap_chan *chan) rsp.scid = cpu_to_le16(chan->dcid); rsp.dcid = cpu_to_le16(chan->scid); rsp.result = cpu_to_le16(result); - rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); } @@ -699,10 +683,7 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason) case BT_CONNECTED: case BT_CONFIG: - /* ATT uses L2CAP_CHAN_CONN_ORIENTED so we must also - * check for chan->psm. - */ - if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && chan->psm) { + if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED) { __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); l2cap_send_disconn_req(chan, reason); } else @@ -737,6 +718,7 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) case L2CAP_CHAN_RAW: switch (chan->sec_level) { case BT_SECURITY_HIGH: + case BT_SECURITY_FIPS: return HCI_AT_DEDICATED_BONDING_MITM; case BT_SECURITY_MEDIUM: return HCI_AT_DEDICATED_BONDING; @@ -745,21 +727,23 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) } break; case L2CAP_CHAN_CONN_LESS: - if (chan->psm == __constant_cpu_to_le16(L2CAP_PSM_3DSP)) { + if (chan->psm == cpu_to_le16(L2CAP_PSM_3DSP)) { if (chan->sec_level == BT_SECURITY_LOW) chan->sec_level = BT_SECURITY_SDP; } - if (chan->sec_level == BT_SECURITY_HIGH) + if (chan->sec_level == BT_SECURITY_HIGH || + chan->sec_level == BT_SECURITY_FIPS) return HCI_AT_NO_BONDING_MITM; else return HCI_AT_NO_BONDING; break; case L2CAP_CHAN_CONN_ORIENTED: - if (chan->psm == __constant_cpu_to_le16(L2CAP_PSM_SDP)) { + if (chan->psm == cpu_to_le16(L2CAP_PSM_SDP)) { if (chan->sec_level == BT_SECURITY_LOW) chan->sec_level = BT_SECURITY_SDP; - if (chan->sec_level == BT_SECURITY_HIGH) + if (chan->sec_level == BT_SECURITY_HIGH || + chan->sec_level == BT_SECURITY_FIPS) return HCI_AT_NO_BONDING_MITM; else return HCI_AT_NO_BONDING; @@ -768,6 +752,7 @@ static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) default: switch (chan->sec_level) { case BT_SECURITY_HIGH: + case BT_SECURITY_FIPS: return HCI_AT_GENERAL_BONDING_MITM; case BT_SECURITY_MEDIUM: return HCI_AT_GENERAL_BONDING; @@ -1288,7 +1273,7 @@ static void l2cap_do_start(struct l2cap_chan *chan) } } else { struct l2cap_info_req req; - req.type = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK); + req.type = cpu_to_le16(L2CAP_IT_FEAT_MASK); conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_SENT; conn->info_ident = l2cap_get_ident(conn); @@ -1330,7 +1315,7 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err) __clear_ack_timer(chan); } - if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) { + if (chan->scid == L2CAP_CID_A2MP) { l2cap_state_change(chan, BT_DISCONN); return; } @@ -1385,18 +1370,18 @@ static void l2cap_conn_start(struct l2cap_conn *conn) if (l2cap_chan_check_security(chan)) { if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { - rsp.result = __constant_cpu_to_le16(L2CAP_CR_PEND); - rsp.status = __constant_cpu_to_le16(L2CAP_CS_AUTHOR_PEND); + rsp.result = cpu_to_le16(L2CAP_CR_PEND); + rsp.status = cpu_to_le16(L2CAP_CS_AUTHOR_PEND); chan->ops->defer(chan); } else { l2cap_state_change(chan, BT_CONFIG); - rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS); - rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); + rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); } } else { - rsp.result = __constant_cpu_to_le16(L2CAP_CR_PEND); - rsp.status = __constant_cpu_to_le16(L2CAP_CS_AUTHEN_PEND); + rsp.result = cpu_to_le16(L2CAP_CR_PEND); + rsp.status = cpu_to_le16(L2CAP_CS_AUTHEN_PEND); } l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, @@ -1493,8 +1478,6 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) if (!chan) goto clean; - chan->dcid = L2CAP_CID_ATT; - bacpy(&chan->src, &hcon->src); bacpy(&chan->dst, &hcon->dst); chan->src_type = bdaddr_type(hcon, hcon->src_type); @@ -1528,7 +1511,7 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) l2cap_chan_lock(chan); - if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) { + if (chan->scid == L2CAP_CID_A2MP) { l2cap_chan_unlock(chan); continue; } @@ -1546,6 +1529,8 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) } mutex_unlock(&conn->chan_lock); + + queue_work(hcon->hdev->workqueue, &conn->pending_rx_work); } /* Notify sockets that we cannot guaranty reliability anymore */ @@ -1671,6 +1656,9 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) kfree_skb(conn->rx_skb); + skb_queue_purge(&conn->pending_rx); + flush_work(&conn->pending_rx_work); + l2cap_unregister_all_users(conn); mutex_lock(&conn->chan_lock); @@ -1718,66 +1706,6 @@ static void security_timeout(struct work_struct *work) } } -static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) -{ - struct l2cap_conn *conn = hcon->l2cap_data; - struct hci_chan *hchan; - - if (conn) - return conn; - - hchan = hci_chan_create(hcon); - if (!hchan) - return NULL; - - conn = kzalloc(sizeof(struct l2cap_conn), GFP_KERNEL); - if (!conn) { - hci_chan_del(hchan); - return NULL; - } - - kref_init(&conn->ref); - hcon->l2cap_data = conn; - conn->hcon = hcon; - hci_conn_get(conn->hcon); - conn->hchan = hchan; - - BT_DBG("hcon %p conn %p hchan %p", hcon, conn, hchan); - - switch (hcon->type) { - case LE_LINK: - if (hcon->hdev->le_mtu) { - conn->mtu = hcon->hdev->le_mtu; - break; - } - /* fall through */ - default: - conn->mtu = hcon->hdev->acl_mtu; - break; - } - - conn->feat_mask = 0; - - if (hcon->type == ACL_LINK) - conn->hs_enabled = test_bit(HCI_HS_ENABLED, - &hcon->hdev->dev_flags); - - spin_lock_init(&conn->lock); - mutex_init(&conn->chan_lock); - - INIT_LIST_HEAD(&conn->chan_l); - INIT_LIST_HEAD(&conn->users); - - if (hcon->type == LE_LINK) - INIT_DELAYED_WORK(&conn->security_timer, security_timeout); - else - INIT_DELAYED_WORK(&conn->info_timer, l2cap_info_timeout); - - conn->disc_reason = HCI_ERROR_REMOTE_USER_TERM; - - return conn; -} - static void l2cap_conn_free(struct kref *ref) { struct l2cap_conn *conn = container_of(ref, struct l2cap_conn, ref); @@ -1848,154 +1776,6 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, return c1; } -static bool is_valid_psm(u16 psm, u8 dst_type) -{ - if (!psm) - return false; - - if (bdaddr_type_is_le(dst_type)) - return (psm <= 0x00ff); - - /* PSM must be odd and lsb of upper byte must be 0 */ - return ((psm & 0x0101) == 0x0001); -} - -int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, - bdaddr_t *dst, u8 dst_type) -{ - struct l2cap_conn *conn; - struct hci_conn *hcon; - struct hci_dev *hdev; - __u8 auth_type; - int err; - - BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", &chan->src, dst, - dst_type, __le16_to_cpu(psm)); - - hdev = hci_get_route(dst, &chan->src); - if (!hdev) - return -EHOSTUNREACH; - - hci_dev_lock(hdev); - - l2cap_chan_lock(chan); - - if (!is_valid_psm(__le16_to_cpu(psm), dst_type) && !cid && - chan->chan_type != L2CAP_CHAN_RAW) { - err = -EINVAL; - goto done; - } - - if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && !(psm || cid)) { - err = -EINVAL; - goto done; - } - - switch (chan->mode) { - case L2CAP_MODE_BASIC: - break; - case L2CAP_MODE_LE_FLOWCTL: - l2cap_le_flowctl_init(chan); - break; - case L2CAP_MODE_ERTM: - case L2CAP_MODE_STREAMING: - if (!disable_ertm) - break; - /* fall through */ - default: - err = -ENOTSUPP; - goto done; - } - - switch (chan->state) { - case BT_CONNECT: - case BT_CONNECT2: - case BT_CONFIG: - /* Already connecting */ - err = 0; - goto done; - - case BT_CONNECTED: - /* Already connected */ - err = -EISCONN; - goto done; - - case BT_OPEN: - case BT_BOUND: - /* Can connect */ - break; - - default: - err = -EBADFD; - goto done; - } - - /* Set destination address and psm */ - bacpy(&chan->dst, dst); - chan->dst_type = dst_type; - - chan->psm = psm; - chan->dcid = cid; - - auth_type = l2cap_get_auth_type(chan); - - if (bdaddr_type_is_le(dst_type)) - hcon = hci_connect(hdev, LE_LINK, dst, dst_type, - chan->sec_level, auth_type); - else - hcon = hci_connect(hdev, ACL_LINK, dst, dst_type, - chan->sec_level, auth_type); - - if (IS_ERR(hcon)) { - err = PTR_ERR(hcon); - goto done; - } - - conn = l2cap_conn_add(hcon); - if (!conn) { - hci_conn_drop(hcon); - err = -ENOMEM; - goto done; - } - - if (cid && __l2cap_get_chan_by_dcid(conn, cid)) { - hci_conn_drop(hcon); - err = -EBUSY; - goto done; - } - - /* Update source addr of the socket */ - bacpy(&chan->src, &hcon->src); - chan->src_type = bdaddr_type(hcon, hcon->src_type); - - l2cap_chan_unlock(chan); - l2cap_chan_add(conn, chan); - l2cap_chan_lock(chan); - - /* l2cap_chan_add takes its own ref so we can drop this one */ - hci_conn_drop(hcon); - - l2cap_state_change(chan, BT_CONNECT); - __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); - - if (hcon->state == BT_CONNECTED) { - if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { - __clear_chan_timer(chan); - if (l2cap_chan_check_security(chan)) - l2cap_state_change(chan, BT_CONNECTED); - } else - l2cap_do_start(chan); - } - - err = 0; - -done: - l2cap_chan_unlock(chan); - hci_dev_unlock(hdev); - hci_dev_put(hdev); - return err; -} - static void l2cap_monitor_timeout(struct work_struct *work) { struct l2cap_chan *chan = container_of(work, struct l2cap_chan, @@ -2654,6 +2434,14 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, if (IS_ERR(skb)) return PTR_ERR(skb); + /* Channel lock is released before requesting new skb and then + * reacquired thus we need to recheck channel state. + */ + if (chan->state != BT_CONNECTED) { + kfree_skb(skb); + return -ENOTCONN; + } + l2cap_do_send(chan, skb); return len; } @@ -2703,6 +2491,14 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, if (IS_ERR(skb)) return PTR_ERR(skb); + /* Channel lock is released before requesting new skb and then + * reacquired thus we need to recheck channel state. + */ + if (chan->state != BT_CONNECTED) { + kfree_skb(skb); + return -ENOTCONN; + } + l2cap_do_send(chan, skb); err = len; break; @@ -3099,9 +2895,9 @@ static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code, lh->len = cpu_to_le16(L2CAP_CMD_HDR_SIZE + dlen); if (conn->hcon->type == LE_LINK) - lh->cid = __constant_cpu_to_le16(L2CAP_CID_LE_SIGNALING); + lh->cid = cpu_to_le16(L2CAP_CID_LE_SIGNALING); else - lh->cid = __constant_cpu_to_le16(L2CAP_CID_SIGNALING); + lh->cid = cpu_to_le16(L2CAP_CID_SIGNALING); cmd = (struct l2cap_cmd_hdr *) skb_put(skb, L2CAP_CMD_HDR_SIZE); cmd->code = code; @@ -3214,8 +3010,8 @@ static void l2cap_add_opt_efs(void **ptr, struct l2cap_chan *chan) efs.stype = chan->local_stype; efs.msdu = cpu_to_le16(chan->local_msdu); efs.sdu_itime = cpu_to_le32(chan->local_sdu_itime); - efs.acc_lat = __constant_cpu_to_le32(L2CAP_DEFAULT_ACC_LAT); - efs.flush_to = __constant_cpu_to_le32(L2CAP_EFS_DEFAULT_FLUSH_TO); + efs.acc_lat = cpu_to_le32(L2CAP_DEFAULT_ACC_LAT); + efs.flush_to = cpu_to_le32(L2CAP_EFS_DEFAULT_FLUSH_TO); break; case L2CAP_MODE_STREAMING: @@ -3356,8 +3152,8 @@ static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan, rfc->retrans_timeout = cpu_to_le16((u16) ertm_to); rfc->monitor_timeout = rfc->retrans_timeout; } else { - rfc->retrans_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); - rfc->monitor_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); + rfc->retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); + rfc->monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); } } @@ -3489,7 +3285,7 @@ done: } req->dcid = cpu_to_le16(chan->dcid); - req->flags = __constant_cpu_to_le16(0); + req->flags = cpu_to_le16(0); return ptr - data; } @@ -3703,7 +3499,7 @@ done: } rsp->scid = cpu_to_le16(chan->dcid); rsp->result = cpu_to_le16(result); - rsp->flags = __constant_cpu_to_le16(0); + rsp->flags = cpu_to_le16(0); return ptr - data; } @@ -3812,7 +3608,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, } req->dcid = cpu_to_le16(chan->dcid); - req->flags = __constant_cpu_to_le16(0); + req->flags = cpu_to_le16(0); return ptr - data; } @@ -3843,7 +3639,7 @@ void __l2cap_le_connect_rsp_defer(struct l2cap_chan *chan) rsp.mtu = cpu_to_le16(chan->imtu); rsp.mps = cpu_to_le16(chan->mps); rsp.credits = cpu_to_le16(chan->rx_credits); - rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS); + rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CONN_RSP, sizeof(rsp), &rsp); @@ -3858,8 +3654,8 @@ void __l2cap_connect_rsp_defer(struct l2cap_chan *chan) rsp.scid = cpu_to_le16(chan->dcid); rsp.dcid = cpu_to_le16(chan->scid); - rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS); - rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); + rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); if (chan->hs_hcon) rsp_code = L2CAP_CREATE_CHAN_RSP; @@ -3888,8 +3684,8 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) u16 txwin_ext = chan->ack_win; struct l2cap_conf_rfc rfc = { .mode = chan->mode, - .retrans_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO), - .monitor_timeout = __constant_cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO), + .retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO), + .monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO), .max_pdu_size = cpu_to_le16(chan->imtu), .txwin_size = min_t(u16, chan->ack_win, L2CAP_DEFAULT_TX_WINDOW), }; @@ -3980,7 +3776,7 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, l2cap_chan_lock(pchan); /* Check if the ACL is secure enough (if not SDP) */ - if (psm != __constant_cpu_to_le16(L2CAP_PSM_SDP) && + if (psm != cpu_to_le16(L2CAP_PSM_SDP) && !hci_conn_check_link_mode(conn->hcon)) { conn->disc_reason = HCI_ERROR_AUTH_FAILURE; result = L2CAP_CR_SEC_BLOCK; @@ -4065,7 +3861,7 @@ sendresp: if (result == L2CAP_CR_PEND && status == L2CAP_CS_NO_INFO) { struct l2cap_info_req info; - info.type = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK); + info.type = cpu_to_le16(L2CAP_IT_FEAT_MASK); conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_SENT; conn->info_ident = l2cap_get_ident(conn); @@ -4214,7 +4010,7 @@ static void cmd_reject_invalid_cid(struct l2cap_conn *conn, u8 ident, { struct l2cap_cmd_rej_cid rej; - rej.reason = __constant_cpu_to_le16(L2CAP_REJ_INVALID_CID); + rej.reason = cpu_to_le16(L2CAP_REJ_INVALID_CID); rej.scid = __cpu_to_le16(scid); rej.dcid = __cpu_to_le16(dcid); @@ -4546,8 +4342,8 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, u8 buf[8]; u32 feat_mask = l2cap_feat_mask; struct l2cap_info_rsp *rsp = (struct l2cap_info_rsp *) buf; - rsp->type = __constant_cpu_to_le16(L2CAP_IT_FEAT_MASK); - rsp->result = __constant_cpu_to_le16(L2CAP_IR_SUCCESS); + rsp->type = cpu_to_le16(L2CAP_IT_FEAT_MASK); + rsp->result = cpu_to_le16(L2CAP_IR_SUCCESS); if (!disable_ertm) feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING | L2CAP_FEAT_FCS; @@ -4567,15 +4363,15 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, else l2cap_fixed_chan[0] &= ~L2CAP_FC_A2MP; - rsp->type = __constant_cpu_to_le16(L2CAP_IT_FIXED_CHAN); - rsp->result = __constant_cpu_to_le16(L2CAP_IR_SUCCESS); + rsp->type = cpu_to_le16(L2CAP_IT_FIXED_CHAN); + rsp->result = cpu_to_le16(L2CAP_IR_SUCCESS); memcpy(rsp->data, l2cap_fixed_chan, sizeof(l2cap_fixed_chan)); l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf), buf); } else { struct l2cap_info_rsp rsp; rsp.type = cpu_to_le16(type); - rsp.result = __constant_cpu_to_le16(L2CAP_IR_NOTSUPP); + rsp.result = cpu_to_le16(L2CAP_IR_NOTSUPP); l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(rsp), &rsp); } @@ -4620,7 +4416,7 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, if (conn->feat_mask & L2CAP_FEAT_FIXED_CHAN) { struct l2cap_info_req req; - req.type = __constant_cpu_to_le16(L2CAP_IT_FIXED_CHAN); + req.type = cpu_to_le16(L2CAP_IT_FIXED_CHAN); conn->info_ident = l2cap_get_ident(conn); @@ -4714,8 +4510,8 @@ static int l2cap_create_channel_req(struct l2cap_conn *conn, error: rsp.dcid = 0; rsp.scid = cpu_to_le16(scid); - rsp.result = __constant_cpu_to_le16(L2CAP_CR_BAD_AMP); - rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.result = cpu_to_le16(L2CAP_CR_BAD_AMP); + rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); l2cap_send_cmd(conn, cmd->ident, L2CAP_CREATE_CHAN_RSP, sizeof(rsp), &rsp); @@ -4779,7 +4575,7 @@ static void l2cap_send_move_chan_cfm_icid(struct l2cap_conn *conn, u16 icid) BT_DBG("conn %p, icid 0x%4.4x", conn, icid); cfm.icid = cpu_to_le16(icid); - cfm.result = __constant_cpu_to_le16(L2CAP_MC_UNCONFIRMED); + cfm.result = cpu_to_le16(L2CAP_MC_UNCONFIRMED); l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_MOVE_CHAN_CFM, sizeof(cfm), &cfm); @@ -4962,12 +4758,12 @@ static void l2cap_do_create(struct l2cap_chan *chan, int result, if (result == L2CAP_CR_SUCCESS) { /* Send successful response */ - rsp.result = __constant_cpu_to_le16(L2CAP_CR_SUCCESS); - rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); + rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); } else { /* Send negative response */ - rsp.result = __constant_cpu_to_le16(L2CAP_CR_NO_MEM); - rsp.status = __constant_cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.result = cpu_to_le16(L2CAP_CR_NO_MEM); + rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); } l2cap_send_cmd(chan->conn, chan->ident, L2CAP_CREATE_CHAN_RSP, @@ -5095,7 +4891,7 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn, chan = l2cap_get_chan_by_dcid(conn, icid); if (!chan) { rsp.icid = cpu_to_le16(icid); - rsp.result = __constant_cpu_to_le16(L2CAP_MR_NOT_ALLOWED); + rsp.result = cpu_to_le16(L2CAP_MR_NOT_ALLOWED); l2cap_send_cmd(conn, cmd->ident, L2CAP_MOVE_CHAN_RSP, sizeof(rsp), &rsp); return 0; @@ -5439,9 +5235,9 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, err = l2cap_check_conn_param(min, max, latency, to_multiplier); if (err) - rsp.result = __constant_cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); + rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else - rsp.result = __constant_cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED); + rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_ACCEPTED); l2cap_send_cmd(conn, cmd->ident, L2CAP_CONN_PARAM_UPDATE_RSP, sizeof(rsp), &rsp); @@ -5709,7 +5505,7 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn, { struct l2cap_le_credits *pkt; struct l2cap_chan *chan; - u16 cid, credits; + u16 cid, credits, max_credits; if (cmd_len != sizeof(*pkt)) return -EPROTO; @@ -5724,6 +5520,17 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn, if (!chan) return -EBADSLT; + max_credits = LE_FLOWCTL_MAX_CREDITS - chan->tx_credits; + if (credits > max_credits) { + BT_ERR("LE credits overflow"); + l2cap_send_disconn_req(chan, ECONNRESET); + + /* Return 0 so that we don't trigger an unnecessary + * command reject packet. + */ + return 0; + } + chan->tx_credits += credits; while (chan->tx_credits && !skb_queue_empty(&chan->tx_q)) { @@ -5770,17 +5577,6 @@ static inline int l2cap_le_sig_cmd(struct l2cap_conn *conn, { int err = 0; - if (!enable_lecoc) { - switch (cmd->code) { - case L2CAP_LE_CONN_REQ: - case L2CAP_LE_CONN_RSP: - case L2CAP_LE_CREDITS: - case L2CAP_DISCONN_REQ: - case L2CAP_DISCONN_RSP: - return -EINVAL; - } - } - switch (cmd->code) { case L2CAP_COMMAND_REJ: l2cap_le_command_rej(conn, cmd, cmd_len, data); @@ -5854,7 +5650,7 @@ static inline void l2cap_le_sig_channel(struct l2cap_conn *conn, BT_ERR("Wrong link type (%d)", err); - rej.reason = __constant_cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); + rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); } @@ -5899,7 +5695,7 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, BT_ERR("Wrong link type (%d)", err); - rej.reason = __constant_cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); + rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); l2cap_send_cmd(conn, cmd.ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); } @@ -6871,6 +6667,7 @@ static int l2cap_le_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) if (!chan->rx_credits) { BT_ERR("No credits to receive LE L2CAP data"); + l2cap_send_disconn_req(chan, ECONNRESET); return -ENOBUFS; } @@ -6995,8 +6792,10 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, * But we don't have any other choice. L2CAP doesn't * provide flow control mechanism. */ - if (chan->imtu < skb->len) + if (chan->imtu < skb->len) { + BT_ERR("Dropping L2CAP data: receive buffer overflow"); goto drop; + } if (!chan->ops->recv(chan, skb)) goto done; @@ -7084,9 +6883,16 @@ drop: static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) { struct l2cap_hdr *lh = (void *) skb->data; + struct hci_conn *hcon = conn->hcon; u16 cid, len; __le16 psm; + if (hcon->state != BT_CONNECTED) { + BT_DBG("queueing pending rx skb"); + skb_queue_tail(&conn->pending_rx, skb); + return; + } + skb_pull(skb, L2CAP_HDR_SIZE); cid = __le16_to_cpu(lh->cid); len = __le16_to_cpu(lh->len); @@ -7132,6 +6938,247 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) } } +static void process_pending_rx(struct work_struct *work) +{ + struct l2cap_conn *conn = container_of(work, struct l2cap_conn, + pending_rx_work); + struct sk_buff *skb; + + BT_DBG(""); + + while ((skb = skb_dequeue(&conn->pending_rx))) + l2cap_recv_frame(conn, skb); +} + +static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) +{ + struct l2cap_conn *conn = hcon->l2cap_data; + struct hci_chan *hchan; + + if (conn) + return conn; + + hchan = hci_chan_create(hcon); + if (!hchan) + return NULL; + + conn = kzalloc(sizeof(struct l2cap_conn), GFP_KERNEL); + if (!conn) { + hci_chan_del(hchan); + return NULL; + } + + kref_init(&conn->ref); + hcon->l2cap_data = conn; + conn->hcon = hcon; + hci_conn_get(conn->hcon); + conn->hchan = hchan; + + BT_DBG("hcon %p conn %p hchan %p", hcon, conn, hchan); + + switch (hcon->type) { + case LE_LINK: + if (hcon->hdev->le_mtu) { + conn->mtu = hcon->hdev->le_mtu; + break; + } + /* fall through */ + default: + conn->mtu = hcon->hdev->acl_mtu; + break; + } + + conn->feat_mask = 0; + + if (hcon->type == ACL_LINK) + conn->hs_enabled = test_bit(HCI_HS_ENABLED, + &hcon->hdev->dev_flags); + + spin_lock_init(&conn->lock); + mutex_init(&conn->chan_lock); + + INIT_LIST_HEAD(&conn->chan_l); + INIT_LIST_HEAD(&conn->users); + + if (hcon->type == LE_LINK) + INIT_DELAYED_WORK(&conn->security_timer, security_timeout); + else + INIT_DELAYED_WORK(&conn->info_timer, l2cap_info_timeout); + + skb_queue_head_init(&conn->pending_rx); + INIT_WORK(&conn->pending_rx_work, process_pending_rx); + + conn->disc_reason = HCI_ERROR_REMOTE_USER_TERM; + + return conn; +} + +static bool is_valid_psm(u16 psm, u8 dst_type) { + if (!psm) + return false; + + if (bdaddr_type_is_le(dst_type)) + return (psm <= 0x00ff); + + /* PSM must be odd and lsb of upper byte must be 0 */ + return ((psm & 0x0101) == 0x0001); +} + +int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, + bdaddr_t *dst, u8 dst_type) +{ + struct l2cap_conn *conn; + struct hci_conn *hcon; + struct hci_dev *hdev; + __u8 auth_type; + int err; + + BT_DBG("%pMR -> %pMR (type %u) psm 0x%2.2x", &chan->src, dst, + dst_type, __le16_to_cpu(psm)); + + hdev = hci_get_route(dst, &chan->src); + if (!hdev) + return -EHOSTUNREACH; + + hci_dev_lock(hdev); + + l2cap_chan_lock(chan); + + if (!is_valid_psm(__le16_to_cpu(psm), dst_type) && !cid && + chan->chan_type != L2CAP_CHAN_RAW) { + err = -EINVAL; + goto done; + } + + if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && !psm) { + err = -EINVAL; + goto done; + } + + if (chan->chan_type == L2CAP_CHAN_FIXED && !cid) { + err = -EINVAL; + goto done; + } + + switch (chan->mode) { + case L2CAP_MODE_BASIC: + break; + case L2CAP_MODE_LE_FLOWCTL: + l2cap_le_flowctl_init(chan); + break; + case L2CAP_MODE_ERTM: + case L2CAP_MODE_STREAMING: + if (!disable_ertm) + break; + /* fall through */ + default: + err = -ENOTSUPP; + goto done; + } + + switch (chan->state) { + case BT_CONNECT: + case BT_CONNECT2: + case BT_CONFIG: + /* Already connecting */ + err = 0; + goto done; + + case BT_CONNECTED: + /* Already connected */ + err = -EISCONN; + goto done; + + case BT_OPEN: + case BT_BOUND: + /* Can connect */ + break; + + default: + err = -EBADFD; + goto done; + } + + /* Set destination address and psm */ + bacpy(&chan->dst, dst); + chan->dst_type = dst_type; + + chan->psm = psm; + chan->dcid = cid; + + auth_type = l2cap_get_auth_type(chan); + + if (bdaddr_type_is_le(dst_type)) { + /* Convert from L2CAP channel address type to HCI address type + */ + if (dst_type == BDADDR_LE_PUBLIC) + dst_type = ADDR_LE_DEV_PUBLIC; + else + dst_type = ADDR_LE_DEV_RANDOM; + + hcon = hci_connect_le(hdev, dst, dst_type, chan->sec_level, + auth_type); + } else { + hcon = hci_connect_acl(hdev, dst, chan->sec_level, auth_type); + } + + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto done; + } + + conn = l2cap_conn_add(hcon); + if (!conn) { + hci_conn_drop(hcon); + err = -ENOMEM; + goto done; + } + + if (cid && __l2cap_get_chan_by_dcid(conn, cid)) { + hci_conn_drop(hcon); + err = -EBUSY; + goto done; + } + + /* Update source addr of the socket */ + bacpy(&chan->src, &hcon->src); + chan->src_type = bdaddr_type(hcon, hcon->src_type); + + l2cap_chan_unlock(chan); + l2cap_chan_add(conn, chan); + l2cap_chan_lock(chan); + + /* l2cap_chan_add takes its own ref so we can drop this one */ + hci_conn_drop(hcon); + + l2cap_state_change(chan, BT_CONNECT); + __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); + + /* Release chan->sport so that it can be reused by other + * sockets (as it's only used for listening sockets). + */ + write_lock(&chan_list_lock); + chan->sport = 0; + write_unlock(&chan_list_lock); + + if (hcon->state == BT_CONNECTED) { + if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { + __clear_chan_timer(chan); + if (l2cap_chan_check_security(chan)) + l2cap_state_change(chan, BT_CONNECTED); + } else + l2cap_do_start(chan); + } + + err = 0; + +done: + l2cap_chan_unlock(chan); + hci_dev_unlock(hdev); + hci_dev_put(hdev); + return err; +} + /* ---- L2CAP interface with lower layer (HCI) ---- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr) @@ -7206,7 +7253,8 @@ static inline void l2cap_check_encryption(struct l2cap_chan *chan, u8 encrypt) if (encrypt == 0x00) { if (chan->sec_level == BT_SECURITY_MEDIUM) { __set_chan_timer(chan, L2CAP_ENC_TIMEOUT); - } else if (chan->sec_level == BT_SECURITY_HIGH) + } else if (chan->sec_level == BT_SECURITY_HIGH || + chan->sec_level == BT_SECURITY_FIPS) l2cap_chan_close(chan, ECONNREFUSED); } else { if (chan->sec_level == BT_SECURITY_MEDIUM) @@ -7226,7 +7274,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) if (hcon->type == LE_LINK) { if (!status && encrypt) - smp_distribute_keys(conn, 0); + smp_distribute_keys(conn); cancel_delayed_work(&conn->security_timer); } @@ -7238,7 +7286,7 @@ int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) BT_DBG("chan %p scid 0x%4.4x state %s", chan, chan->scid, state_to_string(chan->state)); - if (chan->chan_type == L2CAP_CHAN_CONN_FIX_A2MP) { + if (chan->scid == L2CAP_CID_A2MP) { l2cap_chan_unlock(chan); continue; } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index d58f76bcebd1..f59e00c2daa9 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -36,8 +36,6 @@ #include "smp.h" -bool enable_lecoc; - static struct bt_sock_list l2cap_sk_list = { .lock = __RW_LOCK_UNLOCKED(l2cap_sk_list.lock) }; @@ -101,12 +99,19 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) if (!bdaddr_type_is_valid(la.l2_bdaddr_type)) return -EINVAL; + if (la.l2_cid) { + /* When the socket gets created it defaults to + * CHAN_CONN_ORIENTED, so we need to overwrite the + * default here. + */ + chan->chan_type = L2CAP_CHAN_FIXED; + chan->omtu = L2CAP_DEFAULT_MTU; + } + if (bdaddr_type_is_le(la.l2_bdaddr_type)) { - if (!enable_lecoc && la.l2_psm) - return -EINVAL; /* We only allow ATT user space socket */ if (la.l2_cid && - la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT)) + la.l2_cid != cpu_to_le16(L2CAP_CID_ATT)) return -EINVAL; } @@ -204,7 +209,7 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, * ATT. Anything else is an invalid combination. */ if (chan->scid != L2CAP_CID_ATT || - la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT)) + la.l2_cid != cpu_to_le16(L2CAP_CID_ATT)) return -EINVAL; /* We don't have the hdev available here to make a @@ -220,11 +225,9 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL; if (bdaddr_type_is_le(la.l2_bdaddr_type)) { - if (!enable_lecoc && la.l2_psm) - return -EINVAL; /* We only allow ATT user space socket */ if (la.l2_cid && - la.l2_cid != __constant_cpu_to_le16(L2CAP_CID_ATT)) + la.l2_cid != cpu_to_le16(L2CAP_CID_ATT)) return -EINVAL; } @@ -357,17 +360,21 @@ static int l2cap_sock_getname(struct socket *sock, struct sockaddr *addr, BT_DBG("sock %p, sk %p", sock, sk); + if (peer && sk->sk_state != BT_CONNECTED && + sk->sk_state != BT_CONNECT && sk->sk_state != BT_CONNECT2) + return -ENOTCONN; + memset(la, 0, sizeof(struct sockaddr_l2)); addr->sa_family = AF_BLUETOOTH; *len = sizeof(struct sockaddr_l2); + la->l2_psm = chan->psm; + if (peer) { - la->l2_psm = chan->psm; bacpy(&la->l2_bdaddr, &chan->dst); la->l2_cid = cpu_to_le16(chan->dcid); la->l2_bdaddr_type = chan->dst_type; } else { - la->l2_psm = chan->sport; bacpy(&la->l2_bdaddr, &chan->src); la->l2_cid = cpu_to_le16(chan->scid); la->l2_bdaddr_type = chan->src_type; @@ -432,6 +439,10 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT | L2CAP_LM_SECURE; break; + case BT_SECURITY_FIPS: + opt = L2CAP_LM_AUTH | L2CAP_LM_ENCRYPT | + L2CAP_LM_SECURE | L2CAP_LM_FIPS; + break; default: opt = 0; break; @@ -445,6 +456,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, if (put_user(opt, (u32 __user *) optval)) err = -EFAULT; + break; case L2CAP_CONNINFO: @@ -499,6 +511,7 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, switch (optname) { case BT_SECURITY: if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED && + chan->chan_type != L2CAP_CHAN_FIXED && chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; break; @@ -560,11 +573,6 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, break; case BT_SNDMTU: - if (!enable_lecoc) { - err = -EPROTONOSUPPORT; - break; - } - if (!bdaddr_type_is_le(chan->src_type)) { err = -EINVAL; break; @@ -580,11 +588,6 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, break; case BT_RCVMTU: - if (!enable_lecoc) { - err = -EPROTONOSUPPORT; - break; - } - if (!bdaddr_type_is_le(chan->src_type)) { err = -EINVAL; break; @@ -699,6 +702,11 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, break; } + if (opt & L2CAP_LM_FIPS) { + err = -EINVAL; + break; + } + if (opt & L2CAP_LM_AUTH) chan->sec_level = BT_SECURITY_LOW; if (opt & L2CAP_LM_ENCRYPT) @@ -750,6 +758,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, switch (optname) { case BT_SECURITY: if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED && + chan->chan_type != L2CAP_CHAN_FIXED && chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; break; @@ -895,11 +904,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_SNDMTU: - if (!enable_lecoc) { - err = -EPROTONOSUPPORT; - break; - } - if (!bdaddr_type_is_le(chan->src_type)) { err = -EINVAL; break; @@ -912,11 +916,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_RCVMTU: - if (!enable_lecoc) { - err = -EPROTONOSUPPORT; - break; - } - if (!bdaddr_type_is_le(chan->src_type)) { err = -EINVAL; break; @@ -1449,6 +1448,11 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->tx_credits = pchan->tx_credits; chan->rx_credits = pchan->rx_credits; + if (chan->chan_type == L2CAP_CHAN_FIXED) { + chan->scid = pchan->scid; + chan->dcid = pchan->scid; + } + security_sk_clone(parent, sk); } else { switch (sk->sk_type) { @@ -1614,6 +1618,3 @@ void l2cap_cleanup_sockets(void) bt_sock_unregister(BTPROTO_L2CAP); proto_unregister(&l2cap_proto); } - -module_param(enable_lecoc, bool, 0644); -MODULE_PARM_DESC(enable_lecoc, "Enable support for LE CoC"); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index a03ca3ca91bf..d2d4e0d5aed0 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -34,7 +34,7 @@ #include "smp.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 4 +#define MGMT_REVISION 5 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -79,6 +79,10 @@ static const u16 mgmt_commands[] = { MGMT_OP_SET_BREDR, MGMT_OP_SET_STATIC_ADDRESS, MGMT_OP_SET_SCAN_PARAMS, + MGMT_OP_SET_SECURE_CONN, + MGMT_OP_SET_DEBUG_KEYS, + MGMT_OP_SET_PRIVACY, + MGMT_OP_LOAD_IRKS, }; static const u16 mgmt_events[] = { @@ -103,6 +107,8 @@ static const u16 mgmt_events[] = { MGMT_EV_DEVICE_UNBLOCKED, MGMT_EV_DEVICE_UNPAIRED, MGMT_EV_PASSKEY_NOTIFY, + MGMT_EV_NEW_IRK, + MGMT_EV_NEW_CSRK, }; #define CACHE_TIMEOUT msecs_to_jiffies(2 * 1000) @@ -127,7 +133,7 @@ static u8 mgmt_status_table[] = { MGMT_STATUS_FAILED, /* Hardware Failure */ MGMT_STATUS_CONNECT_FAILED, /* Page Timeout */ MGMT_STATUS_AUTH_FAILED, /* Authentication Failed */ - MGMT_STATUS_NOT_PAIRED, /* PIN or Key Missing */ + MGMT_STATUS_AUTH_FAILED, /* PIN or Key Missing */ MGMT_STATUS_NO_RESOURCES, /* Memory Full */ MGMT_STATUS_TIMEOUT, /* Connection Timeout */ MGMT_STATUS_NO_RESOURCES, /* Max Number of Connections */ @@ -207,7 +213,7 @@ static int cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status) hdr = (void *) skb_put(skb, sizeof(*hdr)); - hdr->opcode = __constant_cpu_to_le16(MGMT_EV_CMD_STATUS); + hdr->opcode = cpu_to_le16(MGMT_EV_CMD_STATUS); hdr->index = cpu_to_le16(index); hdr->len = cpu_to_le16(sizeof(*ev)); @@ -238,7 +244,7 @@ static int cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status, hdr = (void *) skb_put(skb, sizeof(*hdr)); - hdr->opcode = __constant_cpu_to_le16(MGMT_EV_CMD_COMPLETE); + hdr->opcode = cpu_to_le16(MGMT_EV_CMD_COMPLETE); hdr->index = cpu_to_le16(index); hdr->len = cpu_to_le16(sizeof(*ev) + rp_len); @@ -264,7 +270,7 @@ static int read_version(struct sock *sk, struct hci_dev *hdev, void *data, BT_DBG("sock %p", sk); rp.version = MGMT_VERSION; - rp.revision = __constant_cpu_to_le16(MGMT_REVISION); + rp.revision = cpu_to_le16(MGMT_REVISION); return cmd_complete(sk, MGMT_INDEX_NONE, MGMT_OP_READ_VERSION, 0, &rp, sizeof(rp)); @@ -288,8 +294,8 @@ static int read_commands(struct sock *sk, struct hci_dev *hdev, void *data, if (!rp) return -ENOMEM; - rp->num_commands = __constant_cpu_to_le16(num_commands); - rp->num_events = __constant_cpu_to_le16(num_events); + rp->num_commands = cpu_to_le16(num_commands); + rp->num_events = cpu_to_le16(num_events); for (i = 0, opcode = rp->opcodes; i < num_commands; i++, opcode++) put_unaligned_le16(mgmt_commands[i], opcode); @@ -363,6 +369,7 @@ static u32 get_supported_settings(struct hci_dev *hdev) settings |= MGMT_SETTING_POWERED; settings |= MGMT_SETTING_PAIRABLE; + settings |= MGMT_SETTING_DEBUG_KEYS; if (lmp_bredr_capable(hdev)) { settings |= MGMT_SETTING_CONNECTABLE; @@ -376,11 +383,16 @@ static u32 get_supported_settings(struct hci_dev *hdev) settings |= MGMT_SETTING_SSP; settings |= MGMT_SETTING_HS; } + + if (lmp_sc_capable(hdev) || + test_bit(HCI_FORCE_SC, &hdev->dev_flags)) + settings |= MGMT_SETTING_SECURE_CONN; } if (lmp_le_capable(hdev)) { settings |= MGMT_SETTING_LE; settings |= MGMT_SETTING_ADVERTISING; + settings |= MGMT_SETTING_PRIVACY; } return settings; @@ -423,6 +435,15 @@ static u32 get_current_settings(struct hci_dev *hdev) if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) settings |= MGMT_SETTING_ADVERTISING; + if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) + settings |= MGMT_SETTING_SECURE_CONN; + + if (test_bit(HCI_DEBUG_KEYS, &hdev->dev_flags)) + settings |= MGMT_SETTING_DEBUG_KEYS; + + if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) + settings |= MGMT_SETTING_PRIVACY; + return settings; } @@ -629,14 +650,8 @@ static u8 create_adv_data(struct hci_dev *hdev, u8 *ptr) flags |= get_adv_discov_flags(hdev); - if (test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) { - if (lmp_le_br_capable(hdev)) - flags |= LE_AD_SIM_LE_BREDR_CTRL; - if (lmp_host_le_br_capable(hdev)) - flags |= LE_AD_SIM_LE_BREDR_HOST; - } else { + if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) flags |= LE_AD_NO_BREDR; - } if (flags) { BT_DBG("adv flags 0x%02x", flags); @@ -803,6 +818,64 @@ static void update_class(struct hci_request *req) hci_req_add(req, HCI_OP_WRITE_CLASS_OF_DEV, sizeof(cod), cod); } +static bool get_connectable(struct hci_dev *hdev) +{ + struct pending_cmd *cmd; + + /* If there's a pending mgmt command the flag will not yet have + * it's final value, so check for this first. + */ + cmd = mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev); + if (cmd) { + struct mgmt_mode *cp = cmd->param; + return cp->val; + } + + return test_bit(HCI_CONNECTABLE, &hdev->dev_flags); +} + +static void enable_advertising(struct hci_request *req) +{ + struct hci_dev *hdev = req->hdev; + struct hci_cp_le_set_adv_param cp; + u8 own_addr_type, enable = 0x01; + bool connectable; + + /* Clear the HCI_ADVERTISING bit temporarily so that the + * hci_update_random_address knows that it's safe to go ahead + * and write a new random address. The flag will be set back on + * as soon as the SET_ADV_ENABLE HCI command completes. + */ + clear_bit(HCI_ADVERTISING, &hdev->dev_flags); + + connectable = get_connectable(hdev); + + /* Set require_privacy to true only when non-connectable + * advertising is used. In that case it is fine to use a + * non-resolvable private address. + */ + if (hci_update_random_address(req, !connectable, &own_addr_type) < 0) + return; + + memset(&cp, 0, sizeof(cp)); + cp.min_interval = cpu_to_le16(0x0800); + cp.max_interval = cpu_to_le16(0x0800); + cp.type = connectable ? LE_ADV_IND : LE_ADV_NONCONN_IND; + cp.own_address_type = own_addr_type; + cp.channel_map = hdev->le_adv_channel_map; + + hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp); + + hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); +} + +static void disable_advertising(struct hci_request *req) +{ + u8 enable = 0x00; + + hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); +} + static void service_cache_off(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, @@ -824,12 +897,39 @@ static void service_cache_off(struct work_struct *work) hci_req_run(&req, NULL); } +static void rpa_expired(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + rpa_expired.work); + struct hci_request req; + + BT_DBG(""); + + set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + + if (!test_bit(HCI_ADVERTISING, &hdev->dev_flags) || + hci_conn_num(hdev, LE_LINK) > 0) + return; + + /* The generation of a new RPA and programming it into the + * controller happens in the enable_advertising() function. + */ + + hci_req_init(&req, hdev); + + disable_advertising(&req); + enable_advertising(&req); + + hci_req_run(&req, NULL); +} + static void mgmt_init_hdev(struct sock *sk, struct hci_dev *hdev) { if (test_and_set_bit(HCI_MGMT, &hdev->dev_flags)) return; INIT_DELAYED_WORK(&hdev->service_cache, service_cache_off); + INIT_DELAYED_WORK(&hdev->rpa_expired, rpa_expired); /* Non-mgmt controlled devices get this bit set * implicitly so that pairing works for them, however @@ -935,6 +1035,71 @@ static int send_settings_rsp(struct sock *sk, u16 opcode, struct hci_dev *hdev) sizeof(settings)); } +static void clean_up_hci_complete(struct hci_dev *hdev, u8 status) +{ + BT_DBG("%s status 0x%02x", hdev->name, status); + + if (hci_conn_count(hdev) == 0) { + cancel_delayed_work(&hdev->power_off); + queue_work(hdev->req_workqueue, &hdev->power_off.work); + } +} + +static int clean_up_hci_state(struct hci_dev *hdev) +{ + struct hci_request req; + struct hci_conn *conn; + + hci_req_init(&req, hdev); + + if (test_bit(HCI_ISCAN, &hdev->flags) || + test_bit(HCI_PSCAN, &hdev->flags)) { + u8 scan = 0x00; + hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); + } + + if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) + disable_advertising(&req); + + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) { + hci_req_add_le_scan_disable(&req); + } + + list_for_each_entry(conn, &hdev->conn_hash.list, list) { + struct hci_cp_disconnect dc; + struct hci_cp_reject_conn_req rej; + + switch (conn->state) { + case BT_CONNECTED: + case BT_CONFIG: + dc.handle = cpu_to_le16(conn->handle); + dc.reason = 0x15; /* Terminated due to Power Off */ + hci_req_add(&req, HCI_OP_DISCONNECT, sizeof(dc), &dc); + break; + case BT_CONNECT: + if (conn->type == LE_LINK) + hci_req_add(&req, HCI_OP_LE_CREATE_CONN_CANCEL, + 0, NULL); + else if (conn->type == ACL_LINK) + hci_req_add(&req, HCI_OP_CREATE_CONN_CANCEL, + 6, &conn->dst); + break; + case BT_CONNECT2: + bacpy(&rej.bdaddr, &conn->dst); + rej.reason = 0x15; /* Terminated due to Power Off */ + if (conn->type == ACL_LINK) + hci_req_add(&req, HCI_OP_REJECT_CONN_REQ, + sizeof(rej), &rej); + else if (conn->type == SCO_LINK) + hci_req_add(&req, HCI_OP_REJECT_SYNC_CONN_REQ, + sizeof(rej), &rej); + break; + } + } + + return hci_req_run(&req, clean_up_hci_complete); +} + static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { @@ -978,12 +1143,23 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - if (cp->val) + if (cp->val) { queue_work(hdev->req_workqueue, &hdev->power_on); - else - queue_work(hdev->req_workqueue, &hdev->power_off.work); - - err = 0; + err = 0; + } else { + /* Disconnect connections, stop scans, etc */ + err = clean_up_hci_state(hdev); + if (!err) + queue_delayed_work(hdev->req_workqueue, &hdev->power_off, + HCI_POWER_OFF_TIMEOUT); + + /* ENODATA means there were no HCI commands queued */ + if (err == -ENODATA) { + cancel_delayed_work(&hdev->power_off); + queue_work(hdev->req_workqueue, &hdev->power_off.work); + err = 0; + } + } failed: hci_dev_unlock(hdev); @@ -1005,7 +1181,7 @@ static int mgmt_event(u16 event, struct hci_dev *hdev, void *data, u16 data_len, if (hdev) hdr->index = cpu_to_le16(hdev->id); else - hdr->index = __constant_cpu_to_le16(MGMT_INDEX_NONE); + hdr->index = cpu_to_le16(MGMT_INDEX_NONE); hdr->len = cpu_to_le16(data_len); if (data) @@ -1317,15 +1493,15 @@ static void write_fast_connectable(struct hci_request *req, bool enable) type = PAGE_SCAN_TYPE_INTERLACED; /* 160 msec page scan interval */ - acp.interval = __constant_cpu_to_le16(0x0100); + acp.interval = cpu_to_le16(0x0100); } else { type = PAGE_SCAN_TYPE_STANDARD; /* default */ /* default 1.28 sec page scan */ - acp.interval = __constant_cpu_to_le16(0x0800); + acp.interval = cpu_to_le16(0x0800); } - acp.window = __constant_cpu_to_le16(0x0012); + acp.window = cpu_to_le16(0x0012); if (__cpu_to_le16(hdev->page_scan_interval) != acp.interval || __cpu_to_le16(hdev->page_scan_window) != acp.window) @@ -1336,50 +1512,6 @@ static void write_fast_connectable(struct hci_request *req, bool enable) hci_req_add(req, HCI_OP_WRITE_PAGE_SCAN_TYPE, 1, &type); } -static u8 get_adv_type(struct hci_dev *hdev) -{ - struct pending_cmd *cmd; - bool connectable; - - /* If there's a pending mgmt command the flag will not yet have - * it's final value, so check for this first. - */ - cmd = mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev); - if (cmd) { - struct mgmt_mode *cp = cmd->param; - connectable = !!cp->val; - } else { - connectable = test_bit(HCI_CONNECTABLE, &hdev->dev_flags); - } - - return connectable ? LE_ADV_IND : LE_ADV_NONCONN_IND; -} - -static void enable_advertising(struct hci_request *req) -{ - struct hci_dev *hdev = req->hdev; - struct hci_cp_le_set_adv_param cp; - u8 enable = 0x01; - - memset(&cp, 0, sizeof(cp)); - cp.min_interval = __constant_cpu_to_le16(0x0800); - cp.max_interval = __constant_cpu_to_le16(0x0800); - cp.type = get_adv_type(hdev); - cp.own_address_type = hdev->own_addr_type; - cp.channel_map = 0x07; - - hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp); - - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); -} - -static void disable_advertising(struct hci_request *req) -{ - u8 enable = 0x00; - - hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); -} - static void set_connectable_complete(struct hci_dev *hdev, u8 status) { struct pending_cmd *cmd; @@ -2065,7 +2197,7 @@ static int remove_uuid(struct sock *sk, struct hci_dev *hdev, void *data, } if (memcmp(cp->uuid, bt_uuid_any, 16) == 0) { - err = hci_uuids_clear(hdev); + hci_uuids_clear(hdev); if (enable_service_cache(hdev)) { err = cmd_complete(sk, hdev->id, MGMT_OP_REMOVE_UUID, @@ -2205,6 +2337,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, { struct mgmt_cp_load_link_keys *cp = data; u16 key_count, expected_len; + bool changed; int i; BT_DBG("request for %s", hdev->name); @@ -2219,7 +2352,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, sizeof(struct mgmt_link_key_info); if (expected_len != len) { BT_ERR("load_link_keys: expected %u bytes, got %u bytes", - len, expected_len); + expected_len, len); return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, MGMT_STATUS_INVALID_PARAMS); } @@ -2234,7 +2367,7 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, for (i = 0; i < key_count; i++) { struct mgmt_link_key_info *key = &cp->keys[i]; - if (key->addr.type != BDADDR_BREDR) + if (key->addr.type != BDADDR_BREDR || key->type > 0x08) return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, MGMT_STATUS_INVALID_PARAMS); } @@ -2244,9 +2377,12 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, hci_link_keys_clear(hdev); if (cp->debug_keys) - set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + changed = !test_and_set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); else - clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + changed = test_and_clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + + if (changed) + new_settings(hdev, NULL); for (i = 0; i < key_count; i++) { struct mgmt_link_key_info *key = &cp->keys[i]; @@ -2306,10 +2442,22 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - if (cp->addr.type == BDADDR_BREDR) + if (cp->addr.type == BDADDR_BREDR) { err = hci_remove_link_key(hdev, &cp->addr.bdaddr); - else - err = hci_remove_ltk(hdev, &cp->addr.bdaddr); + } else { + u8 addr_type; + + if (cp->addr.type == BDADDR_LE_PUBLIC) + addr_type = ADDR_LE_DEV_PUBLIC; + else + addr_type = ADDR_LE_DEV_RANDOM; + + hci_remove_irk(hdev, &cp->addr.bdaddr, addr_type); + + hci_conn_params_del(hdev, &cp->addr.bdaddr, addr_type); + + err = hci_remove_ltk(hdev, &cp->addr.bdaddr, addr_type); + } if (err < 0) { err = cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE, @@ -2633,6 +2781,16 @@ static void pairing_complete(struct pending_cmd *cmd, u8 status) mgmt_pending_remove(cmd); } +void mgmt_smp_complete(struct hci_conn *conn, bool complete) +{ + u8 status = complete ? MGMT_STATUS_SUCCESS : MGMT_STATUS_FAILED; + struct pending_cmd *cmd; + + cmd = find_pairing(conn); + if (cmd) + pairing_complete(cmd, status); +} + static void pairing_complete_cb(struct hci_conn *conn, u8 status) { struct pending_cmd *cmd; @@ -2646,7 +2804,7 @@ static void pairing_complete_cb(struct hci_conn *conn, u8 status) pairing_complete(cmd, mgmt_status(status)); } -static void le_connect_complete_cb(struct hci_conn *conn, u8 status) +static void le_pairing_complete_cb(struct hci_conn *conn, u8 status) { struct pending_cmd *cmd; @@ -2697,12 +2855,22 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, else auth_type = HCI_AT_DEDICATED_BONDING_MITM; - if (cp->addr.type == BDADDR_BREDR) - conn = hci_connect(hdev, ACL_LINK, &cp->addr.bdaddr, - cp->addr.type, sec_level, auth_type); - else - conn = hci_connect(hdev, LE_LINK, &cp->addr.bdaddr, - cp->addr.type, sec_level, auth_type); + if (cp->addr.type == BDADDR_BREDR) { + conn = hci_connect_acl(hdev, &cp->addr.bdaddr, sec_level, + auth_type); + } else { + u8 addr_type; + + /* Convert from L2CAP channel address type to HCI address type + */ + if (cp->addr.type == BDADDR_LE_PUBLIC) + addr_type = ADDR_LE_DEV_PUBLIC; + else + addr_type = ADDR_LE_DEV_RANDOM; + + conn = hci_connect_le(hdev, &cp->addr.bdaddr, addr_type, + sec_level, auth_type); + } if (IS_ERR(conn)) { int status; @@ -2733,13 +2901,16 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, } /* For LE, just connecting isn't a proof that the pairing finished */ - if (cp->addr.type == BDADDR_BREDR) + if (cp->addr.type == BDADDR_BREDR) { conn->connect_cfm_cb = pairing_complete_cb; - else - conn->connect_cfm_cb = le_connect_complete_cb; + conn->security_cfm_cb = pairing_complete_cb; + conn->disconn_cfm_cb = pairing_complete_cb; + } else { + conn->connect_cfm_cb = le_pairing_complete_cb; + conn->security_cfm_cb = le_pairing_complete_cb; + conn->disconn_cfm_cb = le_pairing_complete_cb; + } - conn->security_cfm_cb = pairing_complete_cb; - conn->disconn_cfm_cb = pairing_complete_cb; conn->io_capability = cp->io_cap; cmd->user_data = conn; @@ -3071,7 +3242,12 @@ static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev, goto unlock; } - err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL); + if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags)) + err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_EXT_DATA, + 0, NULL); + else + err = hci_send_cmd(hdev, HCI_OP_READ_LOCAL_OOB_DATA, 0, NULL); + if (err < 0) mgmt_pending_remove(cmd); @@ -3083,23 +3259,46 @@ unlock: static int add_remote_oob_data(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { - struct mgmt_cp_add_remote_oob_data *cp = data; - u8 status; int err; BT_DBG("%s ", hdev->name); hci_dev_lock(hdev); - err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr, cp->hash, - cp->randomizer); - if (err < 0) - status = MGMT_STATUS_FAILED; - else - status = MGMT_STATUS_SUCCESS; + if (len == MGMT_ADD_REMOTE_OOB_DATA_SIZE) { + struct mgmt_cp_add_remote_oob_data *cp = data; + u8 status; - err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, status, - &cp->addr, sizeof(cp->addr)); + err = hci_add_remote_oob_data(hdev, &cp->addr.bdaddr, + cp->hash, cp->randomizer); + if (err < 0) + status = MGMT_STATUS_FAILED; + else + status = MGMT_STATUS_SUCCESS; + + err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, + status, &cp->addr, sizeof(cp->addr)); + } else if (len == MGMT_ADD_REMOTE_OOB_EXT_DATA_SIZE) { + struct mgmt_cp_add_remote_oob_ext_data *cp = data; + u8 status; + + err = hci_add_remote_oob_ext_data(hdev, &cp->addr.bdaddr, + cp->hash192, + cp->randomizer192, + cp->hash256, + cp->randomizer256); + if (err < 0) + status = MGMT_STATUS_FAILED; + else + status = MGMT_STATUS_SUCCESS; + + err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, + status, &cp->addr, sizeof(cp->addr)); + } else { + BT_ERR("add_remote_oob_data: invalid length of %u bytes", len); + err = cmd_status(sk, hdev->id, MGMT_OP_ADD_REMOTE_OOB_DATA, + MGMT_STATUS_INVALID_PARAMS); + } hci_dev_unlock(hdev); return err; @@ -3195,7 +3394,7 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev, struct hci_request req; /* General inquiry access code (GIAC) */ u8 lap[3] = { 0x33, 0x8b, 0x9e }; - u8 status; + u8 status, own_addr_type; int err; BT_DBG("%s", hdev->name); @@ -3280,18 +3479,31 @@ static int start_discovery(struct sock *sk, struct hci_dev *hdev, goto failed; } - if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) { + /* If controller is scanning, it means the background scanning + * is running. Thus, we should temporarily stop it in order to + * set the discovery scanning parameters. + */ + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) + hci_req_add_le_scan_disable(&req); + + memset(¶m_cp, 0, sizeof(param_cp)); + + /* All active scans will be done with either a resolvable + * private address (when privacy feature has been enabled) + * or unresolvable private address. + */ + err = hci_update_random_address(&req, true, &own_addr_type); + if (err < 0) { err = cmd_status(sk, hdev->id, MGMT_OP_START_DISCOVERY, - MGMT_STATUS_BUSY); + MGMT_STATUS_FAILED); mgmt_pending_remove(cmd); goto failed; } - memset(¶m_cp, 0, sizeof(param_cp)); param_cp.type = LE_SCAN_ACTIVE; param_cp.interval = cpu_to_le16(DISCOV_LE_SCAN_INT); param_cp.window = cpu_to_le16(DISCOV_LE_SCAN_WIN); - param_cp.own_address_type = hdev->own_addr_type; + param_cp.own_address_type = own_addr_type; hci_req_add(&req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), ¶m_cp); @@ -3361,7 +3573,6 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data, struct hci_cp_remote_name_req_cancel cp; struct inquiry_entry *e; struct hci_request req; - struct hci_cp_le_set_scan_enable enable_cp; int err; BT_DBG("%s", hdev->name); @@ -3397,10 +3608,7 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data, } else { cancel_delayed_work(&hdev->le_scan_disable); - memset(&enable_cp, 0, sizeof(enable_cp)); - enable_cp.enable = LE_SCAN_DISABLE; - hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE, - sizeof(enable_cp), &enable_cp); + hci_req_add_le_scan_disable(&req); } break; @@ -3457,15 +3665,17 @@ static int confirm_name(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); if (!hci_discovery_active(hdev)) { - err = cmd_status(sk, hdev->id, MGMT_OP_CONFIRM_NAME, - MGMT_STATUS_FAILED); + err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, + MGMT_STATUS_FAILED, &cp->addr, + sizeof(cp->addr)); goto failed; } e = hci_inquiry_cache_lookup_unknown(hdev, &cp->addr.bdaddr); if (!e) { - err = cmd_status(sk, hdev->id, MGMT_OP_CONFIRM_NAME, - MGMT_STATUS_INVALID_PARAMS); + err = cmd_complete(sk, hdev->id, MGMT_OP_CONFIRM_NAME, + MGMT_STATUS_INVALID_PARAMS, &cp->addr, + sizeof(cp->addr)); goto failed; } @@ -3754,6 +3964,21 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev, err = cmd_complete(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, 0, NULL, 0); + /* If background scan is running, restart it so new parameters are + * loaded. + */ + if (test_bit(HCI_LE_SCAN, &hdev->dev_flags) && + hdev->discovery.state == DISCOVERY_STOPPED) { + struct hci_request req; + + hci_req_init(&req, hdev); + + hci_req_add_le_scan_disable(&req); + hci_req_add_le_passive_scan(&req); + + hci_req_run(&req, NULL); + } + hci_dev_unlock(hdev); return err; @@ -3999,15 +4224,269 @@ unlock: return err; } +static int set_secure_conn(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_mode *cp = data; + struct pending_cmd *cmd; + u8 val, status; + int err; + + BT_DBG("request for %s", hdev->name); + + status = mgmt_bredr_support(hdev); + if (status) + return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + status); + + if (!lmp_sc_capable(hdev) && + !test_bit(HCI_FORCE_SC, &hdev->dev_flags)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + MGMT_STATUS_NOT_SUPPORTED); + + if (cp->val != 0x00 && cp->val != 0x01 && cp->val != 0x02) + return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + MGMT_STATUS_INVALID_PARAMS); + + hci_dev_lock(hdev); + + if (!hdev_is_powered(hdev)) { + bool changed; + + if (cp->val) { + changed = !test_and_set_bit(HCI_SC_ENABLED, + &hdev->dev_flags); + if (cp->val == 0x02) + set_bit(HCI_SC_ONLY, &hdev->dev_flags); + else + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + } else { + changed = test_and_clear_bit(HCI_SC_ENABLED, + &hdev->dev_flags); + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + } + + err = send_settings_rsp(sk, MGMT_OP_SET_SECURE_CONN, hdev); + if (err < 0) + goto failed; + + if (changed) + err = new_settings(hdev, sk); + + goto failed; + } + + if (mgmt_pending_find(MGMT_OP_SET_SECURE_CONN, hdev)) { + err = cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN, + MGMT_STATUS_BUSY); + goto failed; + } + + val = !!cp->val; + + if (val == test_bit(HCI_SC_ENABLED, &hdev->dev_flags) && + (cp->val == 0x02) == test_bit(HCI_SC_ONLY, &hdev->dev_flags)) { + err = send_settings_rsp(sk, MGMT_OP_SET_SECURE_CONN, hdev); + goto failed; + } + + cmd = mgmt_pending_add(sk, MGMT_OP_SET_SECURE_CONN, hdev, data, len); + if (!cmd) { + err = -ENOMEM; + goto failed; + } + + err = hci_send_cmd(hdev, HCI_OP_WRITE_SC_SUPPORT, 1, &val); + if (err < 0) { + mgmt_pending_remove(cmd); + goto failed; + } + + if (cp->val == 0x02) + set_bit(HCI_SC_ONLY, &hdev->dev_flags); + else + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + +failed: + hci_dev_unlock(hdev); + return err; +} + +static int set_debug_keys(struct sock *sk, struct hci_dev *hdev, + void *data, u16 len) +{ + struct mgmt_mode *cp = data; + bool changed; + int err; + + BT_DBG("request for %s", hdev->name); + + if (cp->val != 0x00 && cp->val != 0x01) + return cmd_status(sk, hdev->id, MGMT_OP_SET_DEBUG_KEYS, + MGMT_STATUS_INVALID_PARAMS); + + hci_dev_lock(hdev); + + if (cp->val) + changed = !test_and_set_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + else + changed = test_and_clear_bit(HCI_DEBUG_KEYS, &hdev->dev_flags); + + err = send_settings_rsp(sk, MGMT_OP_SET_DEBUG_KEYS, hdev); + if (err < 0) + goto unlock; + + if (changed) + err = new_settings(hdev, sk); + +unlock: + hci_dev_unlock(hdev); + return err; +} + +static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data, + u16 len) +{ + struct mgmt_cp_set_privacy *cp = cp_data; + bool changed; + int err; + + BT_DBG("request for %s", hdev->name); + + if (!lmp_le_capable(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, + MGMT_STATUS_NOT_SUPPORTED); + + if (cp->privacy != 0x00 && cp->privacy != 0x01) + return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, + MGMT_STATUS_INVALID_PARAMS); + + if (hdev_is_powered(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_SET_PRIVACY, + MGMT_STATUS_REJECTED); + + hci_dev_lock(hdev); + + /* If user space supports this command it is also expected to + * handle IRKs. Therefore, set the HCI_RPA_RESOLVING flag. + */ + set_bit(HCI_RPA_RESOLVING, &hdev->dev_flags); + + if (cp->privacy) { + changed = !test_and_set_bit(HCI_PRIVACY, &hdev->dev_flags); + memcpy(hdev->irk, cp->irk, sizeof(hdev->irk)); + set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + } else { + changed = test_and_clear_bit(HCI_PRIVACY, &hdev->dev_flags); + memset(hdev->irk, 0, sizeof(hdev->irk)); + clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags); + } + + err = send_settings_rsp(sk, MGMT_OP_SET_PRIVACY, hdev); + if (err < 0) + goto unlock; + + if (changed) + err = new_settings(hdev, sk); + +unlock: + hci_dev_unlock(hdev); + return err; +} + +static bool irk_is_valid(struct mgmt_irk_info *irk) +{ + switch (irk->addr.type) { + case BDADDR_LE_PUBLIC: + return true; + + case BDADDR_LE_RANDOM: + /* Two most significant bits shall be set */ + if ((irk->addr.bdaddr.b[5] & 0xc0) != 0xc0) + return false; + return true; + } + + return false; +} + +static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, + u16 len) +{ + struct mgmt_cp_load_irks *cp = cp_data; + u16 irk_count, expected_len; + int i, err; + + BT_DBG("request for %s", hdev->name); + + if (!lmp_le_capable(hdev)) + return cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, + MGMT_STATUS_NOT_SUPPORTED); + + irk_count = __le16_to_cpu(cp->irk_count); + + expected_len = sizeof(*cp) + irk_count * sizeof(struct mgmt_irk_info); + if (expected_len != len) { + BT_ERR("load_irks: expected %u bytes, got %u bytes", + expected_len, len); + return cmd_status(sk, hdev->id, MGMT_OP_LOAD_IRKS, + MGMT_STATUS_INVALID_PARAMS); + } + + BT_DBG("%s irk_count %u", hdev->name, irk_count); + + for (i = 0; i < irk_count; i++) { + struct mgmt_irk_info *key = &cp->irks[i]; + + if (!irk_is_valid(key)) + return cmd_status(sk, hdev->id, + MGMT_OP_LOAD_IRKS, + MGMT_STATUS_INVALID_PARAMS); + } + + hci_dev_lock(hdev); + + hci_smp_irks_clear(hdev); + + for (i = 0; i < irk_count; i++) { + struct mgmt_irk_info *irk = &cp->irks[i]; + u8 addr_type; + + if (irk->addr.type == BDADDR_LE_PUBLIC) + addr_type = ADDR_LE_DEV_PUBLIC; + else + addr_type = ADDR_LE_DEV_RANDOM; + + hci_add_irk(hdev, &irk->addr.bdaddr, addr_type, irk->val, + BDADDR_ANY); + } + + set_bit(HCI_RPA_RESOLVING, &hdev->dev_flags); + + err = cmd_complete(sk, hdev->id, MGMT_OP_LOAD_IRKS, 0, NULL, 0); + + hci_dev_unlock(hdev); + + return err; +} + static bool ltk_is_valid(struct mgmt_ltk_info *key) { - if (key->authenticated != 0x00 && key->authenticated != 0x01) - return false; if (key->master != 0x00 && key->master != 0x01) return false; - if (!bdaddr_type_is_le(key->addr.type)) - return false; - return true; + + switch (key->addr.type) { + case BDADDR_LE_PUBLIC: + return true; + + case BDADDR_LE_RANDOM: + /* Two most significant bits shall be set */ + if ((key->addr.bdaddr.b[5] & 0xc0) != 0xc0) + return false; + return true; + } + + return false; } static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, @@ -4029,7 +4508,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, sizeof(struct mgmt_ltk_info); if (expected_len != len) { BT_ERR("load_keys: expected %u bytes, got %u bytes", - len, expected_len); + expected_len, len); return cmd_status(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, MGMT_STATUS_INVALID_PARAMS); } @@ -4063,9 +4542,9 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, else type = HCI_SMP_LTK_SLAVE; - hci_add_ltk(hdev, &key->addr.bdaddr, addr_type, - type, 0, key->authenticated, key->val, - key->enc_size, key->ediv, key->rand); + hci_add_ltk(hdev, &key->addr.bdaddr, addr_type, type, + key->type, key->val, key->enc_size, key->ediv, + key->rand); } err = cmd_complete(sk, hdev->id, MGMT_OP_LOAD_LONG_TERM_KEYS, 0, @@ -4115,7 +4594,7 @@ static const struct mgmt_handler { { user_passkey_reply, false, MGMT_USER_PASSKEY_REPLY_SIZE }, { user_passkey_neg_reply, false, MGMT_USER_PASSKEY_NEG_REPLY_SIZE }, { read_local_oob_data, false, MGMT_READ_LOCAL_OOB_DATA_SIZE }, - { add_remote_oob_data, false, MGMT_ADD_REMOTE_OOB_DATA_SIZE }, + { add_remote_oob_data, true, MGMT_ADD_REMOTE_OOB_DATA_SIZE }, { remove_remote_oob_data, false, MGMT_REMOVE_REMOTE_OOB_DATA_SIZE }, { start_discovery, false, MGMT_START_DISCOVERY_SIZE }, { stop_discovery, false, MGMT_STOP_DISCOVERY_SIZE }, @@ -4127,6 +4606,10 @@ static const struct mgmt_handler { { set_bredr, false, MGMT_SETTING_SIZE }, { set_static_address, false, MGMT_SET_STATIC_ADDRESS_SIZE }, { set_scan_params, false, MGMT_SET_SCAN_PARAMS_SIZE }, + { set_secure_conn, false, MGMT_SETTING_SIZE }, + { set_debug_keys, false, MGMT_SETTING_SIZE }, + { set_privacy, false, MGMT_SET_PRIVACY_SIZE }, + { load_irks, true, MGMT_LOAD_IRKS_SIZE }, }; @@ -4243,6 +4726,17 @@ void mgmt_index_removed(struct hci_dev *hdev) mgmt_event(MGMT_EV_INDEX_REMOVED, hdev, NULL, 0, NULL); } +/* This function requires the caller holds hdev->lock */ +static void restart_le_auto_conns(struct hci_dev *hdev) +{ + struct hci_conn_params *p; + + list_for_each_entry(p, &hdev->le_conn_params, list) { + if (p->auto_connect == HCI_AUTO_CONN_ALWAYS) + hci_pend_le_conn_add(hdev, &p->addr, p->addr_type); + } +} + static void powered_complete(struct hci_dev *hdev, u8 status) { struct cmd_lookup match = { NULL, hdev }; @@ -4251,6 +4745,8 @@ static void powered_complete(struct hci_dev *hdev, u8 status) hci_dev_lock(hdev); + restart_le_auto_conns(hdev); + mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match); new_settings(hdev, match.sk); @@ -4292,11 +4788,6 @@ static int powered_update_hci(struct hci_dev *hdev) } if (lmp_le_capable(hdev)) { - /* Set random address to static address if configured */ - if (bacmp(&hdev->static_addr, BDADDR_ANY)) - hci_req_add(&req, HCI_OP_LE_SET_RANDOM_ADDR, 6, - &hdev->static_addr); - /* Make sure the controller has a good default for * advertising data. This also applies to the case * where BR/EDR was toggled during the AUTO_OFF phase. @@ -4422,6 +4913,10 @@ void mgmt_discoverable(struct hci_dev *hdev, u8 discoverable) if (mgmt_pending_find(MGMT_OP_SET_DISCOVERABLE, hdev)) return; + /* Powering off may clear the scan mode - don't let that interfere */ + if (!discoverable && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) + return; + if (discoverable) { changed = !test_and_set_bit(HCI_DISCOVERABLE, &hdev->dev_flags); } else { @@ -4455,6 +4950,10 @@ void mgmt_connectable(struct hci_dev *hdev, u8 connectable) if (mgmt_pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) return; + /* Powering off may clear the scan mode - don't let that interfere */ + if (!connectable && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) + return; + if (connectable) changed = !test_and_set_bit(HCI_CONNECTABLE, &hdev->dev_flags); else @@ -4464,6 +4963,18 @@ void mgmt_connectable(struct hci_dev *hdev, u8 connectable) new_settings(hdev, NULL); } +void mgmt_advertising(struct hci_dev *hdev, u8 advertising) +{ + /* Powering off may stop advertising - don't let that interfere */ + if (!advertising && mgmt_pending_find(MGMT_OP_SET_POWERED, hdev)) + return; + + if (advertising) + set_bit(HCI_ADVERTISING, &hdev->dev_flags); + else + clear_bit(HCI_ADVERTISING, &hdev->dev_flags); +} + void mgmt_write_scan_failed(struct hci_dev *hdev, u8 scan, u8 status) { u8 mgmt_err = mgmt_status(status); @@ -4494,28 +5005,104 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, mgmt_event(MGMT_EV_NEW_LINK_KEY, hdev, &ev, sizeof(ev), NULL); } -void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, u8 persistent) +void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) { struct mgmt_ev_new_long_term_key ev; memset(&ev, 0, sizeof(ev)); - ev.store_hint = persistent; + /* Devices using resolvable or non-resolvable random addresses + * without providing an indentity resolving key don't require + * to store long term keys. Their addresses will change the + * next time around. + * + * Only when a remote device provides an identity address + * make sure the long term key is stored. If the remote + * identity is known, the long term keys are internally + * mapped to the identity address. So allow static random + * and public addresses here. + */ + if (key->bdaddr_type == ADDR_LE_DEV_RANDOM && + (key->bdaddr.b[5] & 0xc0) != 0xc0) + ev.store_hint = 0x00; + else + ev.store_hint = persistent; + bacpy(&ev.key.addr.bdaddr, &key->bdaddr); ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type); - ev.key.authenticated = key->authenticated; + ev.key.type = key->authenticated; ev.key.enc_size = key->enc_size; ev.key.ediv = key->ediv; + ev.key.rand = key->rand; if (key->type == HCI_SMP_LTK) ev.key.master = 1; - memcpy(ev.key.rand, key->rand, sizeof(key->rand)); memcpy(ev.key.val, key->val, sizeof(key->val)); mgmt_event(MGMT_EV_NEW_LONG_TERM_KEY, hdev, &ev, sizeof(ev), NULL); } +void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk) +{ + struct mgmt_ev_new_irk ev; + + memset(&ev, 0, sizeof(ev)); + + /* For identity resolving keys from devices that are already + * using a public address or static random address, do not + * ask for storing this key. The identity resolving key really + * is only mandatory for devices using resovlable random + * addresses. + * + * Storing all identity resolving keys has the downside that + * they will be also loaded on next boot of they system. More + * identity resolving keys, means more time during scanning is + * needed to actually resolve these addresses. + */ + if (bacmp(&irk->rpa, BDADDR_ANY)) + ev.store_hint = 0x01; + else + ev.store_hint = 0x00; + + bacpy(&ev.rpa, &irk->rpa); + bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr); + ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type); + memcpy(ev.irk.val, irk->val, sizeof(irk->val)); + + mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL); +} + +void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, + bool persistent) +{ + struct mgmt_ev_new_csrk ev; + + memset(&ev, 0, sizeof(ev)); + + /* Devices using resolvable or non-resolvable random addresses + * without providing an indentity resolving key don't require + * to store signature resolving keys. Their addresses will change + * the next time around. + * + * Only when a remote device provides an identity address + * make sure the signature resolving key is stored. So allow + * static random and public addresses here. + */ + if (csrk->bdaddr_type == ADDR_LE_DEV_RANDOM && + (csrk->bdaddr.b[5] & 0xc0) != 0xc0) + ev.store_hint = 0x00; + else + ev.store_hint = persistent; + + bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr); + ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type); + ev.key.master = csrk->master; + memcpy(ev.key.val, csrk->val, sizeof(csrk->val)); + + mgmt_event(MGMT_EV_NEW_CSRK, hdev, &ev, sizeof(ev), NULL); +} + static inline u16 eir_append_data(u8 *eir, u16 eir_len, u8 type, u8 *data, u8 data_len) { @@ -4590,11 +5177,29 @@ static void unpair_device_rsp(struct pending_cmd *cmd, void *data) } void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, - u8 link_type, u8 addr_type, u8 reason) + u8 link_type, u8 addr_type, u8 reason, + bool mgmt_connected) { struct mgmt_ev_device_disconnected ev; + struct pending_cmd *power_off; struct sock *sk = NULL; + power_off = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev); + if (power_off) { + struct mgmt_mode *cp = power_off->param; + + /* The connection is still in hci_conn_hash so test for 1 + * instead of 0 to know if this is the last one. + */ + if (!cp->val && hci_conn_count(hdev) == 1) { + cancel_delayed_work(&hdev->power_off); + queue_work(hdev->req_workqueue, &hdev->power_off.work); + } + } + + if (!mgmt_connected) + return; + if (link_type != ACL_LINK && link_type != LE_LINK) return; @@ -4649,6 +5254,20 @@ void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 status) { struct mgmt_ev_connect_failed ev; + struct pending_cmd *power_off; + + power_off = mgmt_pending_find(MGMT_OP_SET_POWERED, hdev); + if (power_off) { + struct mgmt_mode *cp = power_off->param; + + /* The connection is still in hci_conn_hash so test for 1 + * instead of 0 to know if this is the last one. + */ + if (!cp->val && hci_conn_count(hdev) == 1) { + cancel_delayed_work(&hdev->power_off); + queue_work(hdev->req_workqueue, &hdev->power_off.work); + } + } bacpy(&ev.addr.bdaddr, bdaddr); ev.addr.type = link_to_bdaddr(link_type, addr_type); @@ -4707,7 +5326,7 @@ void mgmt_pin_code_neg_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr, } int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr, - u8 link_type, u8 addr_type, __le32 value, + u8 link_type, u8 addr_type, u32 value, u8 confirm_hint) { struct mgmt_ev_user_confirm_request ev; @@ -4717,7 +5336,7 @@ int mgmt_user_confirm_request(struct hci_dev *hdev, bdaddr_t *bdaddr, bacpy(&ev.addr.bdaddr, bdaddr); ev.addr.type = link_to_bdaddr(link_type, addr_type); ev.confirm_hint = confirm_hint; - ev.value = value; + ev.value = cpu_to_le32(value); return mgmt_event(MGMT_EV_USER_CONFIRM_REQUEST, hdev, &ev, sizeof(ev), NULL); @@ -4910,6 +5529,43 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) hci_req_run(&req, NULL); } +void mgmt_sc_enable_complete(struct hci_dev *hdev, u8 enable, u8 status) +{ + struct cmd_lookup match = { NULL, hdev }; + bool changed = false; + + if (status) { + u8 mgmt_err = mgmt_status(status); + + if (enable) { + if (test_and_clear_bit(HCI_SC_ENABLED, + &hdev->dev_flags)) + new_settings(hdev, NULL); + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + } + + mgmt_pending_foreach(MGMT_OP_SET_SECURE_CONN, hdev, + cmd_status_rsp, &mgmt_err); + return; + } + + if (enable) { + changed = !test_and_set_bit(HCI_SC_ENABLED, &hdev->dev_flags); + } else { + changed = test_and_clear_bit(HCI_SC_ENABLED, &hdev->dev_flags); + clear_bit(HCI_SC_ONLY, &hdev->dev_flags); + } + + mgmt_pending_foreach(MGMT_OP_SET_SECURE_CONN, hdev, + settings_rsp, &match); + + if (changed) + new_settings(hdev, match.sk); + + if (match.sk) + sock_put(match.sk); +} + static void sk_lookup(struct pending_cmd *cmd, void *data) { struct cmd_lookup *match = data; @@ -4964,8 +5620,9 @@ void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status) cmd ? cmd->sk : NULL); } -void mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash, - u8 *randomizer, u8 status) +void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192, + u8 *randomizer192, u8 *hash256, + u8 *randomizer256, u8 status) { struct pending_cmd *cmd; @@ -4979,13 +5636,32 @@ void mgmt_read_local_oob_data_reply_complete(struct hci_dev *hdev, u8 *hash, cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, mgmt_status(status)); } else { - struct mgmt_rp_read_local_oob_data rp; + if (test_bit(HCI_SC_ENABLED, &hdev->dev_flags) && + hash256 && randomizer256) { + struct mgmt_rp_read_local_oob_ext_data rp; + + memcpy(rp.hash192, hash192, sizeof(rp.hash192)); + memcpy(rp.randomizer192, randomizer192, + sizeof(rp.randomizer192)); - memcpy(rp.hash, hash, sizeof(rp.hash)); - memcpy(rp.randomizer, randomizer, sizeof(rp.randomizer)); + memcpy(rp.hash256, hash256, sizeof(rp.hash256)); + memcpy(rp.randomizer256, randomizer256, + sizeof(rp.randomizer256)); + + cmd_complete(cmd->sk, hdev->id, + MGMT_OP_READ_LOCAL_OOB_DATA, 0, + &rp, sizeof(rp)); + } else { + struct mgmt_rp_read_local_oob_data rp; - cmd_complete(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, - 0, &rp, sizeof(rp)); + memcpy(rp.hash, hash192, sizeof(rp.hash)); + memcpy(rp.randomizer, randomizer192, + sizeof(rp.randomizer)); + + cmd_complete(cmd->sk, hdev->id, + MGMT_OP_READ_LOCAL_OOB_DATA, 0, + &rp, sizeof(rp)); + } } mgmt_pending_remove(cmd); @@ -4997,6 +5673,7 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, { char buf[512]; struct mgmt_ev_device_found *ev = (void *) buf; + struct smp_irk *irk; size_t ev_size; if (!hci_discovery_active(hdev)) @@ -5008,13 +5685,20 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, memset(buf, 0, sizeof(buf)); - bacpy(&ev->addr.bdaddr, bdaddr); - ev->addr.type = link_to_bdaddr(link_type, addr_type); + irk = hci_get_irk(hdev, bdaddr, addr_type); + if (irk) { + bacpy(&ev->addr.bdaddr, &irk->bdaddr); + ev->addr.type = link_to_bdaddr(link_type, irk->addr_type); + } else { + bacpy(&ev->addr.bdaddr, bdaddr); + ev->addr.type = link_to_bdaddr(link_type, addr_type); + } + ev->rssi = rssi; if (cfm_name) - ev->flags |= __constant_cpu_to_le32(MGMT_DEV_FOUND_CONFIRM_NAME); + ev->flags |= cpu_to_le32(MGMT_DEV_FOUND_CONFIRM_NAME); if (!ssp) - ev->flags |= __constant_cpu_to_le32(MGMT_DEV_FOUND_LEGACY_PAIRING); + ev->flags |= cpu_to_le32(MGMT_DEV_FOUND_LEGACY_PAIRING); if (eir_len > 0) memcpy(ev->eir, eir, eir_len); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index facd8a79c038..633cceeb943e 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -216,6 +216,7 @@ static int rfcomm_check_security(struct rfcomm_dlc *d) switch (d->sec_level) { case BT_SECURITY_HIGH: + case BT_SECURITY_FIPS: auth_type = HCI_AT_GENERAL_BONDING_MITM; break; case BT_SECURITY_MEDIUM: @@ -359,6 +360,11 @@ static struct rfcomm_dlc *rfcomm_dlc_get(struct rfcomm_session *s, u8 dlci) return NULL; } +static int rfcomm_check_channel(u8 channel) +{ + return channel < 1 || channel > 30; +} + static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 channel) { struct rfcomm_session *s; @@ -368,7 +374,7 @@ static int __rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, BT_DBG("dlc %p state %ld %pMR -> %pMR channel %d", d, d->state, src, dst, channel); - if (channel < 1 || channel > 30) + if (rfcomm_check_channel(channel)) return -EINVAL; if (d->state != BT_OPEN && d->state != BT_CLOSED) @@ -425,6 +431,20 @@ int rfcomm_dlc_open(struct rfcomm_dlc *d, bdaddr_t *src, bdaddr_t *dst, u8 chann return r; } +static void __rfcomm_dlc_disconn(struct rfcomm_dlc *d) +{ + struct rfcomm_session *s = d->session; + + d->state = BT_DISCONN; + if (skb_queue_empty(&d->tx_queue)) { + rfcomm_send_disc(s, d->dlci); + rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT); + } else { + rfcomm_queue_disc(d); + rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT * 2); + } +} + static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err) { struct rfcomm_session *s = d->session; @@ -437,32 +457,29 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err) switch (d->state) { case BT_CONNECT: case BT_CONFIG: + case BT_OPEN: + case BT_CONNECT2: if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { set_bit(RFCOMM_AUTH_REJECT, &d->flags); rfcomm_schedule(); - break; + return 0; } - /* Fall through */ + } + switch (d->state) { + case BT_CONNECT: case BT_CONNECTED: - d->state = BT_DISCONN; - if (skb_queue_empty(&d->tx_queue)) { - rfcomm_send_disc(s, d->dlci); - rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT); - } else { - rfcomm_queue_disc(d); - rfcomm_dlc_set_timer(d, RFCOMM_DISC_TIMEOUT * 2); - } + __rfcomm_dlc_disconn(d); break; - case BT_OPEN: - case BT_CONNECT2: - if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { - set_bit(RFCOMM_AUTH_REJECT, &d->flags); - rfcomm_schedule(); + case BT_CONFIG: + if (s->state != BT_BOUND) { + __rfcomm_dlc_disconn(d); break; } - /* Fall through */ + /* if closing a dlc in a session that hasn't been started, + * just close and unlink the dlc + */ default: rfcomm_dlc_clear_timer(d); @@ -513,6 +530,25 @@ no_session: return r; } +struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel) +{ + struct rfcomm_session *s; + struct rfcomm_dlc *dlc = NULL; + u8 dlci; + + if (rfcomm_check_channel(channel)) + return ERR_PTR(-EINVAL); + + rfcomm_lock(); + s = rfcomm_session_get(src, dst); + if (s) { + dlci = __dlci(!s->initiator, channel); + dlc = rfcomm_dlc_get(s, dlci); + } + rfcomm_unlock(); + return dlc; +} + int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb) { int len = skb->len; @@ -533,6 +569,20 @@ int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb) return len; } +void rfcomm_dlc_send_noerror(struct rfcomm_dlc *d, struct sk_buff *skb) +{ + int len = skb->len; + + BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len); + + rfcomm_make_uih(skb, d->addr); + skb_queue_tail(&d->tx_queue, skb); + + if (d->state == BT_CONNECTED && + !test_bit(RFCOMM_TX_THROTTLED, &d->flags)) + rfcomm_schedule(); +} + void __rfcomm_dlc_throttle(struct rfcomm_dlc *d) { BT_DBG("dlc %p state %ld", d, d->state); @@ -718,7 +768,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, bacpy(&addr.l2_bdaddr, dst); addr.l2_family = AF_BLUETOOTH; - addr.l2_psm = __constant_cpu_to_le16(RFCOMM_PSM); + addr.l2_psm = cpu_to_le16(RFCOMM_PSM); addr.l2_cid = 0; addr.l2_bdaddr_type = BDADDR_BREDR; *err = kernel_connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK); @@ -1943,12 +1993,11 @@ static void rfcomm_process_sessions(void) continue; } - if (s->state == BT_LISTEN) { + switch (s->state) { + case BT_LISTEN: rfcomm_accept_connection(s); continue; - } - switch (s->state) { case BT_BOUND: s = rfcomm_check_connection(s); break; @@ -1983,7 +2032,7 @@ static int rfcomm_add_listener(bdaddr_t *ba) /* Bind socket */ bacpy(&addr.l2_bdaddr, ba); addr.l2_family = AF_BLUETOOTH; - addr.l2_psm = __constant_cpu_to_le16(RFCOMM_PSM); + addr.l2_psm = cpu_to_le16(RFCOMM_PSM); addr.l2_cid = 0; addr.l2_bdaddr_type = BDADDR_BREDR; err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr)); @@ -2085,7 +2134,8 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) set_bit(RFCOMM_SEC_PENDING, &d->flags); rfcomm_dlc_set_timer(d, RFCOMM_AUTH_TIMEOUT); continue; - } else if (d->sec_level == BT_SECURITY_HIGH) { + } else if (d->sec_level == BT_SECURITY_HIGH || + d->sec_level == BT_SECURITY_FIPS) { set_bit(RFCOMM_ENC_DROP, &d->flags); continue; } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 3c2d3e4aa2f5..eabd25ab5ad9 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -105,13 +105,18 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) } /* ---- Socket functions ---- */ -static struct sock *__rfcomm_get_sock_by_addr(u8 channel, bdaddr_t *src) +static struct sock *__rfcomm_get_listen_sock_by_addr(u8 channel, bdaddr_t *src) { struct sock *sk = NULL; sk_for_each(sk, &rfcomm_sk_list.head) { - if (rfcomm_pi(sk)->channel == channel && - !bacmp(&rfcomm_pi(sk)->src, src)) + if (rfcomm_pi(sk)->channel != channel) + continue; + + if (bacmp(&rfcomm_pi(sk)->src, src)) + continue; + + if (sk->sk_state == BT_BOUND || sk->sk_state == BT_LISTEN) break; } @@ -331,6 +336,7 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr { struct sockaddr_rc *sa = (struct sockaddr_rc *) addr; struct sock *sk = sock->sk; + int chan = sa->rc_channel; int err = 0; BT_DBG("sk %p %pMR", sk, &sa->rc_bdaddr); @@ -352,12 +358,12 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr write_lock(&rfcomm_sk_list.lock); - if (sa->rc_channel && __rfcomm_get_sock_by_addr(sa->rc_channel, &sa->rc_bdaddr)) { + if (chan && __rfcomm_get_listen_sock_by_addr(chan, &sa->rc_bdaddr)) { err = -EADDRINUSE; } else { /* Save source address */ bacpy(&rfcomm_pi(sk)->src, &sa->rc_bdaddr); - rfcomm_pi(sk)->channel = sa->rc_channel; + rfcomm_pi(sk)->channel = chan; sk->sk_state = BT_BOUND; } @@ -439,7 +445,7 @@ static int rfcomm_sock_listen(struct socket *sock, int backlog) write_lock(&rfcomm_sk_list.lock); for (channel = 1; channel < 31; channel++) - if (!__rfcomm_get_sock_by_addr(channel, src)) { + if (!__rfcomm_get_listen_sock_by_addr(channel, src)) { rfcomm_pi(sk)->channel = channel; err = 0; break; @@ -528,6 +534,10 @@ static int rfcomm_sock_getname(struct socket *sock, struct sockaddr *addr, int * BT_DBG("sock %p, sk %p", sock, sk); + if (peer && sk->sk_state != BT_CONNECTED && + sk->sk_state != BT_CONNECT && sk->sk_state != BT_CONNECT2) + return -ENOTCONN; + memset(sa, 0, sizeof(*sa)); sa->rc_family = AF_BLUETOOTH; sa->rc_channel = rfcomm_pi(sk)->channel; @@ -648,6 +658,11 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, char __u break; } + if (opt & RFCOMM_LM_FIPS) { + err = -EINVAL; + break; + } + if (opt & RFCOMM_LM_AUTH) rfcomm_pi(sk)->sec_level = BT_SECURITY_LOW; if (opt & RFCOMM_LM_ENCRYPT) @@ -762,7 +777,11 @@ static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __u break; case BT_SECURITY_HIGH: opt = RFCOMM_LM_AUTH | RFCOMM_LM_ENCRYPT | - RFCOMM_LM_SECURE; + RFCOMM_LM_SECURE; + break; + case BT_SECURITY_FIPS: + opt = RFCOMM_LM_AUTH | RFCOMM_LM_ENCRYPT | + RFCOMM_LM_SECURE | RFCOMM_LM_FIPS; break; default: opt = 0; @@ -774,6 +793,7 @@ static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __u if (put_user(opt, (u32 __user *) optval)) err = -EFAULT; + break; case RFCOMM_CONNINFO: diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index f9c0980abeea..403ec09f480a 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -40,6 +40,7 @@ #define RFCOMM_TTY_MAJOR 216 /* device node major id of the usb/bluetooth.c driver */ #define RFCOMM_TTY_MINOR 0 +static DEFINE_MUTEX(rfcomm_ioctl_mutex); static struct tty_driver *rfcomm_tty_driver; struct rfcomm_dev { @@ -51,6 +52,8 @@ struct rfcomm_dev { unsigned long flags; int err; + unsigned long status; /* don't export to userspace */ + bdaddr_t src; bdaddr_t dst; u8 channel; @@ -58,7 +61,6 @@ struct rfcomm_dev { uint modem_status; struct rfcomm_dlc *dlc; - wait_queue_head_t conn_wait; struct device *tty_dev; @@ -83,10 +85,6 @@ static void rfcomm_dev_destruct(struct tty_port *port) BT_DBG("dev %p dlc %p", dev, dlc); - spin_lock(&rfcomm_dev_lock); - list_del(&dev->list); - spin_unlock(&rfcomm_dev_lock); - rfcomm_dlc_lock(dlc); /* Detach DLC if it's owned by this dev */ if (dlc->owner == dev) @@ -95,7 +93,12 @@ static void rfcomm_dev_destruct(struct tty_port *port) rfcomm_dlc_put(dlc); - tty_unregister_device(rfcomm_tty_driver, dev->id); + if (dev->tty_dev) + tty_unregister_device(rfcomm_tty_driver, dev->id); + + spin_lock(&rfcomm_dev_lock); + list_del(&dev->list); + spin_unlock(&rfcomm_dev_lock); kfree(dev); @@ -104,60 +107,24 @@ static void rfcomm_dev_destruct(struct tty_port *port) module_put(THIS_MODULE); } -static struct device *rfcomm_get_device(struct rfcomm_dev *dev) -{ - struct hci_dev *hdev; - struct hci_conn *conn; - - hdev = hci_get_route(&dev->dst, &dev->src); - if (!hdev) - return NULL; - - conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &dev->dst); - - hci_dev_put(hdev); - - return conn ? &conn->dev : NULL; -} - /* device-specific initialization: open the dlc */ static int rfcomm_dev_activate(struct tty_port *port, struct tty_struct *tty) { struct rfcomm_dev *dev = container_of(port, struct rfcomm_dev, port); - DEFINE_WAIT(wait); int err; err = rfcomm_dlc_open(dev->dlc, &dev->src, &dev->dst, dev->channel); if (err) - return err; - - while (1) { - prepare_to_wait(&dev->conn_wait, &wait, TASK_INTERRUPTIBLE); - - if (dev->dlc->state == BT_CLOSED) { - err = -dev->err; - break; - } - - if (dev->dlc->state == BT_CONNECTED) - break; - - if (signal_pending(current)) { - err = -ERESTARTSYS; - break; - } - - tty_unlock(tty); - schedule(); - tty_lock(tty); - } - finish_wait(&dev->conn_wait, &wait); + set_bit(TTY_IO_ERROR, &tty->flags); + return err; +} - if (!err) - device_move(dev->tty_dev, rfcomm_get_device(dev), - DPM_ORDER_DEV_AFTER_PARENT); +/* we block the open until the dlc->state becomes BT_CONNECTED */ +static int rfcomm_dev_carrier_raised(struct tty_port *port) +{ + struct rfcomm_dev *dev = container_of(port, struct rfcomm_dev, port); - return err; + return (dev->dlc->state == BT_CONNECTED); } /* device-specific cleanup: close the dlc */ @@ -176,9 +143,10 @@ static const struct tty_port_operations rfcomm_port_ops = { .destruct = rfcomm_dev_destruct, .activate = rfcomm_dev_activate, .shutdown = rfcomm_dev_shutdown, + .carrier_raised = rfcomm_dev_carrier_raised, }; -static struct rfcomm_dev *__rfcomm_dev_get(int id) +static struct rfcomm_dev *__rfcomm_dev_lookup(int id) { struct rfcomm_dev *dev; @@ -195,20 +163,41 @@ static struct rfcomm_dev *rfcomm_dev_get(int id) spin_lock(&rfcomm_dev_lock); - dev = __rfcomm_dev_get(id); + dev = __rfcomm_dev_lookup(id); - if (dev) { - if (test_bit(RFCOMM_TTY_RELEASED, &dev->flags)) - dev = NULL; - else - tty_port_get(&dev->port); - } + if (dev && !tty_port_get(&dev->port)) + dev = NULL; spin_unlock(&rfcomm_dev_lock); return dev; } +static void rfcomm_reparent_device(struct rfcomm_dev *dev) +{ + struct hci_dev *hdev; + struct hci_conn *conn; + + hdev = hci_get_route(&dev->dst, &dev->src); + if (!hdev) + return; + + /* The lookup results are unsafe to access without the + * hci device lock (FIXME: why is this not documented?) + */ + hci_dev_lock(hdev); + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &dev->dst); + + /* Just because the acl link is in the hash table is no + * guarantee the sysfs device has been added ... + */ + if (conn && device_is_registered(&conn->dev)) + device_move(dev->tty_dev, &conn->dev, DPM_ORDER_DEV_AFTER_PARENT); + + hci_dev_unlock(hdev); + hci_dev_put(hdev); +} + static ssize_t show_address(struct device *tty_dev, struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); @@ -224,17 +213,16 @@ static ssize_t show_channel(struct device *tty_dev, struct device_attribute *att static DEVICE_ATTR(address, S_IRUGO, show_address, NULL); static DEVICE_ATTR(channel, S_IRUGO, show_channel, NULL); -static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) +static struct rfcomm_dev *__rfcomm_dev_add(struct rfcomm_dev_req *req, + struct rfcomm_dlc *dlc) { struct rfcomm_dev *dev, *entry; struct list_head *head = &rfcomm_dev_list; int err = 0; - BT_DBG("id %d channel %d", req->dev_id, req->channel); - dev = kzalloc(sizeof(struct rfcomm_dev), GFP_KERNEL); if (!dev) - return -ENOMEM; + return ERR_PTR(-ENOMEM); spin_lock(&rfcomm_dev_lock); @@ -282,7 +270,6 @@ static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) tty_port_init(&dev->port); dev->port.ops = &rfcomm_port_ops; - init_waitqueue_head(&dev->conn_wait); skb_queue_head_init(&dev->pending); @@ -318,22 +305,37 @@ static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) holds reference to this module. */ __module_get(THIS_MODULE); + spin_unlock(&rfcomm_dev_lock); + return dev; + out: spin_unlock(&rfcomm_dev_lock); + kfree(dev); + return ERR_PTR(err); +} + +static int rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) +{ + struct rfcomm_dev *dev; + struct device *tty; + + BT_DBG("id %d channel %d", req->dev_id, req->channel); - if (err < 0) - goto free; + dev = __rfcomm_dev_add(req, dlc); + if (IS_ERR(dev)) { + rfcomm_dlc_put(dlc); + return PTR_ERR(dev); + } - dev->tty_dev = tty_port_register_device(&dev->port, rfcomm_tty_driver, + tty = tty_port_register_device(&dev->port, rfcomm_tty_driver, dev->id, NULL); - if (IS_ERR(dev->tty_dev)) { - err = PTR_ERR(dev->tty_dev); - spin_lock(&rfcomm_dev_lock); - list_del(&dev->list); - spin_unlock(&rfcomm_dev_lock); - goto free; + if (IS_ERR(tty)) { + tty_port_put(&dev->port); + return PTR_ERR(tty); } + dev->tty_dev = tty; + rfcomm_reparent_device(dev); dev_set_drvdata(dev->tty_dev, dev); if (device_create_file(dev->tty_dev, &dev_attr_address) < 0) @@ -343,24 +345,23 @@ out: BT_ERR("Failed to create channel attribute"); return dev->id; - -free: - kfree(dev); - return err; } /* ---- Send buffer ---- */ -static inline unsigned int rfcomm_room(struct rfcomm_dlc *dlc) +static inline unsigned int rfcomm_room(struct rfcomm_dev *dev) { - /* We can't let it be zero, because we don't get a callback - when tx_credits becomes nonzero, hence we'd never wake up */ - return dlc->mtu * (dlc->tx_credits?:1); + struct rfcomm_dlc *dlc = dev->dlc; + + /* Limit the outstanding number of packets not yet sent to 40 */ + int pending = 40 - atomic_read(&dev->wmem_alloc); + + return max(0, pending) * dlc->mtu; } static void rfcomm_wfree(struct sk_buff *skb) { struct rfcomm_dev *dev = (void *) skb->sk; - atomic_sub(skb->truesize, &dev->wmem_alloc); + atomic_dec(&dev->wmem_alloc); if (test_bit(RFCOMM_TTY_ATTACHED, &dev->flags)) tty_port_tty_wakeup(&dev->port); tty_port_put(&dev->port); @@ -369,28 +370,24 @@ static void rfcomm_wfree(struct sk_buff *skb) static void rfcomm_set_owner_w(struct sk_buff *skb, struct rfcomm_dev *dev) { tty_port_get(&dev->port); - atomic_add(skb->truesize, &dev->wmem_alloc); + atomic_inc(&dev->wmem_alloc); skb->sk = (void *) dev; skb->destructor = rfcomm_wfree; } static struct sk_buff *rfcomm_wmalloc(struct rfcomm_dev *dev, unsigned long size, gfp_t priority) { - if (atomic_read(&dev->wmem_alloc) < rfcomm_room(dev->dlc)) { - struct sk_buff *skb = alloc_skb(size, priority); - if (skb) { - rfcomm_set_owner_w(skb, dev); - return skb; - } - } - return NULL; + struct sk_buff *skb = alloc_skb(size, priority); + if (skb) + rfcomm_set_owner_w(skb, dev); + return skb; } /* ---- Device IOCTLs ---- */ #define NOCAP_FLAGS ((1 << RFCOMM_REUSE_DLC) | (1 << RFCOMM_RELEASE_ONHUP)) -static int rfcomm_create_dev(struct sock *sk, void __user *arg) +static int __rfcomm_create_dev(struct sock *sk, void __user *arg) { struct rfcomm_dev_req req; struct rfcomm_dlc *dlc; @@ -412,16 +409,22 @@ static int rfcomm_create_dev(struct sock *sk, void __user *arg) dlc = rfcomm_pi(sk)->dlc; rfcomm_dlc_hold(dlc); } else { + /* Validate the channel is unused */ + dlc = rfcomm_dlc_exists(&req.src, &req.dst, req.channel); + if (IS_ERR(dlc)) + return PTR_ERR(dlc); + else if (dlc) { + rfcomm_dlc_put(dlc); + return -EBUSY; + } dlc = rfcomm_dlc_alloc(GFP_KERNEL); if (!dlc) return -ENOMEM; } id = rfcomm_dev_add(&req, dlc); - if (id < 0) { - rfcomm_dlc_put(dlc); + if (id < 0) return id; - } if (req.flags & (1 << RFCOMM_REUSE_DLC)) { /* DLC is now used by device. @@ -432,7 +435,7 @@ static int rfcomm_create_dev(struct sock *sk, void __user *arg) return id; } -static int rfcomm_release_dev(void __user *arg) +static int __rfcomm_release_dev(void __user *arg) { struct rfcomm_dev_req req; struct rfcomm_dev *dev; @@ -452,6 +455,12 @@ static int rfcomm_release_dev(void __user *arg) return -EPERM; } + /* only release once */ + if (test_and_set_bit(RFCOMM_DEV_RELEASED, &dev->status)) { + tty_port_put(&dev->port); + return -EALREADY; + } + if (req.flags & (1 << RFCOMM_HANGUP_NOW)) rfcomm_dlc_close(dev->dlc, 0); @@ -462,14 +471,35 @@ static int rfcomm_release_dev(void __user *arg) tty_kref_put(tty); } - if (!test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags) && - !test_and_set_bit(RFCOMM_TTY_RELEASED, &dev->flags)) + if (!test_bit(RFCOMM_TTY_OWNED, &dev->status)) tty_port_put(&dev->port); tty_port_put(&dev->port); return 0; } +static int rfcomm_create_dev(struct sock *sk, void __user *arg) +{ + int ret; + + mutex_lock(&rfcomm_ioctl_mutex); + ret = __rfcomm_create_dev(sk, arg); + mutex_unlock(&rfcomm_ioctl_mutex); + + return ret; +} + +static int rfcomm_release_dev(void __user *arg) +{ + int ret; + + mutex_lock(&rfcomm_ioctl_mutex); + ret = __rfcomm_release_dev(arg); + mutex_unlock(&rfcomm_ioctl_mutex); + + return ret; +} + static int rfcomm_get_dev_list(void __user *arg) { struct rfcomm_dev *dev; @@ -497,7 +527,7 @@ static int rfcomm_get_dev_list(void __user *arg) spin_lock(&rfcomm_dev_lock); list_for_each_entry(dev, &rfcomm_dev_list, list) { - if (test_bit(RFCOMM_TTY_RELEASED, &dev->flags)) + if (!tty_port_get(&dev->port)) continue; (di + n)->id = dev->id; (di + n)->flags = dev->flags; @@ -505,6 +535,7 @@ static int rfcomm_get_dev_list(void __user *arg) (di + n)->channel = dev->channel; bacpy(&(di + n)->src, &dev->src); bacpy(&(di + n)->dst, &dev->dst); + tty_port_put(&dev->port); if (++n >= dev_num) break; } @@ -601,9 +632,11 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) BT_DBG("dlc %p dev %p err %d", dlc, dev, err); dev->err = err; - wake_up_interruptible(&dev->conn_wait); + if (dlc->state == BT_CONNECTED) { + rfcomm_reparent_device(dev); - if (dlc->state == BT_CLOSED) + wake_up_interruptible(&dev->port.open_wait); + } else if (dlc->state == BT_CLOSED) tty_port_tty_hangup(&dev->port, false); } @@ -703,8 +736,10 @@ static int rfcomm_tty_install(struct tty_driver *driver, struct tty_struct *tty) * when the last process closes the tty. The behaviour is expected by * userspace. */ - if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) + if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) { + set_bit(RFCOMM_TTY_OWNED, &dev->status); tty_port_put(&dev->port); + } return 0; } @@ -750,7 +785,7 @@ static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, in struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data; struct rfcomm_dlc *dlc = dev->dlc; struct sk_buff *skb; - int err = 0, sent = 0, size; + int sent = 0, size; BT_DBG("tty %p count %d", tty, count); @@ -758,7 +793,6 @@ static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, in size = min_t(uint, count, dlc->mtu); skb = rfcomm_wmalloc(dev, size + RFCOMM_SKB_RESERVE, GFP_ATOMIC); - if (!skb) break; @@ -766,32 +800,24 @@ static int rfcomm_tty_write(struct tty_struct *tty, const unsigned char *buf, in memcpy(skb_put(skb, size), buf + sent, size); - err = rfcomm_dlc_send(dlc, skb); - if (err < 0) { - kfree_skb(skb); - break; - } + rfcomm_dlc_send_noerror(dlc, skb); sent += size; count -= size; } - return sent ? sent : err; + return sent; } static int rfcomm_tty_write_room(struct tty_struct *tty) { struct rfcomm_dev *dev = (struct rfcomm_dev *) tty->driver_data; - int room; + int room = 0; - BT_DBG("tty %p", tty); - - if (!dev || !dev->dlc) - return 0; + if (dev && dev->dlc) + room = rfcomm_room(dev); - room = rfcomm_room(dev->dlc) - atomic_read(&dev->wmem_alloc); - if (room < 0) - room = 0; + BT_DBG("tty %p room %d", tty, room); return room; } @@ -1125,7 +1151,7 @@ int __init rfcomm_init_ttys(void) rfcomm_tty_driver->subtype = SERIAL_TYPE_NORMAL; rfcomm_tty_driver->flags = TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV; rfcomm_tty_driver->init_termios = tty_std_termios; - rfcomm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL; + rfcomm_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL; rfcomm_tty_driver->init_termios.c_lflag &= ~ICANON; tty_set_operations(rfcomm_tty_driver, &rfcomm_ops); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 24fa3964b3c8..ab1e6fcca4c5 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -676,20 +676,20 @@ static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting) bacpy(&cp.bdaddr, &conn->dst); cp.pkt_type = cpu_to_le16(conn->pkt_type); - cp.tx_bandwidth = __constant_cpu_to_le32(0x00001f40); - cp.rx_bandwidth = __constant_cpu_to_le32(0x00001f40); + cp.tx_bandwidth = cpu_to_le32(0x00001f40); + cp.rx_bandwidth = cpu_to_le32(0x00001f40); cp.content_format = cpu_to_le16(setting); switch (setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (conn->pkt_type & ESCO_2EV3) - cp.max_latency = __constant_cpu_to_le16(0x0008); + cp.max_latency = cpu_to_le16(0x0008); else - cp.max_latency = __constant_cpu_to_le16(0x000D); + cp.max_latency = cpu_to_le16(0x000D); cp.retrans_effort = 0x02; break; case SCO_AIRMODE_CVSD: - cp.max_latency = __constant_cpu_to_le16(0xffff); + cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; } diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 45007362683b..dfb4e1161c10 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -35,14 +35,14 @@ #define AUTH_REQ_MASK 0x07 -static inline void swap128(u8 src[16], u8 dst[16]) +static inline void swap128(const u8 src[16], u8 dst[16]) { int i; for (i = 0; i < 16; i++) dst[15 - i] = src[i]; } -static inline void swap56(u8 src[7], u8 dst[7]) +static inline void swap56(const u8 src[7], u8 dst[7]) { int i; for (i = 0; i < 7; i++) @@ -53,6 +53,7 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) { struct blkcipher_desc desc; struct scatterlist sg; + uint8_t tmp[16], data[16]; int err; if (tfm == NULL) { @@ -63,21 +64,89 @@ static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) desc.tfm = tfm; desc.flags = 0; - err = crypto_blkcipher_setkey(tfm, k, 16); + /* The most significant octet of key corresponds to k[0] */ + swap128(k, tmp); + + err = crypto_blkcipher_setkey(tfm, tmp, 16); if (err) { BT_ERR("cipher setkey failed: %d", err); return err; } - sg_init_one(&sg, r, 16); + /* Most significant octet of plaintextData corresponds to data[0] */ + swap128(r, data); + + sg_init_one(&sg, data, 16); err = crypto_blkcipher_encrypt(&desc, &sg, &sg, 16); if (err) BT_ERR("Encrypt data error %d", err); + /* Most significant octet of encryptedData corresponds to data[0] */ + swap128(data, r); + return err; } +static int smp_ah(struct crypto_blkcipher *tfm, u8 irk[16], u8 r[3], u8 res[3]) +{ + u8 _res[16]; + int err; + + /* r' = padding || r */ + memcpy(_res, r, 3); + memset(_res + 3, 0, 13); + + err = smp_e(tfm, irk, _res); + if (err) { + BT_ERR("Encrypt error"); + return err; + } + + /* The output of the random address function ah is: + * ah(h, r) = e(k, r') mod 2^24 + * The output of the security function e is then truncated to 24 bits + * by taking the least significant 24 bits of the output of e as the + * result of ah. + */ + memcpy(res, _res, 3); + + return 0; +} + +bool smp_irk_matches(struct crypto_blkcipher *tfm, u8 irk[16], + bdaddr_t *bdaddr) +{ + u8 hash[3]; + int err; + + BT_DBG("RPA %pMR IRK %*phN", bdaddr, 16, irk); + + err = smp_ah(tfm, irk, &bdaddr->b[3], hash); + if (err) + return false; + + return !memcmp(bdaddr->b, hash, 3); +} + +int smp_generate_rpa(struct crypto_blkcipher *tfm, u8 irk[16], bdaddr_t *rpa) +{ + int err; + + get_random_bytes(&rpa->b[3], 3); + + rpa->b[5] &= 0x3f; /* Clear two most significant bits */ + rpa->b[5] |= 0x40; /* Set second most significant bit */ + + err = smp_ah(tfm, irk, &rpa->b[3], rpa->b); + if (err < 0) + return err; + + BT_DBG("RPA %pMR", rpa); + + return 0; +} + static int smp_c1(struct crypto_blkcipher *tfm, u8 k[16], u8 r[16], u8 preq[7], u8 pres[7], u8 _iat, bdaddr_t *ia, u8 _rat, bdaddr_t *ra, u8 res[16]) @@ -88,16 +157,15 @@ static int smp_c1(struct crypto_blkcipher *tfm, u8 k[16], u8 r[16], memset(p1, 0, 16); /* p1 = pres || preq || _rat || _iat */ - swap56(pres, p1); - swap56(preq, p1 + 7); - p1[14] = _rat; - p1[15] = _iat; - - memset(p2, 0, 16); + p1[0] = _iat; + p1[1] = _rat; + memcpy(p1 + 2, preq, 7); + memcpy(p1 + 9, pres, 7); /* p2 = padding || ia || ra */ - baswap((bdaddr_t *) (p2 + 4), ia); - baswap((bdaddr_t *) (p2 + 10), ra); + memcpy(p2, ra, 6); + memcpy(p2 + 6, ia, 6); + memset(p2 + 12, 0, 4); /* res = r XOR p1 */ u128_xor((u128 *) res, (u128 *) r, (u128 *) p1); @@ -126,8 +194,8 @@ static int smp_s1(struct crypto_blkcipher *tfm, u8 k[16], u8 r1[16], int err; /* Just least significant octets from r1 and r2 are considered */ - memcpy(_r, r1 + 8, 8); - memcpy(_r + 8, r2 + 8, 8); + memcpy(_r, r2, 8); + memcpy(_r + 8, r1, 8); err = smp_e(tfm, k, _r); if (err) @@ -154,7 +222,7 @@ static struct sk_buff *smp_build_cmd(struct l2cap_conn *conn, u8 code, lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); lh->len = cpu_to_le16(sizeof(code) + dlen); - lh->cid = __constant_cpu_to_le16(L2CAP_CID_SMP); + lh->cid = cpu_to_le16(L2CAP_CID_SMP); memcpy(skb_put(skb, sizeof(code)), &code, sizeof(code)); @@ -203,31 +271,45 @@ static void build_pairing_cmd(struct l2cap_conn *conn, struct smp_cmd_pairing *req, struct smp_cmd_pairing *rsp, __u8 authreq) { - u8 dist_keys = 0; + struct smp_chan *smp = conn->smp_chan; + struct hci_conn *hcon = conn->hcon; + struct hci_dev *hdev = hcon->hdev; + u8 local_dist = 0, remote_dist = 0; if (test_bit(HCI_PAIRABLE, &conn->hcon->hdev->dev_flags)) { - dist_keys = SMP_DIST_ENC_KEY; + local_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN; + remote_dist = SMP_DIST_ENC_KEY | SMP_DIST_SIGN; authreq |= SMP_AUTH_BONDING; } else { authreq &= ~SMP_AUTH_BONDING; } + if (test_bit(HCI_RPA_RESOLVING, &hdev->dev_flags)) + remote_dist |= SMP_DIST_ID_KEY; + + if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) + local_dist |= SMP_DIST_ID_KEY; + if (rsp == NULL) { req->io_capability = conn->hcon->io_capability; req->oob_flag = SMP_OOB_NOT_PRESENT; req->max_key_size = SMP_MAX_ENC_KEY_SIZE; - req->init_key_dist = 0; - req->resp_key_dist = dist_keys; + req->init_key_dist = local_dist; + req->resp_key_dist = remote_dist; req->auth_req = (authreq & AUTH_REQ_MASK); + + smp->remote_key_dist = remote_dist; return; } rsp->io_capability = conn->hcon->io_capability; rsp->oob_flag = SMP_OOB_NOT_PRESENT; rsp->max_key_size = SMP_MAX_ENC_KEY_SIZE; - rsp->init_key_dist = 0; - rsp->resp_key_dist = req->resp_key_dist & dist_keys; + rsp->init_key_dist = req->init_key_dist & remote_dist; + rsp->resp_key_dist = req->resp_key_dist & local_dist; rsp->auth_req = (authreq & AUTH_REQ_MASK); + + smp->remote_key_dist = rsp->init_key_dist; } static u8 check_enc_key_size(struct l2cap_conn *conn, __u8 max_key_size) @@ -305,6 +387,11 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, if (!(auth & SMP_AUTH_BONDING) && method == JUST_CFM) method = JUST_WORKS; + /* Don't confirm locally initiated pairing attempts */ + if (method == JUST_CFM && test_bit(SMP_FLAG_INITIATOR, + &smp->smp_flags)) + method = JUST_WORKS; + /* If Just Works, Continue with Zero TK */ if (method == JUST_WORKS) { set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags); @@ -325,16 +412,14 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, method = REQ_PASSKEY; } - /* Generate random passkey. Not valid until confirmed. */ + /* Generate random passkey. */ if (method == CFM_PASSKEY) { - u8 key[16]; - - memset(key, 0, sizeof(key)); + memset(smp->tk, 0, sizeof(smp->tk)); get_random_bytes(&passkey, sizeof(passkey)); passkey %= 1000000; - put_unaligned_le32(passkey, key); - swap128(key, smp->tk); + put_unaligned_le32(passkey, smp->tk); BT_DBG("PassKey: %d", passkey); + set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags); } hci_dev_lock(hcon->hdev); @@ -342,10 +427,14 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, if (method == REQ_PASSKEY) ret = mgmt_user_passkey_request(hcon->hdev, &hcon->dst, hcon->type, hcon->dst_type); - else + else if (method == JUST_CFM) ret = mgmt_user_confirm_request(hcon->hdev, &hcon->dst, hcon->type, hcon->dst_type, - cpu_to_le32(passkey), 0); + passkey, 1); + else + ret = mgmt_user_passkey_notify(hcon->hdev, &hcon->dst, + hcon->type, hcon->dst_type, + passkey, 0); hci_dev_unlock(hcon->hdev); @@ -356,29 +445,24 @@ static void confirm_work(struct work_struct *work) { struct smp_chan *smp = container_of(work, struct smp_chan, confirm); struct l2cap_conn *conn = smp->conn; - struct crypto_blkcipher *tfm; + struct hci_dev *hdev = conn->hcon->hdev; + struct crypto_blkcipher *tfm = hdev->tfm_aes; struct smp_cmd_pairing_confirm cp; int ret; - u8 res[16], reason; + u8 reason; BT_DBG("conn %p", conn); - tfm = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) { - reason = SMP_UNSPECIFIED; - goto error; - } + /* Prevent mutual access to hdev->tfm_aes */ + hci_dev_lock(hdev); - smp->tfm = tfm; + ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp, + conn->hcon->init_addr_type, &conn->hcon->init_addr, + conn->hcon->resp_addr_type, &conn->hcon->resp_addr, + cp.confirm_val); + + hci_dev_unlock(hdev); - if (conn->hcon->out) - ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp, - conn->hcon->src_type, &conn->hcon->src, - conn->hcon->dst_type, &conn->hcon->dst, res); - else - ret = smp_c1(tfm, smp->tk, smp->prnd, smp->preq, smp->prsp, - conn->hcon->dst_type, &conn->hcon->dst, - conn->hcon->src_type, &conn->hcon->src, res); if (ret) { reason = SMP_UNSPECIFIED; goto error; @@ -386,7 +470,6 @@ static void confirm_work(struct work_struct *work) clear_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags); - swap128(res, cp.confirm_val); smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); return; @@ -400,8 +483,9 @@ static void random_work(struct work_struct *work) struct smp_chan *smp = container_of(work, struct smp_chan, random); struct l2cap_conn *conn = smp->conn; struct hci_conn *hcon = conn->hcon; - struct crypto_blkcipher *tfm = smp->tfm; - u8 reason, confirm[16], res[16], key[16]; + struct hci_dev *hdev = hcon->hdev; + struct crypto_blkcipher *tfm = hdev->tfm_aes; + u8 reason, confirm[16]; int ret; if (IS_ERR_OR_NULL(tfm)) { @@ -411,21 +495,20 @@ static void random_work(struct work_struct *work) BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); - if (hcon->out) - ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp, - hcon->src_type, &hcon->src, - hcon->dst_type, &hcon->dst, res); - else - ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp, - hcon->dst_type, &hcon->dst, - hcon->src_type, &hcon->src, res); + /* Prevent mutual access to hdev->tfm_aes */ + hci_dev_lock(hdev); + + ret = smp_c1(tfm, smp->tk, smp->rrnd, smp->preq, smp->prsp, + hcon->init_addr_type, &hcon->init_addr, + hcon->resp_addr_type, &hcon->resp_addr, confirm); + + hci_dev_unlock(hdev); + if (ret) { reason = SMP_UNSPECIFIED; goto error; } - swap128(res, confirm); - if (memcmp(smp->pcnf, confirm, sizeof(smp->pcnf)) != 0) { BT_ERR("Pairing failed (confirmation values mismatch)"); reason = SMP_CONFIRM_FAILED; @@ -433,14 +516,11 @@ static void random_work(struct work_struct *work) } if (hcon->out) { - u8 stk[16], rand[8]; - __le16 ediv; - - memset(rand, 0, sizeof(rand)); - ediv = 0; + u8 stk[16]; + __le64 rand = 0; + __le16 ediv = 0; - smp_s1(tfm, smp->tk, smp->rrnd, smp->prnd, key); - swap128(key, stk); + smp_s1(tfm, smp->tk, smp->rrnd, smp->prnd, stk); memset(stk + smp->enc_key_size, 0, SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size); @@ -453,23 +533,20 @@ static void random_work(struct work_struct *work) hci_le_start_enc(hcon, ediv, rand, stk); hcon->enc_key_size = smp->enc_key_size; } else { - u8 stk[16], r[16], rand[8]; - __le16 ediv; - - memset(rand, 0, sizeof(rand)); - ediv = 0; + u8 stk[16]; + __le64 rand = 0; + __le16 ediv = 0; - swap128(smp->prnd, r); - smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(r), r); + smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), + smp->prnd); - smp_s1(tfm, smp->tk, smp->prnd, smp->rrnd, key); - swap128(key, stk); + smp_s1(tfm, smp->tk, smp->prnd, smp->rrnd, stk); memset(stk + smp->enc_key_size, 0, SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size); hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, - HCI_SMP_STK_SLAVE, 0, 0, stk, smp->enc_key_size, + HCI_SMP_STK_SLAVE, 0, stk, smp->enc_key_size, ediv, rand); } @@ -502,11 +579,33 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) void smp_chan_destroy(struct l2cap_conn *conn) { struct smp_chan *smp = conn->smp_chan; + bool complete; BUG_ON(!smp); - if (smp->tfm) - crypto_free_blkcipher(smp->tfm); + complete = test_bit(SMP_FLAG_COMPLETE, &smp->smp_flags); + mgmt_smp_complete(conn->hcon, complete); + + kfree(smp->csrk); + kfree(smp->slave_csrk); + + /* If pairing failed clean up any keys we might have */ + if (!complete) { + if (smp->ltk) { + list_del(&smp->ltk->list); + kfree(smp->ltk); + } + + if (smp->slave_ltk) { + list_del(&smp->slave_ltk->list); + kfree(smp->slave_ltk); + } + + if (smp->remote_irk) { + list_del(&smp->remote_irk->list); + kfree(smp->remote_irk); + } + } kfree(smp); conn->smp_chan = NULL; @@ -519,7 +618,6 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey) struct l2cap_conn *conn = hcon->smp_conn; struct smp_chan *smp; u32 value; - u8 key[16]; BT_DBG(""); @@ -531,10 +629,9 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey) switch (mgmt_op) { case MGMT_OP_USER_PASSKEY_REPLY: value = le32_to_cpu(passkey); - memset(key, 0, sizeof(key)); + memset(smp->tk, 0, sizeof(smp->tk)); BT_DBG("PassKey: %d", value); - put_unaligned_le32(value, key); - swap128(key, smp->tk); + put_unaligned_le32(value, smp->tk); /* Fall Through */ case MGMT_OP_USER_CONFIRM_REPLY: set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags); @@ -565,6 +662,9 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); + if (skb->len < sizeof(*req)) + return SMP_UNSPECIFIED; + if (conn->hcon->link_mode & HCI_LM_MASTER) return SMP_CMD_NOTSUPP; @@ -604,6 +704,8 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (ret) return SMP_UNSPECIFIED; + clear_bit(SMP_FLAG_INITIATOR, &smp->smp_flags); + return 0; } @@ -617,6 +719,9 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); + if (skb->len < sizeof(*rsp)) + return SMP_UNSPECIFIED; + if (!(conn->hcon->link_mode & HCI_LM_MASTER)) return SMP_CMD_NOTSUPP; @@ -633,6 +738,11 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) smp->prsp[0] = SMP_CMD_PAIRING_RSP; memcpy(&smp->prsp[1], rsp, sizeof(*rsp)); + /* Update remote key distribution in case the remote cleared + * some bits that we had enabled in our request. + */ + smp->remote_key_dist &= rsp->resp_key_dist; + if ((req->auth_req & SMP_AUTH_BONDING) && (rsp->auth_req & SMP_AUTH_BONDING)) auth = SMP_AUTH_BONDING; @@ -646,10 +756,8 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) set_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags); /* Can't compose response until we have been confirmed */ - if (!test_bit(SMP_FLAG_TK_VALID, &smp->smp_flags)) - return 0; - - queue_work(hdev->workqueue, &smp->confirm); + if (test_bit(SMP_FLAG_TK_VALID, &smp->smp_flags)) + queue_work(hdev->workqueue, &smp->confirm); return 0; } @@ -661,20 +769,19 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); + if (skb->len < sizeof(smp->pcnf)) + return SMP_UNSPECIFIED; + memcpy(smp->pcnf, skb->data, sizeof(smp->pcnf)); skb_pull(skb, sizeof(smp->pcnf)); - if (conn->hcon->out) { - u8 random[16]; - - swap128(smp->prnd, random); - smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(random), - random); - } else if (test_bit(SMP_FLAG_TK_VALID, &smp->smp_flags)) { + if (conn->hcon->out) + smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), + smp->prnd); + else if (test_bit(SMP_FLAG_TK_VALID, &smp->smp_flags)) queue_work(hdev->workqueue, &smp->confirm); - } else { + else set_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags); - } return 0; } @@ -686,7 +793,10 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); - swap128(skb->data, smp->rrnd); + if (skb->len < sizeof(smp->rrnd)) + return SMP_UNSPECIFIED; + + memcpy(smp->rrnd, skb->data, sizeof(smp->rrnd)); skb_pull(skb, sizeof(smp->rrnd)); queue_work(hdev->workqueue, &smp->random); @@ -699,7 +809,8 @@ static u8 smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level) struct smp_ltk *key; struct hci_conn *hcon = conn->hcon; - key = hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type); + key = hci_find_ltk_by_addr(hcon->hdev, &hcon->dst, hcon->dst_type, + hcon->out); if (!key) return 0; @@ -724,6 +835,9 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); + if (skb->len < sizeof(*rp)) + return SMP_UNSPECIFIED; + if (!(conn->hcon->link_mode & HCI_LM_MASTER)) return SMP_CMD_NOTSUPP; @@ -747,6 +861,8 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); + clear_bit(SMP_FLAG_INITIATOR, &smp->smp_flags); + return 0; } @@ -764,11 +880,15 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level) int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) { struct l2cap_conn *conn = hcon->l2cap_data; - struct smp_chan *smp = conn->smp_chan; + struct smp_chan *smp; __u8 authreq; BT_DBG("conn %p hcon %p level 0x%2.2x", conn, hcon, sec_level); + /* This may be NULL if there's an unexpected disconnection */ + if (!conn) + return 1; + if (!test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags)) return 1; @@ -788,6 +908,12 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) authreq = seclevel_to_authreq(sec_level); + /* hcon->auth_type is set by pair_device in mgmt.c. If the MITM + * flag is set we should also set it for the SMP request. + */ + if ((hcon->auth_type & 0x01)) + authreq |= SMP_AUTH_MITM; + if (hcon->link_mode & HCI_LM_MASTER) { struct smp_cmd_pairing cp; @@ -802,6 +928,8 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); } + set_bit(SMP_FLAG_INITIATOR, &smp->smp_flags); + done: hcon->pending_sec_level = sec_level; @@ -813,6 +941,15 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_cmd_encrypt_info *rp = (void *) skb->data; struct smp_chan *smp = conn->smp_chan; + BT_DBG("conn %p", conn); + + if (skb->len < sizeof(*rp)) + return SMP_UNSPECIFIED; + + /* Ignore this PDU if it wasn't requested */ + if (!(smp->remote_key_dist & SMP_DIST_ENC_KEY)) + return 0; + skb_pull(skb, sizeof(*rp)); memcpy(smp->tk, rp->ltk, sizeof(smp->tk)); @@ -826,16 +963,138 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_chan *smp = conn->smp_chan; struct hci_dev *hdev = conn->hcon->hdev; struct hci_conn *hcon = conn->hcon; + struct smp_ltk *ltk; u8 authenticated; + BT_DBG("conn %p", conn); + + if (skb->len < sizeof(*rp)) + return SMP_UNSPECIFIED; + + /* Ignore this PDU if it wasn't requested */ + if (!(smp->remote_key_dist & SMP_DIST_ENC_KEY)) + return 0; + + /* Mark the information as received */ + smp->remote_key_dist &= ~SMP_DIST_ENC_KEY; + skb_pull(skb, sizeof(*rp)); hci_dev_lock(hdev); authenticated = (hcon->sec_level == BT_SECURITY_HIGH); - hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, HCI_SMP_LTK, 1, - authenticated, smp->tk, smp->enc_key_size, - rp->ediv, rp->rand); - smp_distribute_keys(conn, 1); + ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, HCI_SMP_LTK, + authenticated, smp->tk, smp->enc_key_size, + rp->ediv, rp->rand); + smp->ltk = ltk; + if (!(smp->remote_key_dist & SMP_DIST_ID_KEY)) + smp_distribute_keys(conn); + hci_dev_unlock(hdev); + + return 0; +} + +static int smp_cmd_ident_info(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct smp_cmd_ident_info *info = (void *) skb->data; + struct smp_chan *smp = conn->smp_chan; + + BT_DBG(""); + + if (skb->len < sizeof(*info)) + return SMP_UNSPECIFIED; + + /* Ignore this PDU if it wasn't requested */ + if (!(smp->remote_key_dist & SMP_DIST_ID_KEY)) + return 0; + + skb_pull(skb, sizeof(*info)); + + memcpy(smp->irk, info->irk, 16); + + return 0; +} + +static int smp_cmd_ident_addr_info(struct l2cap_conn *conn, + struct sk_buff *skb) +{ + struct smp_cmd_ident_addr_info *info = (void *) skb->data; + struct smp_chan *smp = conn->smp_chan; + struct hci_conn *hcon = conn->hcon; + bdaddr_t rpa; + + BT_DBG(""); + + if (skb->len < sizeof(*info)) + return SMP_UNSPECIFIED; + + /* Ignore this PDU if it wasn't requested */ + if (!(smp->remote_key_dist & SMP_DIST_ID_KEY)) + return 0; + + /* Mark the information as received */ + smp->remote_key_dist &= ~SMP_DIST_ID_KEY; + + skb_pull(skb, sizeof(*info)); + + /* Strictly speaking the Core Specification (4.1) allows sending + * an empty address which would force us to rely on just the IRK + * as "identity information". However, since such + * implementations are not known of and in order to not over + * complicate our implementation, simply pretend that we never + * received an IRK for such a device. + */ + if (!bacmp(&info->bdaddr, BDADDR_ANY)) { + BT_ERR("Ignoring IRK with no identity address"); + smp_distribute_keys(conn); + return 0; + } + + bacpy(&smp->id_addr, &info->bdaddr); + smp->id_addr_type = info->addr_type; + + if (hci_bdaddr_is_rpa(&hcon->dst, hcon->dst_type)) + bacpy(&rpa, &hcon->dst); + else + bacpy(&rpa, BDADDR_ANY); + + smp->remote_irk = hci_add_irk(conn->hcon->hdev, &smp->id_addr, + smp->id_addr_type, smp->irk, &rpa); + + smp_distribute_keys(conn); + + return 0; +} + +static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct smp_cmd_sign_info *rp = (void *) skb->data; + struct smp_chan *smp = conn->smp_chan; + struct hci_dev *hdev = conn->hcon->hdev; + struct smp_csrk *csrk; + + BT_DBG("conn %p", conn); + + if (skb->len < sizeof(*rp)) + return SMP_UNSPECIFIED; + + /* Ignore this PDU if it wasn't requested */ + if (!(smp->remote_key_dist & SMP_DIST_SIGN)) + return 0; + + /* Mark the information as received */ + smp->remote_key_dist &= ~SMP_DIST_SIGN; + + skb_pull(skb, sizeof(*rp)); + + hci_dev_lock(hdev); + csrk = kzalloc(sizeof(*csrk), GFP_KERNEL); + if (csrk) { + csrk->master = 0x01; + memcpy(csrk->val, rp->csrk, sizeof(csrk->val)); + } + smp->csrk = csrk; + if (!(smp->remote_key_dist & SMP_DIST_SIGN)) + smp_distribute_keys(conn); hci_dev_unlock(hdev); return 0; @@ -915,10 +1174,15 @@ int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) break; case SMP_CMD_IDENT_INFO: + reason = smp_cmd_ident_info(conn, skb); + break; + case SMP_CMD_IDENT_ADDR_INFO: + reason = smp_cmd_ident_addr_info(conn, skb); + break; + case SMP_CMD_SIGN_INFO: - /* Just ignored */ - reason = 0; + reason = smp_cmd_sign_info(conn, skb); break; default: @@ -937,26 +1201,78 @@ done: return err; } -int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) +static void smp_notify_keys(struct l2cap_conn *conn) +{ + struct smp_chan *smp = conn->smp_chan; + struct hci_conn *hcon = conn->hcon; + struct hci_dev *hdev = hcon->hdev; + struct smp_cmd_pairing *req = (void *) &smp->preq[1]; + struct smp_cmd_pairing *rsp = (void *) &smp->prsp[1]; + bool persistent; + + if (smp->remote_irk) { + mgmt_new_irk(hdev, smp->remote_irk); + /* Now that user space can be considered to know the + * identity address track the connection based on it + * from now on. + */ + bacpy(&hcon->dst, &smp->remote_irk->bdaddr); + hcon->dst_type = smp->remote_irk->addr_type; + l2cap_conn_update_id_addr(hcon); + } + + /* The LTKs and CSRKs should be persistent only if both sides + * had the bonding bit set in their authentication requests. + */ + persistent = !!((req->auth_req & rsp->auth_req) & SMP_AUTH_BONDING); + + if (smp->csrk) { + smp->csrk->bdaddr_type = hcon->dst_type; + bacpy(&smp->csrk->bdaddr, &hcon->dst); + mgmt_new_csrk(hdev, smp->csrk, persistent); + } + + if (smp->slave_csrk) { + smp->slave_csrk->bdaddr_type = hcon->dst_type; + bacpy(&smp->slave_csrk->bdaddr, &hcon->dst); + mgmt_new_csrk(hdev, smp->slave_csrk, persistent); + } + + if (smp->ltk) { + smp->ltk->bdaddr_type = hcon->dst_type; + bacpy(&smp->ltk->bdaddr, &hcon->dst); + mgmt_new_ltk(hdev, smp->ltk, persistent); + } + + if (smp->slave_ltk) { + smp->slave_ltk->bdaddr_type = hcon->dst_type; + bacpy(&smp->slave_ltk->bdaddr, &hcon->dst); + mgmt_new_ltk(hdev, smp->slave_ltk, persistent); + } +} + +int smp_distribute_keys(struct l2cap_conn *conn) { struct smp_cmd_pairing *req, *rsp; struct smp_chan *smp = conn->smp_chan; + struct hci_conn *hcon = conn->hcon; + struct hci_dev *hdev = hcon->hdev; __u8 *keydist; - BT_DBG("conn %p force %d", conn, force); + BT_DBG("conn %p", conn); - if (!test_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags)) + if (!test_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags)) return 0; rsp = (void *) &smp->prsp[1]; /* The responder sends its keys first */ - if (!force && conn->hcon->out && (rsp->resp_key_dist & 0x07)) + if (hcon->out && (smp->remote_key_dist & 0x07)) return 0; req = (void *) &smp->preq[1]; - if (conn->hcon->out) { + if (hcon->out) { keydist = &rsp->init_key_dist; *keydist &= req->init_key_dist; } else { @@ -964,28 +1280,30 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) *keydist &= req->resp_key_dist; } - BT_DBG("keydist 0x%x", *keydist); if (*keydist & SMP_DIST_ENC_KEY) { struct smp_cmd_encrypt_info enc; struct smp_cmd_master_ident ident; - struct hci_conn *hcon = conn->hcon; + struct smp_ltk *ltk; u8 authenticated; __le16 ediv; + __le64 rand; get_random_bytes(enc.ltk, sizeof(enc.ltk)); get_random_bytes(&ediv, sizeof(ediv)); - get_random_bytes(ident.rand, sizeof(ident.rand)); + get_random_bytes(&rand, sizeof(rand)); smp_send_cmd(conn, SMP_CMD_ENCRYPT_INFO, sizeof(enc), &enc); authenticated = hcon->sec_level == BT_SECURITY_HIGH; - hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, - HCI_SMP_LTK_SLAVE, 1, authenticated, - enc.ltk, smp->enc_key_size, ediv, ident.rand); + ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, + HCI_SMP_LTK_SLAVE, authenticated, enc.ltk, + smp->enc_key_size, ediv, rand); + smp->slave_ltk = ltk; ident.ediv = ediv; + ident.rand = rand; smp_send_cmd(conn, SMP_CMD_MASTER_IDENT, sizeof(ident), &ident); @@ -996,14 +1314,18 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) struct smp_cmd_ident_addr_info addrinfo; struct smp_cmd_ident_info idinfo; - /* Send a dummy key */ - get_random_bytes(idinfo.irk, sizeof(idinfo.irk)); + memcpy(idinfo.irk, hdev->irk, sizeof(idinfo.irk)); smp_send_cmd(conn, SMP_CMD_IDENT_INFO, sizeof(idinfo), &idinfo); - /* Just public address */ - memset(&addrinfo, 0, sizeof(addrinfo)); - bacpy(&addrinfo.bdaddr, &conn->hcon->src); + /* The hci_conn contains the local identity address + * after the connection has been established. + * + * This is true even when the connection has been + * established using a resolvable random address. + */ + bacpy(&addrinfo.bdaddr, &hcon->src); + addrinfo.addr_type = hcon->src_type; smp_send_cmd(conn, SMP_CMD_IDENT_ADDR_INFO, sizeof(addrinfo), &addrinfo); @@ -1013,20 +1335,33 @@ int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) if (*keydist & SMP_DIST_SIGN) { struct smp_cmd_sign_info sign; + struct smp_csrk *csrk; - /* Send a dummy key */ + /* Generate a new random key */ get_random_bytes(sign.csrk, sizeof(sign.csrk)); + csrk = kzalloc(sizeof(*csrk), GFP_KERNEL); + if (csrk) { + csrk->master = 0x00; + memcpy(csrk->val, sign.csrk, sizeof(csrk->val)); + } + smp->slave_csrk = csrk; + smp_send_cmd(conn, SMP_CMD_SIGN_INFO, sizeof(sign), &sign); *keydist &= ~SMP_DIST_SIGN; } - if (conn->hcon->out || force) { - clear_bit(HCI_CONN_LE_SMP_PEND, &conn->hcon->flags); - cancel_delayed_work_sync(&conn->security_timer); - smp_chan_destroy(conn); - } + /* If there are still keys to be received wait for them */ + if ((smp->remote_key_dist & 0x07)) + return 0; + + clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags); + cancel_delayed_work_sync(&conn->security_timer); + set_bit(SMP_FLAG_COMPLETE, &smp->smp_flags); + smp_notify_keys(conn); + + smp_chan_destroy(conn); return 0; } diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index a700bcb490d7..1277147a9150 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -78,7 +78,7 @@ struct smp_cmd_encrypt_info { #define SMP_CMD_MASTER_IDENT 0x07 struct smp_cmd_master_ident { __le16 ediv; - __u8 rand[8]; + __le64 rand; } __packed; #define SMP_CMD_IDENT_INFO 0x08 @@ -118,6 +118,8 @@ struct smp_cmd_security_req { #define SMP_FLAG_TK_VALID 1 #define SMP_FLAG_CFM_PENDING 2 #define SMP_FLAG_MITM_AUTH 3 +#define SMP_FLAG_COMPLETE 4 +#define SMP_FLAG_INITIATOR 5 struct smp_chan { struct l2cap_conn *conn; @@ -128,20 +130,31 @@ struct smp_chan { u8 pcnf[16]; /* SMP Pairing Confirm */ u8 tk[16]; /* SMP Temporary Key */ u8 enc_key_size; + u8 remote_key_dist; + bdaddr_t id_addr; + u8 id_addr_type; + u8 irk[16]; + struct smp_csrk *csrk; + struct smp_csrk *slave_csrk; + struct smp_ltk *ltk; + struct smp_ltk *slave_ltk; + struct smp_irk *remote_irk; unsigned long smp_flags; - struct crypto_blkcipher *tfm; struct work_struct confirm; struct work_struct random; - }; /* SMP Commands */ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level); int smp_conn_security(struct hci_conn *hcon, __u8 sec_level); int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb); -int smp_distribute_keys(struct l2cap_conn *conn, __u8 force); +int smp_distribute_keys(struct l2cap_conn *conn); int smp_user_confirm_reply(struct hci_conn *conn, u16 mgmt_op, __le32 passkey); void smp_chan_destroy(struct l2cap_conn *conn); +bool smp_irk_matches(struct crypto_blkcipher *tfm, u8 irk[16], + bdaddr_t *bdaddr); +int smp_generate_rpa(struct crypto_blkcipher *tfm, u8 irk[16], bdaddr_t *rpa); + #endif /* __SMP_H */ diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 8fe8b71b487a..3e2da2cb72db 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -88,18 +88,11 @@ out: static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - int i; - br->stats = alloc_percpu(struct pcpu_sw_netstats); + br->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!br->stats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *br_dev_stats; - br_dev_stats = per_cpu_ptr(br->stats, i); - u64_stats_init(&br_dev_stats->syncp); - } - return 0; } @@ -143,9 +136,9 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev, const struct pcpu_sw_netstats *bstats = per_cpu_ptr(br->stats, cpu); do { - start = u64_stats_fetch_begin_bh(&bstats->syncp); + start = u64_stats_fetch_begin_irq(&bstats->syncp); memcpy(&tmp, bstats, sizeof(tmp)); - } while (u64_stats_fetch_retry_bh(&bstats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&bstats->syncp, start)); sum.tx_bytes += tmp.tx_bytes; sum.tx_packets += tmp.tx_packets; sum.rx_bytes += tmp.rx_bytes; @@ -225,16 +218,16 @@ static void br_netpoll_cleanup(struct net_device *dev) br_netpoll_disable(p); } -static int __br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) +static int __br_netpoll_enable(struct net_bridge_port *p) { struct netpoll *np; int err; - np = kzalloc(sizeof(*p->np), gfp); + np = kzalloc(sizeof(*p->np), GFP_KERNEL); if (!np) return -ENOMEM; - err = __netpoll_setup(np, p->dev, gfp); + err = __netpoll_setup(np, p->dev); if (err) { kfree(np); return err; @@ -244,16 +237,15 @@ static int __br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) return err; } -int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) +int br_netpoll_enable(struct net_bridge_port *p) { if (!p->br->dev->npinfo) return 0; - return __br_netpoll_enable(p, gfp); + return __br_netpoll_enable(p); } -static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, - gfp_t gfp) +static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p; @@ -262,7 +254,7 @@ static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, list_for_each_entry(p, &br->port_list, list) { if (!p->dev) continue; - err = __br_netpoll_enable(p, gfp); + err = __br_netpoll_enable(p); if (err) goto fail; } @@ -374,7 +366,7 @@ void br_dev_setup(struct net_device *dev) br->bridge_id.prio[0] = 0x80; br->bridge_id.prio[1] = 0x00; - memcpy(br->group_addr, eth_reserved_addr_base, ETH_ALEN); + ether_addr_copy(br->group_addr, eth_reserved_addr_base); br->stp_enabled = BR_NO_STP; br->group_fwd_mask = BR_GROUPFWD_DEFAULT; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index d3409e6b5453..056b67b0e277 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -35,16 +35,11 @@ static inline int should_deliver(const struct net_bridge_port *p, p->state == BR_STATE_FORWARDING; } -static inline unsigned int packet_length(const struct sk_buff *skb) -{ - return skb->len - (skb->protocol == htons(ETH_P_8021Q) ? VLAN_HLEN : 0); -} - int br_dev_queue_push_xmit(struct sk_buff *skb) { /* ip_fragment doesn't copy the MAC header */ if (nf_bridge_maybe_copy_header(skb) || - (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb))) { + !is_skb_forwardable(skb->dev, skb)) { kfree_skb(skb); } else { skb_push(skb, ETH_HLEN); @@ -71,7 +66,7 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) skb->dev = to->dev; if (unlikely(netpoll_tx_running(to->br->dev))) { - if (packet_length(skb) > skb->dev->mtu && !skb_is_gso(skb)) + if (!is_skb_forwardable(skb->dev, skb)) kfree_skb(skb); else { skb_push(skb, ETH_HLEN); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 54d207d3a31c..5262b8617eb9 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -366,7 +366,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (err) goto err2; - err = br_netpoll_enable(p, GFP_KERNEL); + err = br_netpoll_enable(p); if (err) goto err3; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 93067ecdb9a2..7b757b5dc773 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -363,7 +363,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, skb_reset_mac_header(skb); eth = eth_hdr(skb); - memcpy(eth->h_source, br->dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth->h_source, br->dev->dev_addr); eth->h_dest[0] = 1; eth->h_dest[1] = 0; eth->h_dest[2] = 0x5e; @@ -433,7 +433,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, skb_reset_mac_header(skb); eth = eth_hdr(skb); - memcpy(eth->h_source, br->dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth->h_source, br->dev->dev_addr); eth->h_proto = htons(ETH_P_IPV6); skb_put(skb, sizeof(*eth)); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index b008c59a92c4..80e1b0f60a30 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -167,7 +167,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) rt->dst.dev = br->dev; rt->dst.path = &rt->dst; dst_init_metrics(&rt->dst, br_dst_default_metrics, true); - rt->dst.flags = DST_NOXFRM | DST_NOPEER | DST_FAKE_RTABLE; + rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } @@ -506,7 +506,7 @@ bridged_dnat: 1); return 0; } - memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); skb->pkt_type = PACKET_HOST; } } else { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 3ba11bc99b65..06811d79f89f 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -46,12 +46,12 @@ typedef __u16 port_id; struct bridge_id { unsigned char prio[2]; - unsigned char addr[6]; + unsigned char addr[ETH_ALEN]; }; struct mac_addr { - unsigned char addr[6]; + unsigned char addr[ETH_ALEN]; }; struct br_ip @@ -349,7 +349,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p, netpoll_send_skb(np, skb); } -int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp); +int br_netpoll_enable(struct net_bridge_port *p); void br_netpoll_disable(struct net_bridge_port *p); #else static inline void br_netpoll_send_skb(const struct net_bridge_port *p, @@ -357,7 +357,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p, { } -static inline int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) +static inline int br_netpoll_enable(struct net_bridge_port *p) { return 0; } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index f23c74b3a953..91510712c7a7 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -99,9 +99,9 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid) v->num_vlans--; if (bitmap_empty(v->vlan_bitmap, VLAN_N_VID)) { if (v->port_idx) - rcu_assign_pointer(v->parent.port->vlan_info, NULL); + RCU_INIT_POINTER(v->parent.port->vlan_info, NULL); else - rcu_assign_pointer(v->parent.br->vlan_info, NULL); + RCU_INIT_POINTER(v->parent.br->vlan_info, NULL); kfree_rcu(v, rcu); } return 0; @@ -113,9 +113,9 @@ static void __vlan_flush(struct net_port_vlans *v) v->pvid = 0; bitmap_zero(v->vlan_bitmap, VLAN_N_VID); if (v->port_idx) - rcu_assign_pointer(v->parent.port->vlan_info, NULL); + RCU_INIT_POINTER(v->parent.port->vlan_info, NULL); else - rcu_assign_pointer(v->parent.br->vlan_info, NULL); + RCU_INIT_POINTER(v->parent.br->vlan_info, NULL); kfree_rcu(v, rcu); } diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c index 3fb3c848affe..9024283d2bca 100644 --- a/net/bridge/netfilter/ebt_among.c +++ b/net/bridge/netfilter/ebt_among.c @@ -28,7 +28,7 @@ static bool ebt_mac_wormhash_contains(const struct ebt_mac_wormhash *wh, uint32_t cmp[2] = { 0, 0 }; int key = ((const unsigned char *)mac)[5]; - memcpy(((char *) cmp) + 2, mac, ETH_ALEN); + ether_addr_copy(((char *) cmp) + 2, mac); start = wh->table[key]; limit = wh->table[key + 1]; if (ip) { diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index c59f7bfae6e2..4e0b0c359325 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -22,7 +22,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) if (!skb_make_writable(skb, 0)) return EBT_DROP; - memcpy(eth_hdr(skb)->h_dest, info->mac, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, info->mac); return info->target; } diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 46624bb6d9be..203964997a51 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -25,10 +25,10 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) if (par->hooknum != NF_BR_BROUTING) /* rcu_read_lock()ed by nf_hook_slow */ - memcpy(eth_hdr(skb)->h_dest, - br_port_get_rcu(par->in)->br->dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, + br_port_get_rcu(par->in)->br->dev->dev_addr); else - memcpy(eth_hdr(skb)->h_dest, par->in->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, par->in->dev_addr); skb->pkt_type = PACKET_HOST; return info->target; } diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index 0f6b118d6cb2..e56ccd060d26 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -24,7 +24,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) if (!skb_make_writable(skb, 0)) return EBT_DROP; - memcpy(eth_hdr(skb)->h_source, info->mac, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_source, info->mac); if (!(info->target & NAT_ARP_BIT) && eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) { const struct arphdr *ap; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 0676f2b199d6..82750f915865 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2082,7 +2082,6 @@ bad: pr_err("osdc handle_map corrupt msg\n"); ceph_msg_dump(msg); up_write(&osdc->map_sem); - return; } /* @@ -2281,7 +2280,6 @@ done_err: bad: pr_err("osdc handle_watch_notify corrupt msg\n"); - return; } /* diff --git a/net/core/Makefile b/net/core/Makefile index 9628c20acff6..826b925aa453 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -21,5 +21,6 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o +obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o diff --git a/net/core/dev.c b/net/core/dev.c index 4a91591b30a6..757063420ce0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1245,7 +1245,7 @@ static int __dev_open(struct net_device *dev) * If we don't do this there is a chance ndo_poll_controller * or ndo_poll may be running while we open the device */ - netpoll_rx_disable(dev); + netpoll_poll_disable(dev); ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev); ret = notifier_to_errno(ret); @@ -1260,7 +1260,7 @@ static int __dev_open(struct net_device *dev) if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); - netpoll_rx_enable(dev); + netpoll_poll_enable(dev); if (ret) clear_bit(__LINK_STATE_START, &dev->state); @@ -1313,6 +1313,9 @@ static int __dev_close_many(struct list_head *head) might_sleep(); list_for_each_entry(dev, head, close_list) { + /* Temporarily disable netpoll until the interface is down */ + netpoll_poll_disable(dev); + call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); clear_bit(__LINK_STATE_START, &dev->state); @@ -1343,6 +1346,7 @@ static int __dev_close_many(struct list_head *head) dev->flags &= ~IFF_UP; net_dmaengine_put(); + netpoll_poll_enable(dev); } return 0; @@ -1353,14 +1357,10 @@ static int __dev_close(struct net_device *dev) int retval; LIST_HEAD(single); - /* Temporarily disable netpoll until the interface is down */ - netpoll_rx_disable(dev); - list_add(&dev->close_list, &single); retval = __dev_close_many(&single); list_del(&single); - netpoll_rx_enable(dev); return retval; } @@ -1398,14 +1398,9 @@ int dev_close(struct net_device *dev) if (dev->flags & IFF_UP) { LIST_HEAD(single); - /* Block netpoll rx while the interface is going down */ - netpoll_rx_disable(dev); - list_add(&dev->close_list, &single); dev_close_many(&single); list_del(&single); - - netpoll_rx_enable(dev); } return 0; } @@ -1645,8 +1640,7 @@ static inline void net_timestamp_set(struct sk_buff *skb) __net_timestamp(SKB); \ } \ -static inline bool is_skb_forwardable(struct net_device *dev, - struct sk_buff *skb) +bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb) { unsigned int len; @@ -1665,6 +1659,7 @@ static inline bool is_skb_forwardable(struct net_device *dev, return false; } +EXPORT_SYMBOL_GPL(is_skb_forwardable); /** * dev_forward_skb - loopback an skb to another netif @@ -2885,6 +2880,7 @@ recursion_alert: rc = -ENETDOWN; rcu_read_unlock_bh(); + atomic_long_inc(&dev->tx_dropped); kfree_skb(skb); return rc; out: @@ -2957,7 +2953,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb, flow_table = rcu_dereference(rxqueue->rps_flow_table); if (!flow_table) goto out; - flow_id = skb->rxhash & flow_table->mask; + flow_id = skb_get_hash(skb) & flow_table->mask; rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, rxq_index, flow_id); if (rc < 0) @@ -2991,6 +2987,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_sock_flow_table *sock_flow_table; int cpu = -1; u16 tcpu; + u32 hash; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); @@ -3019,7 +3016,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, } skb_reset_network_header(skb); - if (!skb_get_hash(skb)) + hash = skb_get_hash(skb); + if (!hash) goto done; flow_table = rcu_dereference(rxqueue->rps_flow_table); @@ -3028,11 +3026,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, u16 next_cpu; struct rps_dev_flow *rflow; - rflow = &flow_table->flows[skb->rxhash & flow_table->mask]; + rflow = &flow_table->flows[hash & flow_table->mask]; tcpu = rflow->cpu; - next_cpu = sock_flow_table->ents[skb->rxhash & - sock_flow_table->mask]; + next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask]; /* * If the desired CPU (where last recvmsg was done) is @@ -3061,7 +3058,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, } if (map) { - tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; + tcpu = map->cpus[((u64) hash * map->len) >> 32]; if (cpu_online(tcpu)) { cpu = tcpu; @@ -3236,10 +3233,6 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - /* if netpoll wants it, pretend we never saw it */ - if (netpoll_rx(skb)) - return NET_RX_DROP; - net_timestamp_check(netdev_tstamp_prequeue, skb); trace_netif_rx(skb); @@ -3500,11 +3493,11 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); static bool skb_pfmemalloc_protocol(struct sk_buff *skb) { switch (skb->protocol) { - case __constant_htons(ETH_P_ARP): - case __constant_htons(ETH_P_IP): - case __constant_htons(ETH_P_IPV6): - case __constant_htons(ETH_P_8021Q): - case __constant_htons(ETH_P_8021AD): + case htons(ETH_P_ARP): + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + case htons(ETH_P_8021Q): + case htons(ETH_P_8021AD): return true; default: return false; @@ -3525,10 +3518,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) trace_netif_receive_skb(skb); - /* if we've gotten here through NAPI, check netpoll */ - if (netpoll_receive_skb(skb)) - goto out; - orig_dev = skb->dev; skb_reset_network_header(skb); @@ -3655,7 +3644,6 @@ drop: unlock: rcu_read_unlock(); -out: return ret; } @@ -3845,10 +3833,10 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs |= p->vlan_tci ^ skb->vlan_tci; if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); + skb_mac_header(skb)); else if (!diffs) diffs = memcmp(skb_mac_header(p), - skb_gro_mac_header(skb), + skb_mac_header(skb), maclen); NAPI_GRO_CB(p)->same_flow = !diffs; } @@ -3871,6 +3859,27 @@ static void skb_gro_reset_offset(struct sk_buff *skb) } } +static void gro_pull_from_frag0(struct sk_buff *skb, int grow) +{ + struct skb_shared_info *pinfo = skb_shinfo(skb); + + BUG_ON(skb->end - skb->tail < grow); + + memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); + + skb->data_len -= grow; + skb->tail += grow; + + pinfo->frags[0].page_offset += grow; + skb_frag_size_sub(&pinfo->frags[0], grow); + + if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { + skb_frag_unref(skb, 0); + memmove(pinfo->frags, pinfo->frags + 1, + --pinfo->nr_frags * sizeof(pinfo->frags[0])); + } +} + static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; @@ -3879,14 +3888,14 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff struct list_head *head = &offload_base; int same_flow; enum gro_result ret; + int grow; - if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb)) + if (!(skb->dev->features & NETIF_F_GRO)) goto normal; if (skb_is_gso(skb) || skb_has_frag_list(skb)) goto normal; - skb_gro_reset_offset(skb); gro_list_prepare(napi, skb); NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */ @@ -3950,27 +3959,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff ret = GRO_HELD; pull: - if (skb_headlen(skb) < skb_gro_offset(skb)) { - int grow = skb_gro_offset(skb) - skb_headlen(skb); - - BUG_ON(skb->end - skb->tail < grow); - - memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); - - skb->tail += grow; - skb->data_len -= grow; - - skb_shinfo(skb)->frags[0].page_offset += grow; - skb_frag_size_sub(&skb_shinfo(skb)->frags[0], grow); - - if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) { - skb_frag_unref(skb, 0); - memmove(skb_shinfo(skb)->frags, - skb_shinfo(skb)->frags + 1, - --skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t)); - } - } - + grow = skb_gro_offset(skb) - skb_headlen(skb); + if (grow > 0) + gro_pull_from_frag0(skb, grow); ok: return ret; @@ -4038,6 +4029,8 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { trace_napi_gro_receive_entry(skb); + skb_gro_reset_offset(skb); + return napi_skb_finish(dev_gro_receive(napi, skb), skb); } EXPORT_SYMBOL(napi_gro_receive); @@ -4066,12 +4059,16 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) } EXPORT_SYMBOL(napi_get_frags); -static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, - gro_result_t ret) +static gro_result_t napi_frags_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) { switch (ret) { case GRO_NORMAL: - if (netif_receive_skb_internal(skb)) + case GRO_HELD: + __skb_push(skb, ETH_HLEN); + skb->protocol = eth_type_trans(skb, skb->dev); + if (ret == GRO_NORMAL && netif_receive_skb_internal(skb)) ret = GRO_DROP; break; @@ -4080,7 +4077,6 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * napi_reuse_skb(napi, skb); break; - case GRO_HELD: case GRO_MERGED: break; } @@ -4088,17 +4084,41 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * return ret; } +/* Upper GRO stack assumes network header starts at gro_offset=0 + * Drivers could call both napi_gro_frags() and napi_gro_receive() + * We copy ethernet header into skb->data to have a common layout. + */ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) { struct sk_buff *skb = napi->skb; + const struct ethhdr *eth; + unsigned int hlen = sizeof(*eth); napi->skb = NULL; - if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) { - napi_reuse_skb(napi, skb); - return NULL; + skb_reset_mac_header(skb); + skb_gro_reset_offset(skb); + + eth = skb_gro_header_fast(skb, 0); + if (unlikely(skb_gro_header_hard(skb, hlen))) { + eth = skb_gro_header_slow(skb, hlen, 0); + if (unlikely(!eth)) { + napi_reuse_skb(napi, skb); + return NULL; + } + } else { + gro_pull_from_frag0(skb, hlen); + NAPI_GRO_CB(skb)->frag0 += hlen; + NAPI_GRO_CB(skb)->frag0_len -= hlen; } - skb->protocol = eth_type_trans(skb, skb->dev); + __skb_pull(skb, hlen); + + /* + * This works because the only protocols we care about don't require + * special handling. + * We'll fix it up properly in napi_frags_finish() + */ + skb->protocol = eth->h_proto; return skb; } @@ -6251,6 +6271,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, netdev_stats_to_stats64(storage, &dev->stats); } storage->rx_dropped += atomic_long_read(&dev->rx_dropped); + storage->tx_dropped += atomic_long_read(&dev->tx_dropped); return storage; } EXPORT_SYMBOL(dev_get_stats); diff --git a/net/core/filter.c b/net/core/filter.c index ad30d626a5bd..765556ba32ef 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1,11 +1,16 @@ /* * Linux Socket Filter - Kernel level socket filtering * - * Author: - * Jay Schulist <jschlst@samba.org> + * Based on the design of the Berkeley Packet Filter. The new + * internal format has been designed by PLUMgrid: * - * Based on the design of: - * - The Berkeley Packet Filter + * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com + * + * Authors: + * + * Jay Schulist <jschlst@samba.org> + * Alexei Starovoitov <ast@plumgrid.com> + * Daniel Borkmann <dborkman@redhat.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -108,304 +113,1045 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(sk_filter); +/* Base function for offset calculation. Needs to go into .text section, + * therefore keeping it non-static as well; will also be used by JITs + * anyway later on, so do not let the compiler omit it. + */ +noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return 0; +} + /** - * sk_run_filter - run a filter on a socket - * @skb: buffer to run the filter on - * @fentry: filter to apply + * __sk_run_filter - run a filter on a given context + * @ctx: buffer to run the filter on + * @insn: filter to apply * - * Decode and apply filter instructions to the skb->data. - * Return length to keep, 0 for none. @skb is the data we are - * filtering, @filter is the array of filter instructions. - * Because all jumps are guaranteed to be before last instruction, - * and last instruction guaranteed to be a RET, we dont need to check - * flen. (We used to pass to this function the length of filter) + * Decode and apply filter instructions to the skb->data. Return length to + * keep, 0 for none. @ctx is the data we are operating on, @insn is the + * array of filter instructions. */ -unsigned int sk_run_filter(const struct sk_buff *skb, - const struct sock_filter *fentry) +unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) { + u64 stack[MAX_BPF_STACK / sizeof(u64)]; + u64 regs[MAX_BPF_REG], tmp; void *ptr; - u32 A = 0; /* Accumulator */ - u32 X = 0; /* Index Register */ - u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ - u32 tmp; - int k; + int off; - /* - * Process array of filter instructions. - */ - for (;; fentry++) { -#if defined(CONFIG_X86_32) -#define K (fentry->k) -#else - const u32 K = fentry->k; -#endif - - switch (fentry->code) { - case BPF_S_ALU_ADD_X: - A += X; - continue; - case BPF_S_ALU_ADD_K: - A += K; - continue; - case BPF_S_ALU_SUB_X: - A -= X; - continue; - case BPF_S_ALU_SUB_K: - A -= K; - continue; - case BPF_S_ALU_MUL_X: - A *= X; - continue; - case BPF_S_ALU_MUL_K: - A *= K; - continue; - case BPF_S_ALU_DIV_X: - if (X == 0) - return 0; - A /= X; - continue; - case BPF_S_ALU_DIV_K: - A /= K; - continue; - case BPF_S_ALU_MOD_X: - if (X == 0) - return 0; - A %= X; - continue; - case BPF_S_ALU_MOD_K: - A %= K; - continue; - case BPF_S_ALU_AND_X: - A &= X; - continue; - case BPF_S_ALU_AND_K: - A &= K; - continue; - case BPF_S_ALU_OR_X: - A |= X; - continue; - case BPF_S_ALU_OR_K: - A |= K; - continue; - case BPF_S_ANC_ALU_XOR_X: - case BPF_S_ALU_XOR_X: - A ^= X; - continue; - case BPF_S_ALU_XOR_K: - A ^= K; - continue; - case BPF_S_ALU_LSH_X: - A <<= X; - continue; - case BPF_S_ALU_LSH_K: - A <<= K; - continue; - case BPF_S_ALU_RSH_X: - A >>= X; - continue; - case BPF_S_ALU_RSH_K: - A >>= K; - continue; - case BPF_S_ALU_NEG: - A = -A; - continue; - case BPF_S_JMP_JA: - fentry += K; - continue; - case BPF_S_JMP_JGT_K: - fentry += (A > K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JGE_K: - fentry += (A >= K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JEQ_K: - fentry += (A == K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JSET_K: - fentry += (A & K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JGT_X: - fentry += (A > X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JGE_X: - fentry += (A >= X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JEQ_X: - fentry += (A == X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JSET_X: - fentry += (A & X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_LD_W_ABS: - k = K; -load_w: - ptr = load_pointer(skb, k, 4, &tmp); - if (ptr != NULL) { - A = get_unaligned_be32(ptr); - continue; - } - return 0; - case BPF_S_LD_H_ABS: - k = K; -load_h: - ptr = load_pointer(skb, k, 2, &tmp); - if (ptr != NULL) { - A = get_unaligned_be16(ptr); - continue; +#define K insn->imm +#define A regs[insn->a_reg] +#define X regs[insn->x_reg] +#define R0 regs[0] + +#define CONT ({insn++; goto select_insn; }) +#define CONT_JMP ({insn++; goto select_insn; }) + + static const void *jumptable[256] = { + [0 ... 255] = &&default_label, + /* Now overwrite non-defaults ... */ +#define DL(A, B, C) [A|B|C] = &&A##_##B##_##C + DL(BPF_ALU, BPF_ADD, BPF_X), + DL(BPF_ALU, BPF_ADD, BPF_K), + DL(BPF_ALU, BPF_SUB, BPF_X), + DL(BPF_ALU, BPF_SUB, BPF_K), + DL(BPF_ALU, BPF_AND, BPF_X), + DL(BPF_ALU, BPF_AND, BPF_K), + DL(BPF_ALU, BPF_OR, BPF_X), + DL(BPF_ALU, BPF_OR, BPF_K), + DL(BPF_ALU, BPF_LSH, BPF_X), + DL(BPF_ALU, BPF_LSH, BPF_K), + DL(BPF_ALU, BPF_RSH, BPF_X), + DL(BPF_ALU, BPF_RSH, BPF_K), + DL(BPF_ALU, BPF_XOR, BPF_X), + DL(BPF_ALU, BPF_XOR, BPF_K), + DL(BPF_ALU, BPF_MUL, BPF_X), + DL(BPF_ALU, BPF_MUL, BPF_K), + DL(BPF_ALU, BPF_MOV, BPF_X), + DL(BPF_ALU, BPF_MOV, BPF_K), + DL(BPF_ALU, BPF_DIV, BPF_X), + DL(BPF_ALU, BPF_DIV, BPF_K), + DL(BPF_ALU, BPF_MOD, BPF_X), + DL(BPF_ALU, BPF_MOD, BPF_K), + DL(BPF_ALU, BPF_NEG, 0), + DL(BPF_ALU, BPF_END, BPF_TO_BE), + DL(BPF_ALU, BPF_END, BPF_TO_LE), + DL(BPF_ALU64, BPF_ADD, BPF_X), + DL(BPF_ALU64, BPF_ADD, BPF_K), + DL(BPF_ALU64, BPF_SUB, BPF_X), + DL(BPF_ALU64, BPF_SUB, BPF_K), + DL(BPF_ALU64, BPF_AND, BPF_X), + DL(BPF_ALU64, BPF_AND, BPF_K), + DL(BPF_ALU64, BPF_OR, BPF_X), + DL(BPF_ALU64, BPF_OR, BPF_K), + DL(BPF_ALU64, BPF_LSH, BPF_X), + DL(BPF_ALU64, BPF_LSH, BPF_K), + DL(BPF_ALU64, BPF_RSH, BPF_X), + DL(BPF_ALU64, BPF_RSH, BPF_K), + DL(BPF_ALU64, BPF_XOR, BPF_X), + DL(BPF_ALU64, BPF_XOR, BPF_K), + DL(BPF_ALU64, BPF_MUL, BPF_X), + DL(BPF_ALU64, BPF_MUL, BPF_K), + DL(BPF_ALU64, BPF_MOV, BPF_X), + DL(BPF_ALU64, BPF_MOV, BPF_K), + DL(BPF_ALU64, BPF_ARSH, BPF_X), + DL(BPF_ALU64, BPF_ARSH, BPF_K), + DL(BPF_ALU64, BPF_DIV, BPF_X), + DL(BPF_ALU64, BPF_DIV, BPF_K), + DL(BPF_ALU64, BPF_MOD, BPF_X), + DL(BPF_ALU64, BPF_MOD, BPF_K), + DL(BPF_ALU64, BPF_NEG, 0), + DL(BPF_JMP, BPF_CALL, 0), + DL(BPF_JMP, BPF_JA, 0), + DL(BPF_JMP, BPF_JEQ, BPF_X), + DL(BPF_JMP, BPF_JEQ, BPF_K), + DL(BPF_JMP, BPF_JNE, BPF_X), + DL(BPF_JMP, BPF_JNE, BPF_K), + DL(BPF_JMP, BPF_JGT, BPF_X), + DL(BPF_JMP, BPF_JGT, BPF_K), + DL(BPF_JMP, BPF_JGE, BPF_X), + DL(BPF_JMP, BPF_JGE, BPF_K), + DL(BPF_JMP, BPF_JSGT, BPF_X), + DL(BPF_JMP, BPF_JSGT, BPF_K), + DL(BPF_JMP, BPF_JSGE, BPF_X), + DL(BPF_JMP, BPF_JSGE, BPF_K), + DL(BPF_JMP, BPF_JSET, BPF_X), + DL(BPF_JMP, BPF_JSET, BPF_K), + DL(BPF_JMP, BPF_EXIT, 0), + DL(BPF_STX, BPF_MEM, BPF_B), + DL(BPF_STX, BPF_MEM, BPF_H), + DL(BPF_STX, BPF_MEM, BPF_W), + DL(BPF_STX, BPF_MEM, BPF_DW), + DL(BPF_STX, BPF_XADD, BPF_W), + DL(BPF_STX, BPF_XADD, BPF_DW), + DL(BPF_ST, BPF_MEM, BPF_B), + DL(BPF_ST, BPF_MEM, BPF_H), + DL(BPF_ST, BPF_MEM, BPF_W), + DL(BPF_ST, BPF_MEM, BPF_DW), + DL(BPF_LDX, BPF_MEM, BPF_B), + DL(BPF_LDX, BPF_MEM, BPF_H), + DL(BPF_LDX, BPF_MEM, BPF_W), + DL(BPF_LDX, BPF_MEM, BPF_DW), + DL(BPF_LD, BPF_ABS, BPF_W), + DL(BPF_LD, BPF_ABS, BPF_H), + DL(BPF_LD, BPF_ABS, BPF_B), + DL(BPF_LD, BPF_IND, BPF_W), + DL(BPF_LD, BPF_IND, BPF_H), + DL(BPF_LD, BPF_IND, BPF_B), +#undef DL + }; + + regs[FP_REG] = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; + regs[ARG1_REG] = (u64) (unsigned long) ctx; + +select_insn: + goto *jumptable[insn->code]; + + /* ALU */ +#define ALU(OPCODE, OP) \ + BPF_ALU64_##OPCODE##_BPF_X: \ + A = A OP X; \ + CONT; \ + BPF_ALU_##OPCODE##_BPF_X: \ + A = (u32) A OP (u32) X; \ + CONT; \ + BPF_ALU64_##OPCODE##_BPF_K: \ + A = A OP K; \ + CONT; \ + BPF_ALU_##OPCODE##_BPF_K: \ + A = (u32) A OP (u32) K; \ + CONT; + + ALU(BPF_ADD, +) + ALU(BPF_SUB, -) + ALU(BPF_AND, &) + ALU(BPF_OR, |) + ALU(BPF_LSH, <<) + ALU(BPF_RSH, >>) + ALU(BPF_XOR, ^) + ALU(BPF_MUL, *) +#undef ALU + BPF_ALU_BPF_NEG_0: + A = (u32) -A; + CONT; + BPF_ALU64_BPF_NEG_0: + A = -A; + CONT; + BPF_ALU_BPF_MOV_BPF_X: + A = (u32) X; + CONT; + BPF_ALU_BPF_MOV_BPF_K: + A = (u32) K; + CONT; + BPF_ALU64_BPF_MOV_BPF_X: + A = X; + CONT; + BPF_ALU64_BPF_MOV_BPF_K: + A = K; + CONT; + BPF_ALU64_BPF_ARSH_BPF_X: + (*(s64 *) &A) >>= X; + CONT; + BPF_ALU64_BPF_ARSH_BPF_K: + (*(s64 *) &A) >>= K; + CONT; + BPF_ALU64_BPF_MOD_BPF_X: + tmp = A; + if (X) + A = do_div(tmp, X); + CONT; + BPF_ALU_BPF_MOD_BPF_X: + tmp = (u32) A; + if (X) + A = do_div(tmp, (u32) X); + CONT; + BPF_ALU64_BPF_MOD_BPF_K: + tmp = A; + if (K) + A = do_div(tmp, K); + CONT; + BPF_ALU_BPF_MOD_BPF_K: + tmp = (u32) A; + if (K) + A = do_div(tmp, (u32) K); + CONT; + BPF_ALU64_BPF_DIV_BPF_X: + if (X) + do_div(A, X); + CONT; + BPF_ALU_BPF_DIV_BPF_X: + tmp = (u32) A; + if (X) + do_div(tmp, (u32) X); + A = (u32) tmp; + CONT; + BPF_ALU64_BPF_DIV_BPF_K: + if (K) + do_div(A, K); + CONT; + BPF_ALU_BPF_DIV_BPF_K: + tmp = (u32) A; + if (K) + do_div(tmp, (u32) K); + A = (u32) tmp; + CONT; + BPF_ALU_BPF_END_BPF_TO_BE: + switch (K) { + case 16: + A = (__force u16) cpu_to_be16(A); + break; + case 32: + A = (__force u32) cpu_to_be32(A); + break; + case 64: + A = (__force u64) cpu_to_be64(A); + break; + } + CONT; + BPF_ALU_BPF_END_BPF_TO_LE: + switch (K) { + case 16: + A = (__force u16) cpu_to_le16(A); + break; + case 32: + A = (__force u32) cpu_to_le32(A); + break; + case 64: + A = (__force u64) cpu_to_le64(A); + break; + } + CONT; + + /* CALL */ + BPF_JMP_BPF_CALL_0: + /* Function call scratches R1-R5 registers, preserves R6-R9, + * and stores return value into R0. + */ + R0 = (__bpf_call_base + insn->imm)(regs[1], regs[2], regs[3], + regs[4], regs[5]); + CONT; + + /* JMP */ + BPF_JMP_BPF_JA_0: + insn += insn->off; + CONT; + BPF_JMP_BPF_JEQ_BPF_X: + if (A == X) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JEQ_BPF_K: + if (A == K) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JNE_BPF_X: + if (A != X) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JNE_BPF_K: + if (A != K) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JGT_BPF_X: + if (A > X) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JGT_BPF_K: + if (A > K) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JGE_BPF_X: + if (A >= X) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JGE_BPF_K: + if (A >= K) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSGT_BPF_X: + if (((s64)A) > ((s64)X)) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSGT_BPF_K: + if (((s64)A) > ((s64)K)) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSGE_BPF_X: + if (((s64)A) >= ((s64)X)) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSGE_BPF_K: + if (((s64)A) >= ((s64)K)) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSET_BPF_X: + if (A & X) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_JSET_BPF_K: + if (A & K) { + insn += insn->off; + CONT_JMP; + } + CONT; + BPF_JMP_BPF_EXIT_0: + return R0; + + /* STX and ST and LDX*/ +#define LDST(SIZEOP, SIZE) \ + BPF_STX_BPF_MEM_##SIZEOP: \ + *(SIZE *)(unsigned long) (A + insn->off) = X; \ + CONT; \ + BPF_ST_BPF_MEM_##SIZEOP: \ + *(SIZE *)(unsigned long) (A + insn->off) = K; \ + CONT; \ + BPF_LDX_BPF_MEM_##SIZEOP: \ + A = *(SIZE *)(unsigned long) (X + insn->off); \ + CONT; + + LDST(BPF_B, u8) + LDST(BPF_H, u16) + LDST(BPF_W, u32) + LDST(BPF_DW, u64) +#undef LDST + BPF_STX_BPF_XADD_BPF_W: /* lock xadd *(u32 *)(A + insn->off) += X */ + atomic_add((u32) X, (atomic_t *)(unsigned long) + (A + insn->off)); + CONT; + BPF_STX_BPF_XADD_BPF_DW: /* lock xadd *(u64 *)(A + insn->off) += X */ + atomic64_add((u64) X, (atomic64_t *)(unsigned long) + (A + insn->off)); + CONT; + BPF_LD_BPF_ABS_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + K)) */ + off = K; +load_word: + /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only + * appearing in the programs where ctx == skb. All programs + * keep 'ctx' in regs[CTX_REG] == R6, sk_convert_filter() + * saves it in R6, internal BPF verifier will check that + * R6 == ctx. + * + * BPF_ABS and BPF_IND are wrappers of function calls, so + * they scratch R1-R5 registers, preserve R6-R9, and store + * return value into R0. + * + * Implicit input: + * ctx + * + * Explicit input: + * X == any register + * K == 32-bit immediate + * + * Output: + * R0 - 8/16/32-bit skb data converted to cpu endianness + */ + ptr = load_pointer((struct sk_buff *) ctx, off, 4, &tmp); + if (likely(ptr != NULL)) { + R0 = get_unaligned_be32(ptr); + CONT; + } + return 0; + BPF_LD_BPF_ABS_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + K)) */ + off = K; +load_half: + ptr = load_pointer((struct sk_buff *) ctx, off, 2, &tmp); + if (likely(ptr != NULL)) { + R0 = get_unaligned_be16(ptr); + CONT; + } + return 0; + BPF_LD_BPF_ABS_BPF_B: /* R0 = *(u8 *) (ctx + K) */ + off = K; +load_byte: + ptr = load_pointer((struct sk_buff *) ctx, off, 1, &tmp); + if (likely(ptr != NULL)) { + R0 = *(u8 *)ptr; + CONT; + } + return 0; + BPF_LD_BPF_IND_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + X + K)) */ + off = K + X; + goto load_word; + BPF_LD_BPF_IND_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + X + K)) */ + off = K + X; + goto load_half; + BPF_LD_BPF_IND_BPF_B: /* R0 = *(u8 *) (skb->data + X + K) */ + off = K + X; + goto load_byte; + + default_label: + /* If we ever reach this, we have a bug somewhere. */ + WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); + return 0; +#undef CONT_JMP +#undef CONT + +#undef R0 +#undef X +#undef A +#undef K +} + +u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx, + const struct sock_filter_int *insni) + __attribute__ ((alias ("__sk_run_filter"))); + +u32 sk_run_filter_int_skb(const struct sk_buff *ctx, + const struct sock_filter_int *insni) + __attribute__ ((alias ("__sk_run_filter"))); +EXPORT_SYMBOL_GPL(sk_run_filter_int_skb); + +/* Helper to find the offset of pkt_type in sk_buff structure. We want + * to make sure its still a 3bit field starting at a byte boundary; + * taken from arch/x86/net/bpf_jit_comp.c. + */ +#define PKT_TYPE_MAX 7 +static unsigned int pkt_type_offset(void) +{ + struct sk_buff skb_probe = { .pkt_type = ~0, }; + u8 *ct = (u8 *) &skb_probe; + unsigned int off; + + for (off = 0; off < sizeof(struct sk_buff); off++) { + if (ct[off] == PKT_TYPE_MAX) + return off; + } + + pr_err_once("Please fix %s, as pkt_type couldn't be found!\n", __func__); + return -1; +} + +static u64 __skb_get_pay_offset(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(long) ctx; + + return __skb_get_poff(skb); +} + +static u64 __skb_get_nlattr(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(long) ctx; + struct nlattr *nla; + + if (skb_is_nonlinear(skb)) + return 0; + + if (A > skb->len - sizeof(struct nlattr)) + return 0; + + nla = nla_find((struct nlattr *) &skb->data[A], skb->len - A, X); + if (nla) + return (void *) nla - (void *) skb->data; + + return 0; +} + +static u64 __skb_get_nlattr_nest(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(long) ctx; + struct nlattr *nla; + + if (skb_is_nonlinear(skb)) + return 0; + + if (A > skb->len - sizeof(struct nlattr)) + return 0; + + nla = (struct nlattr *) &skb->data[A]; + if (nla->nla_len > A - skb->len) + return 0; + + nla = nla_find_nested(nla, X); + if (nla) + return (void *) nla - (void *) skb->data; + + return 0; +} + +static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +{ + return raw_smp_processor_id(); +} + +/* Register mappings for user programs. */ +#define A_REG 0 +#define X_REG 7 +#define TMP_REG 8 +#define ARG2_REG 2 +#define ARG3_REG 3 + +static bool convert_bpf_extensions(struct sock_filter *fp, + struct sock_filter_int **insnp) +{ + struct sock_filter_int *insn = *insnp; + + switch (fp->k) { + case SKF_AD_OFF + SKF_AD_PROTOCOL: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + + insn->code = BPF_LDX | BPF_MEM | BPF_H; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, protocol); + insn++; + + /* A = ntohs(A) [emitting a nop or swap16] */ + insn->code = BPF_ALU | BPF_END | BPF_FROM_BE; + insn->a_reg = A_REG; + insn->imm = 16; + break; + + case SKF_AD_OFF + SKF_AD_PKTTYPE: + insn->code = BPF_LDX | BPF_MEM | BPF_B; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = pkt_type_offset(); + if (insn->off < 0) + return false; + insn++; + + insn->code = BPF_ALU | BPF_AND | BPF_K; + insn->a_reg = A_REG; + insn->imm = PKT_TYPE_MAX; + break; + + case SKF_AD_OFF + SKF_AD_IFINDEX: + case SKF_AD_OFF + SKF_AD_HATYPE: + if (FIELD_SIZEOF(struct sk_buff, dev) == 8) + insn->code = BPF_LDX | BPF_MEM | BPF_DW; + else + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = TMP_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, dev); + insn++; + + insn->code = BPF_JMP | BPF_JNE | BPF_K; + insn->a_reg = TMP_REG; + insn->imm = 0; + insn->off = 1; + insn++; + + insn->code = BPF_JMP | BPF_EXIT; + insn++; + + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); + + insn->a_reg = A_REG; + insn->x_reg = TMP_REG; + + if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) { + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->off = offsetof(struct net_device, ifindex); + } else { + insn->code = BPF_LDX | BPF_MEM | BPF_H; + insn->off = offsetof(struct net_device, type); + } + break; + + case SKF_AD_OFF + SKF_AD_MARK: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, mark); + break; + + case SKF_AD_OFF + SKF_AD_RXHASH: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, hash); + break; + + case SKF_AD_OFF + SKF_AD_QUEUE: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + + insn->code = BPF_LDX | BPF_MEM | BPF_H; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, queue_mapping); + break; + + case SKF_AD_OFF + SKF_AD_VLAN_TAG: + case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + + insn->code = BPF_LDX | BPF_MEM | BPF_H; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, vlan_tci); + insn++; + + BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + + if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) { + insn->code = BPF_ALU | BPF_AND | BPF_K; + insn->a_reg = A_REG; + insn->imm = ~VLAN_TAG_PRESENT; + } else { + insn->code = BPF_ALU | BPF_RSH | BPF_K; + insn->a_reg = A_REG; + insn->imm = 12; + insn++; + + insn->code = BPF_ALU | BPF_AND | BPF_K; + insn->a_reg = A_REG; + insn->imm = 1; + } + break; + + case SKF_AD_OFF + SKF_AD_PAY_OFFSET: + case SKF_AD_OFF + SKF_AD_NLATTR: + case SKF_AD_OFF + SKF_AD_NLATTR_NEST: + case SKF_AD_OFF + SKF_AD_CPU: + /* arg1 = ctx */ + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = ARG1_REG; + insn->x_reg = CTX_REG; + insn++; + + /* arg2 = A */ + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = ARG2_REG; + insn->x_reg = A_REG; + insn++; + + /* arg3 = X */ + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = ARG3_REG; + insn->x_reg = X_REG; + insn++; + + /* Emit call(ctx, arg2=A, arg3=X) */ + insn->code = BPF_JMP | BPF_CALL; + switch (fp->k) { + case SKF_AD_OFF + SKF_AD_PAY_OFFSET: + insn->imm = __skb_get_pay_offset - __bpf_call_base; + break; + case SKF_AD_OFF + SKF_AD_NLATTR: + insn->imm = __skb_get_nlattr - __bpf_call_base; + break; + case SKF_AD_OFF + SKF_AD_NLATTR_NEST: + insn->imm = __skb_get_nlattr_nest - __bpf_call_base; + break; + case SKF_AD_OFF + SKF_AD_CPU: + insn->imm = __get_raw_cpu_id - __bpf_call_base; + break; + } + break; + + case SKF_AD_OFF + SKF_AD_ALU_XOR_X: + insn->code = BPF_ALU | BPF_XOR | BPF_X; + insn->a_reg = A_REG; + insn->x_reg = X_REG; + break; + + default: + /* This is just a dummy call to avoid letting the compiler + * evict __bpf_call_base() as an optimization. Placed here + * where no-one bothers. + */ + BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0); + return false; + } + + *insnp = insn; + return true; +} + +/** + * sk_convert_filter - convert filter program + * @prog: the user passed filter program + * @len: the length of the user passed filter program + * @new_prog: buffer where converted program will be stored + * @new_len: pointer to store length of converted program + * + * Remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style. + * Conversion workflow: + * + * 1) First pass for calculating the new program length: + * sk_convert_filter(old_prog, old_len, NULL, &new_len) + * + * 2) 2nd pass to remap in two passes: 1st pass finds new + * jump offsets, 2nd pass remapping: + * new_prog = kmalloc(sizeof(struct sock_filter_int) * new_len); + * sk_convert_filter(old_prog, old_len, new_prog, &new_len); + * + * User BPF's register A is mapped to our BPF register 6, user BPF + * register X is mapped to BPF register 7; frame pointer is always + * register 10; Context 'void *ctx' is stored in register 1, that is, + * for socket filters: ctx == 'struct sk_buff *', for seccomp: + * ctx == 'struct seccomp_data *'. + */ +int sk_convert_filter(struct sock_filter *prog, int len, + struct sock_filter_int *new_prog, int *new_len) +{ + int new_flen = 0, pass = 0, target, i; + struct sock_filter_int *new_insn; + struct sock_filter *fp; + int *addrs = NULL; + u8 bpf_src; + + BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK); + BUILD_BUG_ON(FP_REG + 1 != MAX_BPF_REG); + + if (len <= 0 || len >= BPF_MAXINSNS) + return -EINVAL; + + if (new_prog) { + addrs = kzalloc(len * sizeof(*addrs), GFP_KERNEL); + if (!addrs) + return -ENOMEM; + } + +do_pass: + new_insn = new_prog; + fp = prog; + + if (new_insn) { + new_insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + new_insn->a_reg = CTX_REG; + new_insn->x_reg = ARG1_REG; + } + new_insn++; + + for (i = 0; i < len; fp++, i++) { + struct sock_filter_int tmp_insns[6] = { }; + struct sock_filter_int *insn = tmp_insns; + + if (addrs) + addrs[i] = new_insn - new_prog; + + switch (fp->code) { + /* All arithmetic insns and skb loads map as-is. */ + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU | BPF_MOD | BPF_K: + case BPF_ALU | BPF_NEG: + case BPF_LD | BPF_ABS | BPF_W: + case BPF_LD | BPF_ABS | BPF_H: + case BPF_LD | BPF_ABS | BPF_B: + case BPF_LD | BPF_IND | BPF_W: + case BPF_LD | BPF_IND | BPF_H: + case BPF_LD | BPF_IND | BPF_B: + /* Check for overloaded BPF extension and + * directly convert it if found, otherwise + * just move on with mapping. + */ + if (BPF_CLASS(fp->code) == BPF_LD && + BPF_MODE(fp->code) == BPF_ABS && + convert_bpf_extensions(fp, &insn)) + break; + + insn->code = fp->code; + insn->a_reg = A_REG; + insn->x_reg = X_REG; + insn->imm = fp->k; + break; + + /* Jump opcodes map as-is, but offsets need adjustment. */ + case BPF_JMP | BPF_JA: + target = i + fp->k + 1; + insn->code = fp->code; +#define EMIT_JMP \ + do { \ + if (target >= len || target < 0) \ + goto err; \ + insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0; \ + /* Adjust pc relative offset for 2nd or 3rd insn. */ \ + insn->off -= insn - tmp_insns; \ + } while (0) + + EMIT_JMP; + break; + + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) { + /* BPF immediates are signed, zero extend + * immediate into tmp register and use it + * in compare insn. + */ + insn->code = BPF_ALU | BPF_MOV | BPF_K; + insn->a_reg = TMP_REG; + insn->imm = fp->k; + insn++; + + insn->a_reg = A_REG; + insn->x_reg = TMP_REG; + bpf_src = BPF_X; + } else { + insn->a_reg = A_REG; + insn->x_reg = X_REG; + insn->imm = fp->k; + bpf_src = BPF_SRC(fp->code); } - return 0; - case BPF_S_LD_B_ABS: - k = K; -load_b: - ptr = load_pointer(skb, k, 1, &tmp); - if (ptr != NULL) { - A = *(u8 *)ptr; - continue; + + /* Common case where 'jump_false' is next insn. */ + if (fp->jf == 0) { + insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; + target = i + fp->jt + 1; + EMIT_JMP; + break; } - return 0; - case BPF_S_LD_W_LEN: - A = skb->len; - continue; - case BPF_S_LDX_W_LEN: - X = skb->len; - continue; - case BPF_S_LD_W_IND: - k = X + K; - goto load_w; - case BPF_S_LD_H_IND: - k = X + K; - goto load_h; - case BPF_S_LD_B_IND: - k = X + K; - goto load_b; - case BPF_S_LDX_B_MSH: - ptr = load_pointer(skb, K, 1, &tmp); - if (ptr != NULL) { - X = (*(u8 *)ptr & 0xf) << 2; - continue; + + /* Convert JEQ into JNE when 'jump_true' is next insn. */ + if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) { + insn->code = BPF_JMP | BPF_JNE | bpf_src; + target = i + fp->jf + 1; + EMIT_JMP; + break; } - return 0; - case BPF_S_LD_IMM: - A = K; - continue; - case BPF_S_LDX_IMM: - X = K; - continue; - case BPF_S_LD_MEM: - A = mem[K]; - continue; - case BPF_S_LDX_MEM: - X = mem[K]; - continue; - case BPF_S_MISC_TAX: - X = A; - continue; - case BPF_S_MISC_TXA: - A = X; - continue; - case BPF_S_RET_K: - return K; - case BPF_S_RET_A: - return A; - case BPF_S_ST: - mem[K] = A; - continue; - case BPF_S_STX: - mem[K] = X; - continue; - case BPF_S_ANC_PROTOCOL: - A = ntohs(skb->protocol); - continue; - case BPF_S_ANC_PKTTYPE: - A = skb->pkt_type; - continue; - case BPF_S_ANC_IFINDEX: - if (!skb->dev) - return 0; - A = skb->dev->ifindex; - continue; - case BPF_S_ANC_MARK: - A = skb->mark; - continue; - case BPF_S_ANC_QUEUE: - A = skb->queue_mapping; - continue; - case BPF_S_ANC_HATYPE: - if (!skb->dev) - return 0; - A = skb->dev->type; - continue; - case BPF_S_ANC_RXHASH: - A = skb->rxhash; - continue; - case BPF_S_ANC_CPU: - A = raw_smp_processor_id(); - continue; - case BPF_S_ANC_VLAN_TAG: - A = vlan_tx_tag_get(skb); - continue; - case BPF_S_ANC_VLAN_TAG_PRESENT: - A = !!vlan_tx_tag_present(skb); - continue; - case BPF_S_ANC_PAY_OFFSET: - A = __skb_get_poff(skb); - continue; - case BPF_S_ANC_NLATTR: { - struct nlattr *nla; - - if (skb_is_nonlinear(skb)) - return 0; - if (A > skb->len - sizeof(struct nlattr)) - return 0; - - nla = nla_find((struct nlattr *)&skb->data[A], - skb->len - A, X); - if (nla) - A = (void *)nla - (void *)skb->data; - else - A = 0; - continue; - } - case BPF_S_ANC_NLATTR_NEST: { - struct nlattr *nla; - - if (skb_is_nonlinear(skb)) - return 0; - if (A > skb->len - sizeof(struct nlattr)) - return 0; - - nla = (struct nlattr *)&skb->data[A]; - if (nla->nla_len > A - skb->len) - return 0; - - nla = nla_find_nested(nla, X); - if (nla) - A = (void *)nla - (void *)skb->data; - else - A = 0; - continue; - } -#ifdef CONFIG_SECCOMP_FILTER - case BPF_S_ANC_SECCOMP_LD_W: - A = seccomp_bpf_load(fentry->k); - continue; -#endif + + /* Other jumps are mapped into two insns: Jxx and JA. */ + target = i + fp->jt + 1; + insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; + EMIT_JMP; + insn++; + + insn->code = BPF_JMP | BPF_JA; + target = i + fp->jf + 1; + EMIT_JMP; + break; + + /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ + case BPF_LDX | BPF_MSH | BPF_B: + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = TMP_REG; + insn->x_reg = A_REG; + insn++; + + insn->code = BPF_LD | BPF_ABS | BPF_B; + insn->a_reg = A_REG; + insn->imm = fp->k; + insn++; + + insn->code = BPF_ALU | BPF_AND | BPF_K; + insn->a_reg = A_REG; + insn->imm = 0xf; + insn++; + + insn->code = BPF_ALU | BPF_LSH | BPF_K; + insn->a_reg = A_REG; + insn->imm = 2; + insn++; + + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = X_REG; + insn->x_reg = A_REG; + insn++; + + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = A_REG; + insn->x_reg = TMP_REG; + break; + + /* RET_K, RET_A are remaped into 2 insns. */ + case BPF_RET | BPF_A: + case BPF_RET | BPF_K: + insn->code = BPF_ALU | BPF_MOV | + (BPF_RVAL(fp->code) == BPF_K ? + BPF_K : BPF_X); + insn->a_reg = 0; + insn->x_reg = A_REG; + insn->imm = fp->k; + insn++; + + insn->code = BPF_JMP | BPF_EXIT; + break; + + /* Store to stack. */ + case BPF_ST: + case BPF_STX: + insn->code = BPF_STX | BPF_MEM | BPF_W; + insn->a_reg = FP_REG; + insn->x_reg = fp->code == BPF_ST ? A_REG : X_REG; + insn->off = -(BPF_MEMWORDS - fp->k) * 4; + break; + + /* Load from stack. */ + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? + A_REG : X_REG; + insn->x_reg = FP_REG; + insn->off = -(BPF_MEMWORDS - fp->k) * 4; + break; + + /* A = K or X = K */ + case BPF_LD | BPF_IMM: + case BPF_LDX | BPF_IMM: + insn->code = BPF_ALU | BPF_MOV | BPF_K; + insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? + A_REG : X_REG; + insn->imm = fp->k; + break; + + /* X = A */ + case BPF_MISC | BPF_TAX: + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = X_REG; + insn->x_reg = A_REG; + break; + + /* A = X */ + case BPF_MISC | BPF_TXA: + insn->code = BPF_ALU64 | BPF_MOV | BPF_X; + insn->a_reg = A_REG; + insn->x_reg = X_REG; + break; + + /* A = skb->len or X = skb->len */ + case BPF_LD | BPF_W | BPF_LEN: + case BPF_LDX | BPF_W | BPF_LEN: + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? + A_REG : X_REG; + insn->x_reg = CTX_REG; + insn->off = offsetof(struct sk_buff, len); + break; + + /* access seccomp_data fields */ + case BPF_LDX | BPF_ABS | BPF_W: + insn->code = BPF_LDX | BPF_MEM | BPF_W; + insn->a_reg = A_REG; + insn->x_reg = CTX_REG; + insn->off = fp->k; + break; + default: - WARN_RATELIMIT(1, "Unknown code:%u jt:%u tf:%u k:%u\n", - fentry->code, fentry->jt, - fentry->jf, fentry->k); - return 0; + goto err; } + + insn++; + if (new_prog) + memcpy(new_insn, tmp_insns, + sizeof(*insn) * (insn - tmp_insns)); + + new_insn += insn - tmp_insns; + } + + if (!new_prog) { + /* Only calculating new length. */ + *new_len = new_insn - new_prog; + return 0; } + pass++; + if (new_flen != new_insn - new_prog) { + new_flen = new_insn - new_prog; + if (pass > 2) + goto err; + + goto do_pass; + } + + kfree(addrs); + BUG_ON(*new_len != new_flen); return 0; +err: + kfree(addrs); + return -EINVAL; } -EXPORT_SYMBOL(sk_run_filter); -/* - * Security : +/* Security: + * * A BPF program is able to use 16 cells of memory to store intermediate - * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()) + * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()). + * * As we dont want to clear mem[] array for each packet going through * sk_run_filter(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure @@ -629,30 +1375,197 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) } EXPORT_SYMBOL(sk_chk_filter); +static int sk_store_orig_filter(struct sk_filter *fp, + const struct sock_fprog *fprog) +{ + unsigned int fsize = sk_filter_proglen(fprog); + struct sock_fprog_kern *fkprog; + + fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL); + if (!fp->orig_prog) + return -ENOMEM; + + fkprog = fp->orig_prog; + fkprog->len = fprog->len; + fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL); + if (!fkprog->filter) { + kfree(fp->orig_prog); + return -ENOMEM; + } + + return 0; +} + +static void sk_release_orig_filter(struct sk_filter *fp) +{ + struct sock_fprog_kern *fprog = fp->orig_prog; + + if (fprog) { + kfree(fprog->filter); + kfree(fprog); + } +} + /** * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free */ -void sk_filter_release_rcu(struct rcu_head *rcu) +static void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); + sk_release_orig_filter(fp); bpf_jit_free(fp); } -EXPORT_SYMBOL(sk_filter_release_rcu); -static int __sk_prepare_filter(struct sk_filter *fp) +/** + * sk_filter_release - release a socket filter + * @fp: filter to remove + * + * Remove a filter from a socket and release its resources. + */ +static void sk_filter_release(struct sk_filter *fp) +{ + if (atomic_dec_and_test(&fp->refcnt)) + call_rcu(&fp->rcu, sk_filter_release_rcu); +} + +void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) +{ + atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc); + sk_filter_release(fp); +} + +void sk_filter_charge(struct sock *sk, struct sk_filter *fp) +{ + atomic_inc(&fp->refcnt); + atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc); +} + +static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp, + struct sock *sk, + unsigned int len) +{ + struct sk_filter *fp_new; + + if (sk == NULL) + return krealloc(fp, len, GFP_KERNEL); + + fp_new = sock_kmalloc(sk, len, GFP_KERNEL); + if (fp_new) { + memcpy(fp_new, fp, sizeof(struct sk_filter)); + /* As we're kepping orig_prog in fp_new along, + * we need to make sure we're not evicting it + * from the old fp. + */ + fp->orig_prog = NULL; + sk_filter_uncharge(sk, fp); + } + + return fp_new; +} + +static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, + struct sock *sk) +{ + struct sock_filter *old_prog; + struct sk_filter *old_fp; + int i, err, new_len, old_len = fp->len; + + /* We are free to overwrite insns et al right here as it + * won't be used at this point in time anymore internally + * after the migration to the internal BPF instruction + * representation. + */ + BUILD_BUG_ON(sizeof(struct sock_filter) != + sizeof(struct sock_filter_int)); + + /* For now, we need to unfiddle BPF_S_* identifiers in place. + * This can sooner or later on be subject to removal, e.g. when + * JITs have been converted. + */ + for (i = 0; i < fp->len; i++) + sk_decode_filter(&fp->insns[i], &fp->insns[i]); + + /* Conversion cannot happen on overlapping memory areas, + * so we need to keep the user BPF around until the 2nd + * pass. At this time, the user BPF is stored in fp->insns. + */ + old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter), + GFP_KERNEL); + if (!old_prog) { + err = -ENOMEM; + goto out_err; + } + + /* 1st pass: calculate the new program length. */ + err = sk_convert_filter(old_prog, old_len, NULL, &new_len); + if (err) + goto out_err_free; + + /* Expand fp for appending the new filter representation. */ + old_fp = fp; + fp = __sk_migrate_realloc(old_fp, sk, sk_filter_size(new_len)); + if (!fp) { + /* The old_fp is still around in case we couldn't + * allocate new memory, so uncharge on that one. + */ + fp = old_fp; + err = -ENOMEM; + goto out_err_free; + } + + fp->bpf_func = sk_run_filter_int_skb; + fp->len = new_len; + + /* 2nd pass: remap sock_filter insns into sock_filter_int insns. */ + err = sk_convert_filter(old_prog, old_len, fp->insnsi, &new_len); + if (err) + /* 2nd sk_convert_filter() can fail only if it fails + * to allocate memory, remapping must succeed. Note, + * that at this time old_fp has already been released + * by __sk_migrate_realloc(). + */ + goto out_err_free; + + kfree(old_prog); + return fp; + +out_err_free: + kfree(old_prog); +out_err: + /* Rollback filter setup. */ + if (sk != NULL) + sk_filter_uncharge(sk, fp); + else + kfree(fp); + return ERR_PTR(err); +} + +static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, + struct sock *sk) { int err; - fp->bpf_func = sk_run_filter; + fp->bpf_func = NULL; + fp->jited = 0; err = sk_chk_filter(fp->insns, fp->len); if (err) - return err; + return ERR_PTR(err); + /* Probe if we can JIT compile the filter and if so, do + * the compilation of the filter. + */ bpf_jit_compile(fp); - return 0; + + /* JIT compiler couldn't process this filter, so do the + * internal BPF translation for the optimized interpreter. + */ + if (!fp->jited) + fp = __sk_migrate_filter(fp, sk); + + return fp; } /** @@ -668,9 +1581,8 @@ static int __sk_prepare_filter(struct sk_filter *fp) int sk_unattached_filter_create(struct sk_filter **pfp, struct sock_fprog *fprog) { + unsigned int fsize = sk_filter_proglen(fprog); struct sk_filter *fp; - unsigned int fsize = sizeof(struct sock_filter) * fprog->len; - int err; /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) @@ -679,20 +1591,26 @@ int sk_unattached_filter_create(struct sk_filter **pfp, fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL); if (!fp) return -ENOMEM; + memcpy(fp->insns, fprog->filter, fsize); atomic_set(&fp->refcnt, 1); fp->len = fprog->len; + /* Since unattached filters are not copied back to user + * space through sk_get_filter(), we do not need to hold + * a copy here, and can spare us the work. + */ + fp->orig_prog = NULL; - err = __sk_prepare_filter(fp); - if (err) - goto free_mem; + /* __sk_prepare_filter() already takes care of uncharging + * memory in case something goes wrong. + */ + fp = __sk_prepare_filter(fp, NULL); + if (IS_ERR(fp)) + return PTR_ERR(fp); *pfp = fp; return 0; -free_mem: - kfree(fp); - return err; } EXPORT_SYMBOL_GPL(sk_unattached_filter_create); @@ -715,7 +1633,7 @@ EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct sk_filter *fp, *old_fp; - unsigned int fsize = sizeof(struct sock_filter) * fprog->len; + unsigned int fsize = sk_filter_proglen(fprog); unsigned int sk_fsize = sk_filter_size(fprog->len); int err; @@ -729,6 +1647,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL); if (!fp) return -ENOMEM; + if (copy_from_user(fp->insns, fprog->filter, fsize)) { sock_kfree_s(sk, fp, sk_fsize); return -EFAULT; @@ -737,18 +1656,26 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) atomic_set(&fp->refcnt, 1); fp->len = fprog->len; - err = __sk_prepare_filter(fp); + err = sk_store_orig_filter(fp, fprog); if (err) { sk_filter_uncharge(sk, fp); - return err; + return -ENOMEM; } + /* __sk_prepare_filter() already takes care of uncharging + * memory in case something goes wrong. + */ + fp = __sk_prepare_filter(fp, sk); + if (IS_ERR(fp)) + return PTR_ERR(fp); + old_fp = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) sk_filter_uncharge(sk, old_fp); + return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); @@ -768,6 +1695,7 @@ int sk_detach_filter(struct sock *sk) sk_filter_uncharge(sk, filter); ret = 0; } + return ret; } EXPORT_SYMBOL_GPL(sk_detach_filter); @@ -850,34 +1778,41 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to) to->k = filt->k; } -int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) +int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, + unsigned int len) { + struct sock_fprog_kern *fprog; struct sk_filter *filter; - int i, ret; + int ret = 0; lock_sock(sk); filter = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); - ret = 0; + sock_owned_by_user(sk)); if (!filter) goto out; - ret = filter->len; + + /* We're copying the filter that has been originally attached, + * so no conversion/decode needed anymore. + */ + fprog = filter->orig_prog; + + ret = fprog->len; if (!len) + /* User space only enquires number of filter blocks. */ goto out; + ret = -EINVAL; - if (len < filter->len) + if (len < fprog->len) goto out; ret = -EFAULT; - for (i = 0; i < filter->len; i++) { - struct sock_filter fb; - - sk_decode_filter(&filter->insns[i], &fb); - if (copy_to_user(&ubuf[i], &fb, sizeof(fb))) - goto out; - } + if (copy_to_user(ubuf, fprog->filter, sk_filter_proglen(fprog))) + goto out; - ret = filter->len; + /* Instead of bytes, the API requests to return the number + * of filter blocks. + */ + ret = fprog->len; out: release_sock(sk); return ret; diff --git a/net/core/flow.c b/net/core/flow.c index dfa602ceb8cd..31cfb365e0c6 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -24,6 +24,7 @@ #include <net/flow.h> #include <linux/atomic.h> #include <linux/security.h> +#include <net/net_namespace.h> struct flow_cache_entry { union { @@ -38,37 +39,14 @@ struct flow_cache_entry { struct flow_cache_object *object; }; -struct flow_cache_percpu { - struct hlist_head *hash_table; - int hash_count; - u32 hash_rnd; - int hash_rnd_recalc; - struct tasklet_struct flush_tasklet; -}; - struct flow_flush_info { struct flow_cache *cache; atomic_t cpuleft; struct completion completion; }; -struct flow_cache { - u32 hash_shift; - struct flow_cache_percpu __percpu *percpu; - struct notifier_block hotcpu_notifier; - int low_watermark; - int high_watermark; - struct timer_list rnd_timer; -}; - -atomic_t flow_cache_genid = ATOMIC_INIT(0); -EXPORT_SYMBOL(flow_cache_genid); -static struct flow_cache flow_cache_global; static struct kmem_cache *flow_cachep __read_mostly; -static DEFINE_SPINLOCK(flow_cache_gc_lock); -static LIST_HEAD(flow_cache_gc_list); - #define flow_cache_hash_size(cache) (1 << (cache)->hash_shift) #define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) @@ -84,16 +62,18 @@ static void flow_cache_new_hashrnd(unsigned long arg) add_timer(&fc->rnd_timer); } -static int flow_entry_valid(struct flow_cache_entry *fle) +static int flow_entry_valid(struct flow_cache_entry *fle, + struct netns_xfrm *xfrm) { - if (atomic_read(&flow_cache_genid) != fle->genid) + if (atomic_read(&xfrm->flow_cache_genid) != fle->genid) return 0; if (fle->object && !fle->object->ops->check(fle->object)) return 0; return 1; } -static void flow_entry_kill(struct flow_cache_entry *fle) +static void flow_entry_kill(struct flow_cache_entry *fle, + struct netns_xfrm *xfrm) { if (fle->object) fle->object->ops->delete(fle->object); @@ -104,26 +84,28 @@ static void flow_cache_gc_task(struct work_struct *work) { struct list_head gc_list; struct flow_cache_entry *fce, *n; + struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm, + flow_cache_gc_work); INIT_LIST_HEAD(&gc_list); - spin_lock_bh(&flow_cache_gc_lock); - list_splice_tail_init(&flow_cache_gc_list, &gc_list); - spin_unlock_bh(&flow_cache_gc_lock); + spin_lock_bh(&xfrm->flow_cache_gc_lock); + list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list); + spin_unlock_bh(&xfrm->flow_cache_gc_lock); list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) - flow_entry_kill(fce); + flow_entry_kill(fce, xfrm); } -static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task); static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, - int deleted, struct list_head *gc_list) + int deleted, struct list_head *gc_list, + struct netns_xfrm *xfrm) { if (deleted) { fcp->hash_count -= deleted; - spin_lock_bh(&flow_cache_gc_lock); - list_splice_tail(gc_list, &flow_cache_gc_list); - spin_unlock_bh(&flow_cache_gc_lock); - schedule_work(&flow_cache_gc_work); + spin_lock_bh(&xfrm->flow_cache_gc_lock); + list_splice_tail(gc_list, &xfrm->flow_cache_gc_list); + spin_unlock_bh(&xfrm->flow_cache_gc_lock); + schedule_work(&xfrm->flow_cache_gc_work); } } @@ -135,6 +117,8 @@ static void __flow_cache_shrink(struct flow_cache *fc, struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; + struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm, + flow_cache_global); for (i = 0; i < flow_cache_hash_size(fc); i++) { int saved = 0; @@ -142,7 +126,7 @@ static void __flow_cache_shrink(struct flow_cache *fc, hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { if (saved < shrink_to && - flow_entry_valid(fle)) { + flow_entry_valid(fle, xfrm)) { saved++; } else { deleted++; @@ -152,7 +136,7 @@ static void __flow_cache_shrink(struct flow_cache *fc, } } - flow_cache_queue_garbage(fcp, deleted, &gc_list); + flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm); } static void flow_cache_shrink(struct flow_cache *fc, @@ -208,7 +192,7 @@ struct flow_cache_object * flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver, void *ctx) { - struct flow_cache *fc = &flow_cache_global; + struct flow_cache *fc = &net->xfrm.flow_cache_global; struct flow_cache_percpu *fcp; struct flow_cache_entry *fle, *tfle; struct flow_cache_object *flo; @@ -258,7 +242,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]); fcp->hash_count++; } - } else if (likely(fle->genid == atomic_read(&flow_cache_genid))) { + } else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) { flo = fle->object; if (!flo) goto ret_object; @@ -279,7 +263,7 @@ nocache: } flo = resolver(net, key, family, dir, flo, ctx); if (fle) { - fle->genid = atomic_read(&flow_cache_genid); + fle->genid = atomic_read(&net->xfrm.flow_cache_genid); if (!IS_ERR(flo)) fle->object = flo; else @@ -303,12 +287,14 @@ static void flow_cache_flush_tasklet(unsigned long data) struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; + struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm, + flow_cache_global); fcp = this_cpu_ptr(fc->percpu); for (i = 0; i < flow_cache_hash_size(fc); i++) { hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { - if (flow_entry_valid(fle)) + if (flow_entry_valid(fle, xfrm)) continue; deleted++; @@ -317,7 +303,7 @@ static void flow_cache_flush_tasklet(unsigned long data) } } - flow_cache_queue_garbage(fcp, deleted, &gc_list); + flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm); if (atomic_dec_and_test(&info->cpuleft)) complete(&info->completion); @@ -351,10 +337,9 @@ static void flow_cache_flush_per_cpu(void *data) tasklet_schedule(tasklet); } -void flow_cache_flush(void) +void flow_cache_flush(struct net *net) { struct flow_flush_info info; - static DEFINE_MUTEX(flow_flush_sem); cpumask_var_t mask; int i, self; @@ -365,8 +350,8 @@ void flow_cache_flush(void) /* Don't want cpus going down or up during this. */ get_online_cpus(); - mutex_lock(&flow_flush_sem); - info.cache = &flow_cache_global; + mutex_lock(&net->xfrm.flow_flush_sem); + info.cache = &net->xfrm.flow_cache_global; for_each_online_cpu(i) if (!flow_cache_percpu_empty(info.cache, i)) cpumask_set_cpu(i, mask); @@ -386,21 +371,23 @@ void flow_cache_flush(void) wait_for_completion(&info.completion); done: - mutex_unlock(&flow_flush_sem); + mutex_unlock(&net->xfrm.flow_flush_sem); put_online_cpus(); free_cpumask_var(mask); } static void flow_cache_flush_task(struct work_struct *work) { - flow_cache_flush(); -} + struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm, + flow_cache_gc_work); + struct net *net = container_of(xfrm, struct net, xfrm); -static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task); + flow_cache_flush(net); +} -void flow_cache_flush_deferred(void) +void flow_cache_flush_deferred(struct net *net) { - schedule_work(&flow_cache_flush_work); + schedule_work(&net->xfrm.flow_cache_flush_work); } static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) @@ -425,7 +412,8 @@ static int flow_cache_cpu(struct notifier_block *nfb, unsigned long action, void *hcpu) { - struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier); + struct flow_cache *fc = container_of(nfb, struct flow_cache, + hotcpu_notifier); int res, cpu = (unsigned long) hcpu; struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); @@ -444,9 +432,20 @@ static int flow_cache_cpu(struct notifier_block *nfb, return NOTIFY_OK; } -static int __init flow_cache_init(struct flow_cache *fc) +int flow_cache_init(struct net *net) { int i; + struct flow_cache *fc = &net->xfrm.flow_cache_global; + + if (!flow_cachep) + flow_cachep = kmem_cache_create("flow_cache", + sizeof(struct flow_cache_entry), + 0, SLAB_PANIC, NULL); + spin_lock_init(&net->xfrm.flow_cache_gc_lock); + INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list); + INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task); + INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task); + mutex_init(&net->xfrm.flow_flush_sem); fc->hash_shift = 10; fc->low_watermark = 2 * flow_cache_hash_size(fc); @@ -484,14 +483,23 @@ err: return -ENOMEM; } +EXPORT_SYMBOL(flow_cache_init); -static int __init flow_cache_init_global(void) +void flow_cache_fini(struct net *net) { - flow_cachep = kmem_cache_create("flow_cache", - sizeof(struct flow_cache_entry), - 0, SLAB_PANIC, NULL); + int i; + struct flow_cache *fc = &net->xfrm.flow_cache_global; - return flow_cache_init(&flow_cache_global); -} + del_timer_sync(&fc->rnd_timer); + unregister_hotcpu_notifier(&fc->hotcpu_notifier); -module_init(flow_cache_init_global); + for_each_possible_cpu(i) { + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i); + kfree(fcp->hash_table); + fcp->hash_table = NULL; + } + + free_percpu(fc->percpu); + fc->percpu = NULL; +} +EXPORT_SYMBOL(flow_cache_fini); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index e29e810663d7..107ed12a5323 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -61,7 +61,7 @@ bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow) again: switch (proto) { - case __constant_htons(ETH_P_IP): { + case htons(ETH_P_IP): { const struct iphdr *iph; struct iphdr _iph; ip: @@ -77,7 +77,7 @@ ip: iph_to_flow_copy_addrs(flow, iph); break; } - case __constant_htons(ETH_P_IPV6): { + case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; ipv6: @@ -91,8 +91,8 @@ ipv6: nhoff += sizeof(struct ipv6hdr); break; } - case __constant_htons(ETH_P_8021AD): - case __constant_htons(ETH_P_8021Q): { + case htons(ETH_P_8021AD): + case htons(ETH_P_8021Q): { const struct vlan_hdr *vlan; struct vlan_hdr _vlan; @@ -104,7 +104,7 @@ ipv6: nhoff += sizeof(*vlan); goto again; } - case __constant_htons(ETH_P_PPP_SES): { + case htons(ETH_P_PPP_SES): { struct { struct pppoe_hdr hdr; __be16 proto; @@ -115,9 +115,9 @@ ipv6: proto = hdr->proto; nhoff += PPPOE_SES_HLEN; switch (proto) { - case __constant_htons(PPP_IP): + case htons(PPP_IP): goto ip; - case __constant_htons(PPP_IPV6): + case htons(PPP_IPV6): goto ipv6; default: return false; @@ -203,8 +203,8 @@ static __always_inline u32 __flow_hash_1word(u32 a) /* * __skb_get_hash: calculate a flow hash based on src/dst addresses - * and src/dst port numbers. Sets rxhash in skb to non-zero hash value - * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb + * and src/dst port numbers. Sets hash in skb to non-zero hash value + * on success, zero indicates no valid hash. Also, sets l4_hash in skb * if hash is a canonical 4-tuple hash over transport ports. */ void __skb_get_hash(struct sk_buff *skb) @@ -216,7 +216,7 @@ void __skb_get_hash(struct sk_buff *skb) return; if (keys.ports) - skb->l4_rxhash = 1; + skb->l4_hash = 1; /* get a consistent hash (same value on both flow directions) */ if (((__force u32)keys.dst < (__force u32)keys.src) || @@ -232,7 +232,7 @@ void __skb_get_hash(struct sk_buff *skb) if (!hash) hash = 1; - skb->rxhash = hash; + skb->hash = hash; } EXPORT_SYMBOL(__skb_get_hash); @@ -344,7 +344,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) hash = skb->sk->sk_hash; else hash = (__force u16) skb->protocol ^ - skb->rxhash; + skb->hash; hash = __flow_hash_1word(hash); queue_index = map->queues[ ((u64)hash * map->len) >> 32]; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e16129019c66..8f8a96ef9f3f 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -836,10 +836,10 @@ out: static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; - return (n->nud_state & NUD_PROBE) ? - NEIGH_VAR(p, UCAST_PROBES) : - NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) + - NEIGH_VAR(p, MCAST_PROBES); + int max_probes = NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES); + if (!(n->nud_state & NUD_PROBE)) + max_probes += NEIGH_VAR(p, MCAST_PROBES); + return max_probes; } static void neigh_invalidate(struct neighbour *neigh) @@ -945,6 +945,7 @@ static void neigh_timer_handler(unsigned long arg) neigh->nud_state = NUD_FAILED; notify = 1; neigh_invalidate(neigh); + goto out; } if (neigh->nud_state & NUD_IN_TIMER) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 549043c078c9..1cac29ebb05b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -104,6 +104,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, } NETDEVICE_SHOW_RO(dev_id, fmt_hex); +NETDEVICE_SHOW_RO(dev_port, fmt_dec); NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); NETDEVICE_SHOW_RO(addr_len, fmt_dec); NETDEVICE_SHOW_RO(iflink, fmt_dec); @@ -252,6 +253,16 @@ static ssize_t operstate_show(struct device *dev, } static DEVICE_ATTR_RO(operstate); +static ssize_t carrier_changes_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + return sprintf(buf, fmt_dec, + atomic_read(&netdev->carrier_changes)); +} +static DEVICE_ATTR_RO(carrier_changes); + /* read-write attributes */ static int change_mtu(struct net_device *net, unsigned long new_mtu) @@ -373,6 +384,7 @@ static struct attribute *net_class_attrs[] = { &dev_attr_netdev_group.attr, &dev_attr_type.attr, &dev_attr_dev_id.attr, + &dev_attr_dev_port.attr, &dev_attr_iflink.attr, &dev_attr_ifindex.attr, &dev_attr_addr_assign_type.attr, @@ -384,6 +396,7 @@ static struct attribute *net_class_attrs[] = { &dev_attr_duplex.attr, &dev_attr_dormant.attr, &dev_attr_operstate.attr, + &dev_attr_carrier_changes.attr, &dev_attr_ifalias.attr, &dev_attr_carrier.attr, &dev_attr_mtu.attr, @@ -996,15 +1009,12 @@ static struct attribute_group dql_group = { #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS -static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) +static unsigned int get_netdev_queue_index(struct netdev_queue *queue) { struct net_device *dev = queue->dev; - int i; - - for (i = 0; i < dev->num_tx_queues; i++) - if (queue == &dev->_tx[i]) - break; + unsigned int i; + i = queue - dev->_tx; BUG_ON(i >= dev->num_tx_queues); return i; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index df9e6b1a9759..e33937fb32a0 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -46,13 +46,9 @@ static struct sk_buff_head skb_pool; -static atomic_t trapped; - DEFINE_STATIC_SRCU(netpoll_srcu); #define USEC_PER_POLL 50 -#define NETPOLL_RX_ENABLED 1 -#define NETPOLL_RX_DROP 2 #define MAX_SKB_SIZE \ (sizeof(struct ethhdr) + \ @@ -61,7 +57,6 @@ DEFINE_STATIC_SRCU(netpoll_srcu); MAX_UDP_CHUNK) static void zap_completion_queue(void); -static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo); static void netpoll_async_cleanup(struct work_struct *work); static unsigned int carrier_timeout = 4; @@ -74,6 +69,37 @@ module_param(carrier_timeout, uint, 0644); #define np_notice(np, fmt, ...) \ pr_notice("%s: " fmt, np->name, ##__VA_ARGS__) +static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq) +{ + const struct net_device_ops *ops = dev->netdev_ops; + int status = NETDEV_TX_OK; + netdev_features_t features; + + features = netif_skb_features(skb); + + if (vlan_tx_tag_present(skb) && + !vlan_hw_offload_capable(features, skb->vlan_proto)) { + skb = __vlan_put_tag(skb, skb->vlan_proto, + vlan_tx_tag_get(skb)); + if (unlikely(!skb)) { + /* This is actually a packet drop, but we + * don't want the code that calls this + * function to try and operate on a NULL skb. + */ + goto out; + } + skb->vlan_tci = 0; + } + + status = ops->ndo_start_xmit(skb, dev); + if (status == NETDEV_TX_OK) + txq_trans_update(txq); + +out: + return status; +} + static void queue_process(struct work_struct *work) { struct netpoll_info *npinfo = @@ -83,51 +109,31 @@ static void queue_process(struct work_struct *work) while ((skb = skb_dequeue(&npinfo->txq))) { struct net_device *dev = skb->dev; - const struct net_device_ops *ops = dev->netdev_ops; struct netdev_queue *txq; if (!netif_device_present(dev) || !netif_running(dev)) { - __kfree_skb(skb); + kfree_skb(skb); continue; } txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); local_irq_save(flags); - __netif_tx_lock(txq, smp_processor_id()); + HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || - ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) { + netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) { skb_queue_head(&npinfo->txq, skb); - __netif_tx_unlock(txq); + HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); schedule_delayed_work(&npinfo->tx_work, HZ/10); return; } - __netif_tx_unlock(txq); + HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); } } -static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh, - unsigned short ulen, __be32 saddr, __be32 daddr) -{ - __wsum psum; - - if (uh->check == 0 || skb_csum_unnecessary(skb)) - return 0; - - psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); - - if (skb->ip_summed == CHECKSUM_COMPLETE && - !csum_fold(csum_add(psum, skb->csum))) - return 0; - - skb->csum = psum; - - return __skb_checksum_complete(skb); -} - /* * Check whether delayed processing was scheduled for our NIC. If so, * we attempt to grab the poll lock and use ->poll() to pump the card. @@ -138,14 +144,8 @@ static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh, * trylock here and interrupts are already disabled in the softirq * case. Further, we test the poll_owner to avoid recursion on UP * systems where the lock doesn't exist. - * - * In cases where there is bi-directional communications, reading only - * one message at a time can lead to packets being dropped by the - * network adapter, forcing superfluous retries and possibly timeouts. - * Thus, we set our budget to greater than 1. */ -static int poll_one_napi(struct netpoll_info *npinfo, - struct napi_struct *napi, int budget) +static int poll_one_napi(struct napi_struct *napi, int budget) { int work; @@ -156,52 +156,35 @@ static int poll_one_napi(struct netpoll_info *npinfo, if (!test_bit(NAPI_STATE_SCHED, &napi->state)) return budget; - npinfo->rx_flags |= NETPOLL_RX_DROP; - atomic_inc(&trapped); set_bit(NAPI_STATE_NPSVC, &napi->state); work = napi->poll(napi, budget); + WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll); trace_napi_poll(napi); clear_bit(NAPI_STATE_NPSVC, &napi->state); - atomic_dec(&trapped); - npinfo->rx_flags &= ~NETPOLL_RX_DROP; return budget - work; } -static void poll_napi(struct net_device *dev) +static void poll_napi(struct net_device *dev, int budget) { struct napi_struct *napi; - int budget = 16; list_for_each_entry(napi, &dev->napi_list, dev_list) { if (napi->poll_owner != smp_processor_id() && spin_trylock(&napi->poll_lock)) { - budget = poll_one_napi(rcu_dereference_bh(dev->npinfo), - napi, budget); + budget = poll_one_napi(napi, budget); spin_unlock(&napi->poll_lock); - - if (!budget) - break; } } } -static void service_neigh_queue(struct netpoll_info *npi) -{ - if (npi) { - struct sk_buff *skb; - - while ((skb = skb_dequeue(&npi->neigh_tx))) - netpoll_neigh_reply(skb, npi); - } -} - static void netpoll_poll_dev(struct net_device *dev) { const struct net_device_ops *ops; struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); + int budget = 0; /* Don't do any rx activity if the dev_lock mutex is held * the dev_open/close paths use this to block netpoll activity @@ -224,31 +207,14 @@ static void netpoll_poll_dev(struct net_device *dev) /* Process pending work on NIC */ ops->ndo_poll_controller(dev); - poll_napi(dev); + poll_napi(dev, budget); up(&ni->dev_lock); - if (dev->flags & IFF_SLAVE) { - if (ni) { - struct net_device *bond_dev; - struct sk_buff *skb; - struct netpoll_info *bond_ni; - - bond_dev = netdev_master_upper_dev_get_rcu(dev); - bond_ni = rcu_dereference_bh(bond_dev->npinfo); - while ((skb = skb_dequeue(&ni->neigh_tx))) { - skb->dev = bond_dev; - skb_queue_tail(&bond_ni->neigh_tx, skb); - } - } - } - - service_neigh_queue(ni); - zap_completion_queue(); } -void netpoll_rx_disable(struct net_device *dev) +void netpoll_poll_disable(struct net_device *dev) { struct netpoll_info *ni; int idx; @@ -259,9 +225,9 @@ void netpoll_rx_disable(struct net_device *dev) down(&ni->dev_lock); srcu_read_unlock(&netpoll_srcu, idx); } -EXPORT_SYMBOL(netpoll_rx_disable); +EXPORT_SYMBOL(netpoll_poll_disable); -void netpoll_rx_enable(struct net_device *dev) +void netpoll_poll_enable(struct net_device *dev) { struct netpoll_info *ni; rcu_read_lock(); @@ -270,7 +236,7 @@ void netpoll_rx_enable(struct net_device *dev) up(&ni->dev_lock); rcu_read_unlock(); } -EXPORT_SYMBOL(netpoll_rx_enable); +EXPORT_SYMBOL(netpoll_poll_enable); static void refill_skbs(void) { @@ -304,7 +270,7 @@ static void zap_completion_queue(void) while (clist != NULL) { struct sk_buff *skb = clist; clist = clist->next; - if (skb->destructor) { + if (!skb_irq_freeable(skb)) { atomic_inc(&skb->users); dev_kfree_skb_any(skb); /* put this one back */ } else { @@ -359,7 +325,6 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, { int status = NETDEV_TX_BUSY; unsigned long tries; - const struct net_device_ops *ops = dev->netdev_ops; /* It is up to the caller to keep npinfo alive. */ struct netpoll_info *npinfo; @@ -367,7 +332,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, npinfo = rcu_dereference_bh(np->dev->npinfo); if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { - __kfree_skb(skb); + dev_kfree_skb_irq(skb); return; } @@ -380,29 +345,11 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, /* try until next clock tick */ for (tries = jiffies_to_usecs(1)/USEC_PER_POLL; tries > 0; --tries) { - if (__netif_tx_trylock(txq)) { - if (!netif_xmit_stopped(txq)) { - if (vlan_tx_tag_present(skb) && - !vlan_hw_offload_capable(netif_skb_features(skb), - skb->vlan_proto)) { - skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb)); - if (unlikely(!skb)) { - /* This is actually a packet drop, but we - * don't want the code at the end of this - * function to try and re-queue a NULL skb. - */ - status = NETDEV_TX_OK; - goto unlock_txq; - } - skb->vlan_tci = 0; - } - - status = ops->ndo_start_xmit(skb, dev); - if (status == NETDEV_TX_OK) - txq_trans_update(txq); - } - unlock_txq: - __netif_tx_unlock(txq); + if (HARD_TX_TRYLOCK(dev, txq)) { + if (!netif_xmit_stopped(txq)) + status = netpoll_start_xmit(skb, dev, txq); + + HARD_TX_UNLOCK(dev, txq); if (status == NETDEV_TX_OK) break; @@ -417,7 +364,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, WARN_ONCE(!irqs_disabled(), "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n", - dev->name, ops->ndo_start_xmit); + dev->name, dev->netdev_ops->ndo_start_xmit); } @@ -529,384 +476,6 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) } EXPORT_SYMBOL(netpoll_send_udp); -static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo) -{ - int size, type = ARPOP_REPLY; - __be32 sip, tip; - unsigned char *sha; - struct sk_buff *send_skb; - struct netpoll *np, *tmp; - unsigned long flags; - int hlen, tlen; - int hits = 0, proto; - - if (list_empty(&npinfo->rx_np)) - return; - - /* Before checking the packet, we do some early - inspection whether this is interesting at all */ - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (np->dev == skb->dev) - hits++; - } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - - /* No netpoll struct is using this dev */ - if (!hits) - return; - - proto = ntohs(eth_hdr(skb)->h_proto); - if (proto == ETH_P_ARP) { - struct arphdr *arp; - unsigned char *arp_ptr; - /* No arp on this interface */ - if (skb->dev->flags & IFF_NOARP) - return; - - if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) - return; - - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - arp = arp_hdr(skb); - - if ((arp->ar_hrd != htons(ARPHRD_ETHER) && - arp->ar_hrd != htons(ARPHRD_IEEE802)) || - arp->ar_pro != htons(ETH_P_IP) || - arp->ar_op != htons(ARPOP_REQUEST)) - return; - - arp_ptr = (unsigned char *)(arp+1); - /* save the location of the src hw addr */ - sha = arp_ptr; - arp_ptr += skb->dev->addr_len; - memcpy(&sip, arp_ptr, 4); - arp_ptr += 4; - /* If we actually cared about dst hw addr, - it would get copied here */ - arp_ptr += skb->dev->addr_len; - memcpy(&tip, arp_ptr, 4); - - /* Should we ignore arp? */ - if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) - return; - - size = arp_hdr_len(skb->dev); - - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (tip != np->local_ip.ip) - continue; - - hlen = LL_RESERVED_SPACE(np->dev); - tlen = np->dev->needed_tailroom; - send_skb = find_skb(np, size + hlen + tlen, hlen); - if (!send_skb) - continue; - - skb_reset_network_header(send_skb); - arp = (struct arphdr *) skb_put(send_skb, size); - send_skb->dev = skb->dev; - send_skb->protocol = htons(ETH_P_ARP); - - /* Fill the device header for the ARP frame */ - if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP, - sha, np->dev->dev_addr, - send_skb->len) < 0) { - kfree_skb(send_skb); - continue; - } - - /* - * Fill out the arp protocol part. - * - * we only support ethernet device type, - * which (according to RFC 1390) should - * always equal 1 (Ethernet). - */ - - arp->ar_hrd = htons(np->dev->type); - arp->ar_pro = htons(ETH_P_IP); - arp->ar_hln = np->dev->addr_len; - arp->ar_pln = 4; - arp->ar_op = htons(type); - - arp_ptr = (unsigned char *)(arp + 1); - memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &tip, 4); - arp_ptr += 4; - memcpy(arp_ptr, sha, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &sip, 4); - - netpoll_send_skb(np, send_skb); - - /* If there are several rx_skb_hooks for the same - * address we're fine by sending a single reply - */ - break; - } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } else if( proto == ETH_P_IPV6) { -#if IS_ENABLED(CONFIG_IPV6) - struct nd_msg *msg; - u8 *lladdr = NULL; - struct ipv6hdr *hdr; - struct icmp6hdr *icmp6h; - const struct in6_addr *saddr; - const struct in6_addr *daddr; - struct inet6_dev *in6_dev = NULL; - struct in6_addr *target; - - in6_dev = in6_dev_get(skb->dev); - if (!in6_dev || !in6_dev->cnf.accept_ra) - return; - - if (!pskb_may_pull(skb, skb->len)) - return; - - msg = (struct nd_msg *)skb_transport_header(skb); - - __skb_push(skb, skb->data - skb_transport_header(skb)); - - if (ipv6_hdr(skb)->hop_limit != 255) - return; - if (msg->icmph.icmp6_code != 0) - return; - if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) - return; - - saddr = &ipv6_hdr(skb)->saddr; - daddr = &ipv6_hdr(skb)->daddr; - - size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); - - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (!ipv6_addr_equal(daddr, &np->local_ip.in6)) - continue; - - hlen = LL_RESERVED_SPACE(np->dev); - tlen = np->dev->needed_tailroom; - send_skb = find_skb(np, size + hlen + tlen, hlen); - if (!send_skb) - continue; - - send_skb->protocol = htons(ETH_P_IPV6); - send_skb->dev = skb->dev; - - skb_reset_network_header(send_skb); - hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr)); - *(__be32*)hdr = htonl(0x60000000); - hdr->payload_len = htons(size); - hdr->nexthdr = IPPROTO_ICMPV6; - hdr->hop_limit = 255; - hdr->saddr = *saddr; - hdr->daddr = *daddr; - - icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr)); - icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; - icmp6h->icmp6_router = 0; - icmp6h->icmp6_solicited = 1; - - target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr)); - *target = msg->target; - icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size, - IPPROTO_ICMPV6, - csum_partial(icmp6h, - size, 0)); - - if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6, - lladdr, np->dev->dev_addr, - send_skb->len) < 0) { - kfree_skb(send_skb); - continue; - } - - netpoll_send_skb(np, send_skb); - - /* If there are several rx_skb_hooks for the same - * address, we're fine by sending a single reply - */ - break; - } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); -#endif - } -} - -static bool pkt_is_ns(struct sk_buff *skb) -{ - struct nd_msg *msg; - struct ipv6hdr *hdr; - - if (skb->protocol != htons(ETH_P_IPV6)) - return false; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg))) - return false; - - msg = (struct nd_msg *)skb_transport_header(skb); - __skb_push(skb, skb->data - skb_transport_header(skb)); - hdr = ipv6_hdr(skb); - - if (hdr->nexthdr != IPPROTO_ICMPV6) - return false; - if (hdr->hop_limit != 255) - return false; - if (msg->icmph.icmp6_code != 0) - return false; - if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) - return false; - - return true; -} - -int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) -{ - int proto, len, ulen, data_len; - int hits = 0, offset; - const struct iphdr *iph; - struct udphdr *uh; - struct netpoll *np, *tmp; - uint16_t source; - - if (list_empty(&npinfo->rx_np)) - goto out; - - if (skb->dev->type != ARPHRD_ETHER) - goto out; - - /* check if netpoll clients need ARP */ - if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) { - skb_queue_tail(&npinfo->neigh_tx, skb); - return 1; - } else if (pkt_is_ns(skb) && atomic_read(&trapped)) { - skb_queue_tail(&npinfo->neigh_tx, skb); - return 1; - } - - if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { - skb = vlan_untag(skb); - if (unlikely(!skb)) - goto out; - } - - proto = ntohs(eth_hdr(skb)->h_proto); - if (proto != ETH_P_IP && proto != ETH_P_IPV6) - goto out; - if (skb->pkt_type == PACKET_OTHERHOST) - goto out; - if (skb_shared(skb)) - goto out; - - if (proto == ETH_P_IP) { - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto out; - iph = (struct iphdr *)skb->data; - if (iph->ihl < 5 || iph->version != 4) - goto out; - if (!pskb_may_pull(skb, iph->ihl*4)) - goto out; - iph = (struct iphdr *)skb->data; - if (ip_fast_csum((u8 *)iph, iph->ihl) != 0) - goto out; - - len = ntohs(iph->tot_len); - if (skb->len < len || len < iph->ihl*4) - goto out; - - /* - * Our transport medium may have padded the buffer out. - * Now We trim to the true length of the frame. - */ - if (pskb_trim_rcsum(skb, len)) - goto out; - - iph = (struct iphdr *)skb->data; - if (iph->protocol != IPPROTO_UDP) - goto out; - - len -= iph->ihl*4; - uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); - offset = (unsigned char *)(uh + 1) - skb->data; - ulen = ntohs(uh->len); - data_len = skb->len - offset; - source = ntohs(uh->source); - - if (ulen != len) - goto out; - if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) - goto out; - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (np->local_ip.ip && np->local_ip.ip != iph->daddr) - continue; - if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr) - continue; - if (np->local_port && np->local_port != ntohs(uh->dest)) - continue; - - np->rx_skb_hook(np, source, skb, offset, data_len); - hits++; - } - } else { -#if IS_ENABLED(CONFIG_IPV6) - const struct ipv6hdr *ip6h; - - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto out; - ip6h = (struct ipv6hdr *)skb->data; - if (ip6h->version != 6) - goto out; - len = ntohs(ip6h->payload_len); - if (!len) - goto out; - if (len + sizeof(struct ipv6hdr) > skb->len) - goto out; - if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr))) - goto out; - ip6h = ipv6_hdr(skb); - if (!pskb_may_pull(skb, sizeof(struct udphdr))) - goto out; - uh = udp_hdr(skb); - offset = (unsigned char *)(uh + 1) - skb->data; - ulen = ntohs(uh->len); - data_len = skb->len - offset; - source = ntohs(uh->source); - if (ulen != skb->len) - goto out; - if (udp6_csum_init(skb, uh, IPPROTO_UDP)) - goto out; - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr)) - continue; - if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr)) - continue; - if (np->local_port && np->local_port != ntohs(uh->dest)) - continue; - - np->rx_skb_hook(np, source, skb, offset, data_len); - hits++; - } -#endif - } - - if (!hits) - goto out; - - kfree_skb(skb); - return 1; - -out: - if (atomic_read(&trapped)) { - kfree_skb(skb); - return 1; - } - - return 0; -} - void netpoll_print_options(struct netpoll *np) { np_info(np, "local port %d\n", np->local_port); @@ -1026,11 +595,10 @@ int netpoll_parse_options(struct netpoll *np, char *opt) } EXPORT_SYMBOL(netpoll_parse_options); -int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) +int __netpoll_setup(struct netpoll *np, struct net_device *ndev) { struct netpoll_info *npinfo; const struct net_device_ops *ops; - unsigned long flags; int err; np->dev = ndev; @@ -1046,18 +614,13 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) } if (!ndev->npinfo) { - npinfo = kmalloc(sizeof(*npinfo), gfp); + npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); if (!npinfo) { err = -ENOMEM; goto out; } - npinfo->rx_flags = 0; - INIT_LIST_HEAD(&npinfo->rx_np); - - spin_lock_init(&npinfo->rx_lock); sema_init(&npinfo->dev_lock, 1); - skb_queue_head_init(&npinfo->neigh_tx); skb_queue_head_init(&npinfo->txq); INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); @@ -1065,7 +628,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) ops = np->dev->netdev_ops; if (ops->ndo_netpoll_setup) { - err = ops->ndo_netpoll_setup(ndev, npinfo, gfp); + err = ops->ndo_netpoll_setup(ndev, npinfo); if (err) goto free_npinfo; } @@ -1076,13 +639,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) npinfo->netpoll = np; - if (np->rx_skb_hook) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - npinfo->rx_flags |= NETPOLL_RX_ENABLED; - list_add_tail(&np->rx, &npinfo->rx_np); - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } - /* last thing to do is link it to the net device structure */ rcu_assign_pointer(ndev->npinfo, npinfo); @@ -1204,7 +760,7 @@ int netpoll_setup(struct netpoll *np) /* fill up the skb queue */ refill_skbs(); - err = __netpoll_setup(np, ndev, GFP_KERNEL); + err = __netpoll_setup(np, ndev); if (err) goto put; @@ -1231,7 +787,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) struct netpoll_info *npinfo = container_of(rcu_head, struct netpoll_info, rcu); - skb_queue_purge(&npinfo->neigh_tx); skb_queue_purge(&npinfo->txq); /* we can't call cancel_delayed_work_sync here, as we are in softirq */ @@ -1247,7 +802,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; - unsigned long flags; /* rtnl_dereference would be preferable here but * rcu_cleanup_netpoll path can put us in here safely without @@ -1257,14 +811,6 @@ void __netpoll_cleanup(struct netpoll *np) if (!npinfo) return; - if (!list_empty(&npinfo->rx_np)) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_del(&np->rx); - if (list_empty(&npinfo->rx_np)) - npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } - synchronize_srcu(&netpoll_srcu); if (atomic_dec_and_test(&npinfo->refcnt)) { @@ -1274,7 +820,7 @@ void __netpoll_cleanup(struct netpoll *np) if (ops->ndo_netpoll_cleanup) ops->ndo_netpoll_cleanup(np->dev); - rcu_assign_pointer(np->dev->npinfo, NULL); + RCU_INIT_POINTER(np->dev->npinfo, NULL); call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info); } } @@ -1308,18 +854,3 @@ out: rtnl_unlock(); } EXPORT_SYMBOL(netpoll_cleanup); - -int netpoll_trap(void) -{ - return atomic_read(&trapped); -} -EXPORT_SYMBOL(netpoll_trap); - -void netpoll_set_trap(int trap) -{ - if (trap) - atomic_inc(&trapped); - else - atomic_dec(&trapped); -} -EXPORT_SYMBOL(netpoll_set_trap); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index fdac61cac1bd..d0dac57291af 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -476,23 +476,22 @@ static int pgctrl_show(struct seq_file *seq, void *v) static ssize_t pgctrl_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - int err = 0; char data[128]; struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id); - if (!capable(CAP_NET_ADMIN)) { - err = -EPERM; - goto out; - } + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (count == 0) + return -EINVAL; if (count > sizeof(data)) count = sizeof(data); - if (copy_from_user(data, buf, count)) { - err = -EFAULT; - goto out; - } - data[count - 1] = 0; /* Make string */ + if (copy_from_user(data, buf, count)) + return -EFAULT; + + data[count - 1] = 0; /* Strip trailing '\n' and terminate string */ if (!strcmp(data, "stop")) pktgen_stop_all_threads_ifs(pn); @@ -506,10 +505,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, else pr_warning("Unknown command: %s\n", data); - err = count; - -out: - return err; + return count; } static int pgctrl_open(struct inode *inode, struct file *file) @@ -1251,7 +1247,13 @@ static ssize_t pktgen_if_write(struct file *file, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", f, "IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, " - "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC, NODE_ALLOC\n"); + "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, " + "MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, " + "QUEUE_MAP_RND, QUEUE_MAP_CPU, UDPCSUM, " +#ifdef CONFIG_XFRM + "IPSEC, " +#endif + "NODE_ALLOC\n"); return count; } sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags); diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c new file mode 100644 index 000000000000..eaba0f68f860 --- /dev/null +++ b/net/core/ptp_classifier.c @@ -0,0 +1,141 @@ +/* PTP classifier + * + * 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. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +/* The below program is the bpf_asm (tools/net/) representation of + * the opcode array in the ptp_filter structure. + * + * For convenience, this can easily be altered and reviewed with + * bpf_asm and bpf_dbg, e.g. `./bpf_asm -c prog` where prog is a + * simple file containing the below program: + * + * ldh [12] ; load ethertype + * + * ; PTP over UDP over IPv4 over Ethernet + * test_ipv4: + * jneq #0x800, test_ipv6 ; ETH_P_IP ? + * ldb [23] ; load proto + * jneq #17, drop_ipv4 ; IPPROTO_UDP ? + * ldh [20] ; load frag offset field + * jset #0x1fff, drop_ipv4 ; don't allow fragments + * ldxb 4*([14]&0xf) ; load IP header len + * ldh [x + 16] ; load UDP dst port + * jneq #319, drop_ipv4 ; is port PTP_EV_PORT ? + * ldh [x + 22] ; load payload + * and #0xf ; mask PTP_CLASS_VMASK + * or #0x10 ; PTP_CLASS_IPV4 + * ret a ; return PTP class + * drop_ipv4: ret #0x0 ; PTP_CLASS_NONE + * + * ; PTP over UDP over IPv6 over Ethernet + * test_ipv6: + * jneq #0x86dd, test_8021q ; ETH_P_IPV6 ? + * ldb [20] ; load proto + * jneq #17, drop_ipv6 ; IPPROTO_UDP ? + * ldh [56] ; load UDP dst port + * jneq #319, drop_ipv6 ; is port PTP_EV_PORT ? + * ldh [62] ; load payload + * and #0xf ; mask PTP_CLASS_VMASK + * or #0x20 ; PTP_CLASS_IPV6 + * ret a ; return PTP class + * drop_ipv6: ret #0x0 ; PTP_CLASS_NONE + * + * ; PTP over 802.1Q over Ethernet + * test_8021q: + * jneq #0x8100, test_ieee1588 ; ETH_P_8021Q ? + * ldh [16] ; load inner type + * jneq #0x88f7, drop_ieee1588 ; ETH_P_1588 ? + * ldb [18] ; load payload + * and #0x8 ; as we don't have ports here, test + * jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these + * ldh [18] ; reload payload + * and #0xf ; mask PTP_CLASS_VMASK + * or #0x40 ; PTP_CLASS_V2_VLAN + * ret a ; return PTP class + * + * ; PTP over Ethernet + * test_ieee1588: + * jneq #0x88f7, drop_ieee1588 ; ETH_P_1588 ? + * ldb [14] ; load payload + * and #0x8 ; as we don't have ports here, test + * jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these + * ldh [14] ; reload payload + * and #0xf ; mask PTP_CLASS_VMASK + * or #0x30 ; PTP_CLASS_L2 + * ret a ; return PTP class + * drop_ieee1588: ret #0x0 ; PTP_CLASS_NONE + */ + +#include <linux/skbuff.h> +#include <linux/filter.h> +#include <linux/ptp_classify.h> + +static struct sk_filter *ptp_insns __read_mostly; + +unsigned int ptp_classify_raw(const struct sk_buff *skb) +{ + return SK_RUN_FILTER(ptp_insns, skb); +} +EXPORT_SYMBOL_GPL(ptp_classify_raw); + +void __init ptp_classifier_init(void) +{ + static struct sock_filter ptp_filter[] = { + { 0x28, 0, 0, 0x0000000c }, + { 0x15, 0, 12, 0x00000800 }, + { 0x30, 0, 0, 0x00000017 }, + { 0x15, 0, 9, 0x00000011 }, + { 0x28, 0, 0, 0x00000014 }, + { 0x45, 7, 0, 0x00001fff }, + { 0xb1, 0, 0, 0x0000000e }, + { 0x48, 0, 0, 0x00000010 }, + { 0x15, 0, 4, 0x0000013f }, + { 0x48, 0, 0, 0x00000016 }, + { 0x54, 0, 0, 0x0000000f }, + { 0x44, 0, 0, 0x00000010 }, + { 0x16, 0, 0, 0x00000000 }, + { 0x06, 0, 0, 0x00000000 }, + { 0x15, 0, 9, 0x000086dd }, + { 0x30, 0, 0, 0x00000014 }, + { 0x15, 0, 6, 0x00000011 }, + { 0x28, 0, 0, 0x00000038 }, + { 0x15, 0, 4, 0x0000013f }, + { 0x28, 0, 0, 0x0000003e }, + { 0x54, 0, 0, 0x0000000f }, + { 0x44, 0, 0, 0x00000020 }, + { 0x16, 0, 0, 0x00000000 }, + { 0x06, 0, 0, 0x00000000 }, + { 0x15, 0, 9, 0x00008100 }, + { 0x28, 0, 0, 0x00000010 }, + { 0x15, 0, 15, 0x000088f7 }, + { 0x30, 0, 0, 0x00000012 }, + { 0x54, 0, 0, 0x00000008 }, + { 0x15, 0, 12, 0x00000000 }, + { 0x28, 0, 0, 0x00000012 }, + { 0x54, 0, 0, 0x0000000f }, + { 0x44, 0, 0, 0x00000040 }, + { 0x16, 0, 0, 0x00000000 }, + { 0x15, 0, 7, 0x000088f7 }, + { 0x30, 0, 0, 0x0000000e }, + { 0x54, 0, 0, 0x00000008 }, + { 0x15, 0, 4, 0x00000000 }, + { 0x28, 0, 0, 0x0000000e }, + { 0x54, 0, 0, 0x0000000f }, + { 0x44, 0, 0, 0x00000030 }, + { 0x16, 0, 0, 0x00000000 }, + { 0x06, 0, 0, 0x00000000 }, + }; + struct sock_fprog ptp_prog = { + .len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter, + }; + + BUG_ON(sk_unattached_filter_create(&ptp_insns, &ptp_prog)); +} diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 4425148d2b51..467f326126e0 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -221,5 +221,4 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, out: spin_unlock_bh(&fastopenq->lock); sock_put(lsk); - return; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 120eecc0f5a4..d4ff41739b0f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -822,6 +822,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ + nla_total_size(ext_filter_mask & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ @@ -970,7 +971,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, (dev->qdisc && nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || (dev->ifalias && - nla_put_string(skb, IFLA_IFALIAS, dev->ifalias))) + nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) || + nla_put_u32(skb, IFLA_CARRIER_CHANGES, + atomic_read(&dev->carrier_changes))) goto nla_put_failure; if (1) { @@ -1121,56 +1124,7 @@ nla_put_failure: return -EMSGSIZE; } -static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct net *net = sock_net(skb->sk); - int h, s_h; - int idx = 0, s_idx; - struct net_device *dev; - struct hlist_head *head; - struct nlattr *tb[IFLA_MAX+1]; - u32 ext_filter_mask = 0; - - s_h = cb->args[0]; - s_idx = cb->args[1]; - - rcu_read_lock(); - cb->seq = net->dev_base_seq; - - if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, - ifla_policy) >= 0) { - - if (tb[IFLA_EXT_MASK]) - ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); - } - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI, - ext_filter_mask) <= 0) - goto out; - - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } - } -out: - rcu_read_unlock(); - cb->args[1] = idx; - cb->args[0] = h; - - return skb->len; -} - -const struct nla_policy ifla_policy[IFLA_MAX+1] = { +static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 }, [IFLA_ADDRESS] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [IFLA_BROADCAST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, @@ -1196,8 +1150,8 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 }, [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 }, [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN }, + [IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */ }; -EXPORT_SYMBOL(ifla_policy); static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_KIND] = { .type = NLA_STRING }, @@ -1235,6 +1189,61 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { [IFLA_PORT_RESPONSE] = { .type = NLA_U16, }, }; +static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + int h, s_h; + int idx = 0, s_idx; + struct net_device *dev; + struct hlist_head *head; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; + + s_h = cb->args[0]; + s_idx = cb->args[1]; + + rcu_read_lock(); + cb->seq = net->dev_base_seq; + + if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, + ifla_policy) >= 0) { + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + } + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI, + ext_filter_mask) <= 0) + goto out; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); +cont: + idx++; + } + } +out: + rcu_read_unlock(); + cb->args[1] = idx; + cb->args[0] = h; + + return skb->len; +} + +int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len) +{ + return nla_parse(tb, IFLA_MAX, head, len, ifla_policy); +} +EXPORT_SYMBOL(rtnl_nla_parse_ifla); + struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) { struct net *net; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 90b96a11b974..30c7d35dd862 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3300,6 +3300,32 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) return elt; } +/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given + * sglist without mark the sg which contain last skb data as the end. + * So the caller can mannipulate sg list as will when padding new data after + * the first call without calling sg_unmark_end to expend sg list. + * + * Scenario to use skb_to_sgvec_nomark: + * 1. sg_init_table + * 2. skb_to_sgvec_nomark(payload1) + * 3. skb_to_sgvec_nomark(payload2) + * + * This is equivalent to: + * 1. sg_init_table + * 2. skb_to_sgvec(payload1) + * 3. sg_unmark_end + * 4. skb_to_sgvec(payload2) + * + * When mapping mutilple payload conditionally, skb_to_sgvec_nomark + * is more preferable. + */ +int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len) +{ + return __skb_to_sgvec(skb, sg, offset, len); +} +EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark); + int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int nsg = __skb_to_sgvec(skb, sg, offset, len); @@ -3562,15 +3588,47 @@ static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, return 0; } +#define MAX_TCP_HDR_LEN (15 * 4) + +static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, + typeof(IPPROTO_IP) proto, + unsigned int off) +{ + switch (proto) { + int err; + + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), + off + MAX_TCP_HDR_LEN); + if (!err && !skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, + check))) + err = -EPROTO; + return err ? ERR_PTR(err) : &tcp_hdr(skb)->check; + + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr), + off + sizeof(struct udphdr)); + if (!err && !skb_partial_csum_set(skb, off, + offsetof(struct udphdr, + check))) + err = -EPROTO; + return err ? ERR_PTR(err) : &udp_hdr(skb)->check; + } + + return ERR_PTR(-EPROTO); +} + /* This value should be large enough to cover a tagged ethernet header plus * maximally sized IP and TCP or UDP headers. */ #define MAX_IP_HDR_LEN 128 -static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate) +static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate) { unsigned int off; bool fragment; + __sum16 *csum; int err; fragment = false; @@ -3591,51 +3649,15 @@ static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate) if (fragment) goto out; - switch (ip_hdr(skb)->protocol) { - case IPPROTO_TCP: - err = skb_maybe_pull_tail(skb, - off + sizeof(struct tcphdr), - MAX_IP_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct tcphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate) - tcp_hdr(skb)->check = - ~csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - off, - IPPROTO_TCP, 0); - break; - case IPPROTO_UDP: - err = skb_maybe_pull_tail(skb, - off + sizeof(struct udphdr), - MAX_IP_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct udphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate) - udp_hdr(skb)->check = - ~csum_tcpudp_magic(ip_hdr(skb)->saddr, - ip_hdr(skb)->daddr, - skb->len - off, - IPPROTO_UDP, 0); - break; - default: - goto out; - } + csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off); + if (IS_ERR(csum)) + return PTR_ERR(csum); + if (recalculate) + *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + ip_hdr(skb)->protocol, 0); err = 0; out: @@ -3658,6 +3680,7 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) unsigned int len; bool fragment; bool done; + __sum16 *csum; fragment = false; done = false; @@ -3735,51 +3758,14 @@ static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) if (!done || fragment) goto out; - switch (nexthdr) { - case IPPROTO_TCP: - err = skb_maybe_pull_tail(skb, - off + sizeof(struct tcphdr), - MAX_IPV6_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct tcphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate) - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - off, - IPPROTO_TCP, 0); - break; - case IPPROTO_UDP: - err = skb_maybe_pull_tail(skb, - off + sizeof(struct udphdr), - MAX_IPV6_HDR_LEN); - if (err < 0) - goto out; - - if (!skb_partial_csum_set(skb, off, - offsetof(struct udphdr, check))) { - err = -EPROTO; - goto out; - } - - if (recalculate) - udp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len - off, - IPPROTO_UDP, 0); - break; - default: - goto out; - } + csum = skb_checksum_setup_ip(skb, nexthdr, off); + if (IS_ERR(csum)) + return PTR_ERR(csum); + if (recalculate) + *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, nexthdr, 0); err = 0; out: @@ -3797,7 +3783,7 @@ int skb_checksum_setup(struct sk_buff *skb, bool recalculate) switch (skb->protocol) { case htons(ETH_P_IP): - err = skb_checksum_setup_ip(skb, recalculate); + err = skb_checksum_setup_ipv4(skb, recalculate); break; case htons(ETH_P_IPV6): diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index a0e9cf6379de..d7af18859322 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -52,9 +52,10 @@ EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, struct sk_buff *skb, int attrtype) { - struct nlattr *attr; + struct sock_fprog_kern *fprog; struct sk_filter *filter; - unsigned int len; + struct nlattr *attr; + unsigned int flen; int err = 0; if (!ns_capable(user_ns, CAP_NET_ADMIN)) { @@ -63,24 +64,20 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, } rcu_read_lock(); - filter = rcu_dereference(sk->sk_filter); - len = filter ? filter->len * sizeof(struct sock_filter) : 0; + if (!filter) + goto out; - attr = nla_reserve(skb, attrtype, len); + fprog = filter->orig_prog; + flen = sk_filter_proglen(fprog); + + attr = nla_reserve(skb, attrtype, flen); if (attr == NULL) { err = -EMSGSIZE; goto out; } - if (filter) { - struct sock_filter *fb = (struct sock_filter *)nla_data(attr); - int i; - - for (i = 0; i < filter->len; i++, fb++) - sk_decode_filter(&filter->insns[i], fb); - } - + memcpy(nla_data(attr), fprog->filter, flen); out: rcu_read_unlock(); return err; diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 661b5a40ec10..6521dfd8b7c8 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -23,16 +23,11 @@ #include <linux/skbuff.h> #include <linux/export.h> -static struct sock_filter ptp_filter[] = { - PTP_FILTER -}; - static unsigned int classify(const struct sk_buff *skb) { - if (likely(skb->dev && - skb->dev->phydev && + if (likely(skb->dev && skb->dev->phydev && skb->dev->phydev->drv)) - return sk_run_filter(skb, ptp_filter); + return ptp_classify_raw(skb); else return PTP_CLASS_NONE; } @@ -60,11 +55,13 @@ void skb_clone_tx_timestamp(struct sk_buff *skb) if (likely(phydev->drv->txtstamp)) { if (!atomic_inc_not_zero(&sk->sk_refcnt)) return; + clone = skb_clone(skb, GFP_ATOMIC); if (!clone) { sock_put(sk); return; } + clone->sk = sk; phydev->drv->txtstamp(phydev, clone, type); } @@ -89,12 +86,15 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, } *skb_hwtstamps(skb) = *hwtstamps; + serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; skb->sk = NULL; + err = sock_queue_err_skb(sk, skb); + sock_put(sk); if (err) kfree_skb(skb); @@ -132,8 +132,3 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) return false; } EXPORT_SYMBOL_GPL(skb_defer_rx_timestamp); - -void __init skb_timestamping_init(void) -{ - BUG_ON(sk_chk_filter(ptp_filter, ARRAY_SIZE(ptp_filter))); -} diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index cac505f166d5..e5302b7f7ca9 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -209,7 +209,7 @@ static int slave_xmit(struct sk_buff *skb, struct hsr_priv *hsr_priv, /* Address substitution (IEC62439-3 pp 26, 50): replace mac * address of outgoing frame with that of the outgoing slave's. */ - memcpy(hsr_ethhdr->ethhdr.h_source, skb->dev->dev_addr, ETH_ALEN); + ether_addr_copy(hsr_ethhdr->ethhdr.h_source, skb->dev->dev_addr); return dev_queue_xmit(skb); } @@ -346,7 +346,7 @@ static void send_hsr_supervision_frame(struct net_device *hsr_dev, u8 type) /* Payload: MacAddressA */ hsr_sp = (typeof(hsr_sp)) skb_put(skb, sizeof(*hsr_sp)); - memcpy(hsr_sp->MacAddressA, hsr_dev->dev_addr, ETH_ALEN); + ether_addr_copy(hsr_sp->MacAddressA, hsr_dev->dev_addr); dev_queue_xmit(skb); return; @@ -493,7 +493,7 @@ static int check_slave_ok(struct net_device *dev) /* Default multicast address for HSR Supervision frames */ -static const unsigned char def_multicast_addr[ETH_ALEN] = { +static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; @@ -519,7 +519,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], hsr_priv->announce_timer.function = hsr_announce; hsr_priv->announce_timer.data = (unsigned long) hsr_priv; - memcpy(hsr_priv->sup_multicast_addr, def_multicast_addr, ETH_ALEN); + ether_addr_copy(hsr_priv->sup_multicast_addr, def_multicast_addr); hsr_priv->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; /* FIXME: should I modify the value of these? @@ -547,7 +547,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], hsr_dev->features |= NETIF_F_VLAN_CHALLENGED; /* Set hsr_dev's MAC address to that of mac_slave1 */ - memcpy(hsr_dev->dev_addr, hsr_priv->slave[0]->dev_addr, ETH_ALEN); + ether_addr_copy(hsr_dev->dev_addr, hsr_priv->slave[0]->dev_addr); /* Set required header length */ for (i = 0; i < HSR_MAX_SLAVE; i++) { diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 7ae0d7f6dbd0..83e58449366a 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -108,8 +108,8 @@ int hsr_create_self_node(struct list_head *self_node_db, if (!node) return -ENOMEM; - memcpy(node->MacAddressA, addr_a, ETH_ALEN); - memcpy(node->MacAddressB, addr_b, ETH_ALEN); + ether_addr_copy(node->MacAddressA, addr_a); + ether_addr_copy(node->MacAddressB, addr_b); rcu_read_lock(); oldnode = list_first_or_null_rcu(self_node_db, @@ -199,7 +199,7 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv, /* Node is known, but frame was received from an unknown * address. Node is PICS_SUBS capable; merge its AddrB. */ - memcpy(node->MacAddressB, hsr_ethsup->ethhdr.h_source, ETH_ALEN); + ether_addr_copy(node->MacAddressB, hsr_ethsup->ethhdr.h_source); node->AddrB_if = dev_idx; return node; } @@ -208,8 +208,8 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv, if (!node) return NULL; - memcpy(node->MacAddressA, hsr_sp->MacAddressA, ETH_ALEN); - memcpy(node->MacAddressB, hsr_ethsup->ethhdr.h_source, ETH_ALEN); + ether_addr_copy(node->MacAddressA, hsr_sp->MacAddressA); + ether_addr_copy(node->MacAddressB, hsr_ethsup->ethhdr.h_source); if (!ether_addr_equal(hsr_sp->MacAddressA, hsr_ethsup->ethhdr.h_source)) node->AddrB_if = dev_idx; else @@ -250,7 +250,7 @@ void hsr_addr_subst_source(struct hsr_priv *hsr_priv, struct sk_buff *skb) rcu_read_lock(); node = find_node_by_AddrB(&hsr_priv->node_db, ethhdr->h_source); if (node) - memcpy(ethhdr->h_source, node->MacAddressA, ETH_ALEN); + ether_addr_copy(ethhdr->h_source, node->MacAddressA); rcu_read_unlock(); } @@ -272,7 +272,7 @@ void hsr_addr_subst_dest(struct hsr_priv *hsr_priv, struct ethhdr *ethhdr, rcu_read_lock(); node = find_node_by_AddrA(&hsr_priv->node_db, ethhdr->h_dest); if (node && (node->AddrB_if == dev_idx)) - memcpy(ethhdr->h_dest, node->MacAddressB, ETH_ALEN); + ether_addr_copy(ethhdr->h_dest, node->MacAddressB); rcu_read_unlock(); } @@ -428,13 +428,13 @@ void *hsr_get_next_node(struct hsr_priv *hsr_priv, void *_pos, node = list_first_or_null_rcu(&hsr_priv->node_db, struct node_entry, mac_list); if (node) - memcpy(addr, node->MacAddressA, ETH_ALEN); + ether_addr_copy(addr, node->MacAddressA); return node; } node = _pos; list_for_each_entry_continue_rcu(node, &hsr_priv->node_db, mac_list) { - memcpy(addr, node->MacAddressA, ETH_ALEN); + ether_addr_copy(addr, node->MacAddressA); return node; } @@ -462,7 +462,7 @@ int hsr_get_node_data(struct hsr_priv *hsr_priv, return -ENOENT; /* No such entry */ } - memcpy(addr_b, node->MacAddressB, ETH_ALEN); + ether_addr_copy(addr_b, node->MacAddressB); tdiff = jiffies - node->time_in[HSR_DEV_SLAVE_A]; if (node->time_in_stale[HSR_DEV_SLAVE_A]) diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index af68dd83a4e3..3fee5218a691 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -138,8 +138,8 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, break; if (dev == hsr_priv->slave[0]) - memcpy(hsr_priv->dev->dev_addr, - hsr_priv->slave[0]->dev_addr, ETH_ALEN); + ether_addr_copy(hsr_priv->dev->dev_addr, + hsr_priv->slave[0]->dev_addr); /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(&hsr_priv->self_node_db, @@ -459,7 +459,7 @@ static int __init hsr_init(void) static void __exit hsr_exit(void) { unregister_netdevice_notifier(&hsr_nb); - del_timer(&prune_timer); + del_timer_sync(&prune_timer); hsr_netlink_exit(); dev_remove_pack(&hsr_pt); } diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h deleted file mode 100644 index 2b835db3bda8..000000000000 --- a/net/ieee802154/6lowpan.h +++ /dev/null @@ -1,319 +0,0 @@ -/* - * Copyright 2011, Siemens AG - * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> - */ - -/* - * Based on patches from Jon Smirl <jonsmirl@gmail.com> - * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. - */ - -/* Jon's code is based on 6lowpan implementation for Contiki which is: - * Copyright (c) 2008, Swedish Institute of Computer Science. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the Institute nor the names of its contributors - * may be used to endorse or promote products derived from this software - * without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND - * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL - * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS - * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT - * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY - * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF - * SUCH DAMAGE. - */ - -#ifndef __6LOWPAN_H__ -#define __6LOWPAN_H__ - -#define UIP_802154_SHORTADDR_LEN 2 /* compressed ipv6 address length */ -#define UIP_IPH_LEN 40 /* ipv6 fixed header size */ -#define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */ -#define UIP_FRAGH_LEN 8 /* ipv6 fragment header size */ - -/* - * ipv6 address based on mac - * second bit-flip (Universe/Local) is done according RFC2464 - */ -#define is_addr_mac_addr_based(a, m) \ - ((((a)->s6_addr[8]) == (((m)[0]) ^ 0x02)) && \ - (((a)->s6_addr[9]) == (m)[1]) && \ - (((a)->s6_addr[10]) == (m)[2]) && \ - (((a)->s6_addr[11]) == (m)[3]) && \ - (((a)->s6_addr[12]) == (m)[4]) && \ - (((a)->s6_addr[13]) == (m)[5]) && \ - (((a)->s6_addr[14]) == (m)[6]) && \ - (((a)->s6_addr[15]) == (m)[7])) - -/* ipv6 address is unspecified */ -#define is_addr_unspecified(a) \ - ((((a)->s6_addr32[0]) == 0) && \ - (((a)->s6_addr32[1]) == 0) && \ - (((a)->s6_addr32[2]) == 0) && \ - (((a)->s6_addr32[3]) == 0)) - -/* compare ipv6 addresses prefixes */ -#define ipaddr_prefixcmp(addr1, addr2, length) \ - (memcmp(addr1, addr2, length >> 3) == 0) - -/* local link, i.e. FE80::/10 */ -#define is_addr_link_local(a) (((a)->s6_addr16[0]) == htons(0xFE80)) - -/* - * check whether we can compress the IID to 16 bits, - * it's possible for unicast adresses with first 49 bits are zero only. - */ -#define lowpan_is_iid_16_bit_compressable(a) \ - ((((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr[10]) == 0) && \ - (((a)->s6_addr[11]) == 0xff) && \ - (((a)->s6_addr[12]) == 0xfe) && \ - (((a)->s6_addr[13]) == 0)) - -/* multicast address */ -#define is_addr_mcast(a) (((a)->s6_addr[0]) == 0xFF) - -/* check whether the 112-bit gid of the multicast address is mappable to: */ - -/* 9 bits, for FF02::1 (all nodes) and FF02::2 (all routers) addresses only. */ -#define lowpan_is_mcast_addr_compressable(a) \ - ((((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr16[5]) == 0) && \ - (((a)->s6_addr16[6]) == 0) && \ - (((a)->s6_addr[14]) == 0) && \ - ((((a)->s6_addr[15]) == 1) || (((a)->s6_addr[15]) == 2))) - -/* 48 bits, FFXX::00XX:XXXX:XXXX */ -#define lowpan_is_mcast_addr_compressable48(a) \ - ((((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr[10]) == 0)) - -/* 32 bits, FFXX::00XX:XXXX */ -#define lowpan_is_mcast_addr_compressable32(a) \ - ((((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr16[5]) == 0) && \ - (((a)->s6_addr[12]) == 0)) - -/* 8 bits, FF02::00XX */ -#define lowpan_is_mcast_addr_compressable8(a) \ - ((((a)->s6_addr[1]) == 2) && \ - (((a)->s6_addr16[1]) == 0) && \ - (((a)->s6_addr16[2]) == 0) && \ - (((a)->s6_addr16[3]) == 0) && \ - (((a)->s6_addr16[4]) == 0) && \ - (((a)->s6_addr16[5]) == 0) && \ - (((a)->s6_addr16[6]) == 0) && \ - (((a)->s6_addr[14]) == 0)) - -#define lowpan_is_addr_broadcast(a) \ - ((((a)[0]) == 0xFF) && \ - (((a)[1]) == 0xFF) && \ - (((a)[2]) == 0xFF) && \ - (((a)[3]) == 0xFF) && \ - (((a)[4]) == 0xFF) && \ - (((a)[5]) == 0xFF) && \ - (((a)[6]) == 0xFF) && \ - (((a)[7]) == 0xFF)) - -#define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ -#define LOWPAN_DISPATCH_HC1 0x42 /* 01000010 = 66 */ -#define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ -#define LOWPAN_DISPATCH_FRAG1 0xc0 /* 11000xxx */ -#define LOWPAN_DISPATCH_FRAGN 0xe0 /* 11100xxx */ - -#define LOWPAN_DISPATCH_MASK 0xf8 /* 11111000 */ - -#define LOWPAN_FRAG_TIMEOUT (HZ * 60) /* time-out 60 sec */ - -#define LOWPAN_FRAG1_HEAD_SIZE 0x4 -#define LOWPAN_FRAGN_HEAD_SIZE 0x5 - -/* - * According IEEE802.15.4 standard: - * - MTU is 127 octets - * - maximum MHR size is 37 octets - * - MFR size is 2 octets - * - * so minimal payload size that we may guarantee is: - * MTU - MHR - MFR = 88 octets - */ -#define LOWPAN_FRAG_SIZE 88 - -/* - * Values of fields within the IPHC encoding first byte - * (C stands for compressed and I for inline) - */ -#define LOWPAN_IPHC_TF 0x18 - -#define LOWPAN_IPHC_FL_C 0x10 -#define LOWPAN_IPHC_TC_C 0x08 -#define LOWPAN_IPHC_NH_C 0x04 -#define LOWPAN_IPHC_TTL_1 0x01 -#define LOWPAN_IPHC_TTL_64 0x02 -#define LOWPAN_IPHC_TTL_255 0x03 -#define LOWPAN_IPHC_TTL_I 0x00 - - -/* Values of fields within the IPHC encoding second byte */ -#define LOWPAN_IPHC_CID 0x80 - -#define LOWPAN_IPHC_ADDR_00 0x00 -#define LOWPAN_IPHC_ADDR_01 0x01 -#define LOWPAN_IPHC_ADDR_02 0x02 -#define LOWPAN_IPHC_ADDR_03 0x03 - -#define LOWPAN_IPHC_SAC 0x40 -#define LOWPAN_IPHC_SAM 0x30 - -#define LOWPAN_IPHC_SAM_BIT 4 - -#define LOWPAN_IPHC_M 0x08 -#define LOWPAN_IPHC_DAC 0x04 -#define LOWPAN_IPHC_DAM_00 0x00 -#define LOWPAN_IPHC_DAM_01 0x01 -#define LOWPAN_IPHC_DAM_10 0x02 -#define LOWPAN_IPHC_DAM_11 0x03 - -#define LOWPAN_IPHC_DAM_BIT 0 -/* - * LOWPAN_UDP encoding (works together with IPHC) - */ -#define LOWPAN_NHC_UDP_MASK 0xF8 -#define LOWPAN_NHC_UDP_ID 0xF0 -#define LOWPAN_NHC_UDP_CHECKSUMC 0x04 -#define LOWPAN_NHC_UDP_CHECKSUMI 0x00 - -#define LOWPAN_NHC_UDP_4BIT_PORT 0xF0B0 -#define LOWPAN_NHC_UDP_4BIT_MASK 0xFFF0 -#define LOWPAN_NHC_UDP_8BIT_PORT 0xF000 -#define LOWPAN_NHC_UDP_8BIT_MASK 0xFF00 - -/* values for port compression, _with checksum_ ie bit 5 set to 0 */ -#define LOWPAN_NHC_UDP_CS_P_00 0xF0 /* all inline */ -#define LOWPAN_NHC_UDP_CS_P_01 0xF1 /* source 16bit inline, - dest = 0xF0 + 8 bit inline */ -#define LOWPAN_NHC_UDP_CS_P_10 0xF2 /* source = 0xF0 + 8bit inline, - dest = 16 bit inline */ -#define LOWPAN_NHC_UDP_CS_P_11 0xF3 /* source & dest = 0xF0B + 4bit inline */ -#define LOWPAN_NHC_UDP_CS_C 0x04 /* checksum elided */ - -#ifdef DEBUG -/* print data in line */ -static inline void raw_dump_inline(const char *caller, char *msg, - unsigned char *buf, int len) -{ - if (msg) - pr_debug("%s():%s: ", caller, msg); - - print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, buf, len, false); -} - -/* print data in a table format: - * - * addr: xx xx xx xx xx xx - * addr: xx xx xx xx xx xx - * ... - */ -static inline void raw_dump_table(const char *caller, char *msg, - unsigned char *buf, int len) -{ - if (msg) - pr_debug("%s():%s:\n", caller, msg); - - print_hex_dump_debug("\t", DUMP_PREFIX_OFFSET, 16, 1, buf, len, false); -} -#else -static inline void raw_dump_table(const char *caller, char *msg, - unsigned char *buf, int len) { } -static inline void raw_dump_inline(const char *caller, char *msg, - unsigned char *buf, int len) { } -#endif - -static inline int lowpan_fetch_skb_u8(struct sk_buff *skb, u8 *val) -{ - if (unlikely(!pskb_may_pull(skb, 1))) - return -EINVAL; - - *val = skb->data[0]; - skb_pull(skb, 1); - - return 0; -} - -static inline int lowpan_fetch_skb_u16(struct sk_buff *skb, u16 *val) -{ - if (unlikely(!pskb_may_pull(skb, 2))) - return -EINVAL; - - *val = (skb->data[0] << 8) | skb->data[1]; - skb_pull(skb, 2); - - return 0; -} - -static inline bool lowpan_fetch_skb(struct sk_buff *skb, - void *data, const unsigned int len) -{ - if (unlikely(!pskb_may_pull(skb, len))) - return true; - - skb_copy_from_linear_data(skb, data, len); - skb_pull(skb, len); - - return false; -} - -static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, - const size_t len) -{ - memcpy(*hc_ptr, data, len); - *hc_ptr += len; -} - -typedef int (*skb_delivery_cb)(struct sk_buff *skb, struct net_device *dev); - -int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, - const u8 *saddr, const u8 saddr_type, const u8 saddr_len, - const u8 *daddr, const u8 daddr_type, const u8 daddr_len, - u8 iphc0, u8 iphc1, skb_delivery_cb skb_deliver); -int lowpan_header_compress(struct sk_buff *skb, struct net_device *dev, - unsigned short type, const void *_daddr, - const void *_saddr, unsigned int len); - -#endif /* __6LOWPAN_H__ */ diff --git a/net/ieee802154/6lowpan_iphc.c b/net/ieee802154/6lowpan_iphc.c index 860aa2d445ba..211b5686d719 100644 --- a/net/ieee802154/6lowpan_iphc.c +++ b/net/ieee802154/6lowpan_iphc.c @@ -54,11 +54,10 @@ #include <linux/if_arp.h> #include <linux/module.h> #include <linux/netdevice.h> +#include <net/6lowpan.h> #include <net/ipv6.h> #include <net/af_ieee802154.h> -#include "6lowpan.h" - /* * Uncompress address function for source and * destination address(non-multicast). diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan_rtnl.c index 8edfea5da572..0f5a69ed746d 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan_rtnl.c @@ -1,10 +1,8 @@ -/* - * Copyright 2011, Siemens AG +/* Copyright 2011, Siemens AG * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ -/* - * Based on patches from Jon Smirl <jonsmirl@gmail.com> +/* Based on patches from Jon Smirl <jonsmirl@gmail.com> * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> * * This program is free software; you can redistribute it and/or modify @@ -15,10 +13,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. */ /* Jon's code is based on 6lowpan implementation for Contiki which is: @@ -58,9 +52,10 @@ #include <net/af_ieee802154.h> #include <net/ieee802154.h> #include <net/ieee802154_netdev.h> +#include <net/6lowpan.h> #include <net/ipv6.h> -#include "6lowpan.h" +#include "reassembly.h" static LIST_HEAD(lowpan_devices); @@ -68,7 +63,7 @@ static LIST_HEAD(lowpan_devices); struct lowpan_dev_info { struct net_device *real_dev; /* real WPAN device ptr */ struct mutex dev_list_mtx; /* mutex for list ops */ - unsigned short fragment_tag; + __be16 fragment_tag; }; struct lowpan_dev_record { @@ -76,18 +71,6 @@ struct lowpan_dev_record { struct list_head list; }; -struct lowpan_fragment { - struct sk_buff *skb; /* skb to be assembled */ - u16 length; /* length to be assemled */ - u32 bytes_rcv; /* bytes received */ - u16 tag; /* current fragment tag */ - struct timer_list timer; /* assembling timer */ - struct list_head list; /* fragments list */ -}; - -static LIST_HEAD(lowpan_fragments); -static DEFINE_SPINLOCK(flist_lock); - static inline struct lowpan_dev_info *lowpan_dev_info(const struct net_device *dev) { @@ -124,13 +107,11 @@ static int lowpan_header_create(struct sk_buff *skb, lowpan_header_compress(skb, dev, type, daddr, saddr, len); - /* - * NOTE1: I'm still unsure about the fact that compression and WPAN + /* NOTE1: I'm still unsure about the fact that compression and WPAN * header are created here and not later in the xmit. So wait for * an opinion of net maintainers. */ - /* - * NOTE2: to be absolutely correct, we must derive PANid information + /* NOTE2: to be absolutely correct, we must derive PANid information * from MAC subif of the 'dev' and 'real_dev' network devices, but * this isn't implemented in mainline yet, so currently we assign 0xff */ @@ -138,30 +119,29 @@ static int lowpan_header_create(struct sk_buff *skb, mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev); /* prepare wpan address data */ - sa.addr_type = IEEE802154_ADDR_LONG; + sa.mode = IEEE802154_ADDR_LONG; sa.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + sa.extended_addr = ieee802154_devaddr_from_raw(saddr); - memcpy(&(sa.hwaddr), saddr, 8); /* intra-PAN communications */ - da.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); + da.pan_id = sa.pan_id; - /* - * if the destination address is the broadcast address, use the + /* if the destination address is the broadcast address, use the * corresponding short address */ if (lowpan_is_addr_broadcast(daddr)) { - da.addr_type = IEEE802154_ADDR_SHORT; - da.short_addr = IEEE802154_ADDR_BROADCAST; + da.mode = IEEE802154_ADDR_SHORT; + da.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); } else { - da.addr_type = IEEE802154_ADDR_LONG; - memcpy(&(da.hwaddr), daddr, IEEE802154_ADDR_LEN); + da.mode = IEEE802154_ADDR_LONG; + da.extended_addr = ieee802154_devaddr_from_raw(daddr); /* request acknowledgment */ mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ; } return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev, - type, (void *)&da, (void *)&sa, skb->len); + type, (void *)&da, (void *)&sa, 0); } static int lowpan_give_skb_to_devices(struct sk_buff *skb, @@ -188,73 +168,11 @@ static int lowpan_give_skb_to_devices(struct sk_buff *skb, return stat; } -static void lowpan_fragment_timer_expired(unsigned long entry_addr) -{ - struct lowpan_fragment *entry = (struct lowpan_fragment *)entry_addr; - - pr_debug("timer expired for frame with tag %d\n", entry->tag); - - list_del(&entry->list); - dev_kfree_skb(entry->skb); - kfree(entry); -} - -static struct lowpan_fragment * -lowpan_alloc_new_frame(struct sk_buff *skb, u16 len, u16 tag) -{ - struct lowpan_fragment *frame; - - frame = kzalloc(sizeof(struct lowpan_fragment), - GFP_ATOMIC); - if (!frame) - goto frame_err; - - INIT_LIST_HEAD(&frame->list); - - frame->length = len; - frame->tag = tag; - - /* allocate buffer for frame assembling */ - frame->skb = netdev_alloc_skb_ip_align(skb->dev, frame->length + - sizeof(struct ipv6hdr)); - - if (!frame->skb) - goto skb_err; - - frame->skb->priority = skb->priority; - - /* reserve headroom for uncompressed ipv6 header */ - skb_reserve(frame->skb, sizeof(struct ipv6hdr)); - skb_put(frame->skb, frame->length); - - /* copy the first control block to keep a - * trace of the link-layer addresses in case - * of a link-local compressed address - */ - memcpy(frame->skb->cb, skb->cb, sizeof(skb->cb)); - - init_timer(&frame->timer); - /* time out is the same as for ipv6 - 60 sec */ - frame->timer.expires = jiffies + LOWPAN_FRAG_TIMEOUT; - frame->timer.data = (unsigned long)frame; - frame->timer.function = lowpan_fragment_timer_expired; - - add_timer(&frame->timer); - - list_add_tail(&frame->list, &lowpan_fragments); - - return frame; - -skb_err: - kfree(frame); -frame_err: - return NULL; -} - -static int process_data(struct sk_buff *skb) +static int process_data(struct sk_buff *skb, const struct ieee802154_hdr *hdr) { u8 iphc0, iphc1; - const struct ieee802154_addr *_saddr, *_daddr; + struct ieee802154_addr_sa sa, da; + void *sap, *dap; raw_dump_table(__func__, "raw skb data dump", skb->data, skb->len); /* at least two bytes will be used for the encoding */ @@ -264,108 +182,27 @@ static int process_data(struct sk_buff *skb) if (lowpan_fetch_skb_u8(skb, &iphc0)) goto drop; - /* fragments assembling */ - switch (iphc0 & LOWPAN_DISPATCH_MASK) { - case LOWPAN_DISPATCH_FRAG1: - case LOWPAN_DISPATCH_FRAGN: - { - struct lowpan_fragment *frame; - /* slen stores the rightmost 8 bits of the 11 bits length */ - u8 slen, offset = 0; - u16 len, tag; - bool found = false; - - if (lowpan_fetch_skb_u8(skb, &slen) || /* frame length */ - lowpan_fetch_skb_u16(skb, &tag)) /* fragment tag */ - goto drop; - - /* adds the 3 MSB to the 8 LSB to retrieve the 11 bits length */ - len = ((iphc0 & 7) << 8) | slen; - - if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1) { - pr_debug("%s received a FRAG1 packet (tag: %d, " - "size of the entire IP packet: %d)", - __func__, tag, len); - } else { /* FRAGN */ - if (lowpan_fetch_skb_u8(skb, &offset)) - goto unlock_and_drop; - pr_debug("%s received a FRAGN packet (tag: %d, " - "size of the entire IP packet: %d, " - "offset: %d)", __func__, tag, len, offset * 8); - } - - /* - * check if frame assembling with the same tag is - * already in progress - */ - spin_lock_bh(&flist_lock); - - list_for_each_entry(frame, &lowpan_fragments, list) - if (frame->tag == tag) { - found = true; - break; - } - - /* alloc new frame structure */ - if (!found) { - pr_debug("%s first fragment received for tag %d, " - "begin packet reassembly", __func__, tag); - frame = lowpan_alloc_new_frame(skb, len, tag); - if (!frame) - goto unlock_and_drop; - } - - /* if payload fits buffer, copy it */ - if (likely((offset * 8 + skb->len) <= frame->length)) - skb_copy_to_linear_data_offset(frame->skb, offset * 8, - skb->data, skb->len); - else - goto unlock_and_drop; - - frame->bytes_rcv += skb->len; - - /* frame assembling complete */ - if ((frame->bytes_rcv == frame->length) && - frame->timer.expires > jiffies) { - /* if timer haven't expired - first of all delete it */ - del_timer_sync(&frame->timer); - list_del(&frame->list); - spin_unlock_bh(&flist_lock); - - pr_debug("%s successfully reassembled fragment " - "(tag %d)", __func__, tag); - - dev_kfree_skb(skb); - skb = frame->skb; - kfree(frame); - - if (lowpan_fetch_skb_u8(skb, &iphc0)) - goto drop; - - break; - } - spin_unlock_bh(&flist_lock); - - return kfree_skb(skb), 0; - } - default: - break; - } - if (lowpan_fetch_skb_u8(skb, &iphc1)) goto drop; - _saddr = &mac_cb(skb)->sa; - _daddr = &mac_cb(skb)->da; + ieee802154_addr_to_sa(&sa, &hdr->source); + ieee802154_addr_to_sa(&da, &hdr->dest); + + if (sa.addr_type == IEEE802154_ADDR_SHORT) + sap = &sa.short_addr; + else + sap = &sa.hwaddr; - return lowpan_process_data(skb, skb->dev, (u8 *)_saddr->hwaddr, - _saddr->addr_type, IEEE802154_ADDR_LEN, - (u8 *)_daddr->hwaddr, _daddr->addr_type, - IEEE802154_ADDR_LEN, iphc0, iphc1, - lowpan_give_skb_to_devices); + if (da.addr_type == IEEE802154_ADDR_SHORT) + dap = &da.short_addr; + else + dap = &da.hwaddr; + + return lowpan_process_data(skb, skb->dev, sap, sa.addr_type, + IEEE802154_ADDR_LEN, dap, da.addr_type, + IEEE802154_ADDR_LEN, iphc0, iphc1, + lowpan_give_skb_to_devices); -unlock_and_drop: - spin_unlock_bh(&flist_lock); drop: kfree_skb(skb); return -EINVAL; @@ -386,7 +223,7 @@ static int lowpan_set_address(struct net_device *dev, void *p) static int lowpan_fragment_xmit(struct sk_buff *skb, u8 *head, - int mlen, int plen, int offset, int type) + int mlen, int plen, int offset, int type) { struct sk_buff *frag; int hlen; @@ -422,51 +259,68 @@ lowpan_fragment_xmit(struct sk_buff *skb, u8 *head, static int lowpan_skb_fragmentation(struct sk_buff *skb, struct net_device *dev) { - int err, header_length, payload_length, tag, offset = 0; + int err; + u16 dgram_offset, dgram_size, payload_length, header_length, + lowpan_size, frag_plen, offset; + __be16 tag; u8 head[5]; header_length = skb->mac_len; payload_length = skb->len - header_length; tag = lowpan_dev_info(dev)->fragment_tag++; + lowpan_size = skb_network_header_len(skb); + dgram_size = lowpan_uncompress_size(skb, &dgram_offset) - + header_length; /* first fragment header */ - head[0] = LOWPAN_DISPATCH_FRAG1 | ((payload_length >> 8) & 0x7); - head[1] = payload_length & 0xff; - head[2] = tag >> 8; - head[3] = tag & 0xff; + head[0] = LOWPAN_DISPATCH_FRAG1 | ((dgram_size >> 8) & 0x7); + head[1] = dgram_size & 0xff; + memcpy(head + 2, &tag, sizeof(tag)); - err = lowpan_fragment_xmit(skb, head, header_length, LOWPAN_FRAG_SIZE, - 0, LOWPAN_DISPATCH_FRAG1); + /* calc the nearest payload length(divided to 8) for first fragment + * which fits into a IEEE802154_MTU + */ + frag_plen = round_down(IEEE802154_MTU - header_length - + LOWPAN_FRAG1_HEAD_SIZE - lowpan_size - + IEEE802154_MFR_SIZE, 8); + err = lowpan_fragment_xmit(skb, head, header_length, + frag_plen + lowpan_size, 0, + LOWPAN_DISPATCH_FRAG1); if (err) { pr_debug("%s unable to send FRAG1 packet (tag: %d)", __func__, tag); goto exit; } - offset = LOWPAN_FRAG_SIZE; + offset = lowpan_size + frag_plen; + dgram_offset += frag_plen; /* next fragment header */ head[0] &= ~LOWPAN_DISPATCH_FRAG1; head[0] |= LOWPAN_DISPATCH_FRAGN; + frag_plen = round_down(IEEE802154_MTU - header_length - + LOWPAN_FRAGN_HEAD_SIZE - IEEE802154_MFR_SIZE, 8); + while (payload_length - offset > 0) { - int len = LOWPAN_FRAG_SIZE; + int len = frag_plen; - head[4] = offset / 8; + head[4] = dgram_offset >> 3; if (payload_length - offset < len) len = payload_length - offset; - err = lowpan_fragment_xmit(skb, head, header_length, - len, offset, LOWPAN_DISPATCH_FRAGN); + err = lowpan_fragment_xmit(skb, head, header_length, len, + offset, LOWPAN_DISPATCH_FRAGN); if (err) { - pr_debug("%s unable to send a subsequent FRAGN packet " - "(tag: %d, offset: %d", __func__, tag, offset); + pr_debug("%s unable to send a FRAGN packet. (tag: %d, offset: %d)\n", + __func__, tag, offset); goto exit; } offset += len; + dgram_offset += len; } exit: @@ -508,13 +362,13 @@ static struct wpan_phy *lowpan_get_phy(const struct net_device *dev) return ieee802154_mlme_ops(real_dev)->get_phy(real_dev); } -static u16 lowpan_get_pan_id(const struct net_device *dev) +static __le16 lowpan_get_pan_id(const struct net_device *dev) { struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; return ieee802154_mlme_ops(real_dev)->get_pan_id(real_dev); } -static u16 lowpan_get_short_addr(const struct net_device *dev) +static __le16 lowpan_get_short_addr(const struct net_device *dev) { struct net_device *real_dev = lowpan_dev_info(dev)->real_dev; return ieee802154_mlme_ops(real_dev)->get_short_addr(real_dev); @@ -593,45 +447,55 @@ static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct sk_buff *local_skb; + struct ieee802154_hdr hdr; + int ret; - if (!netif_running(dev)) + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) goto drop; + if (!netif_running(dev)) + goto drop_skb; + if (dev->type != ARPHRD_IEEE802154) - goto drop; + goto drop_skb; + + if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) + goto drop_skb; /* check that it's our buffer */ if (skb->data[0] == LOWPAN_DISPATCH_IPV6) { - /* Copy the packet so that the IPv6 header is - * properly aligned. - */ - local_skb = skb_copy_expand(skb, NET_SKB_PAD - 1, - skb_tailroom(skb), GFP_ATOMIC); - if (!local_skb) - goto drop; - - local_skb->protocol = htons(ETH_P_IPV6); - local_skb->pkt_type = PACKET_HOST; + skb->protocol = htons(ETH_P_IPV6); + skb->pkt_type = PACKET_HOST; /* Pull off the 1-byte of 6lowpan header. */ - skb_pull(local_skb, 1); - - lowpan_give_skb_to_devices(local_skb, NULL); + skb_pull(skb, 1); - kfree_skb(local_skb); - kfree_skb(skb); + ret = lowpan_give_skb_to_devices(skb, NULL); + if (ret == NET_RX_DROP) + goto drop; } else { switch (skb->data[0] & 0xe0) { case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ + ret = process_data(skb, &hdr); + if (ret == NET_RX_DROP) + goto drop; + break; case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ + ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAG1); + if (ret == 1) { + ret = process_data(skb, &hdr); + if (ret == NET_RX_DROP) + goto drop; + } + break; case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */ - local_skb = skb_clone(skb, GFP_ATOMIC); - if (!local_skb) - goto drop; - process_data(local_skb); - - kfree_skb(skb); + ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAGN); + if (ret == 1) { + ret = process_data(skb, &hdr); + if (ret == NET_RX_DROP) + goto drop; + } break; default: break; @@ -639,9 +503,9 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, } return NET_RX_SUCCESS; - -drop: +drop_skb: kfree_skb(skb); +drop: return NET_RX_DROP; } @@ -665,10 +529,9 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, } lowpan_dev_info(dev)->real_dev = real_dev; - lowpan_dev_info(dev)->fragment_tag = 0; mutex_init(&lowpan_dev_info(dev)->dev_list_mtx); - entry = kzalloc(sizeof(struct lowpan_dev_record), GFP_KERNEL); + entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { dev_put(real_dev); lowpan_dev_info(dev)->real_dev = NULL; @@ -761,7 +624,7 @@ static struct notifier_block lowpan_dev_notifier = { }; static struct packet_type lowpan_packet_type = { - .type = __constant_htons(ETH_P_IEEE802154), + .type = htons(ETH_P_IEEE802154), .func = lowpan_rcv, }; @@ -769,43 +632,40 @@ static int __init lowpan_init_module(void) { int err = 0; - err = lowpan_netlink_init(); + err = lowpan_net_frag_init(); if (err < 0) goto out; + err = lowpan_netlink_init(); + if (err < 0) + goto out_frag; + dev_add_pack(&lowpan_packet_type); err = register_netdevice_notifier(&lowpan_dev_notifier); - if (err < 0) { - dev_remove_pack(&lowpan_packet_type); - lowpan_netlink_fini(); - } + if (err < 0) + goto out_pack; + + return 0; + +out_pack: + dev_remove_pack(&lowpan_packet_type); + lowpan_netlink_fini(); +out_frag: + lowpan_net_frag_exit(); out: return err; } static void __exit lowpan_cleanup_module(void) { - struct lowpan_fragment *frame, *tframe; - lowpan_netlink_fini(); dev_remove_pack(&lowpan_packet_type); - unregister_netdevice_notifier(&lowpan_dev_notifier); + lowpan_net_frag_exit(); - /* Now 6lowpan packet_type is removed, so no new fragments are - * expected on RX, therefore that's the time to clean incomplete - * fragments. - */ - spin_lock_bh(&flist_lock); - list_for_each_entry_safe(frame, tframe, &lowpan_fragments, list) { - del_timer_sync(&frame->timer); - list_del(&frame->list); - dev_kfree_skb(frame->skb); - kfree(frame); - } - spin_unlock_bh(&flist_lock); + unregister_netdevice_notifier(&lowpan_dev_notifier); } module_init(lowpan_init_module); diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig index 9c9879d5ea64..8af1330b3137 100644 --- a/net/ieee802154/Kconfig +++ b/net/ieee802154/Kconfig @@ -15,7 +15,7 @@ config IEEE802154_6LOWPAN depends on IEEE802154 && IPV6 select 6LOWPAN_IPHC ---help--- - IPv6 compression over IEEE 802.15.4. + IPv6 compression over IEEE 802.15.4. config 6LOWPAN_IPHC tristate diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index e8f05885ced6..bf1b51497a41 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -2,5 +2,9 @@ obj-$(CONFIG_IEEE802154) += ieee802154.o af_802154.o obj-$(CONFIG_IEEE802154_6LOWPAN) += 6lowpan.o obj-$(CONFIG_6LOWPAN_IPHC) += 6lowpan_iphc.o -ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o +6lowpan-y := 6lowpan_rtnl.o reassembly.o +ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o \ + header_ops.o af_802154-y := af_ieee802154.o raw.o dgram.o + +ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/ieee802154/af802154.h b/net/ieee802154/af802154.h index b1ec52537522..8330a09bfc95 100644 --- a/net/ieee802154/af802154.h +++ b/net/ieee802154/af802154.h @@ -25,12 +25,13 @@ #define AF802154_H struct sk_buff; -struct net_devce; +struct net_device; +struct ieee802154_addr; extern struct proto ieee802154_raw_prot; extern struct proto ieee802154_dgram_prot; void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb); int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb); struct net_device *ieee802154_get_dev(struct net *net, - struct ieee802154_addr *addr); + const struct ieee802154_addr *addr); #endif diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index 40e606f3788f..351d9a94ec2f 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -43,25 +43,27 @@ /* * Utility function for families */ -struct net_device *ieee802154_get_dev(struct net *net, - struct ieee802154_addr *addr) +struct net_device* +ieee802154_get_dev(struct net *net, const struct ieee802154_addr *addr) { struct net_device *dev = NULL; struct net_device *tmp; - u16 pan_id, short_addr; + __le16 pan_id, short_addr; + u8 hwaddr[IEEE802154_ADDR_LEN]; - switch (addr->addr_type) { + switch (addr->mode) { case IEEE802154_ADDR_LONG: + ieee802154_devaddr_to_raw(hwaddr, addr->extended_addr); rcu_read_lock(); - dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, addr->hwaddr); + dev = dev_getbyhwaddr_rcu(net, ARPHRD_IEEE802154, hwaddr); if (dev) dev_hold(dev); rcu_read_unlock(); break; case IEEE802154_ADDR_SHORT: - if (addr->pan_id == 0xffff || - addr->short_addr == IEEE802154_ADDR_UNDEF || - addr->short_addr == 0xffff) + if (addr->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST) || + addr->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) || + addr->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) break; rtnl_lock(); @@ -86,7 +88,7 @@ struct net_device *ieee802154_get_dev(struct net *net, break; default: pr_warning("Unsupported ieee802154 address type: %d\n", - addr->addr_type); + addr->mode); break; } @@ -326,7 +328,7 @@ drop: static struct packet_type ieee802154_packet_type = { - .type = __constant_htons(ETH_P_IEEE802154), + .type = htons(ETH_P_IEEE802154), .func = ieee802154_rcv, }; diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 1846c1fe0d06..786437bc0c08 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -73,10 +73,10 @@ static int dgram_init(struct sock *sk) { struct dgram_sock *ro = dgram_sk(sk); - ro->dst_addr.addr_type = IEEE802154_ADDR_LONG; - ro->dst_addr.pan_id = 0xffff; + ro->dst_addr.mode = IEEE802154_ADDR_LONG; + ro->dst_addr.pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); ro->want_ack = 1; - memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr)); + memset(&ro->dst_addr.extended_addr, 0xff, IEEE802154_ADDR_LEN); return 0; } @@ -88,6 +88,7 @@ static void dgram_close(struct sock *sk, long timeout) static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) { struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr; + struct ieee802154_addr haddr; struct dgram_sock *ro = dgram_sk(sk); int err = -EINVAL; struct net_device *dev; @@ -102,7 +103,8 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) if (addr->family != AF_IEEE802154) goto out; - dev = ieee802154_get_dev(sock_net(sk), &addr->addr); + ieee802154_addr_from_sa(&haddr, &addr->addr); + dev = ieee802154_get_dev(sock_net(sk), &haddr); if (!dev) { err = -ENODEV; goto out; @@ -113,7 +115,7 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) goto out_put; } - memcpy(&ro->src_addr, &addr->addr, sizeof(struct ieee802154_addr)); + ro->src_addr = haddr; ro->bound = 1; err = 0; @@ -149,8 +151,7 @@ static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg) * of this packet since that is all * that will be read. */ - /* FIXME: parse the header for more correct value */ - amount = skb->len - (3+8+8); + amount = skb->len - ieee802154_hdr_length(skb); } spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); @@ -181,7 +182,7 @@ static int dgram_connect(struct sock *sk, struct sockaddr *uaddr, goto out; } - memcpy(&ro->dst_addr, &addr->addr, sizeof(struct ieee802154_addr)); + ieee802154_addr_from_sa(&ro->dst_addr, &addr->addr); out: release_sock(sk); @@ -194,8 +195,8 @@ static int dgram_disconnect(struct sock *sk, int flags) lock_sock(sk); - ro->dst_addr.addr_type = IEEE802154_ADDR_LONG; - memset(&ro->dst_addr.hwaddr, 0xff, sizeof(ro->dst_addr.hwaddr)); + ro->dst_addr.mode = IEEE802154_ADDR_LONG; + memset(&ro->dst_addr.extended_addr, 0xff, IEEE802154_ADDR_LEN); release_sock(sk); @@ -232,7 +233,7 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, if (size > mtu) { pr_debug("size = %Zu, mtu = %u\n", size, mtu); - err = -EINVAL; + err = -EMSGSIZE; goto out_dev; } @@ -312,7 +313,7 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk, if (saddr) { saddr->family = AF_IEEE802154; - saddr->addr = mac_cb(skb)->sa; + ieee802154_addr_to_sa(&saddr->addr, &mac_cb(skb)->source); *addr_len = sizeof(*saddr); } @@ -328,6 +329,10 @@ out: static int dgram_rcv_skb(struct sock *sk, struct sk_buff *skb) { + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return NET_RX_DROP; + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; @@ -336,40 +341,43 @@ static int dgram_rcv_skb(struct sock *sk, struct sk_buff *skb) return NET_RX_SUCCESS; } -static inline int ieee802154_match_sock(u8 *hw_addr, u16 pan_id, - u16 short_addr, struct dgram_sock *ro) +static inline bool +ieee802154_match_sock(__le64 hw_addr, __le16 pan_id, __le16 short_addr, + struct dgram_sock *ro) { if (!ro->bound) - return 1; + return true; - if (ro->src_addr.addr_type == IEEE802154_ADDR_LONG && - !memcmp(ro->src_addr.hwaddr, hw_addr, IEEE802154_ADDR_LEN)) - return 1; + if (ro->src_addr.mode == IEEE802154_ADDR_LONG && + hw_addr == ro->src_addr.extended_addr) + return true; - if (ro->src_addr.addr_type == IEEE802154_ADDR_SHORT && - pan_id == ro->src_addr.pan_id && - short_addr == ro->src_addr.short_addr) - return 1; + if (ro->src_addr.mode == IEEE802154_ADDR_SHORT && + pan_id == ro->src_addr.pan_id && + short_addr == ro->src_addr.short_addr) + return true; - return 0; + return false; } int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) { struct sock *sk, *prev = NULL; int ret = NET_RX_SUCCESS; - u16 pan_id, short_addr; + __le16 pan_id, short_addr; + __le64 hw_addr; /* Data frame processing */ BUG_ON(dev->type != ARPHRD_IEEE802154); pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev); + hw_addr = ieee802154_devaddr_from_raw(dev->dev_addr); read_lock(&dgram_lock); sk_for_each(sk, &dgram_head) { - if (ieee802154_match_sock(dev->dev_addr, pan_id, short_addr, - dgram_sk(sk))) { + if (ieee802154_match_sock(hw_addr, pan_id, short_addr, + dgram_sk(sk))) { if (prev) { struct sk_buff *clone; clone = skb_clone(skb, GFP_ATOMIC); diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c new file mode 100644 index 000000000000..bed42a48408c --- /dev/null +++ b/net/ieee802154/header_ops.c @@ -0,0 +1,287 @@ +/* + * Copyright (C) 2014 Fraunhofer ITWM + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Written by: + * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de> + */ + +#include <net/mac802154.h> +#include <net/ieee802154.h> +#include <net/ieee802154_netdev.h> + +static int +ieee802154_hdr_push_addr(u8 *buf, const struct ieee802154_addr *addr, + bool omit_pan) +{ + int pos = 0; + + if (addr->mode == IEEE802154_ADDR_NONE) + return 0; + + if (!omit_pan) { + memcpy(buf + pos, &addr->pan_id, 2); + pos += 2; + } + + switch (addr->mode) { + case IEEE802154_ADDR_SHORT: + memcpy(buf + pos, &addr->short_addr, 2); + pos += 2; + break; + + case IEEE802154_ADDR_LONG: + memcpy(buf + pos, &addr->extended_addr, IEEE802154_ADDR_LEN); + pos += IEEE802154_ADDR_LEN; + break; + + default: + return -EINVAL; + } + + return pos; +} + +static int +ieee802154_hdr_push_sechdr(u8 *buf, const struct ieee802154_sechdr *hdr) +{ + int pos = 5; + + memcpy(buf, hdr, 1); + memcpy(buf + 1, &hdr->frame_counter, 4); + + switch (hdr->key_id_mode) { + case IEEE802154_SCF_KEY_IMPLICIT: + return pos; + + case IEEE802154_SCF_KEY_INDEX: + break; + + case IEEE802154_SCF_KEY_SHORT_INDEX: + memcpy(buf + pos, &hdr->short_src, 4); + pos += 4; + break; + + case IEEE802154_SCF_KEY_HW_INDEX: + memcpy(buf + pos, &hdr->extended_src, IEEE802154_ADDR_LEN); + pos += IEEE802154_ADDR_LEN; + break; + } + + buf[pos++] = hdr->key_id; + + return pos; +} + +int +ieee802154_hdr_push(struct sk_buff *skb, const struct ieee802154_hdr *hdr) +{ + u8 buf[MAC802154_FRAME_HARD_HEADER_LEN]; + int pos = 2; + int rc; + struct ieee802154_hdr_fc fc = hdr->fc; + + buf[pos++] = hdr->seq; + + fc.dest_addr_mode = hdr->dest.mode; + + rc = ieee802154_hdr_push_addr(buf + pos, &hdr->dest, false); + if (rc < 0) + return -EINVAL; + pos += rc; + + fc.source_addr_mode = hdr->source.mode; + + if (hdr->source.pan_id == hdr->dest.pan_id && + hdr->dest.mode != IEEE802154_ADDR_NONE) + fc.intra_pan = true; + + rc = ieee802154_hdr_push_addr(buf + pos, &hdr->source, fc.intra_pan); + if (rc < 0) + return -EINVAL; + pos += rc; + + if (fc.security_enabled) { + fc.version = 1; + + rc = ieee802154_hdr_push_sechdr(buf + pos, &hdr->sec); + if (rc < 0) + return -EINVAL; + + pos += rc; + } + + memcpy(buf, &fc, 2); + + memcpy(skb_push(skb, pos), buf, pos); + + return pos; +} +EXPORT_SYMBOL_GPL(ieee802154_hdr_push); + +static int +ieee802154_hdr_get_addr(const u8 *buf, int mode, bool omit_pan, + struct ieee802154_addr *addr) +{ + int pos = 0; + + addr->mode = mode; + + if (mode == IEEE802154_ADDR_NONE) + return 0; + + if (!omit_pan) { + memcpy(&addr->pan_id, buf + pos, 2); + pos += 2; + } + + if (mode == IEEE802154_ADDR_SHORT) { + memcpy(&addr->short_addr, buf + pos, 2); + return pos + 2; + } else { + memcpy(&addr->extended_addr, buf + pos, IEEE802154_ADDR_LEN); + return pos + IEEE802154_ADDR_LEN; + } +} + +static int ieee802154_hdr_addr_len(int mode, bool omit_pan) +{ + int pan_len = omit_pan ? 0 : 2; + + switch (mode) { + case IEEE802154_ADDR_NONE: return 0; + case IEEE802154_ADDR_SHORT: return 2 + pan_len; + case IEEE802154_ADDR_LONG: return IEEE802154_ADDR_LEN + pan_len; + default: return -EINVAL; + } +} + +static int +ieee802154_hdr_get_sechdr(const u8 *buf, struct ieee802154_sechdr *hdr) +{ + int pos = 5; + + memcpy(hdr, buf, 1); + memcpy(&hdr->frame_counter, buf + 1, 4); + + switch (hdr->key_id_mode) { + case IEEE802154_SCF_KEY_IMPLICIT: + return pos; + + case IEEE802154_SCF_KEY_INDEX: + break; + + case IEEE802154_SCF_KEY_SHORT_INDEX: + memcpy(&hdr->short_src, buf + pos, 4); + pos += 4; + break; + + case IEEE802154_SCF_KEY_HW_INDEX: + memcpy(&hdr->extended_src, buf + pos, IEEE802154_ADDR_LEN); + pos += IEEE802154_ADDR_LEN; + break; + } + + hdr->key_id = buf[pos++]; + + return pos; +} + +static int ieee802154_hdr_sechdr_len(u8 sc) +{ + switch (IEEE802154_SCF_KEY_ID_MODE(sc)) { + case IEEE802154_SCF_KEY_IMPLICIT: return 5; + case IEEE802154_SCF_KEY_INDEX: return 6; + case IEEE802154_SCF_KEY_SHORT_INDEX: return 10; + case IEEE802154_SCF_KEY_HW_INDEX: return 14; + default: return -EINVAL; + } +} + +static int ieee802154_hdr_minlen(const struct ieee802154_hdr *hdr) +{ + int dlen, slen; + + dlen = ieee802154_hdr_addr_len(hdr->fc.dest_addr_mode, false); + slen = ieee802154_hdr_addr_len(hdr->fc.source_addr_mode, + hdr->fc.intra_pan); + + if (slen < 0 || dlen < 0) + return -EINVAL; + + return 3 + dlen + slen + hdr->fc.security_enabled; +} + +static int +ieee802154_hdr_get_addrs(const u8 *buf, struct ieee802154_hdr *hdr) +{ + int pos = 0; + + pos += ieee802154_hdr_get_addr(buf + pos, hdr->fc.dest_addr_mode, + false, &hdr->dest); + pos += ieee802154_hdr_get_addr(buf + pos, hdr->fc.source_addr_mode, + hdr->fc.intra_pan, &hdr->source); + + if (hdr->fc.intra_pan) + hdr->source.pan_id = hdr->dest.pan_id; + + return pos; +} + +int +ieee802154_hdr_pull(struct sk_buff *skb, struct ieee802154_hdr *hdr) +{ + int pos = 3, rc; + + if (!pskb_may_pull(skb, 3)) + return -EINVAL; + + memcpy(hdr, skb->data, 3); + + rc = ieee802154_hdr_minlen(hdr); + if (rc < 0 || !pskb_may_pull(skb, rc)) + return -EINVAL; + + pos += ieee802154_hdr_get_addrs(skb->data + pos, hdr); + + if (hdr->fc.security_enabled) { + int want = pos + ieee802154_hdr_sechdr_len(skb->data[pos]); + + if (!pskb_may_pull(skb, want)) + return -EINVAL; + + pos += ieee802154_hdr_get_sechdr(skb->data + pos, &hdr->sec); + } + + skb_pull(skb, pos); + return pos; +} +EXPORT_SYMBOL_GPL(ieee802154_hdr_pull); + +int +ieee802154_hdr_peek_addrs(const struct sk_buff *skb, struct ieee802154_hdr *hdr) +{ + const u8 *buf = skb_mac_header(skb); + int pos = 3, rc; + + if (buf + 3 > skb_tail_pointer(skb)) + return -EINVAL; + + memcpy(hdr, buf, 3); + + rc = ieee802154_hdr_minlen(hdr); + if (rc < 0 || buf + rc > skb_tail_pointer(skb)) + return -EINVAL; + + pos += ieee802154_hdr_get_addrs(buf + pos, hdr); + return pos; +} +EXPORT_SYMBOL_GPL(ieee802154_hdr_peek_addrs); diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h index cee4425b9956..6693a5cf01ce 100644 --- a/net/ieee802154/ieee802154.h +++ b/net/ieee802154/ieee802154.h @@ -66,5 +66,6 @@ int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info); int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info); int ieee802154_list_iface(struct sk_buff *skb, struct genl_info *info); int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb); +int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info); #endif diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 43f1b2bf469f..04b20589d97a 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -123,6 +123,7 @@ static const struct genl_ops ieee8021154_ops[] = { IEEE802154_OP(IEEE802154_START_REQ, ieee802154_start_req), IEEE802154_DUMP(IEEE802154_LIST_IFACE, ieee802154_list_iface, ieee802154_dump_iface), + IEEE802154_OP(IEEE802154_SET_MACPARAMS, ieee802154_set_macparams), }; static const struct genl_multicast_group ieee802154_mcgrps[] = { diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index ba5c1e002f37..5d285498c0f6 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -39,6 +39,26 @@ #include "ieee802154.h" +static int nla_put_hwaddr(struct sk_buff *msg, int type, __le64 hwaddr) +{ + return nla_put_u64(msg, type, swab64((__force u64)hwaddr)); +} + +static __le64 nla_get_hwaddr(const struct nlattr *nla) +{ + return ieee802154_devaddr_from_raw(nla_data(nla)); +} + +static int nla_put_shortaddr(struct sk_buff *msg, int type, __le16 addr) +{ + return nla_put_u16(msg, type, le16_to_cpu(addr)); +} + +static __le16 nla_get_shortaddr(const struct nlattr *nla) +{ + return cpu_to_le16(nla_get_u16(nla)); +} + int ieee802154_nl_assoc_indic(struct net_device *dev, struct ieee802154_addr *addr, u8 cap) { @@ -46,7 +66,7 @@ int ieee802154_nl_assoc_indic(struct net_device *dev, pr_debug("%s\n", __func__); - if (addr->addr_type != IEEE802154_ADDR_LONG) { + if (addr->mode != IEEE802154_ADDR_LONG) { pr_err("%s: received non-long source address!\n", __func__); return -EINVAL; } @@ -59,8 +79,8 @@ int ieee802154_nl_assoc_indic(struct net_device *dev, nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr) || - nla_put(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, - addr->hwaddr) || + nla_put_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR, + addr->extended_addr) || nla_put_u8(msg, IEEE802154_ATTR_CAPABILITY, cap)) goto nla_put_failure; @@ -72,7 +92,7 @@ nla_put_failure: } EXPORT_SYMBOL(ieee802154_nl_assoc_indic); -int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr, +int ieee802154_nl_assoc_confirm(struct net_device *dev, __le16 short_addr, u8 status) { struct sk_buff *msg; @@ -87,7 +107,7 @@ int ieee802154_nl_assoc_confirm(struct net_device *dev, u16 short_addr, nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr) || - nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) || + nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) || nla_put_u8(msg, IEEE802154_ATTR_STATUS, status)) goto nla_put_failure; return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP); @@ -114,13 +134,13 @@ int ieee802154_nl_disassoc_indic(struct net_device *dev, nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr)) goto nla_put_failure; - if (addr->addr_type == IEEE802154_ADDR_LONG) { - if (nla_put(msg, IEEE802154_ATTR_SRC_HW_ADDR, IEEE802154_ADDR_LEN, - addr->hwaddr)) + if (addr->mode == IEEE802154_ADDR_LONG) { + if (nla_put_hwaddr(msg, IEEE802154_ATTR_SRC_HW_ADDR, + addr->extended_addr)) goto nla_put_failure; } else { - if (nla_put_u16(msg, IEEE802154_ATTR_SRC_SHORT_ADDR, - addr->short_addr)) + if (nla_put_shortaddr(msg, IEEE802154_ATTR_SRC_SHORT_ADDR, + addr->short_addr)) goto nla_put_failure; } if (nla_put_u8(msg, IEEE802154_ATTR_REASON, reason)) @@ -157,8 +177,8 @@ nla_put_failure: } EXPORT_SYMBOL(ieee802154_nl_disassoc_confirm); -int ieee802154_nl_beacon_indic(struct net_device *dev, - u16 panid, u16 coord_addr) +int ieee802154_nl_beacon_indic(struct net_device *dev, __le16 panid, + __le16 coord_addr) { struct sk_buff *msg; @@ -172,8 +192,9 @@ int ieee802154_nl_beacon_indic(struct net_device *dev, nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr) || - nla_put_u16(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, coord_addr) || - nla_put_u16(msg, IEEE802154_ATTR_COORD_PAN_ID, panid)) + nla_put_shortaddr(msg, IEEE802154_ATTR_COORD_SHORT_ADDR, + coord_addr) || + nla_put_shortaddr(msg, IEEE802154_ATTR_COORD_PAN_ID, panid)) goto nla_put_failure; return ieee802154_nl_mcast(msg, IEEE802154_COORD_MCGRP); @@ -243,6 +264,8 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, { void *hdr; struct wpan_phy *phy; + struct ieee802154_mlme_ops *ops; + __le16 short_addr, pan_id; pr_debug("%s\n", __func__); @@ -251,19 +274,45 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, if (!hdr) goto out; - phy = ieee802154_mlme_ops(dev)->get_phy(dev); + ops = ieee802154_mlme_ops(dev); + phy = ops->get_phy(dev); BUG_ON(!phy); + short_addr = ops->get_short_addr(dev); + pan_id = ops->get_pan_id(dev); + if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) || nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) || nla_put(msg, IEEE802154_ATTR_HW_ADDR, IEEE802154_ADDR_LEN, dev->dev_addr) || - nla_put_u16(msg, IEEE802154_ATTR_SHORT_ADDR, - ieee802154_mlme_ops(dev)->get_short_addr(dev)) || - nla_put_u16(msg, IEEE802154_ATTR_PAN_ID, - ieee802154_mlme_ops(dev)->get_pan_id(dev))) + nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) || + nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, pan_id)) goto nla_put_failure; + + if (ops->get_mac_params) { + struct ieee802154_mac_params params; + + ops->get_mac_params(dev, ¶ms); + + if (nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, + params.transmit_power) || + nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, params.lbt) || + nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, + params.cca_mode) || + nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL, + params.cca_ed_level) || + nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES, + params.csma_retries) || + nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE, + params.min_be) || + nla_put_u8(msg, IEEE802154_ATTR_CSMA_MAX_BE, + params.max_be) || + nla_put_s8(msg, IEEE802154_ATTR_FRAME_RETRIES, + params.frame_retries)) + goto nla_put_failure; + } + wpan_phy_put(phy); return genlmsg_end(msg, hdr); @@ -322,16 +371,16 @@ int ieee802154_associate_req(struct sk_buff *skb, struct genl_info *info) goto out; if (info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]) { - addr.addr_type = IEEE802154_ADDR_LONG; - nla_memcpy(addr.hwaddr, - info->attrs[IEEE802154_ATTR_COORD_HW_ADDR], - IEEE802154_ADDR_LEN); + addr.mode = IEEE802154_ADDR_LONG; + addr.extended_addr = nla_get_hwaddr( + info->attrs[IEEE802154_ATTR_COORD_HW_ADDR]); } else { - addr.addr_type = IEEE802154_ADDR_SHORT; - addr.short_addr = nla_get_u16( + addr.mode = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); } - addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); + addr.pan_id = nla_get_shortaddr( + info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); if (info->attrs[IEEE802154_ATTR_PAGE]) page = nla_get_u8(info->attrs[IEEE802154_ATTR_PAGE]); @@ -365,14 +414,13 @@ int ieee802154_associate_resp(struct sk_buff *skb, struct genl_info *info) if (!ieee802154_mlme_ops(dev)->assoc_resp) goto out; - addr.addr_type = IEEE802154_ADDR_LONG; - nla_memcpy(addr.hwaddr, info->attrs[IEEE802154_ATTR_DEST_HW_ADDR], - IEEE802154_ADDR_LEN); + addr.mode = IEEE802154_ADDR_LONG; + addr.extended_addr = nla_get_hwaddr( + info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]); addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); - ret = ieee802154_mlme_ops(dev)->assoc_resp(dev, &addr, - nla_get_u16(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]), + nla_get_shortaddr(info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]), nla_get_u8(info->attrs[IEEE802154_ATTR_STATUS])); out: @@ -398,13 +446,12 @@ int ieee802154_disassociate_req(struct sk_buff *skb, struct genl_info *info) goto out; if (info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]) { - addr.addr_type = IEEE802154_ADDR_LONG; - nla_memcpy(addr.hwaddr, - info->attrs[IEEE802154_ATTR_DEST_HW_ADDR], - IEEE802154_ADDR_LEN); + addr.mode = IEEE802154_ADDR_LONG; + addr.extended_addr = nla_get_hwaddr( + info->attrs[IEEE802154_ATTR_DEST_HW_ADDR]); } else { - addr.addr_type = IEEE802154_ADDR_SHORT; - addr.short_addr = nla_get_u16( + addr.mode = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_DEST_SHORT_ADDR]); } addr.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); @@ -449,10 +496,11 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) if (!ieee802154_mlme_ops(dev)->start_req) goto out; - addr.addr_type = IEEE802154_ADDR_SHORT; - addr.short_addr = nla_get_u16( + addr.mode = IEEE802154_ADDR_SHORT; + addr.short_addr = nla_get_shortaddr( info->attrs[IEEE802154_ATTR_COORD_SHORT_ADDR]); - addr.pan_id = nla_get_u16(info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); + addr.pan_id = nla_get_shortaddr( + info->attrs[IEEE802154_ATTR_COORD_PAN_ID]); channel = nla_get_u8(info->attrs[IEEE802154_ATTR_CHANNEL]); bcn_ord = nla_get_u8(info->attrs[IEEE802154_ATTR_BCN_ORD]); @@ -467,7 +515,7 @@ int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info) page = 0; - if (addr.short_addr == IEEE802154_ADDR_BROADCAST) { + if (addr.short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) { ieee802154_nl_start_confirm(dev, IEEE802154_NO_SHORT_ADDRESS); dev_put(dev); return -EINVAL; @@ -577,3 +625,93 @@ cont: return skb->len; } + +int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info) +{ + struct net_device *dev = NULL; + struct ieee802154_mlme_ops *ops; + struct ieee802154_mac_params params; + struct wpan_phy *phy; + int rc = -EINVAL; + + pr_debug("%s\n", __func__); + + dev = ieee802154_nl_get_dev(info); + if (!dev) + return -ENODEV; + + ops = ieee802154_mlme_ops(dev); + + if (!ops->get_mac_params || !ops->set_mac_params) { + rc = -EOPNOTSUPP; + goto out; + } + + if (netif_running(dev)) { + rc = -EBUSY; + goto out; + } + + if (!info->attrs[IEEE802154_ATTR_LBT_ENABLED] && + !info->attrs[IEEE802154_ATTR_CCA_MODE] && + !info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL] && + !info->attrs[IEEE802154_ATTR_CSMA_RETRIES] && + !info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] && + !info->attrs[IEEE802154_ATTR_CSMA_MAX_BE] && + !info->attrs[IEEE802154_ATTR_FRAME_RETRIES]) + goto out; + + phy = ops->get_phy(dev); + + if ((!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]) || + (!phy->set_cca_mode && info->attrs[IEEE802154_ATTR_CCA_MODE]) || + (!phy->set_cca_ed_level && + info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) || + (!phy->set_csma_params && + (info->attrs[IEEE802154_ATTR_CSMA_RETRIES] || + info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] || + info->attrs[IEEE802154_ATTR_CSMA_MAX_BE])) || + (!phy->set_frame_retries && + info->attrs[IEEE802154_ATTR_FRAME_RETRIES])) { + rc = -EOPNOTSUPP; + goto out_phy; + } + + ops->get_mac_params(dev, ¶ms); + + if (info->attrs[IEEE802154_ATTR_TXPOWER]) + params.transmit_power = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]); + + if (info->attrs[IEEE802154_ATTR_LBT_ENABLED]) + params.lbt = nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]); + + if (info->attrs[IEEE802154_ATTR_CCA_MODE]) + params.cca_mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]); + + if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) + params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]); + + if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES]) + params.csma_retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]); + + if (info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]) + params.min_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]); + + if (info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]) + params.max_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]); + + if (info->attrs[IEEE802154_ATTR_FRAME_RETRIES]) + params.frame_retries = nla_get_s8(info->attrs[IEEE802154_ATTR_FRAME_RETRIES]); + + rc = ops->set_mac_params(dev, ¶ms); + + wpan_phy_put(phy); + dev_put(dev); + return rc; + +out_phy: + wpan_phy_put(phy); +out: + dev_put(dev); + return rc; +} diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c index 6adda4d46f95..fd7be5e45cef 100644 --- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -52,5 +52,15 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_DURATION] = { .type = NLA_U8, }, [IEEE802154_ATTR_ED_LIST] = { .len = 27 }, [IEEE802154_ATTR_CHANNEL_PAGE_LIST] = { .len = 32 * 4, }, + + [IEEE802154_ATTR_TXPOWER] = { .type = NLA_S8, }, + [IEEE802154_ATTR_LBT_ENABLED] = { .type = NLA_U8, }, + [IEEE802154_ATTR_CCA_MODE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, }, + [IEEE802154_ATTR_CSMA_RETRIES] = { .type = NLA_U8, }, + [IEEE802154_ATTR_CSMA_MIN_BE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_CSMA_MAX_BE] = { .type = NLA_U8, }, + + [IEEE802154_ATTR_FRAME_RETRIES] = { .type = NLA_S8, }, }; diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index 41f538b8e59c..74d54fae33d7 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -28,6 +28,7 @@ #include <linux/slab.h> #include <net/sock.h> #include <net/af_ieee802154.h> +#include <net/ieee802154_netdev.h> #include "af802154.h" @@ -55,21 +56,24 @@ static void raw_close(struct sock *sk, long timeout) sk_common_release(sk); } -static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int len) +static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len) { - struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr; + struct ieee802154_addr addr; + struct sockaddr_ieee802154 *uaddr = (struct sockaddr_ieee802154 *)_uaddr; int err = 0; struct net_device *dev = NULL; - if (len < sizeof(*addr)) + if (len < sizeof(*uaddr)) return -EINVAL; - if (addr->family != AF_IEEE802154) + uaddr = (struct sockaddr_ieee802154 *)_uaddr; + if (uaddr->family != AF_IEEE802154) return -EINVAL; lock_sock(sk); - dev = ieee802154_get_dev(sock_net(sk), &addr->addr); + ieee802154_addr_from_sa(&addr, &uaddr->addr); + dev = ieee802154_get_dev(sock_net(sk), &addr); if (!dev) { err = -ENODEV; goto out; @@ -209,6 +213,10 @@ out: static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) { + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return NET_RX_DROP; + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c new file mode 100644 index 000000000000..ef2d54372b13 --- /dev/null +++ b/net/ieee802154/reassembly.c @@ -0,0 +1,571 @@ +/* 6LoWPAN fragment reassembly + * + * + * Authors: + * Alexander Aring <aar@pengutronix.de> + * + * Based on: net/ipv6/reassembly.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) "6LoWPAN: " fmt + +#include <linux/net.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/random.h> +#include <linux/jhash.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/export.h> + +#include <net/ieee802154_netdev.h> +#include <net/6lowpan.h> +#include <net/ipv6.h> +#include <net/inet_frag.h> + +#include "reassembly.h" + +struct lowpan_frag_info { + __be16 d_tag; + u16 d_size; + u8 d_offset; +}; + +struct lowpan_frag_info *lowpan_cb(struct sk_buff *skb) +{ + return (struct lowpan_frag_info *)skb->cb; +} + +static struct inet_frags lowpan_frags; + +static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, + struct sk_buff *prev, struct net_device *dev); + +static unsigned int lowpan_hash_frag(__be16 tag, u16 d_size, + const struct ieee802154_addr *saddr, + const struct ieee802154_addr *daddr) +{ + u32 c; + + net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd)); + c = jhash_3words(ieee802154_addr_hash(saddr), + ieee802154_addr_hash(daddr), + (__force u32)(tag + (d_size << 16)), + lowpan_frags.rnd); + + return c & (INETFRAGS_HASHSZ - 1); +} + +static unsigned int lowpan_hashfn(struct inet_frag_queue *q) +{ + struct lowpan_frag_queue *fq; + + fq = container_of(q, struct lowpan_frag_queue, q); + return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr); +} + +static bool lowpan_frag_match(struct inet_frag_queue *q, void *a) +{ + struct lowpan_frag_queue *fq; + struct lowpan_create_arg *arg = a; + + fq = container_of(q, struct lowpan_frag_queue, q); + return fq->tag == arg->tag && fq->d_size == arg->d_size && + ieee802154_addr_equal(&fq->saddr, arg->src) && + ieee802154_addr_equal(&fq->daddr, arg->dst); +} + +static void lowpan_frag_init(struct inet_frag_queue *q, void *a) +{ + struct lowpan_frag_queue *fq; + struct lowpan_create_arg *arg = a; + + fq = container_of(q, struct lowpan_frag_queue, q); + + fq->tag = arg->tag; + fq->d_size = arg->d_size; + fq->saddr = *arg->src; + fq->daddr = *arg->dst; +} + +static void lowpan_frag_expire(unsigned long data) +{ + struct frag_queue *fq; + struct net *net; + + fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags); + + spin_lock(&fq->q.lock); + + if (fq->q.last_in & INET_FRAG_COMPLETE) + goto out; + + inet_frag_kill(&fq->q, &lowpan_frags); +out: + spin_unlock(&fq->q.lock); + inet_frag_put(&fq->q, &lowpan_frags); +} + +static inline struct lowpan_frag_queue * +fq_find(struct net *net, const struct lowpan_frag_info *frag_info, + const struct ieee802154_addr *src, + const struct ieee802154_addr *dst) +{ + struct inet_frag_queue *q; + struct lowpan_create_arg arg; + unsigned int hash; + + arg.tag = frag_info->d_tag; + arg.d_size = frag_info->d_size; + arg.src = src; + arg.dst = dst; + + read_lock(&lowpan_frags.lock); + hash = lowpan_hash_frag(frag_info->d_tag, frag_info->d_size, src, dst); + + q = inet_frag_find(&net->ieee802154_lowpan.frags, + &lowpan_frags, &arg, hash); + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; + } + return container_of(q, struct lowpan_frag_queue, q); +} + +static int lowpan_frag_queue(struct lowpan_frag_queue *fq, + struct sk_buff *skb, const u8 frag_type) +{ + struct sk_buff *prev, *next; + struct net_device *dev; + int end, offset; + + if (fq->q.last_in & INET_FRAG_COMPLETE) + goto err; + + offset = lowpan_cb(skb)->d_offset << 3; + end = lowpan_cb(skb)->d_size; + + /* Is this the final fragment? */ + if (offset + skb->len == end) { + /* If we already have some bits beyond end + * or have different end, the segment is corrupted. + */ + if (end < fq->q.len || + ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) + goto err; + fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.len = end; + } else { + if (end > fq->q.len) { + /* Some bits beyond end -> corruption. */ + if (fq->q.last_in & INET_FRAG_LAST_IN) + goto err; + fq->q.len = end; + } + } + + /* Find out which fragments are in front and at the back of us + * in the chain of fragments so far. We must know where to put + * this fragment, right? + */ + prev = fq->q.fragments_tail; + if (!prev || lowpan_cb(prev)->d_offset < lowpan_cb(skb)->d_offset) { + next = NULL; + goto found; + } + prev = NULL; + for (next = fq->q.fragments; next != NULL; next = next->next) { + if (lowpan_cb(next)->d_offset >= lowpan_cb(skb)->d_offset) + break; /* bingo! */ + prev = next; + } + +found: + /* Insert this fragment in the chain of fragments. */ + skb->next = next; + if (!next) + fq->q.fragments_tail = skb; + if (prev) + prev->next = skb; + else + fq->q.fragments = skb; + + dev = skb->dev; + if (dev) + skb->dev = NULL; + + fq->q.stamp = skb->tstamp; + if (frag_type == LOWPAN_DISPATCH_FRAG1) { + /* Calculate uncomp. 6lowpan header to estimate full size */ + fq->q.meat += lowpan_uncompress_size(skb, NULL); + fq->q.last_in |= INET_FRAG_FIRST_IN; + } else { + fq->q.meat += skb->len; + } + add_frag_mem_limit(&fq->q, skb->truesize); + + if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + fq->q.meat == fq->q.len) { + int res; + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + res = lowpan_frag_reasm(fq, prev, dev); + skb->_skb_refdst = orefdst; + return res; + } + + inet_frag_lru_move(&fq->q); + return -1; +err: + kfree_skb(skb); + return -1; +} + +/* Check if this packet is complete. + * Returns NULL on failure by any reason, and pointer + * to current nexthdr field in reassembled frame. + * + * It is called with locked fq, and caller must check that + * queue is eligible for reassembly i.e. it is not COMPLETE, + * the last and the first frames arrived and all the bits are here. + */ +static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, + struct net_device *dev) +{ + struct sk_buff *fp, *head = fq->q.fragments; + int sum_truesize; + + inet_frag_kill(&fq->q, &lowpan_frags); + + /* Make the one we just received the head. */ + if (prev) { + head = prev->next; + fp = skb_clone(head, GFP_ATOMIC); + + if (!fp) + goto out_oom; + + fp->next = head->next; + if (!fp->next) + fq->q.fragments_tail = fp; + prev->next = fp; + + skb_morph(head, fq->q.fragments); + head->next = fq->q.fragments->next; + + consume_skb(fq->q.fragments); + fq->q.fragments = head; + } + + /* Head of list must not be cloned. */ + if (skb_unclone(head, GFP_ATOMIC)) + goto out_oom; + + /* If the first fragment is fragmented itself, we split + * it to two chunks: the first with data and paged part + * and the second, holding only fragments. + */ + if (skb_has_frag_list(head)) { + struct sk_buff *clone; + int i, plen = 0; + + clone = alloc_skb(0, GFP_ATOMIC); + if (!clone) + goto out_oom; + clone->next = head->next; + head->next = clone; + skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; + skb_frag_list_init(head); + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); + clone->len = head->data_len - plen; + clone->data_len = clone->len; + head->data_len -= clone->len; + head->len -= clone->len; + add_frag_mem_limit(&fq->q, clone->truesize); + } + + WARN_ON(head == NULL); + + sum_truesize = head->truesize; + for (fp = head->next; fp;) { + bool headstolen; + int delta; + struct sk_buff *next = fp->next; + + sum_truesize += fp->truesize; + if (skb_try_coalesce(head, fp, &headstolen, &delta)) { + kfree_skb_partial(fp, headstolen); + } else { + if (!skb_shinfo(head)->frag_list) + skb_shinfo(head)->frag_list = fp; + head->data_len += fp->len; + head->len += fp->len; + head->truesize += fp->truesize; + } + fp = next; + } + sub_frag_mem_limit(&fq->q, sum_truesize); + + head->next = NULL; + head->dev = dev; + head->tstamp = fq->q.stamp; + + fq->q.fragments = NULL; + fq->q.fragments_tail = NULL; + + return 1; +out_oom: + net_dbg_ratelimited("lowpan_frag_reasm: no memory for reassembly\n"); + return -1; +} + +static int lowpan_get_frag_info(struct sk_buff *skb, const u8 frag_type, + struct lowpan_frag_info *frag_info) +{ + bool fail; + u8 pattern = 0, low = 0; + + fail = lowpan_fetch_skb(skb, &pattern, 1); + fail |= lowpan_fetch_skb(skb, &low, 1); + frag_info->d_size = (pattern & 7) << 8 | low; + fail |= lowpan_fetch_skb(skb, &frag_info->d_tag, 2); + + if (frag_type == LOWPAN_DISPATCH_FRAGN) { + fail |= lowpan_fetch_skb(skb, &frag_info->d_offset, 1); + } else { + skb_reset_network_header(skb); + frag_info->d_offset = 0; + } + + if (unlikely(fail)) + return -EIO; + + return 0; +} + +int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type) +{ + struct lowpan_frag_queue *fq; + struct net *net = dev_net(skb->dev); + struct lowpan_frag_info *frag_info = lowpan_cb(skb); + struct ieee802154_addr source, dest; + int err; + + source = mac_cb(skb)->source; + dest = mac_cb(skb)->dest; + + err = lowpan_get_frag_info(skb, frag_type, frag_info); + if (err < 0) + goto err; + + if (frag_info->d_size > net->ieee802154_lowpan.max_dsize) + goto err; + + inet_frag_evictor(&net->ieee802154_lowpan.frags, &lowpan_frags, false); + + fq = fq_find(net, frag_info, &source, &dest); + if (fq != NULL) { + int ret; + spin_lock(&fq->q.lock); + ret = lowpan_frag_queue(fq, skb, frag_type); + spin_unlock(&fq->q.lock); + + inet_frag_put(&fq->q, &lowpan_frags); + return ret; + } + +err: + kfree_skb(skb); + return -1; +} +EXPORT_SYMBOL(lowpan_frag_rcv); + +#ifdef CONFIG_SYSCTL +static struct ctl_table lowpan_frags_ns_ctl_table[] = { + { + .procname = "6lowpanfrag_high_thresh", + .data = &init_net.ieee802154_lowpan.frags.high_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "6lowpanfrag_low_thresh", + .data = &init_net.ieee802154_lowpan.frags.low_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "6lowpanfrag_time", + .data = &init_net.ieee802154_lowpan.frags.timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "6lowpanfrag_max_datagram_size", + .data = &init_net.ieee802154_lowpan.max_dsize, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { } +}; + +static struct ctl_table lowpan_frags_ctl_table[] = { + { + .procname = "6lowpanfrag_secret_interval", + .data = &lowpan_frags.secret_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; + +static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) +{ + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = lowpan_frags_ns_ctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(lowpan_frags_ns_ctl_table), + GFP_KERNEL); + if (table == NULL) + goto err_alloc; + + table[0].data = &net->ieee802154_lowpan.frags.high_thresh; + table[1].data = &net->ieee802154_lowpan.frags.low_thresh; + table[2].data = &net->ieee802154_lowpan.frags.timeout; + table[3].data = &net->ieee802154_lowpan.max_dsize; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + } + + hdr = register_net_sysctl(net, "net/ieee802154/6lowpan", table); + if (hdr == NULL) + goto err_reg; + + net->ieee802154_lowpan.sysctl.frags_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit lowpan_frags_ns_sysctl_unregister(struct net *net) +{ + struct ctl_table *table; + + table = net->ieee802154_lowpan.sysctl.frags_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->ieee802154_lowpan.sysctl.frags_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct ctl_table_header *lowpan_ctl_header; + +static int lowpan_frags_sysctl_register(void) +{ + lowpan_ctl_header = register_net_sysctl(&init_net, + "net/ieee802154/6lowpan", + lowpan_frags_ctl_table); + return lowpan_ctl_header == NULL ? -ENOMEM : 0; +} + +static void lowpan_frags_sysctl_unregister(void) +{ + unregister_net_sysctl_table(lowpan_ctl_header); +} +#else +static inline int lowpan_frags_ns_sysctl_register(struct net *net) +{ + return 0; +} + +static inline void lowpan_frags_ns_sysctl_unregister(struct net *net) +{ +} + +static inline int lowpan_frags_sysctl_register(void) +{ + return 0; +} + +static inline void lowpan_frags_sysctl_unregister(void) +{ +} +#endif + +static int __net_init lowpan_frags_init_net(struct net *net) +{ + net->ieee802154_lowpan.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; + net->ieee802154_lowpan.frags.low_thresh = IPV6_FRAG_LOW_THRESH; + net->ieee802154_lowpan.frags.timeout = IPV6_FRAG_TIMEOUT; + net->ieee802154_lowpan.max_dsize = 0xFFFF; + + inet_frags_init_net(&net->ieee802154_lowpan.frags); + + return lowpan_frags_ns_sysctl_register(net); +} + +static void __net_exit lowpan_frags_exit_net(struct net *net) +{ + lowpan_frags_ns_sysctl_unregister(net); + inet_frags_exit_net(&net->ieee802154_lowpan.frags, &lowpan_frags); +} + +static struct pernet_operations lowpan_frags_ops = { + .init = lowpan_frags_init_net, + .exit = lowpan_frags_exit_net, +}; + +int __init lowpan_net_frag_init(void) +{ + int ret; + + ret = lowpan_frags_sysctl_register(); + if (ret) + return ret; + + ret = register_pernet_subsys(&lowpan_frags_ops); + if (ret) + goto err_pernet; + + lowpan_frags.hashfn = lowpan_hashfn; + lowpan_frags.constructor = lowpan_frag_init; + lowpan_frags.destructor = NULL; + lowpan_frags.skb_free = NULL; + lowpan_frags.qsize = sizeof(struct frag_queue); + lowpan_frags.match = lowpan_frag_match; + lowpan_frags.frag_expire = lowpan_frag_expire; + lowpan_frags.secret_interval = 10 * 60 * HZ; + inet_frags_init(&lowpan_frags); + + return ret; +err_pernet: + lowpan_frags_sysctl_unregister(); + return ret; +} + +void lowpan_net_frag_exit(void) +{ + inet_frags_fini(&lowpan_frags); + lowpan_frags_sysctl_unregister(); + unregister_pernet_subsys(&lowpan_frags_ops); +} diff --git a/net/ieee802154/reassembly.h b/net/ieee802154/reassembly.h new file mode 100644 index 000000000000..74e4a7c98191 --- /dev/null +++ b/net/ieee802154/reassembly.h @@ -0,0 +1,41 @@ +#ifndef __IEEE802154_6LOWPAN_REASSEMBLY_H__ +#define __IEEE802154_6LOWPAN_REASSEMBLY_H__ + +#include <net/inet_frag.h> + +struct lowpan_create_arg { + __be16 tag; + u16 d_size; + const struct ieee802154_addr *src; + const struct ieee802154_addr *dst; +}; + +/* Equivalent of ipv4 struct ip + */ +struct lowpan_frag_queue { + struct inet_frag_queue q; + + __be16 tag; + u16 d_size; + struct ieee802154_addr saddr; + struct ieee802154_addr daddr; +}; + +static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a) +{ + switch (a->mode) { + case IEEE802154_ADDR_LONG: + return (((__force u64)a->extended_addr) >> 32) ^ + (((__force u64)a->extended_addr) & 0xffffffff); + case IEEE802154_ADDR_SHORT: + return (__force u32)(a->short_addr); + default: + return 0; + } +} + +int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type); +void lowpan_net_frag_exit(void); +int lowpan_net_frag_init(void); + +#endif /* __IEEE802154_6LOWPAN_REASSEMBLY_H__ */ diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c index 4dd37615a749..8d6f6704da84 100644 --- a/net/ieee802154/wpan-class.c +++ b/net/ieee802154/wpan-class.c @@ -44,9 +44,7 @@ static DEVICE_ATTR_RO(name); MASTER_SHOW(current_channel, "%d"); MASTER_SHOW(current_page, "%d"); -MASTER_SHOW_COMPLEX(transmit_power, "%d +- %d dB", - ((signed char) (phy->transmit_power << 2)) >> 2, - (phy->transmit_power >> 6) ? (phy->transmit_power >> 6) * 3 : 1); +MASTER_SHOW(transmit_power, "%d +- 1 dB"); MASTER_SHOW(cca_mode, "%d"); static ssize_t channels_supported_show(struct device *dev, diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index f8c49ce5b283..f032688d20d3 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -55,4 +55,4 @@ obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ - xfrm4_output.o + xfrm4_output.o xfrm4_protocol.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 19ab78aca547..8c54870db792 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1505,9 +1505,9 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset) bhptr = per_cpu_ptr(mib[0], cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { - start = u64_stats_fetch_begin_bh(syncp); + start = u64_stats_fetch_begin_irq(syncp); v = *(((u64 *) bhptr) + offt); - } while (u64_stats_fetch_retry_bh(syncp, start)); + } while (u64_stats_fetch_retry_irq(syncp, start)); res += v; } diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 717902669d2f..a2afa89513a0 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -155,6 +155,10 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) struct iphdr *iph, *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; ahp = x->data; ahash = ahp->ahash; @@ -167,14 +171,19 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah = ip_auth_hdr(skb); ihl = ip_hdrlen(skb); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } err = -ENOMEM; - iph = ah_alloc_tmp(ahash, nfrags, ihl); + iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + seqhi_len); if (!iph) goto out; - - icv = ah_tmp_icv(ahash, iph, ihl); + seqhi = (__be32 *)((char *)iph + ihl); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memset(ah->auth_data, 0, ahp->icv_trunc_len); @@ -210,10 +219,15 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah_output_done, skb); AH_SKB_CB(skb)->tmp = iph; @@ -295,6 +309,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) struct ip_auth_hdr *ah; struct ah_data *ahp; int err = -ENOMEM; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; if (!pskb_may_pull(skb, sizeof(*ah))) goto out; @@ -335,14 +353,22 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) iph = ip_hdr(skb); ihl = ip_hdrlen(skb); - work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + + work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + + ahp->icv_trunc_len + seqhi_len); if (!work_iph) goto out; - auth_data = ah_tmp_auth(work_iph, ihl); + seqhi = (__be32 *)((char *)work_iph + ihl); + auth_data = ah_tmp_auth(seqhi, seqhi_len); icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memcpy(work_iph, iph, ihl); memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); @@ -361,10 +387,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, ihl); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah_input_done, skb); AH_SKB_CB(skb)->tmp = work_iph; @@ -397,7 +428,7 @@ out: return err; } -static void ah4_err(struct sk_buff *skb, u32 info) +static int ah4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; @@ -407,23 +438,25 @@ static void ah4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); + + return 0; } static int ah_init_state(struct xfrm_state *x) @@ -505,6 +538,10 @@ static void ah_destroy(struct xfrm_state *x) kfree(ahp); } +static int ah4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} static const struct xfrm_type ah_type = { @@ -518,11 +555,12 @@ static const struct xfrm_type ah_type = .output = ah_output }; -static const struct net_protocol ah4_protocol = { +static struct xfrm4_protocol ah4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = ah4_rcv_cb, .err_handler = ah4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init ah4_init(void) @@ -531,7 +569,7 @@ static int __init ah4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&ah4_protocol, IPPROTO_AH) < 0) { + if (xfrm4_protocol_register(&ah4_protocol, IPPROTO_AH) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ah_type, AF_INET); return -EAGAIN; @@ -541,7 +579,7 @@ static int __init ah4_init(void) static void __exit ah4_fini(void) { - if (inet_del_protocol(&ah4_protocol, IPPROTO_AH) < 0) + if (xfrm4_protocol_deregister(&ah4_protocol, IPPROTO_AH) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ah_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 7785b28061ac..360b565918c4 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -473,7 +473,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) net_adj) & ~(blksize - 1)) + net_adj - 2; } -static void esp4_err(struct sk_buff *skb, u32 info) +static int esp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; @@ -483,23 +483,25 @@ static void esp4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); + + return 0; } static void esp_destroy(struct xfrm_state *x) @@ -672,6 +674,11 @@ error: return err; } +static int esp4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type esp_type = { .description = "ESP4", @@ -685,11 +692,12 @@ static const struct xfrm_type esp_type = .output = esp_output }; -static const struct net_protocol esp4_protocol = { +static struct xfrm4_protocol esp4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = esp4_rcv_cb, .err_handler = esp4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init esp4_init(void) @@ -698,7 +706,7 @@ static int __init esp4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&esp4_protocol, IPPROTO_ESP) < 0) { + if (xfrm4_protocol_register(&esp4_protocol, IPPROTO_ESP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&esp_type, AF_INET); return -EAGAIN; @@ -708,7 +716,7 @@ static int __init esp4_init(void) static void __exit esp4_fini(void) { - if (inet_del_protocol(&esp4_protocol, IPPROTO_ESP) < 0) + if (xfrm4_protocol_deregister(&esp4_protocol, IPPROTO_ESP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&esp_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c7539e22868b..1a629f870274 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -659,7 +659,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED) - return ip_rt_dump(skb, cb); + return skb->len; s_h = cb->args[0]; s_e = cb->args[1]; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index f3869c186d97..be8abe73bb9f 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -127,6 +127,10 @@ int ip_forward(struct sk_buff *skb) struct rtable *rt; /* Route we use */ struct ip_options *opt = &(IPCB(skb)->opt); + /* that should never happen */ + if (skb->pkt_type != PACKET_HOST) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -136,9 +140,6 @@ int ip_forward(struct sk_buff *skb) if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb)) return NET_RX_SUCCESS; - if (skb->pkt_type != PACKET_HOST) - goto drop; - skb_forward_csum(skb); /* diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 73c6b63bba74..1a0755fea491 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -446,7 +446,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) __be16 not_last_frag; struct rtable *rt = skb_rtable(skb); int err = 0; - bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; dev = rt->dst.dev; @@ -456,7 +455,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) iph = ip_hdr(skb); - mtu = ip_dst_mtu_maybe_forward(&rt->dst, forwarding); + mtu = ip_skb_dst_mtu(skb); if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { @@ -822,8 +821,7 @@ static int __ip_append_data(struct sock *sk, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ? - mtu : 0xFFFF; + maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1146,8 +1144,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ? - mtu : 0xFFFF; + maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu; if (cork->length + size > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1308,8 +1305,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * to fragment the frame generated here. No matter, what transforms * how transforms change size of the packet, it will come out. */ - if (inet->pmtudisc < IP_PMTUDISC_DO) - skb->local_df = 1; + skb->local_df = ip_sk_local_df(sk); /* DF bit is set when we want to see DF on outgoing frames. * If local_df is set too, we still allow to fragment this frame diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 580dd96666e0..64741b938632 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -186,7 +186,8 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) } EXPORT_SYMBOL(ip_cmsg_recv); -int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) +int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, + bool allow_ipv6) { int err, val; struct cmsghdr *cmsg; @@ -194,6 +195,22 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; +#if defined(CONFIG_IPV6) + if (allow_ipv6 && + cmsg->cmsg_level == SOL_IPV6 && + cmsg->cmsg_type == IPV6_PKTINFO) { + struct in6_pktinfo *src_info; + + if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info))) + return -EINVAL; + src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); + if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) + return -EINVAL; + ipc->oif = src_info->ipi6_ifindex; + ipc->addr = src_info->ipi6_addr.s6_addr32[3]; + continue; + } +#endif if (cmsg->cmsg_level != SOL_IP) continue; switch (cmsg->cmsg_type) { @@ -626,7 +643,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->nodefrag = val ? 1 : 0; break; case IP_MTU_DISCOVER: - if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_INTERFACE) + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) goto e_inval; inet->pmtudisc = val; break; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index a82a22d8f77f..e77381d1df9a 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -235,13 +235,17 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, { unsigned int h; __be32 remote; + __be32 i_key = parms->i_key; if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr)) remote = parms->iph.daddr; else remote = 0; - h = ip_tunnel_hash(parms->i_key, remote); + if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI)) + i_key = 0; + + h = ip_tunnel_hash(i_key, remote); return &itn->tunnels[h]; } @@ -398,7 +402,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, fbt = netdev_priv(itn->fb_tunnel_dev); dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms); if (IS_ERR(dev)) - return NULL; + return ERR_CAST(dev); dev->mtu = ip_tunnel_bind_dev(dev); @@ -748,9 +752,13 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); - if (!t && (cmd == SIOCADDTUNNEL)) + if (!t && (cmd == SIOCADDTUNNEL)) { t = ip_tunnel_create(net, itn, p); - + if (IS_ERR(t)) { + err = PTR_ERR(t); + break; + } + } if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { if (t != NULL) { if (t->dev != dev) { @@ -777,8 +785,9 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) if (t) { err = 0; ip_tunnel_update(itn, t, dev, p, true); - } else - err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + } else { + err = -ENOENT; + } break; case SIOCDELTUNNEL: @@ -993,19 +1002,13 @@ int ip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; - int i, err; + int err; dev->destructor = ip_tunnel_dev_free; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ipt_stats; - ipt_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ipt_stats->syncp); - } - tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); if (!tunnel->dst_cache) { free_percpu(dev->tstats); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 8d69626f2206..e0c2b1d2ea4e 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -162,12 +162,12 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, unsigned int start; do { - start = u64_stats_fetch_begin_bh(&tstats->syncp); + start = u64_stats_fetch_begin_irq(&tstats->syncp); rx_packets = tstats->rx_packets; tx_packets = tstats->tx_packets; rx_bytes = tstats->rx_bytes; tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); tot->rx_packets += rx_packets; tot->tx_packets += tx_packets; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 48eafae51769..687ddef4e574 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -34,6 +34,7 @@ #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> +#include <linux/icmpv6.h> #include <net/sock.h> #include <net/ip.h> @@ -49,8 +50,8 @@ static struct rtnl_link_ops vti_link_ops __read_mostly; static int vti_net_id __read_mostly; static int vti_tunnel_init(struct net_device *dev); -/* We dont digest the packet therefore let the packet pass */ -static int vti_rcv(struct sk_buff *skb) +static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) { struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); @@ -60,79 +61,120 @@ static int vti_rcv(struct sk_buff *skb) tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); if (tunnel != NULL) { - struct pcpu_sw_netstats *tstats; - u32 oldmark = skb->mark; - int ret; - - - /* temporarily mark the skb with the tunnel o_key, to - * only match policies with this mark. - */ - skb->mark = be32_to_cpu(tunnel->parms.o_key); - ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb); - skb->mark = oldmark; - if (!ret) - return -1; - - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); - - secpath_reset(skb); - skb->dev = tunnel->dev; + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; + skb->mark = be32_to_cpu(tunnel->parms.i_key); + + return xfrm_input(skb, nexthdr, spi, encap_type); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; +} + +static int vti_rcv(struct sk_buff *skb) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + return vti_input(skb, ip_hdr(skb)->protocol, 0, 0); +} + +static int vti_rcv_cb(struct sk_buff *skb, int err) +{ + unsigned short family; + struct net_device *dev; + struct pcpu_sw_netstats *tstats; + struct xfrm_state *x; + struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; + + if (!tunnel) return 1; + + dev = tunnel->dev; + + if (err) { + dev->stats.rx_errors++; + dev->stats.rx_dropped++; + + return 0; } - return -1; + x = xfrm_input_state(skb); + family = x->inner_mode->afinfo->family; + + if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + return -EPERM; + + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); + skb->dev = dev; + + tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + return 0; } -/* This function assumes it is being called from dev_queue_xmit() - * and that skb is filled properly by that function. - */ +static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src) +{ + xfrm_address_t *daddr = (xfrm_address_t *)&dst; + xfrm_address_t *saddr = (xfrm_address_t *)&src; -static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) + /* if there is no transform then this tunnel is not functional. + * Or if the xfrm is not mode tunnel. + */ + if (!x || x->props.mode != XFRM_MODE_TUNNEL || + x->props.family != AF_INET) + return false; + + if (!dst) + return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET); + + if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET)) + return false; + + return true; +} + +static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, + struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct iphdr *tiph = &tunnel->parms.iph; - u8 tos; - struct rtable *rt; /* Route to the other host */ + struct ip_tunnel_parm *parms = &tunnel->parms; + struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ - struct iphdr *old_iph = ip_hdr(skb); - __be32 dst = tiph->daddr; - struct flowi4 fl4; int err; - if (skb->protocol != htons(ETH_P_IP)) - goto tx_error; - - tos = old_iph->tos; + if (!dst) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } - memset(&fl4, 0, sizeof(fl4)); - flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos), - RT_SCOPE_UNIVERSE, - IPPROTO_IPIP, 0, - dst, tiph->saddr, 0, 0); - rt = ip_route_output_key(dev_net(dev), &fl4); - if (IS_ERR(rt)) { + dst_hold(dst); + dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0); + if (IS_ERR(dst)) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } - /* if there is no transform then this tunnel is not functional. - * Or if the xfrm is not mode tunnel. - */ - if (!rt->dst.xfrm || - rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) { + + if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { dev->stats.tx_carrier_errors++; - ip_rt_put(rt); + dst_release(dst); goto tx_error_icmp; } - tdev = rt->dst.dev; + + tdev = dst->dev; if (tdev == dev) { - ip_rt_put(rt); + dst_release(dst); dev->stats.collisions++; goto tx_error; } @@ -146,10 +188,8 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) tunnel->err_count = 0; } - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - nf_reset(skb); + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); + skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; err = dst_output(skb); @@ -166,6 +206,95 @@ tx_error: return NETDEV_TX_OK; } +/* This function assumes it is being called from dev_queue_xmit() + * and that skb is filled properly by that function. + */ +static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct flowi fl; + + memset(&fl, 0, sizeof(fl)); + + skb->mark = be32_to_cpu(tunnel->parms.o_key); + + switch (skb->protocol) { + case htons(ETH_P_IP): + xfrm_decode_session(skb, &fl, AF_INET); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + break; + case htons(ETH_P_IPV6): + xfrm_decode_session(skb, &fl, AF_INET6); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + break; + default: + dev->stats.tx_errors++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + + return vti_xmit(skb, dev, &fl); +} + +static int vti4_err(struct sk_buff *skb, u32 info) +{ + __be32 spi; + struct xfrm_state *x; + struct ip_tunnel *tunnel; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah ; + struct ip_comp_hdr *ipch; + struct net *net = dev_net(skb->dev); + const struct iphdr *iph = (const struct iphdr *)skb->data; + int protocol = iph->protocol; + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->daddr, iph->saddr, 0); + if (!tunnel) + return -1; + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return 0; + case ICMP_REDIRECT: + break; + default: + return 0; + } + + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET); + if (!x) + return 0; + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0); + else + ipv4_redirect(skb, net, 0, 0, protocol, 0); + xfrm_state_put(x); + + return 0; +} + static int vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -181,12 +310,13 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EINVAL; } + p.i_flags |= VTI_ISVTI; err = ip_tunnel_ioctl(dev, &p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { - p.i_flags |= GRE_KEY | VTI_ISVTI; + p.i_flags |= GRE_KEY; p.o_flags |= GRE_KEY; } @@ -224,7 +354,6 @@ static int vti_tunnel_init(struct net_device *dev) dev->flags = IFF_NOARP; dev->iflink = 0; dev->addr_len = 4; - dev->features |= NETIF_F_NETNS_LOCAL; dev->features |= NETIF_F_LLTX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; @@ -241,9 +370,28 @@ static void __net_init vti_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; } -static struct xfrm_tunnel_notifier vti_handler __read_mostly = { +static struct xfrm4_protocol vti_esp4_protocol __read_mostly = { .handler = vti_rcv, - .priority = 1, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, +}; + +static struct xfrm4_protocol vti_ah4_protocol __read_mostly = { + .handler = vti_rcv, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, +}; + +static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { + .handler = vti_rcv, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, }; static int __net_init vti_init_net(struct net *net) @@ -287,6 +435,8 @@ static void vti_netlink_parms(struct nlattr *data[], if (!data) return; + parms->i_flags = VTI_ISVTI; + if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); @@ -382,10 +532,31 @@ static int __init vti_init(void) err = register_pernet_device(&vti_net_ops); if (err < 0) return err; - err = xfrm4_mode_tunnel_input_register(&vti_handler); + err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP); + if (err < 0) { + unregister_pernet_device(&vti_net_ops); + pr_info("vti init: can't register tunnel\n"); + + return err; + } + + err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH); + if (err < 0) { + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); + unregister_pernet_device(&vti_net_ops); + pr_info("vti init: can't register tunnel\n"); + + return err; + } + + err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP); if (err < 0) { + xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); pr_info("vti init: can't register tunnel\n"); + + return err; } err = rtnl_link_register(&vti_link_ops); @@ -395,7 +566,9 @@ static int __init vti_init(void) return err; rtnl_link_failed: - xfrm4_mode_tunnel_input_deregister(&vti_handler); + xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); + xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); return err; } @@ -403,8 +576,13 @@ rtnl_link_failed: static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); - if (xfrm4_mode_tunnel_input_deregister(&vti_handler)) + if (xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP)) pr_info("vti close: can't deregister tunnel\n"); + if (xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH)) + pr_info("vti close: can't deregister tunnel\n"); + if (xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP)) + pr_info("vti close: can't deregister tunnel\n"); + unregister_pernet_device(&vti_net_ops); } diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 826be4cb482a..c0855d50a3fa 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -23,7 +23,7 @@ #include <net/protocol.h> #include <net/sock.h> -static void ipcomp4_err(struct sk_buff *skb, u32 info) +static int ipcomp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); __be32 spi; @@ -34,24 +34,26 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } spi = htonl(ntohs(ipch->cpi)); x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); + + return 0; } /* We always hold one tunnel user reference to indicate a tunnel */ @@ -147,6 +149,11 @@ out: return err; } +static int ipcomp4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type ipcomp_type = { .description = "IPCOMP4", .owner = THIS_MODULE, @@ -157,11 +164,12 @@ static const struct xfrm_type ipcomp_type = { .output = ipcomp_output }; -static const struct net_protocol ipcomp4_protocol = { +static struct xfrm4_protocol ipcomp4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = ipcomp4_rcv_cb, .err_handler = ipcomp4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init ipcomp4_init(void) @@ -170,7 +178,7 @@ static int __init ipcomp4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) { + if (xfrm4_protocol_register(&ipcomp4_protocol, IPPROTO_COMP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ipcomp_type, AF_INET); return -EAGAIN; @@ -180,7 +188,7 @@ static int __init ipcomp4_init(void) static void __exit ipcomp4_fini(void) { - if (inet_del_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) + if (xfrm4_protocol_deregister(&ipcomp4_protocol, IPPROTO_COMP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ipcomp_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index c3e0adea9c27..7ebd6e37875c 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -61,7 +61,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type) skb_dst_set(skb, NULL); dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0); if (IS_ERR(dst)) - return PTR_ERR(dst);; + return PTR_ERR(dst); skb_dst_set(skb, dst); } #endif diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2d11c094296e..f4b19e5dde54 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -727,7 +727,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m sock_tx_timestamp(sk, &ipc.tx_flags); if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); if (err) return err; if (ipc.opt) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index a6c8a80ec9d6..ad737fad6d8b 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -273,6 +273,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE), SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE), + SNMP_MIB_ITEM("TCPFastOpenActiveFail", LINUX_MIB_TCPFASTOPENACTIVEFAIL), SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE), SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL), SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW), @@ -280,6 +281,11 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES), SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS), SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING), + SNMP_MIB_ITEM("TCPFromZeroWindowAdv", LINUX_MIB_TCPFROMZEROWINDOWADV), + SNMP_MIB_ITEM("TCPToZeroWindowAdv", LINUX_MIB_TCPTOZEROWINDOWADV), + SNMP_MIB_ITEM("TCPWantZeroWindowAdv", LINUX_MIB_TCPWANTZEROWINDOWADV), + SNMP_MIB_ITEM("TCPSynRetrans", LINUX_MIB_TCPSYNRETRANS), + SNMP_MIB_ITEM("TCPOrigDataSent", LINUX_MIB_TCPORIGDATASENT), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index c04518f4850a..a9dbe58bdfe7 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -524,7 +524,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); if (err) goto out; if (ipc.opt) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 4c011ec69ed4..1be9e990514d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -139,11 +139,6 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); -static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int how) -{ -} - static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) { WARN_ON(1); @@ -162,7 +157,6 @@ static struct dst_ops ipv4_dst_ops = { .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, - .ifdown = ipv4_dst_ifdown, .negative_advice = ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, @@ -697,7 +691,6 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, out_unlock: spin_unlock_bh(&fnhe_lock); - return; } static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, @@ -2475,11 +2468,6 @@ errout_free: goto errout; } -int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) -{ - return skb->len; -} - void ip_rt_multicast_event(struct in_device *in_dev) { rt_cache_flush(dev_net(in_dev->dev)); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 97c8f5620c43..4bd6d52eeffb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -387,7 +387,7 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsq_node); icsk->icsk_rto = TCP_TIMEOUT_INIT; - tp->mdev = TCP_TIMEOUT_INIT; + tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -2341,7 +2341,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); - tp->srtt = 0; + tp->srtt_us = 0; if ((tp->write_seq += tp->max_window + 2) == 0) tp->write_seq = 1; icsk->icsk_backoff = 0; @@ -2785,8 +2785,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) info->tcpi_pmtu = icsk->icsk_pmtu_cookie; info->tcpi_rcv_ssthresh = tp->rcv_ssthresh; - info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3; - info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2; + info->tcpi_rtt = tp->srtt_us >> 3; + info->tcpi_rttvar = tp->mdev_us >> 2; info->tcpi_snd_ssthresh = tp->snd_ssthresh; info->tcpi_snd_cwnd = tp->snd_cwnd; info->tcpi_advmss = tp->advmss; @@ -2796,6 +2796,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) info->tcpi_rcv_space = tp->rcvq_space.space; info->tcpi_total_retrans = tp->total_retrans; + + info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ? + sk->sk_pacing_rate : ~0ULL; + info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ? + sk->sk_max_pacing_rate : ~0ULL; } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 2388275adb9b..2b9464c93b88 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -361,21 +361,12 @@ u32 tcp_reno_ssthresh(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_reno_ssthresh); -/* Lower bound on congestion window with halving. */ -u32 tcp_reno_min_cwnd(const struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - return tp->snd_ssthresh/2; -} -EXPORT_SYMBOL_GPL(tcp_reno_min_cwnd); - struct tcp_congestion_ops tcp_reno = { .flags = TCP_CONG_NON_RESTRICTED, .name = "reno", .owner = THIS_MODULE, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, }; /* Initial congestion control used (until SYN) @@ -387,6 +378,5 @@ struct tcp_congestion_ops tcp_init_congestion_ops = { .owner = THIS_MODULE, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, }; EXPORT_SYMBOL_GPL(tcp_init_congestion_ops); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 828e4c3ffbaf..8bf224516ba2 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -476,10 +476,6 @@ static int __init cubictcp_register(void) /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); - /* hystart needs ms clock resolution */ - if (hystart && HZ < 1000) - cubictcp.flags |= TCP_CONG_RTT_STAMP; - return tcp_register_congestion_control(&cubictcp); } diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c index 8ed9305dfdf4..8b9e7bad77c0 100644 --- a/net/ipv4/tcp_highspeed.c +++ b/net/ipv4/tcp_highspeed.c @@ -162,7 +162,6 @@ static struct tcp_congestion_ops tcp_highspeed __read_mostly = { .init = hstcp_init, .ssthresh = hstcp_ssthresh, .cong_avoid = hstcp_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .owner = THIS_MODULE, .name = "highspeed" diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index 478fe82611bf..a15a799bf768 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -21,7 +21,7 @@ struct hybla { u32 rho2; /* Rho * Rho, integer part */ u32 rho_3ls; /* Rho parameter, <<3 */ u32 rho2_7ls; /* Rho^2, <<7 */ - u32 minrtt; /* Minimum smoothed round trip time value seen */ + u32 minrtt_us; /* Minimum smoothed round trip time value seen */ }; /* Hybla reference round trip time (default= 1/40 sec = 25 ms), in ms */ @@ -35,7 +35,9 @@ static inline void hybla_recalc_param (struct sock *sk) { struct hybla *ca = inet_csk_ca(sk); - ca->rho_3ls = max_t(u32, tcp_sk(sk)->srtt / msecs_to_jiffies(rtt0), 8); + ca->rho_3ls = max_t(u32, + tcp_sk(sk)->srtt_us / (rtt0 * USEC_PER_MSEC), + 8U); ca->rho = ca->rho_3ls >> 3; ca->rho2_7ls = (ca->rho_3ls * ca->rho_3ls) << 1; ca->rho2 = ca->rho2_7ls >> 7; @@ -59,7 +61,7 @@ static void hybla_init(struct sock *sk) hybla_recalc_param(sk); /* set minimum rtt as this is the 1st ever seen */ - ca->minrtt = tp->srtt; + ca->minrtt_us = tp->srtt_us; tp->snd_cwnd = ca->rho; } @@ -94,9 +96,9 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked, int is_slowstart = 0; /* Recalculate rho only if this srtt is the lowest */ - if (tp->srtt < ca->minrtt){ + if (tp->srtt_us < ca->minrtt_us) { hybla_recalc_param(sk); - ca->minrtt = tp->srtt; + ca->minrtt_us = tp->srtt_us; } if (!tcp_is_cwnd_limited(sk, in_flight)) @@ -166,7 +168,6 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked, static struct tcp_congestion_ops tcp_hybla __read_mostly = { .init = hybla_init, .ssthresh = tcp_reno_ssthresh, - .min_cwnd = tcp_reno_min_cwnd, .cong_avoid = hybla_cong_avoid, .set_state = hybla_state, diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index e498a62b8f97..863d105e3015 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -325,10 +325,8 @@ static void tcp_illinois_info(struct sock *sk, u32 ext, } static struct tcp_congestion_ops tcp_illinois __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_illinois_init, .ssthresh = tcp_illinois_ssthresh, - .min_cwnd = tcp_reno_min_cwnd, .cong_avoid = tcp_illinois_cong_avoid, .set_state = tcp_illinois_state, .get_info = tcp_illinois_info, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eeaac399420d..e1661f46fd19 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -667,11 +667,11 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics */ -static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) +static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) { struct tcp_sock *tp = tcp_sk(sk); - long m = mrtt; /* RTT */ - u32 srtt = tp->srtt; + long m = mrtt_us; /* RTT */ + u32 srtt = tp->srtt_us; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev @@ -694,7 +694,7 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ - m -= (tp->mdev >> 2); /* similar update on mdev */ + m -= (tp->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain @@ -706,28 +706,29 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) if (m > 0) m >>= 3; } else { - m -= (tp->mdev >> 2); /* similar update on mdev */ + m -= (tp->mdev_us >> 2); /* similar update on mdev */ } - tp->mdev += m; /* mdev = 3/4 mdev + 1/4 new */ - if (tp->mdev > tp->mdev_max) { - tp->mdev_max = tp->mdev; - if (tp->mdev_max > tp->rttvar) - tp->rttvar = tp->mdev_max; + tp->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ + if (tp->mdev_us > tp->mdev_max_us) { + tp->mdev_max_us = tp->mdev_us; + if (tp->mdev_max_us > tp->rttvar_us) + tp->rttvar_us = tp->mdev_max_us; } if (after(tp->snd_una, tp->rtt_seq)) { - if (tp->mdev_max < tp->rttvar) - tp->rttvar -= (tp->rttvar - tp->mdev_max) >> 2; + if (tp->mdev_max_us < tp->rttvar_us) + tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2; tp->rtt_seq = tp->snd_nxt; - tp->mdev_max = tcp_rto_min(sk); + tp->mdev_max_us = tcp_rto_min_us(sk); } } else { /* no previous measure. */ srtt = m << 3; /* take the measured time to be rtt */ - tp->mdev = m << 1; /* make sure rto = 3*rtt */ - tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); + tp->mdev_us = m << 1; /* make sure rto = 3*rtt */ + tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk)); + tp->mdev_max_us = tp->rttvar_us; tp->rtt_seq = tp->snd_nxt; } - tp->srtt = max(1U, srtt); + tp->srtt_us = max(1U, srtt); } /* Set the sk_pacing_rate to allow proper sizing of TSO packets. @@ -742,20 +743,12 @@ static void tcp_update_pacing_rate(struct sock *sk) u64 rate; /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */ - rate = (u64)tp->mss_cache * 2 * (HZ << 3); + rate = (u64)tp->mss_cache * 2 * (USEC_PER_SEC << 3); rate *= max(tp->snd_cwnd, tp->packets_out); - /* Correction for small srtt and scheduling constraints. - * For small rtt, consider noise is too high, and use - * the minimal value (srtt = 1 -> 125 us for HZ=1000) - * - * We probably need usec resolution in the future. - * Note: This also takes care of possible srtt=0 case, - * when tcp_rtt_estimator() was not yet called. - */ - if (tp->srtt > 8 + 2) - do_div(rate, tp->srtt); + if (likely(tp->srtt_us)) + do_div(rate, tp->srtt_us); /* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate * without any lock. We want to make sure compiler wont store @@ -1122,10 +1115,10 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, } struct tcp_sacktag_state { - int reord; - int fack_count; - int flag; - s32 rtt; /* RTT measured by SACKing never-retransmitted data */ + int reord; + int fack_count; + long rtt_us; /* RTT measured by SACKing never-retransmitted data */ + int flag; }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, @@ -1186,7 +1179,8 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, - int dup_sack, int pcount, u32 xmit_time) + int dup_sack, int pcount, + const struct skb_mstamp *xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1227,8 +1221,13 @@ static u8 tcp_sacktag_one(struct sock *sk, if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; /* Pick the earliest sequence sacked for RTT */ - if (state->rtt < 0) - state->rtt = tcp_time_stamp - xmit_time; + if (state->rtt_us < 0) { + struct skb_mstamp now; + + skb_mstamp_get(&now); + state->rtt_us = skb_mstamp_us_delta(&now, + xmit_time); + } } if (sacked & TCPCB_LOST) { @@ -1287,7 +1286,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, - TCP_SKB_CB(skb)->when); + &skb->skb_mstamp); if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1565,7 +1564,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), - TCP_SKB_CB(skb)->when); + &skb->skb_mstamp); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1622,7 +1621,7 @@ static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_bl static int tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, - u32 prior_snd_una, s32 *sack_rtt) + u32 prior_snd_una, long *sack_rtt_us) { struct tcp_sock *tp = tcp_sk(sk); const unsigned char *ptr = (skb_transport_header(ack_skb) + @@ -1640,7 +1639,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, state.flag = 0; state.reord = tp->packets_out; - state.rtt = -1; + state.rtt_us = -1L; if (!tp->sacked_out) { if (WARN_ON(tp->fackets_out)) @@ -1824,7 +1823,7 @@ out: WARN_ON((int)tp->retrans_out < 0); WARN_ON((int)tcp_packets_in_flight(tp) < 0); #endif - *sack_rtt = state.rtt; + *sack_rtt_us = state.rtt_us; return state.flag; } @@ -2035,10 +2034,12 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag) * available, or RTO is scheduled to fire first. */ if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 || - (flag & FLAG_ECE) || !tp->srtt) + (flag & FLAG_ECE) || !tp->srtt_us) return false; - delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2)); + delay = max(usecs_to_jiffies(tp->srtt_us >> 5), + msecs_to_jiffies(2)); + if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay))) return false; @@ -2885,7 +2886,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, } static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, - s32 seq_rtt, s32 sack_rtt) + long seq_rtt_us, long sack_rtt_us) { const struct tcp_sock *tp = tcp_sk(sk); @@ -2895,10 +2896,10 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * is acked (RFC6298). */ if (flag & FLAG_RETRANS_DATA_ACKED) - seq_rtt = -1; + seq_rtt_us = -1L; - if (seq_rtt < 0) - seq_rtt = sack_rtt; + if (seq_rtt_us < 0) + seq_rtt_us = sack_rtt_us; /* RTTM Rule: A TSecr value received in a segment is used to * update the averaged RTT measurement only if the segment @@ -2906,14 +2907,14 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ - if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && + if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) - seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr; + seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr); - if (seq_rtt < 0) + if (seq_rtt_us < 0) return false; - tcp_rtt_estimator(sk, seq_rtt); + tcp_rtt_estimator(sk, seq_rtt_us); tcp_set_rto(sk); /* RFC6298: only reset backoff on valid RTT measurement. */ @@ -2925,16 +2926,16 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp) { struct tcp_sock *tp = tcp_sk(sk); - s32 seq_rtt = -1; + long seq_rtt_us = -1L; if (synack_stamp && !tp->total_retrans) - seq_rtt = tcp_time_stamp - synack_stamp; + seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - synack_stamp); /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack() */ - if (!tp->srtt) - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); + if (!tp->srtt_us) + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L); } static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight) @@ -3023,26 +3024,27 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) * arrived at the other end. */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, - u32 prior_snd_una, s32 sack_rtt) + u32 prior_snd_una, long sack_rtt_us) { - struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - struct sk_buff *skb; - u32 now = tcp_time_stamp; + struct skb_mstamp first_ackt, last_ackt, now; + struct tcp_sock *tp = tcp_sk(sk); + u32 prior_sacked = tp->sacked_out; + u32 reord = tp->packets_out; bool fully_acked = true; - int flag = 0; + long ca_seq_rtt_us = -1L; + long seq_rtt_us = -1L; + struct sk_buff *skb; u32 pkts_acked = 0; - u32 reord = tp->packets_out; - u32 prior_sacked = tp->sacked_out; - s32 seq_rtt = -1; - s32 ca_seq_rtt = -1; - ktime_t last_ackt = net_invalid_timestamp(); bool rtt_update; + int flag = 0; + + first_ackt.v64 = 0; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); - u32 acked_pcount; u8 sacked = scb->sacked; + u32 acked_pcount; /* Determine how many packets and what bytes were acked, tso and else */ if (after(scb->end_seq, tp->snd_una)) { @@ -3064,11 +3066,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->retrans_out -= acked_pcount; flag |= FLAG_RETRANS_DATA_ACKED; } else { - ca_seq_rtt = now - scb->when; - last_ackt = skb->tstamp; - if (seq_rtt < 0) { - seq_rtt = ca_seq_rtt; - } + last_ackt = skb->skb_mstamp; + WARN_ON_ONCE(last_ackt.v64 == 0); + if (!first_ackt.v64) + first_ackt = last_ackt; + if (!(sacked & TCPCB_SACKED_ACKED)) reord = min(pkts_acked, reord); if (!after(scb->end_seq, tp->high_seq)) @@ -3114,7 +3116,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt); + skb_mstamp_get(&now); + if (first_ackt.v64) { + seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt); + ca_seq_rtt_us = skb_mstamp_us_delta(&now, &last_ackt); + } + + rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us); if (flag & FLAG_ACKED) { const struct tcp_congestion_ops *ca_ops @@ -3142,25 +3150,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); - if (ca_ops->pkts_acked) { - s32 rtt_us = -1; - - /* Is the ACK triggering packet unambiguous? */ - if (!(flag & FLAG_RETRANS_DATA_ACKED)) { - /* High resolution needed and available? */ - if (ca_ops->flags & TCP_CONG_RTT_STAMP && - !ktime_equal(last_ackt, - net_invalid_timestamp())) - rtt_us = ktime_us_delta(ktime_get_real(), - last_ackt); - else if (ca_seq_rtt >= 0) - rtt_us = jiffies_to_usecs(ca_seq_rtt); - } + if (ca_ops->pkts_acked) + ca_ops->pkts_acked(sk, pkts_acked, ca_seq_rtt_us); - ca_ops->pkts_acked(sk, pkts_acked, rtt_us); - } - } else if (skb && rtt_update && sack_rtt >= 0 && - sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) { + } else if (skb && rtt_update && sack_rtt_us >= 0 && + sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3370,12 +3364,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; - u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt; + u32 prior_in_flight; u32 prior_fackets; int prior_packets = tp->packets_out; const int prior_unsacked = tp->packets_out - tp->sacked_out; int acked = 0; /* Number of packets newly acked */ - s32 sack_rtt = -1; + long sack_rtt_us = -1L; /* If the ack is older than previous acks * then we can probably ignore it. @@ -3433,7 +3427,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (TCP_SKB_CB(skb)->sacked) flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, - &sack_rtt); + &sack_rtt_us); if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb))) flag |= FLAG_ECE; @@ -3452,7 +3446,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ acked = tp->packets_out; - flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt); + flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, + sack_rtt_us); acked -= tp->packets_out; /* Advance cwnd if state allows */ @@ -3475,8 +3470,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (icsk->icsk_pending == ICSK_TIME_RETRANS) tcp_schedule_loss_probe(sk); - if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd) - tcp_update_pacing_rate(sk); + tcp_update_pacing_rate(sk); return 1; no_queue: @@ -3505,7 +3499,7 @@ old_ack: */ if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, - &sack_rtt); + &sack_rtt_us); tcp_fastretrans_alert(sk, acked, prior_unsacked, is_dupack, flag); } @@ -5401,9 +5395,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, break; } tcp_rearm_rto(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; } tp->syn_data_acked = tp->syn_data; + if (tp->syn_data_acked) + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); return false; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1e4eac779f51..6379894ec210 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -435,7 +435,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) break; icsk->icsk_backoff--; - inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) : + inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT) << icsk->icsk_backoff; tcp_bound_rto(sk); @@ -854,8 +854,10 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req) { int res = tcp_v4_send_synack(sk, NULL, req, 0); - if (!res) + if (!res) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + } return res; } @@ -878,8 +880,6 @@ bool tcp_syn_flood_action(struct sock *sk, bool want_cookie = false; struct listen_sock *lopt; - - #ifdef CONFIG_SYN_COOKIES if (sysctl_tcp_syncookies) { msg = "Sending cookies"; diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 991d62a2f9bb..c9aecae31327 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -315,11 +315,9 @@ static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us) } static struct tcp_congestion_ops tcp_lp __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_lp_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_lp_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .pkts_acked = tcp_lp_pkts_acked, .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index d547075d8300..dcaf72f10216 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -33,6 +33,11 @@ struct tcp_fastopen_metrics { struct tcp_fastopen_cookie cookie; }; +/* TCP_METRIC_MAX includes 2 extra fields for userspace compatibility + * Kernel only stores RTT and RTTVAR in usec resolution + */ +#define TCP_METRIC_MAX_KERNEL (TCP_METRIC_MAX - 2) + struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; struct inetpeer_addr tcpm_saddr; @@ -41,7 +46,7 @@ struct tcp_metrics_block { u32 tcpm_ts; u32 tcpm_ts_stamp; u32 tcpm_lock; - u32 tcpm_vals[TCP_METRIC_MAX + 1]; + u32 tcpm_vals[TCP_METRIC_MAX_KERNEL + 1]; struct tcp_fastopen_metrics tcpm_fastopen; struct rcu_head rcu_head; @@ -59,12 +64,6 @@ static u32 tcp_metric_get(struct tcp_metrics_block *tm, return tm->tcpm_vals[idx]; } -static u32 tcp_metric_get_jiffies(struct tcp_metrics_block *tm, - enum tcp_metric_index idx) -{ - return msecs_to_jiffies(tm->tcpm_vals[idx]); -} - static void tcp_metric_set(struct tcp_metrics_block *tm, enum tcp_metric_index idx, u32 val) @@ -72,13 +71,6 @@ static void tcp_metric_set(struct tcp_metrics_block *tm, tm->tcpm_vals[idx] = val; } -static void tcp_metric_set_msecs(struct tcp_metrics_block *tm, - enum tcp_metric_index idx, - u32 val) -{ - tm->tcpm_vals[idx] = jiffies_to_msecs(val); -} - static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { @@ -101,9 +93,11 @@ struct tcpm_hash_bucket { static DEFINE_SPINLOCK(tcp_metrics_lock); -static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst, +static void tcpm_suck_dst(struct tcp_metrics_block *tm, + const struct dst_entry *dst, bool fastopen_clear) { + u32 msval; u32 val; tm->tcpm_stamp = jiffies; @@ -121,8 +115,11 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst, val |= 1 << TCP_METRIC_REORDERING; tm->tcpm_lock = val; - tm->tcpm_vals[TCP_METRIC_RTT] = dst_metric_raw(dst, RTAX_RTT); - tm->tcpm_vals[TCP_METRIC_RTTVAR] = dst_metric_raw(dst, RTAX_RTTVAR); + msval = dst_metric_raw(dst, RTAX_RTT); + tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; + + msval = dst_metric_raw(dst, RTAX_RTTVAR); + tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC; 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); @@ -384,7 +381,7 @@ void tcp_update_metrics(struct sock *sk) dst_confirm(dst); rcu_read_lock(); - if (icsk->icsk_backoff || !tp->srtt) { + if (icsk->icsk_backoff || !tp->srtt_us) { /* This session failed to estimate rtt. Why? * Probably, no packets returned in time. Reset our * results. @@ -399,8 +396,8 @@ void tcp_update_metrics(struct sock *sk) if (!tm) goto out_unlock; - rtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT); - m = rtt - tp->srtt; + rtt = tcp_metric_get(tm, TCP_METRIC_RTT); + m = rtt - tp->srtt_us; /* If newly calculated rtt larger than stored one, store new * one. Otherwise, use EWMA. Remember, rtt overestimation is @@ -408,10 +405,10 @@ void tcp_update_metrics(struct sock *sk) */ if (!tcp_metric_locked(tm, TCP_METRIC_RTT)) { if (m <= 0) - rtt = tp->srtt; + rtt = tp->srtt_us; else rtt -= (m >> 3); - tcp_metric_set_msecs(tm, TCP_METRIC_RTT, rtt); + tcp_metric_set(tm, TCP_METRIC_RTT, rtt); } if (!tcp_metric_locked(tm, TCP_METRIC_RTTVAR)) { @@ -422,16 +419,16 @@ void tcp_update_metrics(struct sock *sk) /* Scale deviation to rttvar fixed point */ m >>= 1; - if (m < tp->mdev) - m = tp->mdev; + if (m < tp->mdev_us) + m = tp->mdev_us; - var = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR); + var = tcp_metric_get(tm, TCP_METRIC_RTTVAR); if (m >= var) var = m; else var -= (var - m) >> 2; - tcp_metric_set_msecs(tm, TCP_METRIC_RTTVAR, var); + tcp_metric_set(tm, TCP_METRIC_RTTVAR, var); } if (tcp_in_initial_slowstart(tp)) { @@ -528,7 +525,7 @@ void tcp_init_metrics(struct sock *sk) tp->reordering = val; } - crtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT); + crtt = tcp_metric_get(tm, TCP_METRIC_RTT); rcu_read_unlock(); reset: /* The initial RTT measurement from the SYN/SYN-ACK is not ideal @@ -551,18 +548,20 @@ reset: * to low value, and then abruptly stops to do it and starts to delay * ACKs, wait for troubles. */ - if (crtt > tp->srtt) { + if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt >>= 3; + crtt /= 8 * USEC_PER_MSEC; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); - } else if (tp->srtt == 0) { + } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from * 3WHS. This is most likely due to retransmission, * including spurious one. Reset the RTO back to 3secs * from the more aggressive 1sec to avoid more spurious * retransmission. */ - tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK; + tp->rttvar_us = jiffies_to_usecs(TCP_TIMEOUT_FALLBACK); + tp->mdev_us = tp->mdev_max_us = tp->rttvar_us; + inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK; } /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been @@ -809,10 +808,26 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS); if (!nest) goto nla_put_failure; - for (i = 0; i < TCP_METRIC_MAX + 1; i++) { - if (!tm->tcpm_vals[i]) + for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { + u32 val = tm->tcpm_vals[i]; + + if (!val) continue; - if (nla_put_u32(msg, i + 1, tm->tcpm_vals[i]) < 0) + if (i == TCP_METRIC_RTT) { + if (nla_put_u32(msg, TCP_METRIC_RTT_US + 1, + val) < 0) + goto nla_put_failure; + n++; + val = max(val / 1000, 1U); + } + if (i == TCP_METRIC_RTTVAR) { + if (nla_put_u32(msg, TCP_METRIC_RTTVAR_US + 1, + val) < 0) + goto nla_put_failure; + n++; + val = max(val / 1000, 1U); + } + if (nla_put_u32(msg, i + 1, val) < 0) goto nla_put_failure; n++; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7a436c517e44..ca788ada5bd3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -398,8 +398,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, tcp_init_wl(newtp, treq->rcv_isn); - newtp->srtt = 0; - newtp->mdev = TCP_TIMEOUT_INIT; + newtp->srtt_us = 0; + newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); newicsk->icsk_rto = TCP_TIMEOUT_INIT; newtp->packets_out = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 17a11e65e57f..699fb102e971 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -86,6 +86,9 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { tcp_rearm_rto(sk); } + + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, + tcp_skb_pcount(skb)); } /* SND.NXT, if window was not shrunk. @@ -269,6 +272,7 @@ EXPORT_SYMBOL(tcp_select_initial_window); static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 old_win = tp->rcv_wnd; u32 cur_win = tcp_receive_window(tp); u32 new_win = __tcp_select_window(sk); @@ -281,6 +285,9 @@ static u16 tcp_select_window(struct sock *sk) * * Relax Will Robinson. */ + if (new_win == 0) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPWANTZEROWINDOWADV); new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; @@ -298,8 +305,14 @@ static u16 tcp_select_window(struct sock *sk) new_win >>= tp->rx_opt.rcv_wscale; /* If we advertise zero window, disable fast path. */ - if (new_win == 0) + if (new_win == 0) { tp->pred_flags = 0; + if (old_win) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPTOZEROWINDOWADV); + } else if (old_win == 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV); + } return new_win; } @@ -867,11 +880,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (clone_it) { const struct sk_buff *fclone = skb + 1; - /* If congestion control is doing timestamping, we must - * take such a timestamp before we potentially clone/copy. - */ - if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP) - __net_timestamp(skb); + skb_mstamp_get(&skb->skb_mstamp); if (unlikely(skb->fclone == SKB_FCLONE_ORIG && fclone->fclone == SKB_FCLONE_CLONE)) @@ -884,6 +893,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb = skb_clone(skb, gfp_mask); if (unlikely(!skb)) return -ENOBUFS; + /* Our usage of tstamp should remain private */ + skb->tstamp.tv64 = 0; } inet = inet_sk(sk); @@ -1426,7 +1437,7 @@ static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now, * With Minshall's modification: all sent small packets are ACKed. */ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, - unsigned int mss_now, int nonagle) + int nonagle) { return partial && ((nonagle & TCP_NAGLE_CORK) || @@ -1458,7 +1469,7 @@ static unsigned int tcp_mss_split_point(const struct sock *sk, * to include this last segment in this skb. * Otherwise, we'll split the skb at last MSS boundary */ - if (tcp_nagle_check(partial != 0, tp, mss_now, nonagle)) + if (tcp_nagle_check(partial != 0, tp, nonagle)) return needed - partial; return needed; @@ -1521,7 +1532,7 @@ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buf if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) return true; - if (!tcp_nagle_check(skb->len < cur_mss, tp, cur_mss, nonagle)) + if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle)) return true; return false; @@ -1975,7 +1986,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 timeout, tlp_time_stamp, rto_time_stamp; - u32 rtt = tp->srtt >> 3; + u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3); if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS)) return false; @@ -1997,7 +2008,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ - if (sysctl_tcp_early_retrans < 3 || !tp->srtt || !tp->packets_out || + if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out || !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open) return false; @@ -2082,7 +2093,6 @@ rearm_timer: if (likely(!err)) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); - return; } /* Push out any pending frames which were held back due to @@ -2180,7 +2190,8 @@ u32 __tcp_select_window(struct sock *sk) */ int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); - int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk)); + int allowed_space = tcp_full_space(sk); + int full_space = min_t(int, tp->window_clamp, allowed_space); int window; if (mss > full_space) @@ -2193,7 +2204,19 @@ u32 __tcp_select_window(struct sock *sk) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); - if (free_space < mss) + /* free_space might become our new window, make sure we don't + * increase it due to wscale. + */ + free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); + + /* if free space is less than mss estimate, or is below 1/16th + * of the maximum allowed, try to move to zero-window, else + * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and + * new incoming data is dropped due to memory limits. + * With large window, mss test triggers way too late in order + * to announce zero window in time before rmem limit kicks in. + */ + if (free_space < (allowed_space >> 4) || free_space < mss) return 0; } @@ -2431,7 +2454,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (err == 0) { /* Update global TCP statistics. */ TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); - + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); tp->total_retrans++; #if FASTRETRANS_DEBUG > 0 @@ -2717,7 +2741,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, int tcp_header_size; int mss; - skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC); + skb = sock_wmalloc(sk, MAX_TCP_HEADER, 1, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; @@ -2787,7 +2811,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, th->window = htons(min(req->rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), tp, &opts); th->doff = (tcp_header_size >> 2); - TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ @@ -2959,9 +2983,15 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) tcp_connect_queue_skb(sk, data); fo->copied = data->len; + /* syn_data is about to be sent, we need to take current time stamps + * for the packets that are in write queue : SYN packet and DATA + */ + skb_mstamp_get(&syn->skb_mstamp); + data->skb_mstamp = syn->skb_mstamp; + if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { tp->syn_data = (fo->copied > 0); - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } syn_data = NULL; @@ -3049,8 +3079,9 @@ void tcp_send_delayed_ack(struct sock *sk) * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements * directly. */ - if (tp->srtt) { - int rtt = max(tp->srtt >> 3, TCP_DELACK_MIN); + if (tp->srtt_us) { + int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3), + TCP_DELACK_MIN); if (rtt < max_ato) max_ato = rtt; diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 1f2d37613c9e..3b66610d4156 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -154,7 +154,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, p->snd_wnd = tp->snd_wnd; p->rcv_wnd = tp->rcv_wnd; p->ssthresh = tcp_current_ssthresh(sk); - p->srtt = tp->srtt >> 3; + p->srtt = tp->srtt_us >> 3; tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1); } diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 19ea6c2951f3..0ac50836da4d 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -39,7 +39,6 @@ static u32 tcp_scalable_ssthresh(struct sock *sk) static struct tcp_congestion_ops tcp_scalable __read_mostly = { .ssthresh = tcp_scalable_ssthresh, .cong_avoid = tcp_scalable_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .owner = THIS_MODULE, .name = "scalable", diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 64f0354c84c7..286227abed10 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -165,6 +165,9 @@ static int tcp_write_timeout(struct sock *sk) dst_negative_advice(sk); if (tp->syn_fastopen || tp->syn_data) tcp_fastopen_cache_set(sk, 0, NULL, true); + if (tp->syn_data) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENACTIVEFAIL); } retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; syn_set = true; diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 06cae62bf208..48539fff6357 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -306,11 +306,9 @@ void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) EXPORT_SYMBOL_GPL(tcp_vegas_get_info); static struct tcp_congestion_ops tcp_vegas __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_vegas_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_vegas_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .pkts_acked = tcp_vegas_pkts_acked, .set_state = tcp_vegas_state, .cwnd_event = tcp_vegas_cwnd_event, diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 326475a94865..1b8e28fcd7e1 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -203,7 +203,6 @@ static u32 tcp_veno_ssthresh(struct sock *sk) } static struct tcp_congestion_ops tcp_veno __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_veno_init, .ssthresh = tcp_veno_ssthresh, .cong_avoid = tcp_veno_cong_avoid, diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index 76a1e23259e1..b94a04ae2ed5 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -276,7 +276,6 @@ static struct tcp_congestion_ops tcp_westwood __read_mostly = { .init = tcp_westwood_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, - .min_cwnd = tcp_westwood_bw_rttmin, .cwnd_event = tcp_westwood_event, .get_info = tcp_westwood_info, .pkts_acked = tcp_westwood_pkts_acked, diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 1a8d271f994d..5ede0e727945 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -227,11 +227,9 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) { } static struct tcp_congestion_ops tcp_yeah __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_yeah_init, .ssthresh = tcp_yeah_ssthresh, .cong_avoid = tcp_yeah_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .set_state = tcp_vegas_state, .cwnd_event = tcp_vegas_cwnd_event, .get_info = tcp_vegas_get_info, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 77bd16fa9f34..4468e1adc094 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -931,7 +931,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sock_tx_timestamp(sk, &ipc.tx_flags); if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, + sk->sk_family == AF_INET6); if (err) return err; if (ipc.opt) diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 1f12c8b45864..aac6197b7a71 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -37,15 +37,6 @@ drop: return NET_RX_DROP; } -int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, - int encap_type) -{ - XFRM_SPI_SKB_CB(skb)->family = AF_INET; - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - return xfrm_input(skb, nexthdr, spi, encap_type); -} -EXPORT_SYMBOL(xfrm4_rcv_encap); - int xfrm4_transport_finish(struct sk_buff *skb, int async) { struct iphdr *iph = ip_hdr(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 31b18152528f..05f2b484954f 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -15,65 +15,6 @@ #include <net/ip.h> #include <net/xfrm.h> -/* Informational hook. The decap is still done here. */ -static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly; -static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex); - -int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -EEXIST; - int priority = handler->priority; - - mutex_lock(&xfrm4_mode_tunnel_input_mutex); - - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t->priority > priority) - break; - if (t->priority == priority) - goto err; - - } - - handler->next = *pprev; - rcu_assign_pointer(*pprev, handler); - - ret = 0; - -err: - mutex_unlock(&xfrm4_mode_tunnel_input_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register); - -int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -ENOENT; - - mutex_lock(&xfrm4_mode_tunnel_input_mutex); - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t == handler) { - *pprev = handler->next; - ret = 0; - break; - } - } - mutex_unlock(&xfrm4_mode_tunnel_input_mutex); - synchronize_net(); - - return ret; -} -EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_deregister); - static inline void ipip_ecn_decapsulate(struct sk_buff *skb) { struct iphdr *inner_iph = ipip_hdr(skb); @@ -127,14 +68,8 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } -#define for_each_input_rcu(head, handler) \ - for (handler = rcu_dereference(head); \ - handler != NULL; \ - handler = rcu_dereference(handler->next)) - static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - struct xfrm_tunnel_notifier *handler; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) @@ -143,9 +78,6 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; - for_each_input_rcu(rcv_notify_handlers, handler) - handler->handler(skb); - err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index e1a63930a967..6156f68a1e90 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -325,6 +325,7 @@ void __init xfrm4_init(void) xfrm4_state_init(); xfrm4_policy_init(); + xfrm4_protocol_init(); #ifdef CONFIG_SYSCTL register_pernet_subsys(&xfrm4_net_ops); #endif diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c new file mode 100644 index 000000000000..7f7b243e8139 --- /dev/null +++ b/net/ipv4/xfrm4_protocol.c @@ -0,0 +1,286 @@ +/* xfrm4_protocol.c - Generic xfrm protocol multiplexer. + * + * Copyright (C) 2013 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + * + * Based on: + * net/ipv4/tunnel4.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/skbuff.h> +#include <net/icmp.h> +#include <net/ip.h> +#include <net/protocol.h> +#include <net/xfrm.h> + +static struct xfrm4_protocol __rcu *esp4_handlers __read_mostly; +static struct xfrm4_protocol __rcu *ah4_handlers __read_mostly; +static struct xfrm4_protocol __rcu *ipcomp4_handlers __read_mostly; +static DEFINE_MUTEX(xfrm4_protocol_mutex); + +static inline struct xfrm4_protocol __rcu **proto_handlers(u8 protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp4_handlers; + case IPPROTO_AH: + return &ah4_handlers; + case IPPROTO_COMP: + return &ipcomp4_handlers; + } + + return NULL; +} + +#define for_each_protocol_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) \ + +int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err) +{ + int ret; + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(*proto_handlers(protocol), handler) + if ((ret = handler->cb_handler(skb, err)) <= 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(xfrm4_rcv_cb); + +int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + for_each_protocol_rcu(*proto_handlers(nexthdr), handler) + if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} +EXPORT_SYMBOL(xfrm4_rcv_encap); + +static int xfrm4_esp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(esp4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_esp_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(esp4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static int xfrm4_ah_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(ah4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret;; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_ah_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(ah4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static int xfrm4_ipcomp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(ipcomp4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_ipcomp_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(ipcomp4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static const struct net_protocol esp4_protocol = { + .handler = xfrm4_esp_rcv, + .err_handler = xfrm4_esp_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static const struct net_protocol ah4_protocol = { + .handler = xfrm4_ah_rcv, + .err_handler = xfrm4_ah_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static const struct net_protocol ipcomp4_protocol = { + .handler = xfrm4_ipcomp_rcv, + .err_handler = xfrm4_ipcomp_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static struct xfrm_input_afinfo xfrm4_input_afinfo = { + .family = AF_INET, + .owner = THIS_MODULE, + .callback = xfrm4_rcv_cb, +}; + +static inline const struct net_protocol *netproto(unsigned char protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp4_protocol; + case IPPROTO_AH: + return &ah4_protocol; + case IPPROTO_COMP: + return &ipcomp4_protocol; + } + + return NULL; +} + +int xfrm4_protocol_register(struct xfrm4_protocol *handler, + unsigned char protocol) +{ + struct xfrm4_protocol __rcu **pprev; + struct xfrm4_protocol *t; + bool add_netproto = false; + int ret = -EEXIST; + int priority = handler->priority; + + mutex_lock(&xfrm4_protocol_mutex); + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm4_protocol_mutex))) + add_netproto = true; + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm4_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t->priority < priority) + break; + if (t->priority == priority) + goto err; + } + + handler->next = *pprev; + rcu_assign_pointer(*pprev, handler); + + ret = 0; + +err: + mutex_unlock(&xfrm4_protocol_mutex); + + if (add_netproto) { + if (inet_add_protocol(netproto(protocol), protocol)) { + pr_err("%s: can't add protocol\n", __func__); + ret = -EAGAIN; + } + } + + return ret; +} +EXPORT_SYMBOL(xfrm4_protocol_register); + +int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, + unsigned char protocol) +{ + struct xfrm4_protocol __rcu **pprev; + struct xfrm4_protocol *t; + int ret = -ENOENT; + + mutex_lock(&xfrm4_protocol_mutex); + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm4_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { + *pprev = handler->next; + ret = 0; + break; + } + } + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm4_protocol_mutex))) { + if (inet_del_protocol(netproto(protocol), protocol) < 0) { + pr_err("%s: can't remove protocol\n", __func__); + ret = -EAGAIN; + } + } + + mutex_unlock(&xfrm4_protocol_mutex); + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(xfrm4_protocol_deregister); + +void __init xfrm4_protocol_init(void) +{ + xfrm_input_register_afinfo(&xfrm4_input_afinfo); +} +EXPORT_SYMBOL(xfrm4_protocol_init); diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 17bb830872db..2fe68364bb20 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -16,7 +16,7 @@ ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \ - xfrm6_output.o + xfrm6_output.o xfrm6_protocol.o ipv6-$(CONFIG_NETFILTER) += netfilter.o ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o ipv6-$(CONFIG_PROC_FS) += proc.o diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index b30ad3741b46..731e1e1722d9 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -6,7 +6,7 @@ */ /* * Author: - * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org> + * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org> */ #include <linux/kernel.h> @@ -22,14 +22,13 @@ #if 0 #define ADDRLABEL(x...) printk(x) #else -#define ADDRLABEL(x...) do { ; } while(0) +#define ADDRLABEL(x...) do { ; } while (0) #endif /* * Policy Table */ -struct ip6addrlbl_entry -{ +struct ip6addrlbl_entry { #ifdef CONFIG_NET_NS struct net *lbl_net; #endif @@ -88,39 +87,39 @@ static const __net_initconst struct ip6addrlbl_init_table { /* ::/0 */ .prefix = &in6addr_any, .label = 1, - },{ /* fc00::/7 */ - .prefix = &(struct in6_addr){{{ 0xfc }}}, + }, { /* fc00::/7 */ + .prefix = &(struct in6_addr){ { { 0xfc } } } , .prefixlen = 7, .label = 5, - },{ /* fec0::/10 */ - .prefix = &(struct in6_addr){{{ 0xfe, 0xc0 }}}, + }, { /* fec0::/10 */ + .prefix = &(struct in6_addr){ { { 0xfe, 0xc0 } } }, .prefixlen = 10, .label = 11, - },{ /* 2002::/16 */ - .prefix = &(struct in6_addr){{{ 0x20, 0x02 }}}, + }, { /* 2002::/16 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x02 } } }, .prefixlen = 16, .label = 2, - },{ /* 3ffe::/16 */ - .prefix = &(struct in6_addr){{{ 0x3f, 0xfe }}}, + }, { /* 3ffe::/16 */ + .prefix = &(struct in6_addr){ { { 0x3f, 0xfe } } }, .prefixlen = 16, .label = 12, - },{ /* 2001::/32 */ - .prefix = &(struct in6_addr){{{ 0x20, 0x01 }}}, + }, { /* 2001::/32 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x01 } } }, .prefixlen = 32, .label = 6, - },{ /* 2001:10::/28 */ - .prefix = &(struct in6_addr){{{ 0x20, 0x01, 0x00, 0x10 }}}, + }, { /* 2001:10::/28 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x01, 0x00, 0x10 } } }, .prefixlen = 28, .label = 7, - },{ /* ::ffff:0:0 */ - .prefix = &(struct in6_addr){{{ [10] = 0xff, [11] = 0xff }}}, + }, { /* ::ffff:0:0 */ + .prefix = &(struct in6_addr){ { { [10] = 0xff, [11] = 0xff } } }, .prefixlen = 96, .label = 4, - },{ /* ::/96 */ + }, { /* ::/96 */ .prefix = &in6addr_any, .prefixlen = 96, .label = 3, - },{ /* ::1/128 */ + }, { /* ::1/128 */ .prefix = &in6addr_loopback, .prefixlen = 128, .label = 0, @@ -441,7 +440,7 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh) if (label == IPV6_ADDR_LABEL_DEFAULT) return -EINVAL; - switch(nlh->nlmsg_type) { + switch (nlh->nlmsg_type) { case RTM_NEWADDRLABEL: if (ifal->ifal_index && !__dev_get_by_index(net, ifal->ifal_index)) @@ -505,12 +504,13 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { if (idx >= s_idx && net_eq(ip6addrlbl_net(p), net)) { - if ((err = ip6addrlbl_fill(skb, p, - ip6addrlbl_table.seq, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWADDRLABEL, - NLM_F_MULTI)) <= 0) + err = ip6addrlbl_fill(skb, p, + ip6addrlbl_table.seq, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWADDRLABEL, + NLM_F_MULTI); + if (err <= 0) break; } idx++; @@ -527,7 +527,7 @@ static inline int ip6addrlbl_msgsize(void) + nla_total_size(4); /* IFAL_LABEL */ } -static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh) +static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh) { struct net *net = sock_net(in_skb->sk); struct ifaddrlblmsg *ifal; @@ -568,7 +568,8 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh) goto out; } - if (!(skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL))) { + skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL); + if (!skb) { ip6addrlbl_put(p); return -ENOBUFS; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 81e496a2e008..72a4930bdc0a 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -346,6 +346,10 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) struct ip_auth_hdr *ah; struct ah_data *ahp; struct tmp_ext *iph_ext; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; ahp = x->data; ahash = ahp->ahash; @@ -359,15 +363,22 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) if (extlen) extlen += sizeof(*iph_ext); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } err = -ENOMEM; - iph_base = ah_alloc_tmp(ahash, nfrags, IPV6HDR_BASELEN + extlen); + iph_base = ah_alloc_tmp(ahash, nfrags + sglists, IPV6HDR_BASELEN + + extlen + seqhi_len); if (!iph_base) goto out; iph_ext = ah_tmp_ext(iph_base); - icv = ah_tmp_icv(ahash, iph_ext, extlen); + seqhi = (__be32 *)((char *)iph_ext + extlen); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; ah = ip_auth_hdr(skb); memset(ah->auth_data, 0, ahp->icv_trunc_len); @@ -411,10 +422,15 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah6_output_done, skb); AH_SKB_CB(skb)->tmp = iph_base; @@ -514,6 +530,10 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) int nexthdr; int nfrags; int err = -ENOMEM; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr))) goto out; @@ -550,14 +570,22 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, hdr_len); - work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + + work_iph = ah_alloc_tmp(ahash, nfrags + sglists, hdr_len + + ahp->icv_trunc_len + seqhi_len); if (!work_iph) goto out; - auth_data = ah_tmp_auth(work_iph, hdr_len); - icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); + auth_data = ah_tmp_auth((u8 *)work_iph, hdr_len); + seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memcpy(work_iph, ip6h, hdr_len); memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); @@ -572,10 +600,16 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) ip6h->flow_lbl[2] = 0; ip6h->hop_limit = 0; - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); + + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(seqhisg, seqhi, seqhi_len); + } - ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah6_input_done, skb); AH_SKB_CB(skb)->tmp = work_iph; @@ -609,8 +643,8 @@ out: return err; } -static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) +static int ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); struct ipv6hdr *iph = (struct ipv6hdr*)skb->data; @@ -619,17 +653,19 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) - return; + return 0; x = xfrm_state_lookup(net, skb->mark, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET6); if (!x) - return; + return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0); else ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); + + return 0; } static int ah6_init_state(struct xfrm_state *x) @@ -714,6 +750,11 @@ static void ah6_destroy(struct xfrm_state *x) kfree(ahp); } +static int ah6_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type ah6_type = { .description = "AH6", @@ -727,10 +768,11 @@ static const struct xfrm_type ah6_type = .hdr_offset = xfrm6_find_1stfragopt, }; -static const struct inet6_protocol ah6_protocol = { +static struct xfrm6_protocol ah6_protocol = { .handler = xfrm6_rcv, + .cb_handler = ah6_rcv_cb, .err_handler = ah6_err, - .flags = INET6_PROTO_NOPOLICY, + .priority = 0, }; static int __init ah6_init(void) @@ -740,7 +782,7 @@ static int __init ah6_init(void) return -EAGAIN; } - if (inet6_add_protocol(&ah6_protocol, IPPROTO_AH) < 0) { + if (xfrm6_protocol_register(&ah6_protocol, IPPROTO_AH) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ah6_type, AF_INET6); return -EAGAIN; @@ -751,7 +793,7 @@ static int __init ah6_init(void) static void __exit ah6_fini(void) { - if (inet6_del_protocol(&ah6_protocol, IPPROTO_AH) < 0) + if (xfrm6_protocol_deregister(&ah6_protocol, IPPROTO_AH) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ah6_type, AF_INET6) < 0) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 6eef8a7e35f2..d15da1377149 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -421,8 +421,8 @@ static u32 esp6_get_mtu(struct xfrm_state *x, int mtu) net_adj) & ~(blksize - 1)) + net_adj - 2; } -static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) +static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; @@ -431,18 +431,20 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) - return; + return 0; x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) - return; + return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0); else ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); + + return 0; } static void esp6_destroy(struct xfrm_state *x) @@ -614,6 +616,11 @@ error: return err; } +static int esp6_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type esp6_type = { .description = "ESP6", @@ -628,10 +635,11 @@ static const struct xfrm_type esp6_type = .hdr_offset = xfrm6_find_1stfragopt, }; -static const struct inet6_protocol esp6_protocol = { - .handler = xfrm6_rcv, +static struct xfrm6_protocol esp6_protocol = { + .handler = xfrm6_rcv, + .cb_handler = esp6_rcv_cb, .err_handler = esp6_err, - .flags = INET6_PROTO_NOPOLICY, + .priority = 0, }; static int __init esp6_init(void) @@ -640,7 +648,7 @@ static int __init esp6_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet6_add_protocol(&esp6_protocol, IPPROTO_ESP) < 0) { + if (xfrm6_protocol_register(&esp6_protocol, IPPROTO_ESP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&esp6_type, AF_INET6); return -EAGAIN; @@ -651,7 +659,7 @@ static int __init esp6_init(void) static void __exit esp6_fini(void) { - if (inet6_del_protocol(&esp6_protocol, IPPROTO_ESP) < 0) + if (xfrm6_protocol_deregister(&esp6_protocol, IPPROTO_ESP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&esp6_type, AF_INET6) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f2610e157660..7b326529e6a2 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -520,7 +520,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) np->tclass, NULL, &fl6, (struct rt6_info *)dst, MSG_DONTWAIT, np->dontfrag); if (err) { - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index 72d198b8e4d2..ee7a97f510cb 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -79,7 +79,9 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) /* RFC 2460 section 8.1 says that we SHOULD log this error. Well, it is reasonable. */ - LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); + LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n", + &ipv6_hdr(skb)->saddr, ntohs(uh->source), + &ipv6_hdr(skb)->daddr, ntohs(uh->dest)); return 1; } if (skb->ip_summed == CHECKSUM_COMPLETE && diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 075602fc6b6a..34e0ded5c14b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -9,14 +9,12 @@ * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. - */ - -/* - * Changes: - * Yuji SEKIYA @USAGI: Support default route on router node; - * remove ip6_null_entry from the top of - * routing table. - * Ville Nuorvala: Fixed routing subtrees. + * + * Changes: + * Yuji SEKIYA @USAGI: Support default route on router node; + * remove ip6_null_entry from the top of + * routing table. + * Ville Nuorvala: Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt @@ -46,10 +44,9 @@ #define RT6_TRACE(x...) do { ; } while (0) #endif -static struct kmem_cache * fib6_node_kmem __read_mostly; +static struct kmem_cache *fib6_node_kmem __read_mostly; -enum fib_walk_state_t -{ +enum fib_walk_state_t { #ifdef CONFIG_IPV6_SUBTREES FWS_S, #endif @@ -59,8 +56,7 @@ enum fib_walk_state_t FWS_U }; -struct fib6_cleaner_t -{ +struct fib6_cleaner_t { struct fib6_walker_t w; struct net *net; int (*func)(struct rt6_info *, void *arg); @@ -138,7 +134,7 @@ static __inline__ __be32 addr_bit_set(const void *token, int fn_bit) const __be32 *addr = token; /* * Here, - * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) + * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) * is optimized version of * htonl(1 << ((~fn_bit)&0x1F)) * See include/asm-generic/bitops/le.h. @@ -147,7 +143,7 @@ static __inline__ __be32 addr_bit_set(const void *token, int fn_bit) addr[fn_bit >> 5]; } -static __inline__ struct fib6_node * node_alloc(void) +static __inline__ struct fib6_node *node_alloc(void) { struct fib6_node *fn; @@ -156,7 +152,7 @@ static __inline__ struct fib6_node * node_alloc(void) return fn; } -static __inline__ void node_free(struct fib6_node * fn) +static __inline__ void node_free(struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); } @@ -292,7 +288,7 @@ static int fib6_dump_node(struct fib6_walker_t *w) static void fib6_dump_end(struct netlink_callback *cb) { - struct fib6_walker_t *w = (void*)cb->args[2]; + struct fib6_walker_t *w = (void *)cb->args[2]; if (w) { if (cb->args[4]) { @@ -302,7 +298,7 @@ static void fib6_dump_end(struct netlink_callback *cb) cb->args[2] = 0; kfree(w); } - cb->done = (void*)cb->args[3]; + cb->done = (void *)cb->args[3]; cb->args[1] = 3; } @@ -485,7 +481,7 @@ static struct fib6_node *fib6_add_1(struct fib6_node *root, fn->fn_sernum = sernum; dir = addr_bit_set(addr, fn->fn_bit); pn = fn; - fn = dir ? fn->right: fn->left; + fn = dir ? fn->right : fn->left; } while (fn); if (!allow_create) { @@ -638,12 +634,41 @@ static inline bool rt6_qualify_for_ecmp(struct rt6_info *rt) RTF_GATEWAY; } +static int fib6_commit_metrics(struct dst_entry *dst, + struct nlattr *mx, int mx_len) +{ + struct nlattr *nla; + int remaining; + u32 *mp; + + if (dst->flags & DST_HOST) { + mp = dst_metrics_write_ptr(dst); + } else { + mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); + if (!mp) + return -ENOMEM; + dst_init_metrics(dst, mp, 0); + } + + nla_for_each_attr(nla, mx, mx_len, remaining) { + int type = nla_type(nla); + + if (type) { + if (type > RTAX_MAX) + return -EINVAL; + + mp[type - 1] = nla_get_u32(nla); + } + } + return 0; +} + /* * Insert routing information in a node. */ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nl_info *info) + struct nl_info *info, struct nlattr *mx, int mx_len) { struct rt6_info *iter = NULL; struct rt6_info **ins; @@ -653,6 +678,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); + int err; ins = &fn->leaf; @@ -751,6 +777,11 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: + if (mx) { + err = fib6_commit_metrics(&rt->dst, mx, mx_len); + if (err) + return err; + } rt->dst.rt6_next = iter; *ins = rt; rt->rt6i_node = fn; @@ -770,6 +801,11 @@ add: pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); return -ENOENT; } + if (mx) { + err = fib6_commit_metrics(&rt->dst, mx, mx_len); + if (err) + return err; + } *ins = rt; rt->rt6i_node = fn; rt->dst.rt6_next = iter->dst.rt6_next; @@ -806,7 +842,8 @@ void fib6_force_start_gc(struct net *net) * with source addr info in sub-trees */ -int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) +int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, + struct nlattr *mx, int mx_len) { struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; @@ -900,7 +937,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) } #endif - err = fib6_add_rt2node(fn, rt, info); + err = fib6_add_rt2node(fn, rt, info, mx, mx_len); if (!err) { fib6_start_gc(info->nl_net, rt); if (!(rt->rt6i_flags & RTF_CACHE)) @@ -955,8 +992,8 @@ struct lookup_args { const struct in6_addr *addr; /* search key */ }; -static struct fib6_node * fib6_lookup_1(struct fib6_node *root, - struct lookup_args *args) +static struct fib6_node *fib6_lookup_1(struct fib6_node *root, + struct lookup_args *args) { struct fib6_node *fn; __be32 dir; @@ -1018,8 +1055,8 @@ backtrack: return NULL; } -struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, - const struct in6_addr *saddr) +struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct fib6_node *fn; struct lookup_args args[] = { @@ -1051,9 +1088,9 @@ struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *da */ -static struct fib6_node * fib6_locate_1(struct fib6_node *root, - const struct in6_addr *addr, - int plen, int offset) +static struct fib6_node *fib6_locate_1(struct fib6_node *root, + const struct in6_addr *addr, + int plen, int offset) { struct fib6_node *fn; @@ -1081,9 +1118,9 @@ static struct fib6_node * fib6_locate_1(struct fib6_node *root, return NULL; } -struct fib6_node * fib6_locate(struct fib6_node *root, - const struct in6_addr *daddr, int dst_len, - const struct in6_addr *saddr, int src_len) +struct fib6_node *fib6_locate(struct fib6_node *root, + const struct in6_addr *daddr, int dst_len, + const struct in6_addr *saddr, int src_len) { struct fib6_node *fn; @@ -1151,8 +1188,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net, children = 0; child = NULL; - if (fn->right) child = fn->right, children |= 1; - if (fn->left) child = fn->left, children |= 2; + if (fn->right) + child = fn->right, children |= 1; + if (fn->left) + child = fn->left, children |= 2; if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES @@ -1180,8 +1219,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net, } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif - if (pn->right == fn) pn->right = child; - else if (pn->left == fn) pn->left = child; + if (pn->right == fn) + pn->right = child; + else if (pn->left == fn) + pn->left = child; #if RT6_DEBUG >= 2 else WARN_ON(1); @@ -1213,10 +1254,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net, w->node = child; if (children&2) { RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); - w->state = w->state>=FWS_R ? FWS_U : FWS_INIT; + w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); - w->state = w->state>=FWS_C ? FWS_U : FWS_INIT; + w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } } @@ -1314,7 +1355,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info) struct rt6_info **rtp; #if RT6_DEBUG >= 2 - if (rt->dst.obsolete>0) { + if (rt->dst.obsolete > 0) { WARN_ON(fn != NULL); return -ENOENT; } @@ -1707,7 +1748,7 @@ out_rt6_stats: kfree(net->ipv6.rt6_stats); out_timer: return -ENOMEM; - } +} static void fib6_net_exit(struct net *net) { diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index dfa41bb4e0dc..0961b5ef866d 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -15,9 +15,7 @@ #include <linux/socket.h> #include <linux/net.h> #include <linux/netdevice.h> -#include <linux/if_arp.h> #include <linux/in6.h> -#include <linux/route.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> @@ -28,12 +26,8 @@ #include <net/sock.h> #include <net/ipv6.h> -#include <net/ndisc.h> -#include <net/protocol.h> -#include <net/ip6_route.h> #include <net/addrconf.h> #include <net/rawv6.h> -#include <net/icmp.h> #include <net/transp_v6.h> #include <asm/uaccess.h> diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f3ffb43f59c0..c98338b81d30 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1454,7 +1454,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[], static int ip6gre_tap_init(struct net_device *dev) { struct ip6_tnl *tunnel; - int i; tunnel = netdev_priv(dev); @@ -1464,16 +1463,10 @@ static int ip6gre_tap_init(struct net_device *dev) ip6gre_tnl_link_config(tunnel, 1); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ip6gre_tap_stats; - ip6gre_tap_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ip6gre_tap_stats->syncp); - } - return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 64d6073731d3..3284d61577c0 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -367,6 +367,9 @@ int ip6_forward(struct sk_buff *skb) if (net->ipv6.devconf_all->forwarding == 0) goto error; + if (skb->pkt_type != PACKET_HOST) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -376,9 +379,6 @@ int ip6_forward(struct sk_buff *skb) goto drop; } - if (skb->pkt_type != PACKET_HOST) - goto drop; - skb_forward_csum(skb); /* @@ -1230,8 +1230,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; - maxnonfragsize = (np->pmtudisc >= IPV6_PMTUDISC_DO) ? - mtu : sizeof(struct ipv6hdr) + IPV6_MAXPLEN; + if (ip6_sk_local_df(sk)) + maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN; + else + maxnonfragsize = mtu; /* dontfrag active */ if ((cork->length + length > mtu - headersize) && dontfrag && @@ -1538,8 +1540,7 @@ int ip6_push_pending_frames(struct sock *sk) } /* Allow local fragmentation. */ - if (np->pmtudisc < IPV6_PMTUDISC_DO) - skb->local_df = 1; + skb->local_df = ip6_sk_local_df(sk); *final_dst = fl6->daddr; __skb_pull(skb, skb_network_header_len(skb)); @@ -1566,8 +1567,8 @@ int ip6_push_pending_frames(struct sock *sk) if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); - ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type); - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } err = ip6_local_out(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5db8d310f9c0..e1df691d78be 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -108,12 +108,12 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) per_cpu_ptr(dev->tstats, i); do { - start = u64_stats_fetch_begin_bh(&tstats->syncp); + start = u64_stats_fetch_begin_irq(&tstats->syncp); tmp.rx_packets = tstats->rx_packets; tmp.rx_bytes = tstats->rx_bytes; tmp.tx_packets = tstats->tx_packets; tmp.tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&tstats->syncp, start)); sum.rx_packets += tmp.rx_packets; sum.rx_bytes += tmp.rx_bytes; @@ -1502,19 +1502,12 @@ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - int i; t->dev = dev; t->net = dev_net(dev); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ip6_tnl_stats; - ip6_tnl_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ip6_tnl_stats->syncp); - } return 0; } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 2d19272b8cee..b7c0f827140b 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -278,7 +278,6 @@ static void vti6_dev_uninit(struct net_device *dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else vti6_tnl_unlink(ip6n, t); - ip6_tnl_dst_reset(t); dev_put(dev); } @@ -288,11 +287,8 @@ static int vti6_rcv(struct sk_buff *skb) const struct ipv6hdr *ipv6h = ipv6_hdr(skb); rcu_read_lock(); - if ((t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { - struct pcpu_sw_netstats *tstats; - if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) { rcu_read_unlock(); goto discard; @@ -309,27 +305,58 @@ static int vti6_rcv(struct sk_buff *skb) goto discard; } - tstats = this_cpu_ptr(t->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); - - skb->mark = 0; - secpath_reset(skb); - skb->dev = t->dev; + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; + skb->mark = be32_to_cpu(t->parms.i_key); rcu_read_unlock(); - return 0; + + return xfrm6_rcv(skb); } rcu_read_unlock(); - return 1; - + return -EINVAL; discard: kfree_skb(skb); return 0; } +static int vti6_rcv_cb(struct sk_buff *skb, int err) +{ + unsigned short family; + struct net_device *dev; + struct pcpu_sw_netstats *tstats; + struct xfrm_state *x; + struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; + + if (!t) + return 1; + + dev = t->dev; + + if (err) { + dev->stats.rx_errors++; + dev->stats.rx_dropped++; + + return 0; + } + + x = xfrm_input_state(skb); + family = x->inner_mode->afinfo->family; + + if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + return -EPERM; + + skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev))); + skb->dev = dev; + + tstats = this_cpu_ptr(dev->tstats); + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + return 0; +} + /** * vti6_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device @@ -349,44 +376,56 @@ vti6_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } +static bool vti6_state_check(const struct xfrm_state *x, + const struct in6_addr *dst, + const struct in6_addr *src) +{ + xfrm_address_t *daddr = (xfrm_address_t *)dst; + xfrm_address_t *saddr = (xfrm_address_t *)src; + + /* if there is no transform then this tunnel is not functional. + * Or if the xfrm is not mode tunnel. + */ + if (!x || x->props.mode != XFRM_MODE_TUNNEL || + x->props.family != AF_INET6) + return false; + + if (ipv6_addr_any(dst)) + return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET6); + + if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET6)) + return false; + + return true; +} + /** * vti6_xmit - send a packet * @skb: the outgoing socket buffer * @dev: the outgoing tunnel device + * @fl: the flow informations for the xfrm_lookup **/ -static int vti6_xmit(struct sk_buff *skb, struct net_device *dev) +static int +vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { - struct net *net = dev_net(dev); struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; - struct dst_entry *dst = NULL, *ndst = NULL; - struct flowi6 fl6; - struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; int err = -1; - if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || - !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h)) - return err; - - dst = ip6_tnl_dst_check(t); - if (!dst) { - memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); - - ndst = ip6_route_output(net, NULL, &fl6); + if (!dst) + goto tx_err_link_failure; - if (ndst->error) - goto tx_err_link_failure; - ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(&fl6), NULL, 0); - if (IS_ERR(ndst)) { - err = PTR_ERR(ndst); - ndst = NULL; - goto tx_err_link_failure; - } - dst = ndst; + dst_hold(dst); + dst = xfrm_lookup(t->net, dst, fl, NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + goto tx_err_link_failure; } - if (!dst->xfrm || dst->xfrm->props.mode != XFRM_MODE_TUNNEL) + if (!vti6_state_check(dst->xfrm, &t->parms.raddr, &t->parms.laddr)) goto tx_err_link_failure; tdev = dst->dev; @@ -398,14 +437,21 @@ static int vti6_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_err_dst_release; } + skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); + skb_dst_set(skb, dst); + skb->dev = skb_dst(skb)->dev; - skb_dst_drop(skb); - skb_dst_set_noref(skb, dst); + err = dst_output(skb); + if (net_xmit_eval(err) == 0) { + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); - ip6tunnel_xmit(skb, dev); - if (ndst) { - dev->mtu = dst_mtu(ndst); - ip6_tnl_dst_store(t, ndst); + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += skb->len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + stats->tx_errors++; + stats->tx_aborted_errors++; } return 0; @@ -413,7 +459,7 @@ tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(ndst); + dst_release(dst); return err; } @@ -422,16 +468,33 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; + struct ipv6hdr *ipv6h; + struct flowi fl; int ret; + memset(&fl, 0, sizeof(fl)); + skb->mark = be32_to_cpu(t->parms.o_key); + switch (skb->protocol) { case htons(ETH_P_IPV6): - ret = vti6_xmit(skb, dev); + ipv6h = ipv6_hdr(skb); + + if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || + !ip6_tnl_xmit_ctl(t) || vti6_addr_conflict(t, ipv6h)) + goto tx_err; + + xfrm_decode_session(skb, &fl, AF_INET6); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + break; + case htons(ETH_P_IP): + xfrm_decode_session(skb, &fl, AF_INET); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); break; default: goto tx_err; } + ret = vti6_xmit(skb, dev, &fl); if (ret < 0) goto tx_err; @@ -444,24 +507,66 @@ tx_err: return NETDEV_TX_OK; } +static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + __be32 spi; + struct xfrm_state *x; + struct ip6_tnl *t; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah; + struct ip_comp_hdr *ipch; + struct net *net = dev_net(skb->dev); + const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; + int protocol = iph->nexthdr; + + t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr); + if (!t) + return -1; + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data + offset); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data + offset); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data + offset); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + if (type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) + return 0; + + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET6); + if (!x) + return 0; + + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0); + else + ip6_update_pmtu(skb, net, info, 0, 0); + xfrm_state_put(x); + + return 0; +} + static void vti6_link_config(struct ip6_tnl *t) { - struct dst_entry *dst; struct net_device *dev = t->dev; struct __ip6_tnl_parm *p = &t->parms; - struct flowi6 *fl6 = &t->fl.u.ip6; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); - /* Set up flowi template */ - fl6->saddr = p->laddr; - fl6->daddr = p->raddr; - fl6->flowi6_oif = p->link; - fl6->flowi6_mark = be32_to_cpu(p->i_key); - fl6->flowi6_proto = p->proto; - fl6->flowlabel = 0; - p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV | IP6_TNL_F_CAP_PER_PACKET); p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); @@ -472,28 +577,6 @@ static void vti6_link_config(struct ip6_tnl *t) dev->flags &= ~IFF_POINTOPOINT; dev->iflink = p->link; - - if (p->flags & IP6_TNL_F_CAP_XMIT) { - - dst = ip6_route_output(dev_net(dev), NULL, fl6); - if (dst->error) - return; - - dst = xfrm_lookup(dev_net(dev), dst, flowi6_to_flowi(fl6), - NULL, 0); - if (IS_ERR(dst)) - return; - - if (dst->dev) { - dev->hard_header_len = dst->dev->hard_header_len; - - dev->mtu = dst_mtu(dst); - - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; - } - dst_release(dst); - } } /** @@ -720,7 +803,6 @@ static void vti6_dev_setup(struct net_device *dev) t = netdev_priv(dev); dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; } @@ -731,18 +813,12 @@ static void vti6_dev_setup(struct net_device *dev) static inline int vti6_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - int i; t->dev = dev; t->net = dev_net(dev); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *stats; - stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&stats->syncp); - } return 0; } @@ -914,11 +990,6 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = { .fill_info = vti6_fill_info, }; -static struct xfrm_tunnel_notifier vti6_handler __read_mostly = { - .handler = vti6_rcv, - .priority = 1, -}; - static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n) { int h; @@ -990,6 +1061,27 @@ static struct pernet_operations vti6_net_ops = { .size = sizeof(struct vti6_net), }; +static struct xfrm6_protocol vti_esp6_protocol __read_mostly = { + .handler = vti6_rcv, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 100, +}; + +static struct xfrm6_protocol vti_ah6_protocol __read_mostly = { + .handler = vti6_rcv, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 100, +}; + +static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { + .handler = vti6_rcv, + .cb_handler = vti6_rcv_cb, + .err_handler = vti6_err, + .priority = 100, +}; + /** * vti6_tunnel_init - register protocol and reserve needed resources * @@ -1003,11 +1095,33 @@ static int __init vti6_tunnel_init(void) if (err < 0) goto out_pernet; - err = xfrm6_mode_tunnel_input_register(&vti6_handler); + err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP); if (err < 0) { - pr_err("%s: can't register vti6\n", __func__); + unregister_pernet_device(&vti6_net_ops); + pr_err("%s: can't register vti6 protocol\n", __func__); + goto out; } + + err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH); + if (err < 0) { + xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); + unregister_pernet_device(&vti6_net_ops); + pr_err("%s: can't register vti6 protocol\n", __func__); + + goto out; + } + + err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP); + if (err < 0) { + xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); + xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); + unregister_pernet_device(&vti6_net_ops); + pr_err("%s: can't register vti6 protocol\n", __func__); + + goto out; + } + err = rtnl_link_register(&vti6_link_ops); if (err < 0) goto rtnl_link_failed; @@ -1015,7 +1129,9 @@ static int __init vti6_tunnel_init(void) return 0; rtnl_link_failed: - xfrm6_mode_tunnel_input_deregister(&vti6_handler); + xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); + xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); + xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); out: unregister_pernet_device(&vti6_net_ops); out_pernet: @@ -1028,8 +1144,12 @@ out_pernet: static void __exit vti6_tunnel_cleanup(void) { rtnl_link_unregister(&vti6_link_ops); - if (xfrm6_mode_tunnel_input_deregister(&vti6_handler)) - pr_info("%s: can't deregister vti6\n", __func__); + if (xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP)) + pr_info("%s: can't deregister protocol\n", __func__); + if (xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH)) + pr_info("%s: can't deregister protocol\n", __func__); + if (xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP)) + pr_info("%s: can't deregister protocol\n", __func__); unregister_pernet_device(&vti6_net_ops); } diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index da9becb42e81..d1c793cffcb5 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -53,7 +53,7 @@ #include <linux/icmpv6.h> #include <linux/mutex.h> -static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, +static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); @@ -65,19 +65,21 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) - return; + return 0; spi = htonl(ntohs(ipcomph->cpi)); x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET6); if (!x) - return; + return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0); else ip6_update_pmtu(skb, net, info, 0, 0); xfrm_state_put(x); + + return 0; } static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) @@ -174,6 +176,11 @@ out: return err; } +static int ipcomp6_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type ipcomp6_type = { .description = "IPCOMP6", @@ -186,11 +193,12 @@ static const struct xfrm_type ipcomp6_type = .hdr_offset = xfrm6_find_1stfragopt, }; -static const struct inet6_protocol ipcomp6_protocol = +static struct xfrm6_protocol ipcomp6_protocol = { .handler = xfrm6_rcv, + .cb_handler = ipcomp6_rcv_cb, .err_handler = ipcomp6_err, - .flags = INET6_PROTO_NOPOLICY, + .priority = 0, }; static int __init ipcomp6_init(void) @@ -199,7 +207,7 @@ static int __init ipcomp6_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet6_add_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) { + if (xfrm6_protocol_register(&ipcomp6_protocol, IPPROTO_COMP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ipcomp6_type, AF_INET6); return -EAGAIN; @@ -209,7 +217,7 @@ static int __init ipcomp6_init(void) static void __exit ipcomp6_fini(void) { - if (inet6_del_protocol(&ipcomp6_protocol, IPPROTO_COMP) < 0) + if (xfrm6_protocol_deregister(&ipcomp6_protocol, IPPROTO_COMP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ipcomp6_type, AF_INET6) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 0a00f449de5e..edb58aff4ae7 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -722,7 +722,7 @@ done: case IPV6_MTU_DISCOVER: if (optlen < sizeof(int)) goto e_inval; - if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_INTERFACE) + if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT) goto e_inval; np->pmtudisc = val; retv = 0; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index e1e47350784b..08b367c6b9cf 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1620,11 +1620,12 @@ static void mld_sendpack(struct sk_buff *skb) dst_output); out: if (!err) { - ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT); - ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); - IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); - } else - IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS); + ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); + ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len); + } else { + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + } rcu_read_unlock(); return; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 827f795209cf..6313abd53c9d 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -6,24 +6,24 @@ #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/addrconf.h> +#include <net/secure_seq.h> void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) { static atomic_t ipv6_fragmentation_id; + struct in6_addr addr; int old, new; #if IS_ENABLED(CONFIG_IPV6) - if (rt && !(rt->dst.flags & DST_NOPEER)) { - struct inet_peer *peer; - struct net *net; - - net = dev_net(rt->dst.dev); - peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); - if (peer) { - fhdr->identification = htonl(inet_getid(peer, 0)); - inet_putpeer(peer); - return; - } + struct inet_peer *peer; + struct net *net; + + net = dev_net(rt->dst.dev); + peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1); + if (peer) { + fhdr->identification = htonl(inet_getid(peer, 0)); + inet_putpeer(peer); + return; } #endif do { @@ -32,7 +32,10 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) if (!new) new = 1; } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); - fhdr->identification = htonl(new); + + addr = rt->rt6i_dst.addr; + addr.s6_addr32[0] ^= (__force __be32)new; + fhdr->identification = htonl(secure_ipv6_id(addr.s6_addr32)); } EXPORT_SYMBOL(ipv6_select_ident); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 587bbdcb22b4..bda74291c3e0 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -182,8 +182,8 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, MSG_DONTWAIT, np->dontfrag); if (err) { - ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev, - ICMP6_MIB_OUTERRORS); + ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev, + ICMP6_MIB_OUTERRORS); ip6_flush_pending_frames(sk); } else { err = icmpv6_push_pending_frames(sk, &fl6, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fba54a407bb2..5015c50a5ba7 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -149,7 +149,8 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) unsigned long prev, new; p = peer->metrics; - if (inet_metrics_new(peer)) + if (inet_metrics_new(peer) || + (old & DST_METRICS_FORCE_OVERWRITE)) memcpy(p, old_p, sizeof(u32) * RTAX_MAX); new = (unsigned long) p; @@ -373,12 +374,6 @@ static bool rt6_check_expired(const struct rt6_info *rt) return false; } -static bool rt6_need_strict(const struct in6_addr *daddr) -{ - return ipv6_addr_type(daddr) & - (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); -} - /* Multipath route selection: * Hash based function using packet header and flowlabel. * Adapted from fib_info_hashfn() @@ -857,14 +852,15 @@ EXPORT_SYMBOL(rt6_lookup); be destroyed. */ -static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info) +static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, + struct nlattr *mx, int mx_len) { int err; struct fib6_table *table; table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, info); + err = fib6_add(&table->tb6_root, rt, info, mx, mx_len); write_unlock_bh(&table->tb6_lock); return err; @@ -875,7 +871,7 @@ int ip6_ins_rt(struct rt6_info *rt) struct nl_info info = { .nl_net = dev_net(rt->dst.dev), }; - return __ip6_ins_rt(rt, &info); + return __ip6_ins_rt(rt, &info, NULL, 0); } static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, @@ -1543,17 +1539,11 @@ int ip6_route_add(struct fib6_config *cfg) ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->rt6i_dst.plen = cfg->fc_dst_len; - if (rt->rt6i_dst.plen == 128) - rt->dst.flags |= DST_HOST; - - if (!(rt->dst.flags & DST_HOST) && cfg->fc_mx) { - u32 *metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); - if (!metrics) { - err = -ENOMEM; - goto out; - } - dst_init_metrics(&rt->dst, metrics, 0); + if (rt->rt6i_dst.plen == 128) { + rt->dst.flags |= DST_HOST; + dst_metrics_set_force_overwrite(&rt->dst); } + #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); rt->rt6i_src.plen = cfg->fc_src_len; @@ -1672,31 +1662,13 @@ int ip6_route_add(struct fib6_config *cfg) rt->rt6i_flags = cfg->fc_flags; install_route: - if (cfg->fc_mx) { - struct nlattr *nla; - int remaining; - - nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { - int type = nla_type(nla); - - if (type) { - if (type > RTAX_MAX) { - err = -EINVAL; - goto out; - } - - dst_metric_set(&rt->dst, type, nla_get_u32(nla)); - } - } - } - rt->dst.dev = dev; rt->rt6i_idev = idev; rt->rt6i_table = table; cfg->fc_nlinfo.nl_net = dev_net(dev); - return __ip6_ins_rt(rt, &cfg->fc_nlinfo); + return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len); out: if (dev) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b4d74c86586c..1693c8d885f0 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1363,7 +1363,6 @@ static void ipip6_tunnel_setup(struct net_device *dev) static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - int i; tunnel->dev = dev; tunnel->net = dev_net(dev); @@ -1372,16 +1371,10 @@ static int ipip6_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip6_tunnel_bind_dev(dev); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ipip6_tunnel_stats; - ipip6_tunnel_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ipip6_tunnel_stats->syncp); - } - tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); if (!tunnel->dst_cache) { free_percpu(dev->tstats); @@ -1397,7 +1390,6 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) struct iphdr *iph = &tunnel->parms.iph; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); - int i; tunnel->dev = dev; tunnel->net = dev_net(dev); @@ -1408,16 +1400,10 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; iph->ttl = 64; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ipip6_fb_stats; - ipip6_fb_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ipip6_fb_stats->syncp); - } - tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); if (!tunnel->dst_cache) { free_percpu(dev->tstats); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 889079b2ea85..5ca56cee2dae 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -39,7 +39,7 @@ #include <linux/ipsec.h> #include <linux/times.h> #include <linux/slab.h> - +#include <linux/uaccess.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/random.h> @@ -65,8 +65,6 @@ #include <net/tcp_memcontrol.h> #include <net/busy_poll.h> -#include <asm/uaccess.h> - #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -501,8 +499,10 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req) int res; res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0); - if (!res) + if (!res) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + } return res; } @@ -530,8 +530,8 @@ static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, return tcp_v6_md5_do_lookup(sk, &inet_rsk(req)->ir_v6_rmt_addr); } -static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, - int optlen) +static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, + int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; @@ -715,7 +715,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset, - .syn_ack_timeout = tcp_syn_ack_timeout, + .syn_ack_timeout = tcp_syn_ack_timeout, }; #ifdef CONFIG_TCP_MD5SIG @@ -726,7 +726,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { #endif static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, - u32 tsval, u32 tsecr, + u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int rst, u8 tclass, u32 label) { @@ -798,8 +798,10 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); fl6.flowi6_proto = IPPROTO_TCP; - if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL) + if (rt6_need_strict(&fl6.daddr) || !oif) fl6.flowi6_oif = inet6_iif(skb); + else + fl6.flowi6_oif = oif; fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source; security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); @@ -833,6 +835,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) int genhash; struct sock *sk1 = NULL; #endif + int oif; if (th->rst) return; @@ -876,7 +879,8 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); - tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, key, 1, 0, 0); + oif = sk ? sk->sk_bound_dev_if : 0; + tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0, 0); #ifdef CONFIG_TCP_MD5SIG release_sk1: @@ -888,11 +892,11 @@ release_sk1: } static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, - u32 win, u32 tsval, u32 tsecr, + u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, u8 tclass, u32 label) { - tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, key, 0, tclass, + tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, oif, key, 0, tclass, label); } @@ -904,7 +908,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, - tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw), + tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_tclass, (tw->tw_flowlabel << 12)); inet_twsk_put(tw); @@ -914,7 +918,7 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, - req->rcv_wnd, tcp_time_stamp, req->ts_recent, + req->rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); } @@ -1259,7 +1263,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ - if ((key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr)) != NULL) { + key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr); + if (key != NULL) { /* We're using one, so create a matching key * on the newsk structure. If we fail to get * memory, then we end up not copying the key @@ -1303,9 +1308,8 @@ static __sum16 tcp_v6_checksum_init(struct sk_buff *skb) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, 0)); - if (skb->len <= 76) { + if (skb->len <= 76) return __skb_checksum_complete(skb); - } return 0; } @@ -1335,7 +1339,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) return tcp_v4_do_rcv(sk, skb); #ifdef CONFIG_TCP_MD5SIG - if (tcp_v6_inbound_md5_hash (sk, skb)) + if (tcp_v6_inbound_md5_hash(sk, skb)) goto discard; #endif @@ -1602,7 +1606,8 @@ do_time_wait: break; case TCP_TW_RST: goto no_tcp_socket; - case TCP_TW_SUCCESS:; + case TCP_TW_SUCCESS: + ; } goto discard_it; } @@ -1647,7 +1652,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_unique = tcp_twsk_unique, - .twsk_destructor= tcp_twsk_destructor, + .twsk_destructor = tcp_twsk_destructor, }; static const struct inet_connection_sock_af_ops ipv6_specific = { @@ -1681,7 +1686,6 @@ static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { /* * TCP over IPv4 via INET6 API */ - static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index cb04f7a16b5e..901ef6f8addc 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -18,65 +18,6 @@ #include <net/ipv6.h> #include <net/xfrm.h> -/* Informational hook. The decap is still done here. */ -static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly; -static DEFINE_MUTEX(xfrm6_mode_tunnel_input_mutex); - -int xfrm6_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -EEXIST; - int priority = handler->priority; - - mutex_lock(&xfrm6_mode_tunnel_input_mutex); - - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t->priority > priority) - break; - if (t->priority == priority) - goto err; - - } - - handler->next = *pprev; - rcu_assign_pointer(*pprev, handler); - - ret = 0; - -err: - mutex_unlock(&xfrm6_mode_tunnel_input_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_register); - -int xfrm6_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -ENOENT; - - mutex_lock(&xfrm6_mode_tunnel_input_mutex); - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm6_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t == handler) { - *pprev = handler->next; - ret = 0; - break; - } - } - mutex_unlock(&xfrm6_mode_tunnel_input_mutex); - synchronize_net(); - - return ret; -} -EXPORT_SYMBOL_GPL(xfrm6_mode_tunnel_input_deregister); - static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) { const struct ipv6hdr *outer_iph = ipv6_hdr(skb); @@ -130,7 +71,6 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - struct xfrm_tunnel_notifier *handler; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) @@ -138,9 +78,6 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; - for_each_input_rcu(rcv_notify_handlers, handler) - handler->handler(skb); - err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 5f8e128c512d..2a0bbda2c76a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -389,11 +389,17 @@ int __init xfrm6_init(void) if (ret) goto out_policy; + ret = xfrm6_protocol_init(); + if (ret) + goto out_state; + #ifdef CONFIG_SYSCTL register_pernet_subsys(&xfrm6_net_ops); #endif out: return ret; +out_state: + xfrm6_state_fini(); out_policy: xfrm6_policy_fini(); goto out; @@ -404,6 +410,7 @@ void xfrm6_fini(void) #ifdef CONFIG_SYSCTL unregister_pernet_subsys(&xfrm6_net_ops); #endif + xfrm6_protocol_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); dst_entries_destroy(&xfrm6_dst_ops); diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c new file mode 100644 index 000000000000..6ab989c486f7 --- /dev/null +++ b/net/ipv6/xfrm6_protocol.c @@ -0,0 +1,270 @@ +/* xfrm6_protocol.c - Generic xfrm protocol multiplexer for ipv6. + * + * Copyright (C) 2013 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + * + * Based on: + * net/ipv4/xfrm4_protocol.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/skbuff.h> +#include <linux/icmpv6.h> +#include <net/ipv6.h> +#include <net/protocol.h> +#include <net/xfrm.h> + +static struct xfrm6_protocol __rcu *esp6_handlers __read_mostly; +static struct xfrm6_protocol __rcu *ah6_handlers __read_mostly; +static struct xfrm6_protocol __rcu *ipcomp6_handlers __read_mostly; +static DEFINE_MUTEX(xfrm6_protocol_mutex); + +static inline struct xfrm6_protocol __rcu **proto_handlers(u8 protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp6_handlers; + case IPPROTO_AH: + return &ah6_handlers; + case IPPROTO_COMP: + return &ipcomp6_handlers; + } + + return NULL; +} + +#define for_each_protocol_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) \ + +int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err) +{ + int ret; + struct xfrm6_protocol *handler; + + for_each_protocol_rcu(*proto_handlers(protocol), handler) + if ((ret = handler->cb_handler(skb, err)) <= 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(xfrm6_rcv_cb); + +static int xfrm6_esp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm6_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + + for_each_protocol_rcu(esp6_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct xfrm6_protocol *handler; + + for_each_protocol_rcu(esp6_handlers, handler) + if (!handler->err_handler(skb, opt, type, code, offset, info)) + break; +} + +static int xfrm6_ah_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm6_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + + for_each_protocol_rcu(ah6_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct xfrm6_protocol *handler; + + for_each_protocol_rcu(ah6_handlers, handler) + if (!handler->err_handler(skb, opt, type, code, offset, info)) + break; +} + +static int xfrm6_ipcomp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm6_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + + for_each_protocol_rcu(ipcomp6_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct xfrm6_protocol *handler; + + for_each_protocol_rcu(ipcomp6_handlers, handler) + if (!handler->err_handler(skb, opt, type, code, offset, info)) + break; +} + +static const struct inet6_protocol esp6_protocol = { + .handler = xfrm6_esp_rcv, + .err_handler = xfrm6_esp_err, + .flags = INET6_PROTO_NOPOLICY, +}; + +static const struct inet6_protocol ah6_protocol = { + .handler = xfrm6_ah_rcv, + .err_handler = xfrm6_ah_err, + .flags = INET6_PROTO_NOPOLICY, +}; + +static const struct inet6_protocol ipcomp6_protocol = { + .handler = xfrm6_ipcomp_rcv, + .err_handler = xfrm6_ipcomp_err, + .flags = INET6_PROTO_NOPOLICY, +}; + +static struct xfrm_input_afinfo xfrm6_input_afinfo = { + .family = AF_INET6, + .owner = THIS_MODULE, + .callback = xfrm6_rcv_cb, +}; + +static inline const struct inet6_protocol *netproto(unsigned char protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp6_protocol; + case IPPROTO_AH: + return &ah6_protocol; + case IPPROTO_COMP: + return &ipcomp6_protocol; + } + + return NULL; +} + +int xfrm6_protocol_register(struct xfrm6_protocol *handler, + unsigned char protocol) +{ + struct xfrm6_protocol __rcu **pprev; + struct xfrm6_protocol *t; + bool add_netproto = false; + + int ret = -EEXIST; + int priority = handler->priority; + + mutex_lock(&xfrm6_protocol_mutex); + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm6_protocol_mutex))) + add_netproto = true; + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t->priority < priority) + break; + if (t->priority == priority) + goto err; + } + + handler->next = *pprev; + rcu_assign_pointer(*pprev, handler); + + ret = 0; + +err: + mutex_unlock(&xfrm6_protocol_mutex); + + if (add_netproto) { + if (inet6_add_protocol(netproto(protocol), protocol)) { + pr_err("%s: can't add protocol\n", __func__); + ret = -EAGAIN; + } + } + + return ret; +} +EXPORT_SYMBOL(xfrm6_protocol_register); + +int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, + unsigned char protocol) +{ + struct xfrm6_protocol __rcu **pprev; + struct xfrm6_protocol *t; + int ret = -ENOENT; + + mutex_lock(&xfrm6_protocol_mutex); + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm6_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { + *pprev = handler->next; + ret = 0; + break; + } + } + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm6_protocol_mutex))) { + if (inet6_del_protocol(netproto(protocol), protocol) < 0) { + pr_err("%s: can't remove protocol\n", __func__); + ret = -EAGAIN; + } + } + + mutex_unlock(&xfrm6_protocol_mutex); + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(xfrm6_protocol_deregister); + +int __init xfrm6_protocol_init(void) +{ + return xfrm_input_register_afinfo(&xfrm6_input_afinfo); +} + +void xfrm6_protocol_fini(void) +{ + xfrm_input_unregister_afinfo(&xfrm6_input_afinfo); +} diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index 00b2a6d1c009..41e4e93cb3aa 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -1368,6 +1368,7 @@ static int ipx_release(struct socket *sock) goto out; lock_sock(sk); + sk->sk_shutdown = SHUTDOWN_MASK; if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); @@ -1791,8 +1792,11 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &rc); - if (!skb) + if (!skb) { + if (rc == -EAGAIN && (sk->sk_shutdown & RCV_SHUTDOWN)) + rc = 0; goto out; + } ipx = ipx_hdr(skb); copied = ntohs(ipx->ipx_pktsize) - sizeof(struct ipxhdr); @@ -1922,6 +1926,26 @@ static int ipx_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long } #endif +static int ipx_shutdown(struct socket *sock, int mode) +{ + struct sock *sk = sock->sk; + + if (mode < SHUT_RD || mode > SHUT_RDWR) + return -EINVAL; + /* This maps: + * SHUT_RD (0) -> RCV_SHUTDOWN (1) + * SHUT_WR (1) -> SEND_SHUTDOWN (2) + * SHUT_RDWR (2) -> SHUTDOWN_MASK (3) + */ + ++mode; + + lock_sock(sk); + sk->sk_shutdown |= mode; + release_sock(sk); + sk->sk_state_change(sk); + + return 0; +} /* * Socket family declarations @@ -1948,7 +1972,7 @@ static const struct proto_ops ipx_dgram_ops = { .compat_ioctl = ipx_compat_ioctl, #endif .listen = sock_no_listen, - .shutdown = sock_no_shutdown, /* FIXME: support shutdown */ + .shutdown = ipx_shutdown, .setsockopt = ipx_setsockopt, .getsockopt = ipx_getsockopt, .sendmsg = ipx_sendmsg, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index c4b7218058b6..a5e03119107a 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1382,6 +1382,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (sk->sk_type == SOCK_STREAM) { if (copied < rlen) { IUCV_SKB_CB(skb)->offset = offset + copied; + skb_queue_head(&sk->sk_receive_queue, skb); goto done; } } diff --git a/net/key/af_key.c b/net/key/af_key.c index 79326978517a..e72589a8400d 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -365,6 +365,7 @@ static const u8 sadb_ext_min_len[] = { [SADB_X_EXT_NAT_T_OA] = (u8) sizeof(struct sadb_address), [SADB_X_EXT_SEC_CTX] = (u8) sizeof(struct sadb_x_sec_ctx), [SADB_X_EXT_KMADDRESS] = (u8) sizeof(struct sadb_x_kmaddress), + [SADB_X_EXT_FILTER] = (u8) sizeof(struct sadb_x_filter), }; /* Verify sadb_address_{len,prefixlen} against sa_family. */ @@ -1799,6 +1800,7 @@ static void pfkey_dump_sa_done(struct pfkey_sock *pfk) static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { u8 proto; + struct xfrm_address_filter *filter = NULL; struct pfkey_sock *pfk = pfkey_sk(sk); if (pfk->dump.dump != NULL) @@ -1808,11 +1810,27 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (proto == 0) return -EINVAL; + if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { + struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; + + filter = kmalloc(sizeof(*filter), GFP_KERNEL); + if (filter == NULL) + return -ENOMEM; + + memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr, + sizeof(xfrm_address_t)); + memcpy(&filter->daddr, &xfilter->sadb_x_filter_daddr, + sizeof(xfrm_address_t)); + filter->family = xfilter->sadb_x_filter_family; + filter->splen = xfilter->sadb_x_filter_splen; + filter->dplen = xfilter->sadb_x_filter_dplen; + } + pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sa; pfk->dump.done = pfkey_dump_sa_done; - xfrm_state_walk_init(&pfk->dump.u.state, proto); + xfrm_state_walk_init(&pfk->dump.u.state, proto, filter); return pfkey_do_dump(pfk); } @@ -3060,6 +3078,24 @@ static u32 get_acqseq(void) return res; } +static bool pfkey_is_alive(const struct km_event *c) +{ + struct netns_pfkey *net_pfkey = net_generic(c->net, pfkey_net_id); + struct sock *sk; + bool is_alive = false; + + rcu_read_lock(); + sk_for_each_rcu(sk, &net_pfkey->table) { + if (pfkey_sk(sk)->registered) { + is_alive = true; + break; + } + } + rcu_read_unlock(); + + return is_alive; +} + static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *xp) { struct sk_buff *skb; @@ -3785,6 +3821,7 @@ static struct xfrm_mgr pfkeyv2_mgr = .new_mapping = pfkey_send_new_mapping, .notify_policy = pfkey_send_policy_notify, .migrate = pfkey_send_migrate, + .is_alive = pfkey_is_alive, }; static int __net_init pfkey_net_init(struct net *net) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index c83827e7c324..47f7a5490555 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1130,7 +1130,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->local_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped) + if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped) error = inet6_csk_xmit(skb, NULL); else #endif @@ -1150,23 +1150,6 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, return 0; } -/* Automatically called when the skb is freed. - */ -static void l2tp_sock_wfree(struct sk_buff *skb) -{ - sock_put(skb->sk); -} - -/* For data skbs that we transmit, we associate with the tunnel socket - * but don't do accounting. - */ -static inline void l2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk) -{ - sock_hold(sk); - skb->sk = sk; - skb->destructor = l2tp_sock_wfree; -} - #if IS_ENABLED(CONFIG_IPV6) static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb, int udp_len) @@ -1220,7 +1203,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len return NET_XMIT_DROP; } - skb_orphan(skb); /* Setup L2TP header */ session->build_header(session, __skb_push(skb, hdr_len)); @@ -1286,8 +1268,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len break; } - l2tp_skb_set_owner_w(skb, sk); - l2tp_xmit_core(session, skb, fl, data_len); out_unlock: bh_unlock_sock(sk); @@ -1808,8 +1788,6 @@ void l2tp_session_free(struct l2tp_session *session) } kfree(session); - - return; } EXPORT_SYMBOL_GPL(l2tp_session_free); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 5990919356a5..d276e2d4a589 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -456,13 +456,11 @@ static void pppol2tp_session_close(struct l2tp_session *session) BUG_ON(session->magic != L2TP_SESSION_MAGIC); - if (sock) { inet_shutdown(sock, 2); /* Don't let the session go away before our socket does */ l2tp_session_inc_refcount(session); } - return; } /* Really kill the session socket. (Called from sock_put() if @@ -476,7 +474,6 @@ static void pppol2tp_session_destruct(struct sock *sk) BUG_ON(session->magic != L2TP_SESSION_MAGIC); l2tp_session_dec_refcount(session); } - return; } /* Called when the PPPoX socket (session) is closed. diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 13b7683de5a4..ce9633a3cfb0 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -107,7 +107,7 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata, mgmt->u.action.u.addba_req.start_seq_num = cpu_to_le16(start_seq_num << 4); - ieee80211_tx_skb_tid(sdata, skb, tid); + ieee80211_tx_skb(sdata, skb); } void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 453e974287d1..aaa59d719592 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -451,11 +451,11 @@ void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) rinfo->flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH; if (sta->last_rx_rate_flag & RX_FLAG_SHORT_GI) rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; - if (sta->last_rx_rate_flag & RX_FLAG_80MHZ) + if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_80MHZ) rinfo->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH; - if (sta->last_rx_rate_flag & RX_FLAG_80P80MHZ) + if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_80P80MHZ) rinfo->flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH; - if (sta->last_rx_rate_flag & RX_FLAG_160MHZ) + if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_160MHZ) rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH; } @@ -970,9 +970,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, /* TODO: make hostapd tell us what it wants */ sdata->smps_mode = IEEE80211_SMPS_OFF; sdata->needed_rx_chains = sdata->local->rx_chains; - sdata->radar_required = params->radar_required; mutex_lock(&local->mtx); + sdata->radar_required = params->radar_required; err = ieee80211_vif_use_channel(sdata, ¶ms->chandef, IEEE80211_CHANCTX_SHARED); mutex_unlock(&local->mtx); @@ -1056,6 +1056,7 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, int err; sdata = IEEE80211_DEV_TO_SUB_IF(dev); + sdata_assert_lock(sdata); /* don't allow changing the beacon while CSA is in place - offset * of channel switch counter may change @@ -1083,6 +1084,8 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) struct probe_resp *old_probe_resp; struct cfg80211_chan_def chandef; + sdata_assert_lock(sdata); + old_beacon = sdata_dereference(sdata->u.ap.beacon, sdata); if (!old_beacon) return -ENOENT; @@ -1343,6 +1346,15 @@ static int sta_apply_parameters(struct ieee80211_local *local, ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, params->vht_capa, sta); + if (params->opmode_notif_used) { + /* returned value is only needed for rc update, but the + * rc isn't initialized here yet, so ignore it + */ + __ieee80211_vht_handle_opmode(sdata, sta, + params->opmode_notif, + band, false); + } + if (ieee80211_vif_is_mesh(&sdata->vif)) { #ifdef CONFIG_MAC80211_MESH u32 changed = 0; @@ -2630,6 +2642,18 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, if (!roc) return -ENOMEM; + /* + * If the duration is zero, then the driver + * wouldn't actually do anything. Set it to + * 10 for now. + * + * TODO: cancel the off-channel operation + * when we get the SKB's TX status and + * the wait time was zero before. + */ + if (!duration) + duration = 10; + roc->chan = channel; roc->duration = duration; roc->req_duration = duration; @@ -2671,18 +2695,6 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, /* otherwise actually kick it off here (for error handling) */ - /* - * If the duration is zero, then the driver - * wouldn't actually do anything. Set it to - * 10 for now. - * - * TODO: cancel the off-channel operation - * when we get the SKB's TX status and - * the wait time was zero before. - */ - if (!duration) - duration = 10; - ret = drv_remain_on_channel(local, sdata, channel, duration, type); if (ret) { kfree(roc); @@ -2902,11 +2914,11 @@ static int ieee80211_cancel_remain_on_channel(struct wiphy *wiphy, static int ieee80211_start_radar_detection(struct wiphy *wiphy, struct net_device *dev, - struct cfg80211_chan_def *chandef) + struct cfg80211_chan_def *chandef, + u32 cac_time_ms) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; - unsigned long timeout; int err; mutex_lock(&local->mtx); @@ -2925,9 +2937,9 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy, if (err) goto out_unlock; - timeout = msecs_to_jiffies(IEEE80211_DFS_MIN_CAC_TIME_MS); ieee80211_queue_delayed_work(&sdata->local->hw, - &sdata->dfs_cac_timer_work, timeout); + &sdata->dfs_cac_timer_work, + msecs_to_jiffies(cac_time_ms)); out_unlock: mutex_unlock(&local->mtx); @@ -2990,136 +3002,135 @@ cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) return new_beacon; } -void ieee80211_csa_finalize_work(struct work_struct *work) +void ieee80211_csa_finish(struct ieee80211_vif *vif) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + ieee80211_queue_work(&sdata->local->hw, + &sdata->csa_finalize_work); +} +EXPORT_SYMBOL(ieee80211_csa_finish); + +static void ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) { - struct ieee80211_sub_if_data *sdata = - container_of(work, struct ieee80211_sub_if_data, - csa_finalize_work); struct ieee80211_local *local = sdata->local; int err, changed = 0; - sdata_lock(sdata); - /* AP might have been stopped while waiting for the lock. */ - if (!sdata->vif.csa_active) - goto unlock; - - if (!ieee80211_sdata_running(sdata)) - goto unlock; + sdata_assert_lock(sdata); - sdata->radar_required = sdata->csa_radar_required; mutex_lock(&local->mtx); + sdata->radar_required = sdata->csa_radar_required; err = ieee80211_vif_change_channel(sdata, &changed); mutex_unlock(&local->mtx); if (WARN_ON(err < 0)) - goto unlock; + return; if (!local->use_chanctx) { local->_oper_chandef = sdata->csa_chandef; ieee80211_hw_config(local, 0); } - ieee80211_bss_info_change_notify(sdata, changed); - sdata->vif.csa_active = false; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: err = ieee80211_assign_beacon(sdata, sdata->u.ap.next_beacon); - if (err < 0) - goto unlock; - - changed |= err; kfree(sdata->u.ap.next_beacon); sdata->u.ap.next_beacon = NULL; - ieee80211_bss_info_change_notify(sdata, err); + if (err < 0) + return; + changed |= err; break; case NL80211_IFTYPE_ADHOC: - ieee80211_ibss_finish_csa(sdata); + err = ieee80211_ibss_finish_csa(sdata); + if (err < 0) + return; + changed |= err; break; #ifdef CONFIG_MAC80211_MESH case NL80211_IFTYPE_MESH_POINT: err = ieee80211_mesh_finish_csa(sdata); if (err < 0) - goto unlock; + return; + changed |= err; break; #endif default: WARN_ON(1); - goto unlock; + return; } + ieee80211_bss_info_change_notify(sdata, changed); + ieee80211_wake_queues_by_reason(&sdata->local->hw, IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA); cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef); - -unlock: - sdata_unlock(sdata); } -int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, - struct cfg80211_csa_settings *params) +void ieee80211_csa_finalize_work(struct work_struct *work) { - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = sdata->local; - struct ieee80211_chanctx_conf *chanctx_conf; - struct ieee80211_chanctx *chanctx; - struct ieee80211_if_mesh __maybe_unused *ifmsh; - int err, num_chanctx; - - lockdep_assert_held(&sdata->wdev.mtx); - - if (!list_empty(&local->roc_list) || local->scanning) - return -EBUSY; + struct ieee80211_sub_if_data *sdata = + container_of(work, struct ieee80211_sub_if_data, + csa_finalize_work); - if (sdata->wdev.cac_started) - return -EBUSY; + sdata_lock(sdata); + /* AP might have been stopped while waiting for the lock. */ + if (!sdata->vif.csa_active) + goto unlock; - if (cfg80211_chandef_identical(¶ms->chandef, - &sdata->vif.bss_conf.chandef)) - return -EINVAL; + if (!ieee80211_sdata_running(sdata)) + goto unlock; - rcu_read_lock(); - chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); - if (!chanctx_conf) { - rcu_read_unlock(); - return -EBUSY; - } + ieee80211_csa_finalize(sdata); - /* don't handle for multi-VIF cases */ - chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); - if (chanctx->refcount > 1) { - rcu_read_unlock(); - return -EBUSY; - } - num_chanctx = 0; - list_for_each_entry_rcu(chanctx, &local->chanctx_list, list) - num_chanctx++; - rcu_read_unlock(); - - if (num_chanctx > 1) - return -EBUSY; +unlock: + sdata_unlock(sdata); +} - /* don't allow another channel switch if one is already active. */ - if (sdata->vif.csa_active) - return -EBUSY; +static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, + struct cfg80211_csa_settings *params, + u32 *changed) +{ + int err; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: - sdata->csa_counter_offset_beacon = - params->counter_offset_beacon; - sdata->csa_counter_offset_presp = params->counter_offset_presp; sdata->u.ap.next_beacon = cfg80211_beacon_dup(¶ms->beacon_after); if (!sdata->u.ap.next_beacon) return -ENOMEM; + /* + * With a count of 0, we don't have to wait for any + * TBTT before switching, so complete the CSA + * immediately. In theory, with a count == 1 we + * should delay the switch until just before the next + * TBTT, but that would complicate things so we switch + * immediately too. If we would delay the switch + * until the next TBTT, we would have to set the probe + * response here. + * + * TODO: A channel switch with count <= 1 without + * sending a CSA action frame is kind of useless, + * because the clients won't know we're changing + * channels. The action frame must be implemented + * either here or in the userspace. + */ + if (params->count <= 1) + break; + + sdata->csa_counter_offset_beacon = + params->counter_offset_beacon; + sdata->csa_counter_offset_presp = params->counter_offset_presp; err = ieee80211_assign_beacon(sdata, ¶ms->beacon_csa); if (err < 0) { kfree(sdata->u.ap.next_beacon); return err; } + *changed |= err; + break; case NL80211_IFTYPE_ADHOC: if (!sdata->vif.bss_conf.ibss_joined) @@ -3147,16 +3158,20 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, params->chandef.chan->band) return -EINVAL; - err = ieee80211_ibss_csa_beacon(sdata, params); - if (err < 0) - return err; + /* see comments in the NL80211_IFTYPE_AP block */ + if (params->count > 1) { + err = ieee80211_ibss_csa_beacon(sdata, params); + if (err < 0) + return err; + *changed |= err; + } + + ieee80211_send_action_csa(sdata, params); + break; #ifdef CONFIG_MAC80211_MESH - case NL80211_IFTYPE_MESH_POINT: - ifmsh = &sdata->u.mesh; - - if (!ifmsh->mesh_id) - return -EINVAL; + case NL80211_IFTYPE_MESH_POINT: { + struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; if (params->chandef.width != sdata->vif.bss_conf.chandef.width) return -EINVAL; @@ -3166,23 +3181,87 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, params->chandef.chan->band) return -EINVAL; - ifmsh->chsw_init = true; - if (!ifmsh->pre_value) - ifmsh->pre_value = 1; - else - ifmsh->pre_value++; + if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_NONE) { + ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_INIT; + if (!ifmsh->pre_value) + ifmsh->pre_value = 1; + else + ifmsh->pre_value++; + } - err = ieee80211_mesh_csa_beacon(sdata, params, true); - if (err < 0) { - ifmsh->chsw_init = false; - return err; + /* see comments in the NL80211_IFTYPE_AP block */ + if (params->count > 1) { + err = ieee80211_mesh_csa_beacon(sdata, params); + if (err < 0) { + ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE; + return err; + } + *changed |= err; } + + if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_INIT) + ieee80211_send_action_csa(sdata, params); + break; + } #endif default: return -EOPNOTSUPP; } + return 0; +} + +int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_csa_settings *params) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + struct ieee80211_chanctx_conf *chanctx_conf; + struct ieee80211_chanctx *chanctx; + int err, num_chanctx, changed = 0; + + sdata_assert_lock(sdata); + + if (!list_empty(&local->roc_list) || local->scanning) + return -EBUSY; + + if (sdata->wdev.cac_started) + return -EBUSY; + + if (cfg80211_chandef_identical(¶ms->chandef, + &sdata->vif.bss_conf.chandef)) + return -EINVAL; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!chanctx_conf) { + rcu_read_unlock(); + return -EBUSY; + } + + /* don't handle for multi-VIF cases */ + chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); + if (chanctx->refcount > 1) { + rcu_read_unlock(); + return -EBUSY; + } + num_chanctx = 0; + list_for_each_entry_rcu(chanctx, &local->chanctx_list, list) + num_chanctx++; + rcu_read_unlock(); + + if (num_chanctx > 1) + return -EBUSY; + + /* don't allow another channel switch if one is already active. */ + if (sdata->vif.csa_active) + return -EBUSY; + + err = ieee80211_set_csa_beacon(sdata, params, &changed); + if (err) + return err; + sdata->csa_radar_required = params->radar_required; if (params->block_tx) @@ -3193,8 +3272,13 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, sdata->csa_chandef = params->chandef; sdata->vif.csa_active = true; - ieee80211_bss_info_change_notify(sdata, err); - drv_channel_switch_beacon(sdata, ¶ms->chandef); + if (changed) { + ieee80211_bss_info_change_notify(sdata, changed); + drv_channel_switch_beacon(sdata, ¶ms->chandef); + } else { + /* if the beacon didn't change, we can finalize immediately */ + ieee80211_csa_finalize(sdata); + } return 0; } @@ -3573,8 +3657,8 @@ ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, u8 *peer, u8 action_code, u8 dialog_token, - u16 status_code, const u8 *extra_ies, - size_t extra_ies_len) + u16 status_code, u32 peer_capability, + const u8 *extra_ies, size_t extra_ies_len) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; @@ -3865,7 +3949,7 @@ static int ieee80211_set_qos_map(struct wiphy *wiphy, return 0; } -struct cfg80211_ops mac80211_config_ops = { +const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, .change_virtual_intf = ieee80211_change_iface, diff --git a/net/mac80211/cfg.h b/net/mac80211/cfg.h index 7d7879f5b00b..2d51f62dc76c 100644 --- a/net/mac80211/cfg.h +++ b/net/mac80211/cfg.h @@ -4,6 +4,6 @@ #ifndef __CFG_H #define __CFG_H -extern struct cfg80211_ops mac80211_config_ops; +extern const struct cfg80211_ops mac80211_config_ops; #endif /* __CFG_H */ diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 0c1ecfdf9a12..bd1fd8ea5105 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -202,6 +202,8 @@ static bool ieee80211_is_radar_required(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; + lockdep_assert_held(&local->mtx); + rcu_read_lock(); list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (sdata->radar_required) { diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index ebf80f3abd83..40a648938985 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -358,6 +358,18 @@ static ssize_t ieee80211_if_parse_tkip_mic_test( } IEEE80211_IF_FILE_W(tkip_mic_test); +static ssize_t ieee80211_if_parse_beacon_loss( + struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) +{ + if (!ieee80211_sdata_running(sdata) || !sdata->vif.bss_conf.assoc) + return -ENOTCONN; + + ieee80211_beacon_loss(&sdata->vif); + + return buflen; +} +IEEE80211_IF_FILE_W(beacon_loss); + static ssize_t ieee80211_if_fmt_uapsd_queues( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { @@ -569,6 +581,7 @@ static void add_sta_files(struct ieee80211_sub_if_data *sdata) DEBUGFS_ADD(beacon_timeout); DEBUGFS_ADD_MODE(smps, 0600); DEBUGFS_ADD_MODE(tkip_mic_test, 0200); + DEBUGFS_ADD_MODE(beacon_loss, 0200); DEBUGFS_ADD_MODE(uapsd_queues, 0600); DEBUGFS_ADD_MODE(uapsd_max_sp_len, 0600); } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 80194b557a0c..2ecb4deddb5d 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -195,7 +195,7 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, static ssize_t sta_agg_status_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { - char _buf[12], *buf = _buf; + char _buf[12] = {}, *buf = _buf; struct sta_info *sta = file->private_data; bool start, tx; unsigned long tid; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index ef8b385eff04..fc689f5d971e 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -354,16 +354,20 @@ drv_sched_scan_start(struct ieee80211_local *local, return ret; } -static inline void drv_sched_scan_stop(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) +static inline int drv_sched_scan_stop(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) { + int ret; + might_sleep(); check_sdata_in_driver(sdata); trace_drv_sched_scan_stop(local, sdata); - local->ops->sched_scan_stop(&local->hw, &sdata->vif); - trace_drv_return_void(local); + ret = local->ops->sched_scan_stop(&local->hw, &sdata->vif); + trace_drv_return_int(local, ret); + + return ret; } static inline void drv_sw_scan_start(struct ieee80211_local *local) diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 70dd013de836..c150b68436d7 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -375,7 +375,7 @@ void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata, mgmt->u.action.u.delba.params = cpu_to_le16(params); mgmt->u.action.u.delba.reason_code = cpu_to_le16(reason_code); - ieee80211_tx_skb_tid(sdata, skb, tid); + ieee80211_tx_skb(sdata, skb); } void ieee80211_process_delba(struct ieee80211_sub_if_data *sdata, @@ -482,8 +482,6 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, return; if (vif->type == NL80211_IFTYPE_STATION) { - if (WARN_ON(smps_mode == IEEE80211_SMPS_OFF)) - smps_mode = IEEE80211_SMPS_AUTOMATIC; if (sdata->u.mgd.driver_smps_mode == smps_mode) return; sdata->u.mgd.driver_smps_mode = smps_mode; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 2796a198728f..06d28787945b 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -220,7 +220,6 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct ieee80211_local *local = sdata->local; - struct ieee80211_supported_band *sband; struct ieee80211_mgmt *mgmt; struct cfg80211_bss *bss; u32 bss_change; @@ -284,6 +283,11 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy, &chandef); + if (err < 0) { + sdata_info(sdata, + "Failed to join IBSS, invalid chandef\n"); + return; + } if (err > 0) { if (!ifibss->userspace_handles_dfs) { sdata_info(sdata, @@ -294,7 +298,6 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, } mutex_lock(&local->mtx); - ieee80211_vif_release_channel(sdata); if (ieee80211_vif_use_channel(sdata, &chandef, ifibss->fixed_channel ? IEEE80211_CHANCTX_SHARED : @@ -303,12 +306,11 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, mutex_unlock(&local->mtx); return; } + sdata->radar_required = radar_required; mutex_unlock(&local->mtx); memcpy(ifibss->bssid, bssid, ETH_ALEN); - sband = local->hw.wiphy->bands[chan->band]; - presp = ieee80211_ibss_build_presp(sdata, beacon_int, basic_rates, capability, tsf, &chandef, &have_higher_than_11mbit, NULL); @@ -318,7 +320,6 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, rcu_assign_pointer(ifibss->presp, presp); mgmt = (void *)presp->head; - sdata->radar_required = radar_required; sdata->vif.bss_conf.enable_beacon = true; sdata->vif.bss_conf.beacon_int = beacon_int; sdata->vif.bss_conf.basic_rates = basic_rates; @@ -386,7 +387,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, presp->head_len, 0, GFP_KERNEL); cfg80211_put_bss(local->hw.wiphy, bss); netif_carrier_on(sdata->dev); - cfg80211_ibss_joined(sdata->dev, ifibss->bssid, GFP_KERNEL); + cfg80211_ibss_joined(sdata->dev, ifibss->bssid, chan, GFP_KERNEL); } static void ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, @@ -521,12 +522,6 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata, if (old_presp) kfree_rcu(old_presp, rcu_head); - /* it might not send the beacon for a while. send an action frame - * immediately to announce the channel switch. - */ - if (csa_settings) - ieee80211_send_action_csa(sdata, csa_settings); - return BSS_CHANGED_BEACON; out: return ret; @@ -536,7 +531,7 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; struct cfg80211_bss *cbss; - int err; + int err, changed = 0; u16 capability; sdata_assert_lock(sdata); @@ -568,10 +563,9 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata) if (err < 0) return err; - if (err) - ieee80211_bss_info_change_notify(sdata, err); + changed |= err; - return 0; + return changed; } void ieee80211_ibss_stop(struct ieee80211_sub_if_data *sdata) @@ -799,6 +793,8 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, int err; u32 sta_flags; + sdata_assert_lock(sdata); + sta_flags = IEEE80211_STA_DISABLE_VHT; switch (ifibss->chandef.width) { case NL80211_CHAN_WIDTH_5: @@ -995,7 +991,6 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems) { struct ieee80211_local *local = sdata->local; - int freq; struct cfg80211_bss *cbss; struct ieee80211_bss *bss; struct sta_info *sta; @@ -1007,15 +1002,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band]; bool rates_updated = false; - if (elems->ds_params) - freq = ieee80211_channel_to_frequency(elems->ds_params[0], - band); - else - freq = rx_status->freq; - - channel = ieee80211_get_channel(local->hw.wiphy, freq); - - if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) + channel = ieee80211_get_channel(local->hw.wiphy, rx_status->freq); + if (!channel) return; if (sdata->vif.type == NL80211_IFTYPE_ADHOC && @@ -1468,6 +1456,11 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, memcpy(((struct ieee80211_mgmt *) skb->data)->da, mgmt->sa, ETH_ALEN); ibss_dbg(sdata, "Sending ProbeResp to %pM\n", mgmt->sa); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; + + /* avoid excessive retries for probe request to wildcard SSIDs */ + if (pos[1] == 0) + IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_CTL_NO_ACK; + ieee80211_tx_skb(sdata, skb); } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 5e44e3179e02..222c28b75315 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -616,7 +616,11 @@ struct ieee80211_if_mesh { struct ps_data ps; /* Channel Switching Support */ struct mesh_csa_settings __rcu *csa; - bool chsw_init; + enum { + IEEE80211_MESH_CSA_ROLE_NONE, + IEEE80211_MESH_CSA_ROLE_INIT, + IEEE80211_MESH_CSA_ROLE_REPEATER, + } csa_role; u8 chsw_ttl; u16 pre_value; @@ -1238,6 +1242,8 @@ struct ieee80211_local { struct ieee80211_sub_if_data __rcu *p2p_sdata; + struct napi_struct *napi; + /* virtual monitor interface */ struct ieee80211_sub_if_data __rcu *monitor_sdata; struct cfg80211_chan_def monitor_chandef; @@ -1385,6 +1391,7 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata); void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata); void ieee80211_mgd_conn_tx_status(struct ieee80211_sub_if_data *sdata, __le16 fc, bool acked); +void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata); /* IBSS code */ @@ -1408,8 +1415,7 @@ void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata, - struct cfg80211_csa_settings *csa_settings, - bool csa_action); + struct cfg80211_csa_settings *csa_settings); int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata); /* scan/BSS handling */ @@ -1553,6 +1559,9 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, struct sta_info *sta); enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta); void ieee80211_sta_set_rx_nss(struct sta_info *sta); +u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, u8 opmode, + enum ieee80211_band band, bool nss_only); void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, u8 opmode, enum ieee80211_band band, bool nss_only); @@ -1605,7 +1614,7 @@ static inline int __ieee80211_resume(struct ieee80211_hw *hw) } /* utility functions/constants */ -extern void *mac80211_wiphy_privid; /* for wiphy privid */ +extern const void *const mac80211_wiphy_privid; /* for wiphy privid */ u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, enum nl80211_iftype type); int ieee80211_frame_duration(enum ieee80211_band band, size_t len, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index ce1c44370610..b8d331e7d883 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -101,9 +101,8 @@ static u32 __ieee80211_idle_on(struct ieee80211_local *local) static u32 __ieee80211_recalc_idle(struct ieee80211_local *local, bool force_active) { - bool working = false, scanning, active; + bool working, scanning, active; unsigned int led_trig_start = 0, led_trig_stop = 0; - struct ieee80211_roc_work *roc; lockdep_assert_held(&local->mtx); @@ -111,12 +110,8 @@ static u32 __ieee80211_recalc_idle(struct ieee80211_local *local, !list_empty(&local->chanctx_list) || local->monitors; - if (!local->ops->remain_on_channel) { - list_for_each_entry(roc, &local->roc_list, list) { - working = true; - break; - } - } + working = !local->ops->remain_on_channel && + !list_empty(&local->roc_list); scanning = test_bit(SCAN_SW_SCANNING, &local->scanning) || test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning); @@ -833,7 +828,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, cancel_work_sync(&local->dynamic_ps_enable_work); cancel_work_sync(&sdata->recalc_smps); + sdata_lock(sdata); sdata->vif.csa_active = false; + sdata_unlock(sdata); cancel_work_sync(&sdata->csa_finalize_work); cancel_delayed_work_sync(&sdata->dfs_cac_timer_work); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index d767cfb9b45f..b055f6a55c68 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -893,10 +893,15 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) /* mac80211 supports control port protocol changing */ local->hw.wiphy->flags |= WIPHY_FLAG_CONTROL_PORT_PROTOCOL; - if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM) + if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM) { local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM; - else if (local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC) + } else if (local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC) { local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC; + if (hw->max_signal <= 0) { + result = -EINVAL; + goto fail_wiphy_register; + } + } WARN((local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD) && (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK), @@ -1071,6 +1076,18 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } EXPORT_SYMBOL(ieee80211_register_hw); +void ieee80211_napi_add(struct ieee80211_hw *hw, struct napi_struct *napi, + struct net_device *napi_dev, + int (*poll)(struct napi_struct *, int), + int weight) +{ + struct ieee80211_local *local = hw_to_local(hw); + + netif_napi_add(napi_dev, napi, poll, weight); + local->napi = napi; +} +EXPORT_SYMBOL_GPL(ieee80211_napi_add); + void ieee80211_unregister_hw(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 5b919cab1de0..f70e9cd10552 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -688,7 +688,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) *pos++ = csa->settings.count; *pos++ = WLAN_EID_CHAN_SWITCH_PARAM; *pos++ = 6; - if (ifmsh->chsw_init) { + if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_INIT) { *pos++ = ifmsh->mshcfg.dot11MeshTTL; *pos |= WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR; } else { @@ -859,18 +859,12 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, { struct cfg80211_csa_settings params; struct ieee80211_csa_ie csa_ie; - struct ieee80211_chanctx_conf *chanctx_conf; - struct ieee80211_chanctx *chanctx; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; enum ieee80211_band band = ieee80211_get_sdata_band(sdata); - int err, num_chanctx; + int err; u32 sta_flags; - if (sdata->vif.csa_active) - return true; - - if (!ifmsh->mesh_id) - return false; + sdata_assert_lock(sdata); sta_flags = IEEE80211_STA_DISABLE_VHT; switch (sdata->vif.bss_conf.chandef.width) { @@ -896,10 +890,6 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, params.chandef = csa_ie.chandef; params.count = csa_ie.count; - if (sdata->vif.bss_conf.chandef.chan->band != - params.chandef.chan->band) - return false; - if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, ¶ms.chandef, IEEE80211_CHAN_DISABLED)) { sdata_info(sdata, @@ -922,24 +912,12 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, return false; } - rcu_read_lock(); - chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); - if (!chanctx_conf) - goto failed_chswitch; - - /* don't handle for multi-VIF cases */ - chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); - if (chanctx->refcount > 1) - goto failed_chswitch; - - num_chanctx = 0; - list_for_each_entry_rcu(chanctx, &sdata->local->chanctx_list, list) - num_chanctx++; - - if (num_chanctx > 1) - goto failed_chswitch; - - rcu_read_unlock(); + if (cfg80211_chandef_identical(¶ms.chandef, + &sdata->vif.bss_conf.chandef)) { + mcsa_dbg(sdata, + "received csa with an identical chandef, ignoring\n"); + return true; + } mcsa_dbg(sdata, "received channel switch announcement to go to channel %d MHz\n", @@ -953,30 +931,16 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, ifmsh->pre_value = csa_ie.pre_value; } - if (ifmsh->chsw_ttl < ifmsh->mshcfg.dot11MeshTTL) { - if (ieee80211_mesh_csa_beacon(sdata, ¶ms, false) < 0) - return false; - } else { + if (ifmsh->chsw_ttl >= ifmsh->mshcfg.dot11MeshTTL) return false; - } - sdata->csa_radar_required = params.radar_required; + ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_REPEATER; - if (params.block_tx) - ieee80211_stop_queues_by_reason(&sdata->local->hw, - IEEE80211_MAX_QUEUE_MAP, - IEEE80211_QUEUE_STOP_REASON_CSA); - - sdata->csa_chandef = params.chandef; - sdata->vif.csa_active = true; - - ieee80211_bss_info_change_notify(sdata, err); - drv_channel_switch_beacon(sdata, ¶ms.chandef); + if (ieee80211_channel_switch(sdata->local->hw.wiphy, sdata->dev, + ¶ms) < 0) + return false; return true; -failed_chswitch: - rcu_read_unlock(); - return false; } static void @@ -1086,7 +1050,8 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, ifmsh->sync_ops->rx_bcn_presp(sdata, stype, mgmt, &elems, rx_status); - if (!ifmsh->chsw_init) + if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT && + !sdata->vif.csa_active) ieee80211_mesh_process_chnswitch(sdata, &elems, true); } @@ -1095,29 +1060,30 @@ int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct mesh_csa_settings *tmp_csa_settings; int ret = 0; + int changed = 0; /* Reset the TTL value and Initiator flag */ - ifmsh->chsw_init = false; + ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE; ifmsh->chsw_ttl = 0; /* Remove the CSA and MCSP elements from the beacon */ tmp_csa_settings = rcu_dereference(ifmsh->csa); rcu_assign_pointer(ifmsh->csa, NULL); - kfree_rcu(tmp_csa_settings, rcu_head); + if (tmp_csa_settings) + kfree_rcu(tmp_csa_settings, rcu_head); ret = ieee80211_mesh_rebuild_beacon(sdata); if (ret) return -EINVAL; - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON); + changed |= BSS_CHANGED_BEACON; mcsa_dbg(sdata, "complete switching to center freq %d MHz", sdata->vif.bss_conf.chandef.chan->center_freq); - return 0; + return changed; } int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata, - struct cfg80211_csa_settings *csa_settings, - bool csa_action) + struct cfg80211_csa_settings *csa_settings) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct mesh_csa_settings *tmp_csa_settings; @@ -1141,12 +1107,7 @@ int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata, return ret; } - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON); - - if (csa_action) - ieee80211_send_action_csa(sdata, csa_settings); - - return 0; + return BSS_CHANGED_BEACON; } static int mesh_fwd_csa_frame(struct ieee80211_sub_if_data *sdata, @@ -1210,7 +1171,8 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata, ifmsh->pre_value = pre_value; - if (!ieee80211_mesh_process_chnswitch(sdata, &elems, false)) { + if (!sdata->vif.csa_active && + !ieee80211_mesh_process_chnswitch(sdata, &elems, false)) { mcsa_dbg(sdata, "Failed to process CSA action frame"); return; } @@ -1257,7 +1219,7 @@ void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, sdata_lock(sdata); /* mesh already went down */ - if (!sdata->wdev.mesh_id_len) + if (!sdata->u.mesh.mesh_id_len) goto out; rx_status = IEEE80211_SKB_RXCB(skb); @@ -1310,7 +1272,7 @@ void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata) sdata_lock(sdata); /* mesh already went down */ - if (!sdata->wdev.mesh_id_len) + if (!sdata->u.mesh.mesh_id_len) goto out; if (ifmsh->preq_queue_len && @@ -1365,7 +1327,7 @@ void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) mesh_rmc_init(sdata); ifmsh->last_preq = jiffies; ifmsh->next_perr = jiffies; - ifmsh->chsw_init = false; + ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE; /* Allocate all mesh structures when creating the first mesh interface. */ if (!mesh_allocated) ieee80211s_init(); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 245dce969b31..dee50aefd6e8 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -131,13 +131,13 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata) if (unlikely(!sdata->u.mgd.associated)) return; + ifmgd->probe_send_count = 0; + if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR) return; mod_timer(&sdata->u.mgd.conn_mon_timer, round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); - - ifmgd->probe_send_count = 0; } static int ecw2cw(int ecw) @@ -531,6 +531,7 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, u8 *pos; u32 cap; struct ieee80211_sta_vht_cap vht_cap; + u32 mask, ap_bf_sts, our_bf_sts; BUILD_BUG_ON(sizeof(vht_cap) != sizeof(sband->vht_cap)); @@ -558,6 +559,16 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, cpu_to_le32(IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE))) cap &= ~IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE; + mask = IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK; + + ap_bf_sts = le32_to_cpu(ap_vht_cap->vht_cap_info) & mask; + our_bf_sts = cap & mask; + + if (ap_bf_sts < our_bf_sts) { + cap &= ~mask; + cap |= ap_bf_sts; + } + /* reserve and fill IE */ pos = skb_put(skb, sizeof(struct ieee80211_vht_cap) + 2); ieee80211_ie_build_vht_cap(pos, &vht_cap, cap); @@ -768,6 +779,34 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) ieee80211_add_ht_ie(sdata, skb, assoc_data->ap_ht_param, sband, chan, sdata->smps_mode); + /* if present, add any custom IEs that go before VHT */ + if (assoc_data->ie_len) { + static const u8 before_vht[] = { + WLAN_EID_SSID, + WLAN_EID_SUPP_RATES, + WLAN_EID_EXT_SUPP_RATES, + WLAN_EID_PWR_CAPABILITY, + WLAN_EID_SUPPORTED_CHANNELS, + WLAN_EID_RSN, + WLAN_EID_QOS_CAPA, + WLAN_EID_RRM_ENABLED_CAPABILITIES, + WLAN_EID_MOBILITY_DOMAIN, + WLAN_EID_SUPPORTED_REGULATORY_CLASSES, + WLAN_EID_HT_CAPABILITY, + WLAN_EID_BSS_COEX_2040, + WLAN_EID_EXT_CAPABILITY, + WLAN_EID_QOS_TRAFFIC_CAPA, + WLAN_EID_TIM_BCAST_REQ, + WLAN_EID_INTERWORKING, + }; + noffset = ieee80211_ie_split(assoc_data->ie, assoc_data->ie_len, + before_vht, ARRAY_SIZE(before_vht), + offset); + pos = skb_put(skb, noffset - offset); + memcpy(pos, assoc_data->ie + offset, noffset - offset); + offset = noffset; + } + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) ieee80211_add_vht_ie(sdata, skb, sband, &assoc_data->ap_vht_cap); @@ -1024,7 +1063,6 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, } ifmgd->flags |= IEEE80211_STA_CSA_RECEIVED; - sdata->vif.csa_active = true; mutex_lock(&local->chanctx_mtx); if (local->use_chanctx) { @@ -1062,6 +1100,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, mutex_unlock(&local->chanctx_mtx); sdata->csa_chandef = csa_ie.chandef; + sdata->vif.csa_active = true; if (csa_ie.mode) ieee80211_stop_queues_by_reason(&local->hw, @@ -2233,6 +2272,62 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, /* ignore frame -- wait for timeout */ } +#define case_WLAN(type) \ + case WLAN_REASON_##type: return #type + +static const char *ieee80211_get_reason_code_string(u16 reason_code) +{ + switch (reason_code) { + case_WLAN(UNSPECIFIED); + case_WLAN(PREV_AUTH_NOT_VALID); + case_WLAN(DEAUTH_LEAVING); + case_WLAN(DISASSOC_DUE_TO_INACTIVITY); + case_WLAN(DISASSOC_AP_BUSY); + case_WLAN(CLASS2_FRAME_FROM_NONAUTH_STA); + case_WLAN(CLASS3_FRAME_FROM_NONASSOC_STA); + case_WLAN(DISASSOC_STA_HAS_LEFT); + case_WLAN(STA_REQ_ASSOC_WITHOUT_AUTH); + case_WLAN(DISASSOC_BAD_POWER); + case_WLAN(DISASSOC_BAD_SUPP_CHAN); + case_WLAN(INVALID_IE); + case_WLAN(MIC_FAILURE); + case_WLAN(4WAY_HANDSHAKE_TIMEOUT); + case_WLAN(GROUP_KEY_HANDSHAKE_TIMEOUT); + case_WLAN(IE_DIFFERENT); + case_WLAN(INVALID_GROUP_CIPHER); + case_WLAN(INVALID_PAIRWISE_CIPHER); + case_WLAN(INVALID_AKMP); + case_WLAN(UNSUPP_RSN_VERSION); + case_WLAN(INVALID_RSN_IE_CAP); + case_WLAN(IEEE8021X_FAILED); + case_WLAN(CIPHER_SUITE_REJECTED); + case_WLAN(DISASSOC_UNSPECIFIED_QOS); + case_WLAN(DISASSOC_QAP_NO_BANDWIDTH); + case_WLAN(DISASSOC_LOW_ACK); + case_WLAN(DISASSOC_QAP_EXCEED_TXOP); + case_WLAN(QSTA_LEAVE_QBSS); + case_WLAN(QSTA_NOT_USE); + case_WLAN(QSTA_REQUIRE_SETUP); + case_WLAN(QSTA_TIMEOUT); + case_WLAN(QSTA_CIPHER_NOT_SUPP); + case_WLAN(MESH_PEER_CANCELED); + case_WLAN(MESH_MAX_PEERS); + case_WLAN(MESH_CONFIG); + case_WLAN(MESH_CLOSE); + case_WLAN(MESH_MAX_RETRIES); + case_WLAN(MESH_CONFIRM_TIMEOUT); + case_WLAN(MESH_INVALID_GTK); + case_WLAN(MESH_INCONSISTENT_PARAM); + case_WLAN(MESH_INVALID_SECURITY); + case_WLAN(MESH_PATH_ERROR); + case_WLAN(MESH_PATH_NOFORWARD); + case_WLAN(MESH_PATH_DEST_UNREACHABLE); + case_WLAN(MAC_EXISTS_IN_MBSS); + case_WLAN(MESH_CHAN_REGULATORY); + case_WLAN(MESH_CHAN); + default: return "<unknown>"; + } +} static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len) @@ -2254,8 +2349,8 @@ static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, reason_code = le16_to_cpu(mgmt->u.deauth.reason_code); - sdata_info(sdata, "deauthenticated from %pM (Reason: %u)\n", - bssid, reason_code); + sdata_info(sdata, "deauthenticated from %pM (Reason: %u=%s)\n", + bssid, reason_code, ieee80211_get_reason_code_string(reason_code)); ieee80211_set_disassoc(sdata, 0, 0, false, NULL); @@ -2688,28 +2783,20 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems) { struct ieee80211_local *local = sdata->local; - int freq; struct ieee80211_bss *bss; struct ieee80211_channel *channel; sdata_assert_lock(sdata); - if (elems->ds_params) - freq = ieee80211_channel_to_frequency(elems->ds_params[0], - rx_status->band); - else - freq = rx_status->freq; - - channel = ieee80211_get_channel(local->hw.wiphy, freq); - - if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) + channel = ieee80211_get_channel(local->hw.wiphy, rx_status->freq); + if (!channel) return; bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems, channel); if (bss) { - ieee80211_rx_bss_put(local, bss); sdata->vif.bss_conf.beacon_rate = bss->beacon_rate; + ieee80211_rx_bss_put(local, bss); } } @@ -3504,6 +3591,32 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) } #ifdef CONFIG_PM +void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + + sdata_lock(sdata); + + if (ifmgd->auth_data) { + /* + * If we are trying to authenticate while suspending, cfg80211 + * won't know and won't actually abort those attempts, thus we + * need to do that ourselves. + */ + ieee80211_send_deauth_disassoc(sdata, + ifmgd->auth_data->bss->bssid, + IEEE80211_STYPE_DEAUTH, + WLAN_REASON_DEAUTH_LEAVING, + false, frame_buf); + ieee80211_destroy_auth_data(sdata, false); + cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, + IEEE80211_DEAUTH_FRAME_LEN); + } + + sdata_unlock(sdata); +} + void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -4322,37 +4435,41 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; bool tx = !req->local_state_change; - bool report_frame = false; - sdata_info(sdata, - "deauthenticating from %pM by local choice (reason=%d)\n", - req->bssid, req->reason_code); + if (ifmgd->auth_data && + ether_addr_equal(ifmgd->auth_data->bss->bssid, req->bssid)) { + sdata_info(sdata, + "aborting authentication with %pM by local choice (Reason: %u=%s)\n", + req->bssid, req->reason_code, + ieee80211_get_reason_code_string(req->reason_code)); - if (ifmgd->auth_data) { drv_mgd_prepare_tx(sdata->local, sdata); ieee80211_send_deauth_disassoc(sdata, req->bssid, IEEE80211_STYPE_DEAUTH, req->reason_code, tx, frame_buf); ieee80211_destroy_auth_data(sdata, false); + cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, + IEEE80211_DEAUTH_FRAME_LEN); - report_frame = true; - goto out; + return 0; } if (ifmgd->associated && ether_addr_equal(ifmgd->associated->bssid, req->bssid)) { + sdata_info(sdata, + "deauthenticating from %pM by local choice (Reason: %u=%s)\n", + req->bssid, req->reason_code, + ieee80211_get_reason_code_string(req->reason_code)); + ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, req->reason_code, tx, frame_buf); - report_frame = true; - } - - out: - if (report_frame) cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf, IEEE80211_DEAUTH_FRAME_LEN); + return 0; + } - return 0; + return -ENOTCONN; } int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, @@ -4372,8 +4489,8 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, return -ENOLINK; sdata_info(sdata, - "disassociating from %pM by local choice (reason=%d)\n", - req->bss->bssid, req->reason_code); + "disassociating from %pM by local choice (Reason: %u=%s)\n", + req->bss->bssid, req->reason_code, ieee80211_get_reason_code_string(req->reason_code)); memcpy(bssid, req->bss->bssid, ETH_ALEN); ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DISASSOC, diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index af64fb8e8add..d478b880a0af 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -100,10 +100,18 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) /* remove all interfaces that were created in the driver */ list_for_each_entry(sdata, &local->interfaces, list) { - if (!ieee80211_sdata_running(sdata) || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - sdata->vif.type == NL80211_IFTYPE_MONITOR) + if (!ieee80211_sdata_running(sdata)) continue; + switch (sdata->vif.type) { + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MONITOR: + continue; + case NL80211_IFTYPE_STATION: + ieee80211_mgd_quiesce(sdata); + break; + default: + break; + } drv_remove_interface(local, sdata); } diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 22b223f13c9f..8fdadfd94ba8 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -10,15 +10,15 @@ #include <linux/kernel.h> #include <linux/rtnetlink.h> -#include <linux/slab.h> #include <linux/module.h> +#include <linux/slab.h> #include "rate.h" #include "ieee80211_i.h" #include "debugfs.h" struct rate_control_alg { struct list_head list; - struct rate_control_ops *ops; + const struct rate_control_ops *ops; }; static LIST_HEAD(rate_ctrl_algs); @@ -29,7 +29,7 @@ module_param(ieee80211_default_rc_algo, charp, 0644); MODULE_PARM_DESC(ieee80211_default_rc_algo, "Default rate control algorithm for mac80211 to use"); -int ieee80211_rate_control_register(struct rate_control_ops *ops) +int ieee80211_rate_control_register(const struct rate_control_ops *ops) { struct rate_control_alg *alg; @@ -60,7 +60,7 @@ int ieee80211_rate_control_register(struct rate_control_ops *ops) } EXPORT_SYMBOL(ieee80211_rate_control_register); -void ieee80211_rate_control_unregister(struct rate_control_ops *ops) +void ieee80211_rate_control_unregister(const struct rate_control_ops *ops) { struct rate_control_alg *alg; @@ -76,32 +76,31 @@ void ieee80211_rate_control_unregister(struct rate_control_ops *ops) } EXPORT_SYMBOL(ieee80211_rate_control_unregister); -static struct rate_control_ops * +static const struct rate_control_ops * ieee80211_try_rate_control_ops_get(const char *name) { struct rate_control_alg *alg; - struct rate_control_ops *ops = NULL; + const struct rate_control_ops *ops = NULL; if (!name) return NULL; mutex_lock(&rate_ctrl_mutex); list_for_each_entry(alg, &rate_ctrl_algs, list) { - if (!strcmp(alg->ops->name, name)) - if (try_module_get(alg->ops->module)) { - ops = alg->ops; - break; - } + if (!strcmp(alg->ops->name, name)) { + ops = alg->ops; + break; + } } mutex_unlock(&rate_ctrl_mutex); return ops; } /* Get the rate control algorithm. */ -static struct rate_control_ops * +static const struct rate_control_ops * ieee80211_rate_control_ops_get(const char *name) { - struct rate_control_ops *ops; + const struct rate_control_ops *ops; const char *alg_name; kparam_block_sysfs_write(ieee80211_default_rc_algo); @@ -111,10 +110,6 @@ ieee80211_rate_control_ops_get(const char *name) alg_name = name; ops = ieee80211_try_rate_control_ops_get(alg_name); - if (!ops) { - request_module("rc80211_%s", alg_name); - ops = ieee80211_try_rate_control_ops_get(alg_name); - } if (!ops && name) /* try default if specific alg requested but not found */ ops = ieee80211_try_rate_control_ops_get(ieee80211_default_rc_algo); @@ -127,11 +122,6 @@ ieee80211_rate_control_ops_get(const char *name) return ops; } -static void ieee80211_rate_control_ops_put(struct rate_control_ops *ops) -{ - module_put(ops->module); -} - #ifdef CONFIG_MAC80211_DEBUGFS static ssize_t rcname_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) @@ -158,11 +148,11 @@ static struct rate_control_ref *rate_control_alloc(const char *name, ref = kmalloc(sizeof(struct rate_control_ref), GFP_KERNEL); if (!ref) - goto fail_ref; + return NULL; ref->local = local; ref->ops = ieee80211_rate_control_ops_get(name); if (!ref->ops) - goto fail_ops; + goto free; #ifdef CONFIG_MAC80211_DEBUGFS debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir); @@ -172,14 +162,11 @@ static struct rate_control_ref *rate_control_alloc(const char *name, ref->priv = ref->ops->alloc(&local->hw, debugfsdir); if (!ref->priv) - goto fail_priv; + goto free; return ref; -fail_priv: - ieee80211_rate_control_ops_put(ref->ops); -fail_ops: +free: kfree(ref); -fail_ref: return NULL; } @@ -192,7 +179,6 @@ static void rate_control_free(struct rate_control_ref *ctrl_ref) ctrl_ref->local->debugfs.rcdir = NULL; #endif - ieee80211_rate_control_ops_put(ctrl_ref->ops); kfree(ctrl_ref); } diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index b95e16c07081..9aa2a1190a86 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -21,7 +21,7 @@ struct rate_control_ref { struct ieee80211_local *local; - struct rate_control_ops *ops; + const struct rate_control_ops *ops; void *priv; }; diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index f3d88b0c054c..26fd94fa0aed 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -657,7 +657,7 @@ minstrel_free(void *priv) kfree(priv); } -struct rate_control_ops mac80211_minstrel = { +const struct rate_control_ops mac80211_minstrel = { .name = "minstrel", .tx_status = minstrel_tx_status, .get_rate = minstrel_get_rate, diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h index f4301f4b2e41..046d1bd598a8 100644 --- a/net/mac80211/rc80211_minstrel.h +++ b/net/mac80211/rc80211_minstrel.h @@ -123,7 +123,7 @@ struct minstrel_debugfs_info { char buf[]; }; -extern struct rate_control_ops mac80211_minstrel; +extern const struct rate_control_ops mac80211_minstrel; void minstrel_add_sta_debugfs(void *priv, void *priv_sta, struct dentry *dir); void minstrel_remove_sta_debugfs(void *priv, void *priv_sta); diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index c1b5b73c5b91..bccaf854a309 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -124,7 +124,7 @@ const struct mcs_group minstrel_mcs_groups[] = { #define MINSTREL_CCK_GROUP (ARRAY_SIZE(minstrel_mcs_groups) - 1) -static u8 sample_table[SAMPLE_COLUMNS][MCS_GROUP_RATES]; +static u8 sample_table[SAMPLE_COLUMNS][MCS_GROUP_RATES] __read_mostly; static void minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi); @@ -1031,7 +1031,7 @@ minstrel_ht_free(void *priv) mac80211_minstrel.free(priv); } -static struct rate_control_ops mac80211_minstrel_ht = { +static const struct rate_control_ops mac80211_minstrel_ht = { .name = "minstrel_ht", .tx_status = minstrel_ht_tx_status, .get_rate = minstrel_ht_get_rate, @@ -1048,8 +1048,7 @@ static struct rate_control_ops mac80211_minstrel_ht = { }; -static void -init_sample_table(void) +static void __init init_sample_table(void) { int col, i, new_idx; u8 rnd[MCS_GROUP_RATES]; diff --git a/net/mac80211/rc80211_pid_algo.c b/net/mac80211/rc80211_pid_algo.c index 958fad07b54c..d0da2a70fe68 100644 --- a/net/mac80211/rc80211_pid_algo.c +++ b/net/mac80211/rc80211_pid_algo.c @@ -452,7 +452,7 @@ static void rate_control_pid_free_sta(void *priv, struct ieee80211_sta *sta, kfree(priv_sta); } -static struct rate_control_ops mac80211_rcpid = { +static const struct rate_control_ops mac80211_rcpid = { .name = "pid", .tx_status = rate_control_pid_tx_status, .get_rate = rate_control_pid_get_rate, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3e57f96c9666..216c45b949e5 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -40,8 +40,6 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local, struct sk_buff *skb) { - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) { if (likely(skb->len > FCS_LEN)) __pskb_trim(skb, skb->len - FCS_LEN); @@ -53,9 +51,6 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local, } } - if (status->vendor_radiotap_len) - __pskb_pull(skb, status->vendor_radiotap_len); - return skb; } @@ -64,14 +59,13 @@ static inline int should_drop_frame(struct sk_buff *skb, int present_fcs_len) struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_hdr *hdr; - hdr = (void *)(skb->data + status->vendor_radiotap_len); + hdr = (void *)(skb->data); if (status->flag & (RX_FLAG_FAILED_FCS_CRC | RX_FLAG_FAILED_PLCP_CRC | RX_FLAG_AMPDU_IS_ZEROLEN)) return 1; - if (unlikely(skb->len < 16 + present_fcs_len + - status->vendor_radiotap_len)) + if (unlikely(skb->len < 16 + present_fcs_len)) return 1; if (ieee80211_is_ctl(hdr->frame_control) && !ieee80211_is_pspoll(hdr->frame_control) && @@ -90,8 +84,6 @@ ieee80211_rx_radiotap_space(struct ieee80211_local *local, len = sizeof(struct ieee80211_radiotap_header) + 8; /* allocate extra bitmaps */ - if (status->vendor_radiotap_len) - len += 4; if (status->chains) len += 4 * hweight8(status->chains); @@ -127,18 +119,6 @@ ieee80211_rx_radiotap_space(struct ieee80211_local *local, len += 2 * hweight8(status->chains); } - if (status->vendor_radiotap_len) { - if (WARN_ON_ONCE(status->vendor_radiotap_align == 0)) - status->vendor_radiotap_align = 1; - /* align standard part of vendor namespace */ - len = ALIGN(len, 2); - /* allocate standard part of vendor namespace */ - len += 6; - /* align vendor-defined part */ - len = ALIGN(len, status->vendor_radiotap_align); - /* vendor-defined part is already in skb */ - } - return len; } @@ -172,7 +152,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, it_present = &rthdr->it_present; /* radiotap header, set always present flags */ - rthdr->it_len = cpu_to_le16(rtap_len + status->vendor_radiotap_len); + rthdr->it_len = cpu_to_le16(rtap_len); it_present_val = BIT(IEEE80211_RADIOTAP_FLAGS) | BIT(IEEE80211_RADIOTAP_CHANNEL) | BIT(IEEE80211_RADIOTAP_RX_FLAGS); @@ -190,14 +170,6 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, BIT(IEEE80211_RADIOTAP_DBM_ANTSIGNAL); } - if (status->vendor_radiotap_len) { - it_present_val |= BIT(IEEE80211_RADIOTAP_VENDOR_NAMESPACE) | - BIT(IEEE80211_RADIOTAP_EXT); - put_unaligned_le32(it_present_val, it_present); - it_present++; - it_present_val = status->vendor_radiotap_bitmap; - } - put_unaligned_le32(it_present_val, it_present); pos = (void *)(it_present + 1); @@ -307,6 +279,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, *pos |= IEEE80211_RADIOTAP_MCS_BW_40; if (status->flag & RX_FLAG_HT_GF) *pos |= IEEE80211_RADIOTAP_MCS_FMT_GF; + if (status->flag & RX_FLAG_LDPC) + *pos |= IEEE80211_RADIOTAP_MCS_FEC_LDPC; stbc = (status->flag & RX_FLAG_STBC_MASK) >> RX_FLAG_STBC_SHIFT; *pos |= stbc << IEEE80211_RADIOTAP_MCS_STBC_SHIFT; pos++; @@ -349,20 +323,25 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT); /* known field - how to handle 80+80? */ - if (status->flag & RX_FLAG_80P80MHZ) + if (status->vht_flag & RX_VHT_FLAG_80P80MHZ) known &= ~IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH; put_unaligned_le16(known, pos); pos += 2; /* flags */ if (status->flag & RX_FLAG_SHORT_GI) *pos |= IEEE80211_RADIOTAP_VHT_FLAG_SGI; + /* in VHT, STBC is binary */ + if (status->flag & RX_FLAG_STBC_MASK) + *pos |= IEEE80211_RADIOTAP_VHT_FLAG_STBC; + if (status->vht_flag & RX_VHT_FLAG_BF) + *pos |= IEEE80211_RADIOTAP_VHT_FLAG_BEAMFORMED; pos++; /* bandwidth */ - if (status->flag & RX_FLAG_80MHZ) + if (status->vht_flag & RX_VHT_FLAG_80MHZ) *pos++ = 4; - else if (status->flag & RX_FLAG_80P80MHZ) + else if (status->vht_flag & RX_VHT_FLAG_80P80MHZ) *pos++ = 0; /* marked not known above */ - else if (status->flag & RX_FLAG_160MHZ) + else if (status->vht_flag & RX_VHT_FLAG_160MHZ) *pos++ = 11; else if (status->flag & RX_FLAG_40MHZ) *pos++ = 1; @@ -372,6 +351,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, *pos = (status->rate_idx << 4) | status->vht_nss; pos += 4; /* coding field */ + if (status->flag & RX_FLAG_LDPC) + *pos |= IEEE80211_RADIOTAP_CODING_LDPC_USER0; pos++; /* group ID */ pos++; @@ -383,21 +364,6 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, *pos++ = status->chain_signal[chain]; *pos++ = chain; } - - if (status->vendor_radiotap_len) { - /* ensure 2 byte alignment for the vendor field as required */ - if ((pos - (u8 *)rthdr) & 1) - *pos++ = 0; - *pos++ = status->vendor_radiotap_oui[0]; - *pos++ = status->vendor_radiotap_oui[1]; - *pos++ = status->vendor_radiotap_oui[2]; - *pos++ = status->vendor_radiotap_subns; - put_unaligned_le16(status->vendor_radiotap_len, pos); - pos += 2; - /* align the actual payload as requested */ - while ((pos - (u8 *)rthdr) & (status->vendor_radiotap_align - 1)) - *pos++ = 0; - } } /* @@ -428,8 +394,8 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) present_fcs_len = FCS_LEN; - /* ensure hdr->frame_control and vendor radiotap data are in skb head */ - if (!pskb_may_pull(origskb, 2 + status->vendor_radiotap_len)) { + /* ensure hdr->frame_control is in skb head */ + if (!pskb_may_pull(origskb, 2)) { dev_kfree_skb(origskb); return NULL; } @@ -599,10 +565,10 @@ static int ieee80211_is_unicast_robust_mgmt_frame(struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - if (skb->len < 24 || is_multicast_ether_addr(hdr->addr1)) + if (is_multicast_ether_addr(hdr->addr1)) return 0; - return ieee80211_is_robust_mgmt_frame(hdr); + return ieee80211_is_robust_mgmt_frame(skb); } @@ -610,10 +576,10 @@ static int ieee80211_is_multicast_robust_mgmt_frame(struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - if (skb->len < 24 || !is_multicast_ether_addr(hdr->addr1)) + if (!is_multicast_ether_addr(hdr->addr1)) return 0; - return ieee80211_is_robust_mgmt_frame(hdr); + return ieee80211_is_robust_mgmt_frame(skb); } @@ -626,7 +592,7 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) if (skb->len < 24 + sizeof(*mmie) || !is_multicast_ether_addr(hdr->da)) return -1; - if (!ieee80211_is_robust_mgmt_frame((struct ieee80211_hdr *) hdr)) + if (!ieee80211_is_robust_mgmt_frame(skb)) return -1; /* not a robust management frame */ mmie = (struct ieee80211_mmie *) @@ -1268,6 +1234,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) if (ieee80211_is_data(hdr->frame_control)) { sta->last_rx_rate_idx = status->rate_idx; sta->last_rx_rate_flag = status->flag; + sta->last_rx_rate_vht_flag = status->vht_flag; sta->last_rx_rate_vht_nss = status->vht_nss; } } @@ -1280,6 +1247,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) if (ieee80211_is_data(hdr->frame_control)) { sta->last_rx_rate_idx = status->rate_idx; sta->last_rx_rate_flag = status->flag; + sta->last_rx_rate_vht_flag = status->vht_flag; sta->last_rx_rate_vht_nss = status->vht_nss; } } @@ -1318,18 +1286,15 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) !ieee80211_has_morefrags(hdr->frame_control) && !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) && (rx->sdata->vif.type == NL80211_IFTYPE_AP || - rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) { + rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && + /* PM bit is only checked in frames where it isn't reserved, + * in AP mode it's reserved in non-bufferable management frames + * (cf. IEEE 802.11-2012 8.2.4.1.7 Power Management field) + */ + (!ieee80211_is_mgmt(hdr->frame_control) || + ieee80211_is_bufferable_mmpdu(hdr->frame_control))) { if (test_sta_flag(sta, WLAN_STA_PS_STA)) { - /* - * Ignore doze->wake transitions that are - * indicated by non-data frames, the standard - * is unclear here, but for example going to - * PS mode and then scanning would cause a - * doze->wake transition for the probe request, - * and that is clearly undesirable. - */ - if (ieee80211_is_data(hdr->frame_control) && - !ieee80211_has_pm(hdr->frame_control)) + if (!ieee80211_has_pm(hdr->frame_control)) sta_ps_end(sta); } else { if (ieee80211_has_pm(hdr->frame_control)) @@ -1852,8 +1817,7 @@ static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) * having configured keys. */ if (unlikely(ieee80211_is_action(fc) && !rx->key && - ieee80211_is_robust_mgmt_frame( - (struct ieee80211_hdr *) rx->skb->data))) + ieee80211_is_robust_mgmt_frame(rx->skb))) return -EACCES; } @@ -2000,7 +1964,10 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) /* deliver to local stack */ skb->protocol = eth_type_trans(skb, dev); memset(skb->cb, 0, sizeof(skb->cb)); - netif_receive_skb(skb); + if (rx->local->napi) + napi_gro_receive(rx->local->napi, skb); + else + netif_receive_skb(skb); } if (xmit_skb) { diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 88c81616f8f7..3ce7f2c8539a 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -472,9 +472,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, if (local->ops->hw_scan) { u8 *ies; - local->hw_scan_ies_bufsize = 2 + IEEE80211_MAX_SSID_LEN + - local->scan_ies_len + - req->ie_len; + local->hw_scan_ies_bufsize = local->scan_ies_len + req->ie_len; local->hw_scan_req = kmalloc( sizeof(*local->hw_scan_req) + req->n_channels * sizeof(req->channels[0]) + @@ -979,8 +977,7 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_chan_def chandef; int ret, i, iebufsz; - iebufsz = 2 + IEEE80211_MAX_SSID_LEN + - local->scan_ies_len + req->ie_len; + iebufsz = local->scan_ies_len + req->ie_len; lockdep_assert_held(&local->mtx); @@ -1058,9 +1055,11 @@ int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata) /* We don't want to restart sched scan anymore. */ local->sched_scan_req = NULL; - if (rcu_access_pointer(local->sched_scan_sdata)) - drv_sched_scan_stop(local, sdata); - + if (rcu_access_pointer(local->sched_scan_sdata)) { + ret = drv_sched_scan_stop(local, sdata); + if (!ret) + rcu_assign_pointer(local->sched_scan_sdata, NULL); + } out: mutex_unlock(&local->mtx); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index d3a6d8208f2f..4acc5fc402fa 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -261,6 +261,7 @@ struct ieee80211_tx_latency_stat { * "the" transmit rate * @last_rx_rate_idx: rx status rate index of the last data packet * @last_rx_rate_flag: rx status flag of the last data packet + * @last_rx_rate_vht_flag: rx status vht flag of the last data packet * @last_rx_rate_vht_nss: rx status nss of last data packet * @lock: used for locking all fields that require locking, see comments * in the header file. @@ -396,6 +397,7 @@ struct sta_info { struct ieee80211_tx_rate last_tx_rate; int last_rx_rate_idx; u32 last_rx_rate_flag; + u32 last_rx_rate_vht_flag; u8 last_rx_rate_vht_nss; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 1ee85c402439..e6e574a307c8 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -479,7 +479,7 @@ static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local, u32 msrmnt; u16 tid; u8 *qc; - int i, bin_range_count, bin_count; + int i, bin_range_count; u32 *bin_ranges; __le16 fc; struct ieee80211_tx_latency_stat *tx_lat; @@ -522,7 +522,6 @@ static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local, /* count how many Tx frames transmitted with the appropriate latency */ bin_range_count = tx_latency->n_ranges; bin_ranges = tx_latency->ranges; - bin_count = tx_lat->bin_count; for (i = 0; i < bin_range_count; i++) { if (msrmnt <= bin_ranges[i]) { diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 4080c615636f..19d36d4117e0 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -452,8 +452,7 @@ static int ieee80211_use_mfp(__le16 fc, struct sta_info *sta, if (sta == NULL || !test_sta_flag(sta, WLAN_STA_MFP)) return 0; - if (!ieee80211_is_robust_mgmt_frame((struct ieee80211_hdr *) - skb->data)) + if (!ieee80211_is_robust_mgmt_frame(skb)) return 0; return 1; @@ -538,11 +537,8 @@ ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx) if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED)) return TX_CONTINUE; - /* only deauth, disassoc and action are bufferable MMPDUs */ if (ieee80211_is_mgmt(hdr->frame_control) && - !ieee80211_is_deauth(hdr->frame_control) && - !ieee80211_is_disassoc(hdr->frame_control) && - !ieee80211_is_action(hdr->frame_control)) { + !ieee80211_is_bufferable_mmpdu(hdr->frame_control)) { if (tx->flags & IEEE80211_TX_UNICAST) info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; return TX_CONTINUE; @@ -582,7 +578,7 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) tx->key = key; else if (ieee80211_is_mgmt(hdr->frame_control) && is_multicast_ether_addr(hdr->addr1) && - ieee80211_is_robust_mgmt_frame(hdr) && + ieee80211_is_robust_mgmt_frame(tx->skb) && (key = rcu_dereference(tx->sdata->default_mgmt_key))) tx->key = key; else if (is_multicast_ether_addr(hdr->addr1) && @@ -597,12 +593,12 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) tx->key = NULL; else if (tx->skb->protocol == tx->sdata->control_port_protocol) tx->key = NULL; - else if (ieee80211_is_robust_mgmt_frame(hdr) && + else if (ieee80211_is_robust_mgmt_frame(tx->skb) && !(ieee80211_is_action(hdr->frame_control) && tx->sta && test_sta_flag(tx->sta, WLAN_STA_MFP))) tx->key = NULL; else if (ieee80211_is_mgmt(hdr->frame_control) && - !ieee80211_is_robust_mgmt_frame(hdr)) + !ieee80211_is_robust_mgmt_frame(tx->skb)) tx->key = NULL; else { I802_DEBUG_INC(tx->local->tx_handlers_drop_unencrypted); @@ -2417,15 +2413,6 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, return 0; } -void ieee80211_csa_finish(struct ieee80211_vif *vif) -{ - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); - - ieee80211_queue_work(&sdata->local->hw, - &sdata->csa_finalize_work); -} -EXPORT_SYMBOL(ieee80211_csa_finish); - static void ieee80211_update_csa(struct ieee80211_sub_if_data *sdata, struct beacon_data *beacon) { @@ -2454,8 +2441,12 @@ static void ieee80211_update_csa(struct ieee80211_sub_if_data *sdata, if (WARN_ON(counter_offset_beacon >= beacon_data_len)) return; - /* warn if the driver did not check for/react to csa completeness */ - if (WARN_ON(beacon_data[counter_offset_beacon] == 0)) + /* Warn if the driver did not check for/react to csa + * completeness. A beacon with CSA counter set to 0 should + * never occur, because a counter of 1 means switch just + * before the next beacon. + */ + if (WARN_ON(beacon_data[counter_offset_beacon] == 1)) return; beacon_data[counter_offset_beacon]--; @@ -2521,7 +2512,7 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) if (WARN_ON(counter_beacon > beacon_data_len)) goto out; - if (beacon_data[counter_beacon] == 0) + if (beacon_data[counter_beacon] == 1) ret = true; out: rcu_read_unlock(); @@ -2909,7 +2900,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, cpu_to_le16(IEEE80211_FCTL_MOREDATA); } - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + if (sdata->vif.type == NL80211_IFTYPE_AP) sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev); if (!ieee80211_tx_prepare(sdata, &tx, skb)) break; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index b8700d417a9c..275c94f995f7 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -34,7 +34,7 @@ #include "wep.h" /* privid for wiphys to determine whether they belong to us or not */ -void *mac80211_wiphy_privid = &mac80211_wiphy_privid; +const void *const mac80211_wiphy_privid = &mac80211_wiphy_privid; struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy) { @@ -1277,13 +1277,32 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, * that calculates local->scan_ies_len. */ - /* add any remaining custom IEs */ + /* insert custom IEs that go before VHT */ if (ie && ie_len) { - noffset = ie_len; + static const u8 before_vht[] = { + WLAN_EID_SSID, + WLAN_EID_SUPP_RATES, + WLAN_EID_REQUEST, + WLAN_EID_EXT_SUPP_RATES, + WLAN_EID_DS_PARAMS, + WLAN_EID_SUPPORTED_REGULATORY_CLASSES, + WLAN_EID_HT_CAPABILITY, + WLAN_EID_BSS_COEX_2040, + WLAN_EID_EXT_CAPABILITY, + WLAN_EID_SSID_LIST, + WLAN_EID_CHANNEL_USAGE, + WLAN_EID_INTERWORKING, + /* mesh ID can't happen here */ + /* 60 GHz can't happen here right now */ + }; + noffset = ieee80211_ie_split(ie, ie_len, + before_vht, ARRAY_SIZE(before_vht), + offset); if (end - pos < noffset - offset) goto out_err; memcpy(pos, ie + offset, noffset - offset); pos += noffset - offset; + offset = noffset; } if (sband->vht_cap.vht_supported) { @@ -1293,6 +1312,15 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, sband->vht_cap.cap); } + /* add any remaining custom IEs */ + if (ie && ie_len) { + noffset = ie_len; + if (end - pos < noffset - offset) + goto out_err; + memcpy(pos, ie + offset, noffset - offset); + pos += noffset - offset; + } + return pos - buffer; out_err: WARN_ONCE(1, "not enough space for preq IEs\n"); @@ -1370,7 +1398,6 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, enum ieee80211_band band, u32 *basic_rates) { struct ieee80211_supported_band *sband; - struct ieee80211_rate *bitrates; size_t num_rates; u32 supp_rates, rate_flags; int i, j, shift; @@ -1382,7 +1409,6 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, if (WARN_ON(!sband)) return 1; - bitrates = sband->bitrates; num_rates = sband->n_bitrates; supp_rates = 0; for (i = 0; i < elems->supp_rates_len + @@ -2268,11 +2294,11 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, ri.nss = status->vht_nss; if (status->flag & RX_FLAG_40MHZ) ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH; - if (status->flag & RX_FLAG_80MHZ) + if (status->vht_flag & RX_VHT_FLAG_80MHZ) ri.flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH; - if (status->flag & RX_FLAG_80P80MHZ) + if (status->vht_flag & RX_VHT_FLAG_80P80MHZ) ri.flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH; - if (status->flag & RX_FLAG_160MHZ) + if (status->vht_flag & RX_VHT_FLAG_160MHZ) ri.flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH; if (status->flag & RX_FLAG_SHORT_GI) ri.flags |= RATE_INFO_FLAGS_SHORT_GI; diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index d75f35c6e1a0..e9e36a256165 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -349,9 +349,9 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta) sta->sta.rx_nss = max_t(u8, 1, ht_rx_nss); } -void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, u8 opmode, - enum ieee80211_band band, bool nss_only) +u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, u8 opmode, + enum ieee80211_band band, bool nss_only) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; @@ -363,7 +363,7 @@ void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, /* ignore - no support for BF yet */ if (opmode & IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF) - return; + return 0; nss = opmode & IEEE80211_OPMODE_NOTIF_RX_NSS_MASK; nss >>= IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT; @@ -375,7 +375,7 @@ void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, } if (nss_only) - goto change; + return changed; switch (opmode & IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK) { case IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: @@ -398,7 +398,19 @@ void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, changed |= IEEE80211_RC_BW_CHANGED; } - change: - if (changed) + return changed; +} + +void ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, u8 opmode, + enum ieee80211_band band, bool nss_only) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_supported_band *sband = local->hw.wiphy->bands[band]; + + u32 changed = __ieee80211_vht_handle_opmode(sdata, sta, opmode, + band, nss_only); + + if (changed > 0) rate_control_rate_update(local, sband, sta, changed); } diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 21448d629b15..b8600e3c29c8 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -301,8 +301,7 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) } -static void ccmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *b_0, u8 *aad, - int encrypted) +static void ccmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *b_0, u8 *aad) { __le16 mask_fc; int a4_included, mgmt; @@ -456,7 +455,7 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) return 0; pos += IEEE80211_CCMP_HDR_LEN; - ccmp_special_blocks(skb, pn, b_0, aad, 0); + ccmp_special_blocks(skb, pn, b_0, aad); ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len, skb_put(skb, IEEE80211_CCMP_MIC_LEN)); @@ -495,7 +494,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx) hdrlen = ieee80211_hdrlen(hdr->frame_control); if (!ieee80211_is_data(hdr->frame_control) && - !ieee80211_is_robust_mgmt_frame(hdr)) + !ieee80211_is_robust_mgmt_frame(skb)) return RX_CONTINUE; data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - @@ -524,7 +523,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx) u8 aad[2 * AES_BLOCK_SIZE]; u8 b_0[AES_BLOCK_SIZE]; /* hardware didn't decrypt/verify MIC */ - ccmp_special_blocks(skb, pn, b_0, aad, 1); + ccmp_special_blocks(skb, pn, b_0, aad); if (ieee80211_aes_ccm_decrypt( key->u.ccmp.tfm, b_0, aad, diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile index 57cf5d1a2e4a..15d62df52182 100644 --- a/net/mac802154/Makefile +++ b/net/mac802154/Makefile @@ -1,2 +1,4 @@ obj-$(CONFIG_MAC802154) += mac802154.o mac802154-objs := ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o wpan.o + +ccflags-y += -D__CHECK_ENDIAN__ diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c index 52ae6646a411..2cf66d885e68 100644 --- a/net/mac802154/ieee802154_dev.c +++ b/net/mac802154/ieee802154_dev.c @@ -27,6 +27,7 @@ #include <net/netlink.h> #include <linux/nl802154.h> #include <net/mac802154.h> +#include <net/ieee802154_netdev.h> #include <net/route.h> #include <net/wpan-phy.h> @@ -35,9 +36,28 @@ int mac802154_slave_open(struct net_device *dev) { struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct mac802154_sub_if_data *subif; struct mac802154_priv *ipriv = priv->hw; int res = 0; + ASSERT_RTNL(); + + if (priv->type == IEEE802154_DEV_WPAN) { + mutex_lock(&priv->hw->slaves_mtx); + list_for_each_entry(subif, &priv->hw->slaves, list) { + if (subif != priv && subif->type == priv->type && + subif->running) { + mutex_unlock(&priv->hw->slaves_mtx); + return -EBUSY; + } + } + mutex_unlock(&priv->hw->slaves_mtx); + } + + mutex_lock(&priv->hw->slaves_mtx); + priv->running = true; + mutex_unlock(&priv->hw->slaves_mtx); + if (ipriv->open_count++ == 0) { res = ipriv->ops->start(&ipriv->hw); WARN_ON(res); @@ -46,7 +66,9 @@ int mac802154_slave_open(struct net_device *dev) } if (ipriv->ops->ieee_addr) { - res = ipriv->ops->ieee_addr(&ipriv->hw, dev->dev_addr); + __le64 addr = ieee802154_devaddr_from_raw(dev->dev_addr); + + res = ipriv->ops->ieee_addr(&ipriv->hw, addr); WARN_ON(res); if (res) goto err; @@ -66,8 +88,14 @@ int mac802154_slave_close(struct net_device *dev) struct mac802154_sub_if_data *priv = netdev_priv(dev); struct mac802154_priv *ipriv = priv->hw; + ASSERT_RTNL(); + netif_stop_queue(dev); + mutex_lock(&priv->hw->slaves_mtx); + priv->running = false; + mutex_unlock(&priv->hw->slaves_mtx); + if (!--ipriv->open_count) ipriv->ops->stop(&ipriv->hw); @@ -165,6 +193,49 @@ err: return ERR_PTR(err); } +static int mac802154_set_txpower(struct wpan_phy *phy, int db) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + return priv->ops->set_txpower(&priv->hw, db); +} + +static int mac802154_set_lbt(struct wpan_phy *phy, bool on) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + return priv->ops->set_lbt(&priv->hw, on); +} + +static int mac802154_set_cca_mode(struct wpan_phy *phy, u8 mode) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + return priv->ops->set_cca_mode(&priv->hw, mode); +} + +static int mac802154_set_cca_ed_level(struct wpan_phy *phy, s32 level) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + return priv->ops->set_cca_ed_level(&priv->hw, level); +} + +static int mac802154_set_csma_params(struct wpan_phy *phy, u8 min_be, + u8 max_be, u8 retries) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + return priv->ops->set_csma_params(&priv->hw, min_be, max_be, retries); +} + +static int mac802154_set_frame_retries(struct wpan_phy *phy, s8 retries) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + return priv->ops->set_frame_retries(&priv->hw, retries); +} + struct ieee802154_dev * ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops) { @@ -242,6 +313,18 @@ int ieee802154_register_device(struct ieee802154_dev *dev) priv->phy->add_iface = mac802154_add_iface; priv->phy->del_iface = mac802154_del_iface; + if (priv->ops->set_txpower) + priv->phy->set_txpower = mac802154_set_txpower; + if (priv->ops->set_lbt) + priv->phy->set_lbt = mac802154_set_lbt; + if (priv->ops->set_cca_mode) + priv->phy->set_cca_mode = mac802154_set_cca_mode; + if (priv->ops->set_cca_ed_level) + priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level; + if (priv->ops->set_csma_params) + priv->phy->set_csma_params = mac802154_set_csma_params; + if (priv->ops->set_frame_retries) + priv->phy->set_frame_retries = mac802154_set_frame_retries; rc = wpan_phy_register(priv->phy); if (rc < 0) diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h index d48422e27110..28ef59c566e6 100644 --- a/net/mac802154/mac802154.h +++ b/net/mac802154/mac802154.h @@ -23,6 +23,8 @@ #ifndef MAC802154_H #define MAC802154_H +#include <net/ieee802154_netdev.h> + /* mac802154 device private data */ struct mac802154_priv { struct ieee802154_dev hw; @@ -71,15 +73,19 @@ struct mac802154_sub_if_data { struct net_device *dev; int type; + bool running; spinlock_t mib_lock; __le16 pan_id; __le16 short_addr; + __le64 extended_addr; u8 chan; u8 page; + struct ieee802154_mac_params mac_params; + /* MAC BSN field */ u8 bsn; /* MAC DSN field */ @@ -106,12 +112,17 @@ netdev_tx_t mac802154_tx(struct mac802154_priv *priv, struct sk_buff *skb, u8 page, u8 chan); /* MIB callbacks */ -void mac802154_dev_set_short_addr(struct net_device *dev, u16 val); -u16 mac802154_dev_get_short_addr(const struct net_device *dev); +void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val); +__le16 mac802154_dev_get_short_addr(const struct net_device *dev); void mac802154_dev_set_ieee_addr(struct net_device *dev); -u16 mac802154_dev_get_pan_id(const struct net_device *dev); -void mac802154_dev_set_pan_id(struct net_device *dev, u16 val); +__le16 mac802154_dev_get_pan_id(const struct net_device *dev); +void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val); void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan); u8 mac802154_dev_get_dsn(const struct net_device *dev); +int mac802154_set_mac_params(struct net_device *dev, + const struct ieee802154_mac_params *params); +void mac802154_get_mac_params(struct net_device *dev, + struct ieee802154_mac_params *params); + #endif /* MAC802154_H */ diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c index a99910d4d52f..d40c0928bc62 100644 --- a/net/mac802154/mac_cmd.c +++ b/net/mac802154/mac_cmd.c @@ -40,7 +40,7 @@ static int mac802154_mlme_start_req(struct net_device *dev, u8 pan_coord, u8 blx, u8 coord_realign) { - BUG_ON(addr->addr_type != IEEE802154_ADDR_SHORT); + BUG_ON(addr->mode != IEEE802154_ADDR_SHORT); mac802154_dev_set_pan_id(dev, addr->pan_id); mac802154_dev_set_short_addr(dev, addr->short_addr); @@ -74,4 +74,7 @@ struct ieee802154_mlme_ops mac802154_mlme_wpan = { .get_pan_id = mac802154_dev_get_pan_id, .get_short_addr = mac802154_dev_get_short_addr, .get_dsn = mac802154_dev_get_dsn, + + .set_mac_params = mac802154_set_mac_params, + .get_mac_params = mac802154_get_mac_params, }; diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c index 8ded97cf1c33..153bd1ddbfbb 100644 --- a/net/mac802154/mib.c +++ b/net/mac802154/mib.c @@ -24,7 +24,9 @@ #include <linux/if_arp.h> #include <net/mac802154.h> +#include <net/ieee802154_netdev.h> #include <net/wpan-phy.h> +#include <net/ieee802154_netdev.h> #include "mac802154.h" @@ -62,8 +64,6 @@ static void hw_addr_notify(struct work_struct *work) pr_debug("failed changed mask %lx\n", nw->changed); kfree(nw); - - return; } static void set_hw_addr_filt(struct net_device *dev, unsigned long changed) @@ -79,11 +79,9 @@ static void set_hw_addr_filt(struct net_device *dev, unsigned long changed) work->dev = dev; work->changed = changed; queue_work(priv->hw->dev_workqueue, &work->work); - - return; } -void mac802154_dev_set_short_addr(struct net_device *dev, u16 val) +void mac802154_dev_set_short_addr(struct net_device *dev, __le16 val) { struct mac802154_sub_if_data *priv = netdev_priv(dev); @@ -100,10 +98,10 @@ void mac802154_dev_set_short_addr(struct net_device *dev, u16 val) } } -u16 mac802154_dev_get_short_addr(const struct net_device *dev) +__le16 mac802154_dev_get_short_addr(const struct net_device *dev) { struct mac802154_sub_if_data *priv = netdev_priv(dev); - u16 ret; + __le16 ret; BUG_ON(dev->type != ARPHRD_IEEE802154); @@ -119,19 +117,19 @@ void mac802154_dev_set_ieee_addr(struct net_device *dev) struct mac802154_sub_if_data *priv = netdev_priv(dev); struct mac802154_priv *mac = priv->hw; + priv->extended_addr = ieee802154_devaddr_from_raw(dev->dev_addr); + if (mac->ops->set_hw_addr_filt && - memcmp(mac->hw.hw_filt.ieee_addr, - dev->dev_addr, IEEE802154_ADDR_LEN)) { - memcpy(mac->hw.hw_filt.ieee_addr, - dev->dev_addr, IEEE802154_ADDR_LEN); + mac->hw.hw_filt.ieee_addr != priv->extended_addr) { + mac->hw.hw_filt.ieee_addr = priv->extended_addr; set_hw_addr_filt(dev, IEEE802515_AFILT_IEEEADDR_CHANGED); } } -u16 mac802154_dev_get_pan_id(const struct net_device *dev) +__le16 mac802154_dev_get_pan_id(const struct net_device *dev) { struct mac802154_sub_if_data *priv = netdev_priv(dev); - u16 ret; + __le16 ret; BUG_ON(dev->type != ARPHRD_IEEE802154); @@ -142,7 +140,7 @@ u16 mac802154_dev_get_pan_id(const struct net_device *dev) return ret; } -void mac802154_dev_set_pan_id(struct net_device *dev, u16 val) +void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val) { struct mac802154_sub_if_data *priv = netdev_priv(dev); diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index 38548ec2098f..03855b0677cc 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -80,7 +80,6 @@ mac802154_subif_rx(struct ieee802154_dev *hw, struct sk_buff *skb, u8 lqi) mac802154_wpans_rx(priv, skb); out: dev_kfree_skb(skb); - return; } static void mac802154_rx_worker(struct work_struct *work) diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c index 372d8a222b91..1df7a6a57386 100644 --- a/net/mac802154/wpan.c +++ b/net/mac802154/wpan.c @@ -35,35 +35,6 @@ #include "mac802154.h" -static inline int mac802154_fetch_skb_u8(struct sk_buff *skb, u8 *val) -{ - if (unlikely(!pskb_may_pull(skb, 1))) - return -EINVAL; - - *val = skb->data[0]; - skb_pull(skb, 1); - - return 0; -} - -static inline int mac802154_fetch_skb_u16(struct sk_buff *skb, u16 *val) -{ - if (unlikely(!pskb_may_pull(skb, 2))) - return -EINVAL; - - *val = skb->data[0] | (skb->data[1] << 8); - skb_pull(skb, 2); - - return 0; -} - -static inline void mac802154_haddr_copy_swap(u8 *dest, const u8 *src) -{ - int i; - for (i = 0; i < IEEE802154_ADDR_LEN; i++) - dest[IEEE802154_ADDR_LEN - i - 1] = src[i]; -} - static int mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -76,19 +47,25 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCGIFADDR: - if (priv->pan_id == IEEE802154_PANID_BROADCAST || - priv->short_addr == IEEE802154_ADDR_BROADCAST) { + { + u16 pan_id, short_addr; + + pan_id = le16_to_cpu(priv->pan_id); + short_addr = le16_to_cpu(priv->short_addr); + if (pan_id == IEEE802154_PANID_BROADCAST || + short_addr == IEEE802154_ADDR_BROADCAST) { err = -EADDRNOTAVAIL; break; } sa->family = AF_IEEE802154; sa->addr.addr_type = IEEE802154_ADDR_SHORT; - sa->addr.pan_id = priv->pan_id; - sa->addr.short_addr = priv->short_addr; + sa->addr.pan_id = pan_id; + sa->addr.short_addr = short_addr; err = 0; break; + } case SIOCSIFADDR: dev_warn(&dev->dev, "Using DEBUGing ioctl SIOCSIFADDR isn't recommened!\n"); @@ -101,8 +78,8 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; } - priv->pan_id = sa->addr.pan_id; - priv->short_addr = sa->addr.short_addr; + priv->pan_id = cpu_to_le16(sa->addr.pan_id); + priv->short_addr = cpu_to_le16(sa->addr.short_addr); err = 0; break; @@ -125,190 +102,154 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) return 0; } -static int mac802154_header_create(struct sk_buff *skb, - struct net_device *dev, - unsigned short type, - const void *_daddr, - const void *_saddr, - unsigned len) +int mac802154_set_mac_params(struct net_device *dev, + const struct ieee802154_mac_params *params) { - const struct ieee802154_addr *saddr = _saddr; - const struct ieee802154_addr *daddr = _daddr; - struct ieee802154_addr dev_addr; struct mac802154_sub_if_data *priv = netdev_priv(dev); - int pos = 2; - u8 head[MAC802154_FRAME_HARD_HEADER_LEN]; - u16 fc; - if (!daddr) - return -EINVAL; + mutex_lock(&priv->hw->slaves_mtx); + priv->mac_params = *params; + mutex_unlock(&priv->hw->slaves_mtx); - head[pos++] = mac_cb(skb)->seq; /* DSN/BSN */ - fc = mac_cb_type(skb); - if (mac_cb_is_ackreq(skb)) - fc |= IEEE802154_FC_ACK_REQ; + return 0; +} - if (!saddr) { - spin_lock_bh(&priv->mib_lock); +void mac802154_get_mac_params(struct net_device *dev, + struct ieee802154_mac_params *params) +{ + struct mac802154_sub_if_data *priv = netdev_priv(dev); - if (priv->short_addr == IEEE802154_ADDR_BROADCAST || - priv->short_addr == IEEE802154_ADDR_UNDEF || - priv->pan_id == IEEE802154_PANID_BROADCAST) { - dev_addr.addr_type = IEEE802154_ADDR_LONG; - memcpy(dev_addr.hwaddr, dev->dev_addr, - IEEE802154_ADDR_LEN); - } else { - dev_addr.addr_type = IEEE802154_ADDR_SHORT; - dev_addr.short_addr = priv->short_addr; - } + mutex_lock(&priv->hw->slaves_mtx); + *params = priv->mac_params; + mutex_unlock(&priv->hw->slaves_mtx); +} - dev_addr.pan_id = priv->pan_id; - saddr = &dev_addr; +int mac802154_wpan_open(struct net_device *dev) +{ + int rc; + struct mac802154_sub_if_data *priv = netdev_priv(dev); + struct wpan_phy *phy = priv->hw->phy; - spin_unlock_bh(&priv->mib_lock); - } + rc = mac802154_slave_open(dev); + if (rc < 0) + return rc; - if (daddr->addr_type != IEEE802154_ADDR_NONE) { - fc |= (daddr->addr_type << IEEE802154_FC_DAMODE_SHIFT); + mutex_lock(&phy->pib_lock); - head[pos++] = daddr->pan_id & 0xff; - head[pos++] = daddr->pan_id >> 8; + if (phy->set_txpower) { + rc = phy->set_txpower(phy, priv->mac_params.transmit_power); + if (rc < 0) + goto out; + } - if (daddr->addr_type == IEEE802154_ADDR_SHORT) { - head[pos++] = daddr->short_addr & 0xff; - head[pos++] = daddr->short_addr >> 8; - } else { - mac802154_haddr_copy_swap(head + pos, daddr->hwaddr); - pos += IEEE802154_ADDR_LEN; - } + if (phy->set_lbt) { + rc = phy->set_lbt(phy, priv->mac_params.lbt); + if (rc < 0) + goto out; } - if (saddr->addr_type != IEEE802154_ADDR_NONE) { - fc |= (saddr->addr_type << IEEE802154_FC_SAMODE_SHIFT); + if (phy->set_cca_mode) { + rc = phy->set_cca_mode(phy, priv->mac_params.cca_mode); + if (rc < 0) + goto out; + } - if ((saddr->pan_id == daddr->pan_id) && - (saddr->pan_id != IEEE802154_PANID_BROADCAST)) { - /* PANID compression/intra PAN */ - fc |= IEEE802154_FC_INTRA_PAN; - } else { - head[pos++] = saddr->pan_id & 0xff; - head[pos++] = saddr->pan_id >> 8; - } + if (phy->set_cca_ed_level) { + rc = phy->set_cca_ed_level(phy, priv->mac_params.cca_ed_level); + if (rc < 0) + goto out; + } - if (saddr->addr_type == IEEE802154_ADDR_SHORT) { - head[pos++] = saddr->short_addr & 0xff; - head[pos++] = saddr->short_addr >> 8; - } else { - mac802154_haddr_copy_swap(head + pos, saddr->hwaddr); - pos += IEEE802154_ADDR_LEN; - } + if (phy->set_csma_params) { + rc = phy->set_csma_params(phy, priv->mac_params.min_be, + priv->mac_params.max_be, + priv->mac_params.csma_retries); + if (rc < 0) + goto out; } - head[0] = fc; - head[1] = fc >> 8; + if (phy->set_frame_retries) { + rc = phy->set_frame_retries(phy, + priv->mac_params.frame_retries); + if (rc < 0) + goto out; + } - memcpy(skb_push(skb, pos), head, pos); - skb_reset_mac_header(skb); - skb->mac_len = pos; + mutex_unlock(&phy->pib_lock); + return 0; - return pos; +out: + mutex_unlock(&phy->pib_lock); + return rc; } -static int -mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr) +static int mac802154_header_create(struct sk_buff *skb, + struct net_device *dev, + unsigned short type, + const void *daddr, + const void *saddr, + unsigned len) { - const u8 *hdr = skb_mac_header(skb); - const u8 *tail = skb_tail_pointer(skb); - struct ieee802154_addr *addr = (struct ieee802154_addr *)haddr; - u16 fc; - int da_type; - - if (hdr + 3 > tail) - goto malformed; + struct ieee802154_hdr hdr; + struct mac802154_sub_if_data *priv = netdev_priv(dev); + int hlen; - fc = hdr[0] | (hdr[1] << 8); + if (!daddr) + return -EINVAL; - hdr += 3; + memset(&hdr.fc, 0, sizeof(hdr.fc)); + hdr.fc.type = mac_cb_type(skb); + hdr.fc.security_enabled = mac_cb_is_secen(skb); + hdr.fc.ack_request = mac_cb_is_ackreq(skb); - da_type = IEEE802154_FC_DAMODE(fc); - addr->addr_type = IEEE802154_FC_SAMODE(fc); + if (!saddr) { + spin_lock_bh(&priv->mib_lock); - switch (da_type) { - case IEEE802154_ADDR_NONE: - if (fc & IEEE802154_FC_INTRA_PAN) - goto malformed; - break; - case IEEE802154_ADDR_LONG: - if (fc & IEEE802154_FC_INTRA_PAN) { - if (hdr + 2 > tail) - goto malformed; - addr->pan_id = hdr[0] | (hdr[1] << 8); - hdr += 2; + if (priv->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) || + priv->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) || + priv->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) { + hdr.source.mode = IEEE802154_ADDR_LONG; + hdr.source.extended_addr = priv->extended_addr; + } else { + hdr.source.mode = IEEE802154_ADDR_SHORT; + hdr.source.short_addr = priv->short_addr; } - if (hdr + IEEE802154_ADDR_LEN > tail) - goto malformed; + hdr.source.pan_id = priv->pan_id; - hdr += IEEE802154_ADDR_LEN; - break; - case IEEE802154_ADDR_SHORT: - if (fc & IEEE802154_FC_INTRA_PAN) { - if (hdr + 2 > tail) - goto malformed; - addr->pan_id = hdr[0] | (hdr[1] << 8); - hdr += 2; - } - - if (hdr + 2 > tail) - goto malformed; + spin_unlock_bh(&priv->mib_lock); + } else { + hdr.source = *(const struct ieee802154_addr *)saddr; + } - hdr += 2; - break; - default: - goto malformed; + hdr.dest = *(const struct ieee802154_addr *)daddr; - } + hlen = ieee802154_hdr_push(skb, &hdr); + if (hlen < 0) + return -EINVAL; - switch (addr->addr_type) { - case IEEE802154_ADDR_NONE: - break; - case IEEE802154_ADDR_LONG: - if (!(fc & IEEE802154_FC_INTRA_PAN)) { - if (hdr + 2 > tail) - goto malformed; - addr->pan_id = hdr[0] | (hdr[1] << 8); - hdr += 2; - } + skb_reset_mac_header(skb); + skb->mac_len = hlen; - if (hdr + IEEE802154_ADDR_LEN > tail) - goto malformed; + if (hlen + len + 2 > dev->mtu) + return -EMSGSIZE; - mac802154_haddr_copy_swap(addr->hwaddr, hdr); - hdr += IEEE802154_ADDR_LEN; - break; - case IEEE802154_ADDR_SHORT: - if (!(fc & IEEE802154_FC_INTRA_PAN)) { - if (hdr + 2 > tail) - goto malformed; - addr->pan_id = hdr[0] | (hdr[1] << 8); - hdr += 2; - } + return hlen; +} - if (hdr + 2 > tail) - goto malformed; +static int +mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr) +{ + struct ieee802154_hdr hdr; + struct ieee802154_addr *addr = (struct ieee802154_addr *)haddr; - addr->short_addr = hdr[0] | (hdr[1] << 8); - hdr += 2; - break; - default: - goto malformed; + if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) { + pr_debug("malformed packet\n"); + return 0; } - return sizeof(struct ieee802154_addr); - -malformed: - pr_debug("malformed packet\n"); - return 0; + *addr = hdr.source; + return sizeof(*addr); } static netdev_tx_t @@ -344,7 +285,7 @@ static struct header_ops mac802154_header_ops = { }; static const struct net_device_ops mac802154_wpan_ops = { - .ndo_open = mac802154_slave_open, + .ndo_open = mac802154_wpan_open, .ndo_stop = mac802154_slave_close, .ndo_start_xmit = mac802154_wpan_xmit, .ndo_do_ioctl = mac802154_wpan_ioctl, @@ -382,8 +323,14 @@ void mac802154_wpan_setup(struct net_device *dev) get_random_bytes(&priv->bsn, 1); get_random_bytes(&priv->dsn, 1); - priv->pan_id = IEEE802154_PANID_BROADCAST; - priv->short_addr = IEEE802154_ADDR_BROADCAST; + /* defaults per 802.15.4-2011 */ + priv->mac_params.min_be = 3; + priv->mac_params.max_be = 5; + priv->mac_params.csma_retries = 4; + priv->mac_params.frame_retries = -1; /* for compatibility, actual default is 3 */ + + priv->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); + priv->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); } static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) @@ -394,13 +341,18 @@ static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) static int mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) { + __le16 span, sshort; + pr_debug("getting packet via slave interface %s\n", sdata->dev->name); spin_lock_bh(&sdata->mib_lock); - switch (mac_cb(skb)->da.addr_type) { + span = sdata->pan_id; + sshort = sdata->short_addr; + + switch (mac_cb(skb)->dest.mode) { case IEEE802154_ADDR_NONE: - if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE) + if (mac_cb(skb)->dest.mode != IEEE802154_ADDR_NONE) /* FIXME: check if we are PAN coordinator */ skb->pkt_type = PACKET_OTHERHOST; else @@ -408,23 +360,22 @@ mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) skb->pkt_type = PACKET_HOST; break; case IEEE802154_ADDR_LONG: - if (mac_cb(skb)->da.pan_id != sdata->pan_id && - mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST) + if (mac_cb(skb)->dest.pan_id != span && + mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST)) skb->pkt_type = PACKET_OTHERHOST; - else if (!memcmp(mac_cb(skb)->da.hwaddr, sdata->dev->dev_addr, - IEEE802154_ADDR_LEN)) + else if (mac_cb(skb)->dest.extended_addr == sdata->extended_addr) skb->pkt_type = PACKET_HOST; else skb->pkt_type = PACKET_OTHERHOST; break; case IEEE802154_ADDR_SHORT: - if (mac_cb(skb)->da.pan_id != sdata->pan_id && - mac_cb(skb)->da.pan_id != IEEE802154_PANID_BROADCAST) + if (mac_cb(skb)->dest.pan_id != span && + mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST)) skb->pkt_type = PACKET_OTHERHOST; - else if (mac_cb(skb)->da.short_addr == sdata->short_addr) + else if (mac_cb(skb)->dest.short_addr == sshort) skb->pkt_type = PACKET_HOST; - else if (mac_cb(skb)->da.short_addr == - IEEE802154_ADDR_BROADCAST) + else if (mac_cb(skb)->dest.short_addr == + cpu_to_le16(IEEE802154_ADDR_BROADCAST)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_OTHERHOST; @@ -451,88 +402,82 @@ mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb) } } -static int mac802154_parse_frame_start(struct sk_buff *skb) +static void mac802154_print_addr(const char *name, + const struct ieee802154_addr *addr) { - u8 *head = skb->data; - u16 fc; - - if (mac802154_fetch_skb_u16(skb, &fc) || - mac802154_fetch_skb_u8(skb, &(mac_cb(skb)->seq))) - goto err; - - pr_debug("fc: %04x dsn: %02x\n", fc, head[2]); - - mac_cb(skb)->flags = IEEE802154_FC_TYPE(fc); - mac_cb(skb)->sa.addr_type = IEEE802154_FC_SAMODE(fc); - mac_cb(skb)->da.addr_type = IEEE802154_FC_DAMODE(fc); + if (addr->mode == IEEE802154_ADDR_NONE) + pr_debug("%s not present\n", name); - if (fc & IEEE802154_FC_INTRA_PAN) - mac_cb(skb)->flags |= MAC_CB_FLAG_INTRAPAN; + pr_debug("%s PAN ID: %04x\n", name, le16_to_cpu(addr->pan_id)); + if (addr->mode == IEEE802154_ADDR_SHORT) { + pr_debug("%s is short: %04x\n", name, + le16_to_cpu(addr->short_addr)); + } else { + u64 hw = swab64((__force u64) addr->extended_addr); - if (mac_cb(skb)->da.addr_type != IEEE802154_ADDR_NONE) { - if (mac802154_fetch_skb_u16(skb, &(mac_cb(skb)->da.pan_id))) - goto err; - - /* source PAN id compression */ - if (mac_cb_is_intrapan(skb)) - mac_cb(skb)->sa.pan_id = mac_cb(skb)->da.pan_id; + pr_debug("%s is hardware: %8phC\n", name, &hw); + } +} - pr_debug("dest PAN addr: %04x\n", mac_cb(skb)->da.pan_id); +static int mac802154_parse_frame_start(struct sk_buff *skb) +{ + int hlen; + struct ieee802154_hdr hdr; - if (mac_cb(skb)->da.addr_type == IEEE802154_ADDR_SHORT) { - u16 *da = &(mac_cb(skb)->da.short_addr); + hlen = ieee802154_hdr_pull(skb, &hdr); + if (hlen < 0) + return -EINVAL; - if (mac802154_fetch_skb_u16(skb, da)) - goto err; + skb->mac_len = hlen; - pr_debug("destination address is short: %04x\n", - mac_cb(skb)->da.short_addr); - } else { - if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN)) - goto err; + pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr.fc), + hdr.seq); - mac802154_haddr_copy_swap(mac_cb(skb)->da.hwaddr, - skb->data); - skb_pull(skb, IEEE802154_ADDR_LEN); + mac_cb(skb)->flags = hdr.fc.type; - pr_debug("destination address is hardware\n"); - } - } + if (hdr.fc.ack_request) + mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ; + if (hdr.fc.security_enabled) + mac_cb(skb)->flags |= MAC_CB_FLAG_SECEN; - if (mac_cb(skb)->sa.addr_type != IEEE802154_ADDR_NONE) { - /* non PAN-compression, fetch source address id */ - if (!(mac_cb_is_intrapan(skb))) { - u16 *sa_pan = &(mac_cb(skb)->sa.pan_id); + mac802154_print_addr("destination", &hdr.dest); + mac802154_print_addr("source", &hdr.source); - if (mac802154_fetch_skb_u16(skb, sa_pan)) - goto err; - } + mac_cb(skb)->source = hdr.source; + mac_cb(skb)->dest = hdr.dest; - pr_debug("source PAN addr: %04x\n", mac_cb(skb)->da.pan_id); + if (hdr.fc.security_enabled) { + u64 key; - if (mac_cb(skb)->sa.addr_type == IEEE802154_ADDR_SHORT) { - u16 *sa = &(mac_cb(skb)->sa.short_addr); + pr_debug("seclevel %i\n", hdr.sec.level); - if (mac802154_fetch_skb_u16(skb, sa)) - goto err; + switch (hdr.sec.key_id_mode) { + case IEEE802154_SCF_KEY_IMPLICIT: + pr_debug("implicit key\n"); + break; - pr_debug("source address is short: %04x\n", - mac_cb(skb)->sa.short_addr); - } else { - if (!pskb_may_pull(skb, IEEE802154_ADDR_LEN)) - goto err; + case IEEE802154_SCF_KEY_INDEX: + pr_debug("key %02x\n", hdr.sec.key_id); + break; - mac802154_haddr_copy_swap(mac_cb(skb)->sa.hwaddr, - skb->data); - skb_pull(skb, IEEE802154_ADDR_LEN); + case IEEE802154_SCF_KEY_SHORT_INDEX: + pr_debug("key %04x:%04x %02x\n", + le32_to_cpu(hdr.sec.short_src) >> 16, + le32_to_cpu(hdr.sec.short_src) & 0xffff, + hdr.sec.key_id); + break; - pr_debug("source address is hardware\n"); + case IEEE802154_SCF_KEY_HW_INDEX: + key = swab64((__force u64) hdr.sec.extended_src); + pr_debug("key source %8phC %02x\n", &key, + hdr.sec.key_id); + break; } + + return -EINVAL; } return 0; -err: - return -EINVAL; } void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb) diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig index 44cd4f58adf0..2f7f5c32c6f9 100644 --- a/net/netfilter/ipset/Kconfig +++ b/net/netfilter/ipset/Kconfig @@ -61,6 +61,15 @@ config IP_SET_HASH_IP To compile it as a module, choose M here. If unsure, say N. +config IP_SET_HASH_IPMARK + tristate "hash:ip,mark set support" + depends on IP_SET + help + This option adds the hash:ip,mark set type support, by which one + can store IPv4/IPv6 address and mark pairs. + + To compile it as a module, choose M here. If unsure, say N. + config IP_SET_HASH_IPPORT tristate "hash:ip,port set support" depends on IP_SET diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile index 44b2d38476fa..231f10196cb9 100644 --- a/net/netfilter/ipset/Makefile +++ b/net/netfilter/ipset/Makefile @@ -14,6 +14,7 @@ obj-$(CONFIG_IP_SET_BITMAP_PORT) += ip_set_bitmap_port.o # hash types obj-$(CONFIG_IP_SET_HASH_IP) += ip_set_hash_ip.o +obj-$(CONFIG_IP_SET_HASH_IPMARK) += ip_set_hash_ipmark.o obj-$(CONFIG_IP_SET_HASH_IPPORT) += ip_set_hash_ipport.o obj-$(CONFIG_IP_SET_HASH_IPPORTIP) += ip_set_hash_ipportip.o obj-$(CONFIG_IP_SET_HASH_IPPORTNET) += ip_set_hash_ipportnet.o diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index de770ec39e51..117208321f16 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -54,10 +54,10 @@ MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); /* When the nfnl mutex is held: */ -#define nfnl_dereference(p) \ +#define ip_set_dereference(p) \ rcu_dereference_protected(p, 1) -#define nfnl_set(inst, id) \ - nfnl_dereference((inst)->ip_set_list)[id] +#define ip_set(inst, id) \ + ip_set_dereference((inst)->ip_set_list)[id] /* * The set types are implemented in modules and registered set types @@ -368,6 +368,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len) if (tb[IPSET_ATTR_CADT_FLAGS]) cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_WITH_FORCEADD) + set->flags |= IPSET_CREATE_FLAG_FORCEADD; for (id = 0; id < IPSET_EXT_ID_MAX; id++) { if (!add_extension(id, cadt_flags, tb)) continue; @@ -510,7 +512,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, if (opt->dim < set->type->dimension || !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) - return 0; + return -IPSET_ERR_TYPE_MISMATCH; write_lock_bh(&set->lock); ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt); @@ -533,7 +535,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, if (opt->dim < set->type->dimension || !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) - return 0; + return -IPSET_ERR_TYPE_MISMATCH; write_lock_bh(&set->lock); ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt); @@ -640,7 +642,7 @@ ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index) return IPSET_INVALID_ID; nfnl_lock(NFNL_SUBSYS_IPSET); - set = nfnl_set(inst, index); + set = ip_set(inst, index); if (set) __ip_set_get(set); else @@ -666,7 +668,7 @@ ip_set_nfnl_put(struct net *net, ip_set_id_t index) nfnl_lock(NFNL_SUBSYS_IPSET); if (!inst->is_deleted) { /* already deleted from ip_set_net_exit() */ - set = nfnl_set(inst, index); + set = ip_set(inst, index); if (set != NULL) __ip_set_put(set); } @@ -734,7 +736,7 @@ find_set_and_id(struct ip_set_net *inst, const char *name, ip_set_id_t *id) *id = IPSET_INVALID_ID; for (i = 0; i < inst->ip_set_max; i++) { - set = nfnl_set(inst, i); + set = ip_set(inst, i); if (set != NULL && STREQ(set->name, name)) { *id = i; break; @@ -760,7 +762,7 @@ find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index, *index = IPSET_INVALID_ID; for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); + s = ip_set(inst, i); if (s == NULL) { if (*index == IPSET_INVALID_ID) *index = i; @@ -883,7 +885,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ - tmp = nfnl_dereference(inst->ip_set_list); + tmp = ip_set_dereference(inst->ip_set_list); memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max); rcu_assign_pointer(inst->ip_set_list, list); /* Make sure all current packets have passed through */ @@ -900,7 +902,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, * Finally! Add our shiny new set to the list, and be done. */ pr_debug("create: '%s' created with index %u!\n", set->name, index); - nfnl_set(inst, index) = set; + ip_set(inst, index) = set; return ret; @@ -925,10 +927,10 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = { static void ip_set_destroy_set(struct ip_set_net *inst, ip_set_id_t index) { - struct ip_set *set = nfnl_set(inst, index); + struct ip_set *set = ip_set(inst, index); pr_debug("set: %s\n", set->name); - nfnl_set(inst, index) = NULL; + ip_set(inst, index) = NULL; /* Must call it without holding any lock */ set->variant->destroy(set); @@ -962,7 +964,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); + s = ip_set(inst, i); if (s != NULL && s->ref) { ret = -IPSET_ERR_BUSY; goto out; @@ -970,7 +972,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, } read_unlock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); + s = ip_set(inst, i); if (s != NULL) ip_set_destroy_set(inst, i); } @@ -1020,7 +1022,7 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb, if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); + s = ip_set(inst, i); if (s != NULL) ip_set_flush_set(s); } @@ -1074,7 +1076,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb, name2 = nla_data(attr[IPSET_ATTR_SETNAME2]); for (i = 0; i < inst->ip_set_max; i++) { - s = nfnl_set(inst, i); + s = ip_set(inst, i); if (s != NULL && STREQ(s->name, name2)) { ret = -IPSET_ERR_EXIST_SETNAME2; goto out; @@ -1134,8 +1136,8 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, write_lock_bh(&ip_set_ref_lock); swap(from->ref, to->ref); - nfnl_set(inst, from_id) = to; - nfnl_set(inst, to_id) = from; + ip_set(inst, from_id) = to; + ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); return 0; @@ -1157,7 +1159,7 @@ ip_set_dump_done(struct netlink_callback *cb) struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET]; if (cb->args[IPSET_CB_ARG0]) { pr_debug("release set %s\n", - nfnl_set(inst, cb->args[IPSET_CB_INDEX])->name); + ip_set(inst, cb->args[IPSET_CB_INDEX])->name); __ip_set_put_byindex(inst, (ip_set_id_t) cb->args[IPSET_CB_INDEX]); } @@ -1254,7 +1256,7 @@ dump_last: dump_type, dump_flags, cb->args[IPSET_CB_INDEX]); for (; cb->args[IPSET_CB_INDEX] < max; cb->args[IPSET_CB_INDEX]++) { index = (ip_set_id_t) cb->args[IPSET_CB_INDEX]; - set = nfnl_set(inst, index); + set = ip_set(inst, index); if (set == NULL) { if (dump_type == DUMP_ONE) { ret = -ENOENT; @@ -1332,7 +1334,7 @@ next_set: release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[IPSET_CB_ARG0]) { - pr_debug("release set %s\n", nfnl_set(inst, index)->name); + pr_debug("release set %s\n", ip_set(inst, index)->name); __ip_set_put_byindex(inst, index); cb->args[IPSET_CB_ARG0] = 0; } @@ -1887,7 +1889,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) find_set_and_id(inst, req_get->set.name, &id); req_get->set.index = id; if (id != IPSET_INVALID_ID) - req_get->family = nfnl_set(inst, id)->family; + req_get->family = ip_set(inst, id)->family; nfnl_unlock(NFNL_SUBSYS_IPSET); goto copy; } @@ -1901,7 +1903,7 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) goto done; } nfnl_lock(NFNL_SUBSYS_IPSET); - set = nfnl_set(inst, req_get->set.index); + set = ip_set(inst, req_get->set.index); strncpy(req_get->set.name, set ? set->name : "", IPSET_MAXNAMELEN); nfnl_unlock(NFNL_SUBSYS_IPSET); @@ -1945,7 +1947,6 @@ ip_set_net_init(struct net *net) return -ENOMEM; inst->is_deleted = 0; rcu_assign_pointer(inst->ip_set_list, list); - pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL); return 0; } @@ -1960,7 +1961,7 @@ ip_set_net_exit(struct net *net) inst->is_deleted = 1; /* flag for ip_set_nfnl_put */ for (i = 0; i < inst->ip_set_max; i++) { - set = nfnl_set(inst, i); + set = ip_set(inst, i); if (set != NULL) ip_set_destroy_set(inst, i); } @@ -1996,6 +1997,7 @@ ip_set_init(void) nfnetlink_subsys_unregister(&ip_set_netlink_subsys); return ret; } + pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL); return 0; } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index be6932ad3a86..61c7fb052802 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -263,6 +263,9 @@ struct htype { u32 maxelem; /* max elements in the hash */ u32 elements; /* current element (vs timeout) */ u32 initval; /* random jhash init value */ +#ifdef IP_SET_HASH_WITH_MARKMASK + u32 markmask; /* markmask value for mark mask to store */ +#endif struct timer_list gc; /* garbage collection when timeout enabled */ struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_MULTI @@ -454,6 +457,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b) #ifdef IP_SET_HASH_WITH_NETMASK x->netmask == y->netmask && #endif +#ifdef IP_SET_HASH_WITH_MARKMASK + x->markmask == y->markmask && +#endif a->extensions == b->extensions; } @@ -627,6 +633,18 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, bool flag_exist = flags & IPSET_FLAG_EXIST; u32 key, multi = 0; + if (h->elements >= h->maxelem && SET_WITH_FORCEADD(set)) { + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + n = hbucket(t,key); + if (n->pos) { + /* Choosing the first entry in the array to replace */ + j = 0; + goto reuse_slot; + } + rcu_read_unlock_bh(); + } if (SET_WITH_TIMEOUT(set) && h->elements >= h->maxelem) /* FIXME: when set is full, we slow down here */ mtype_expire(set, h, NLEN(set->family), set->dsize); @@ -908,6 +926,10 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask)) goto nla_put_failure; #endif +#ifdef IP_SET_HASH_WITH_MARKMASK + if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask)) + goto nla_put_failure; +#endif if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize))) goto nla_put_failure; @@ -1016,6 +1038,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) { u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; +#ifdef IP_SET_HASH_WITH_MARKMASK + u32 markmask; +#endif u8 hbits; #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; @@ -1026,6 +1051,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6)) return -IPSET_ERR_INVALID_FAMILY; + +#ifdef IP_SET_HASH_WITH_MARKMASK + markmask = 0xffffffff; +#endif #ifdef IP_SET_HASH_WITH_NETMASK netmask = set->family == NFPROTO_IPV4 ? 32 : 128; pr_debug("Create set %s with family %s\n", @@ -1034,6 +1063,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || +#ifdef IP_SET_HASH_WITH_MARKMASK + !ip_set_optattr_netorder(tb, IPSET_ATTR_MARKMASK) || +#endif !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; @@ -1057,6 +1089,14 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, return -IPSET_ERR_INVALID_NETMASK; } #endif +#ifdef IP_SET_HASH_WITH_MARKMASK + if (tb[IPSET_ATTR_MARKMASK]) { + markmask = ntohl(nla_get_u32(tb[IPSET_ATTR_MARKMASK])); + + if ((markmask > 4294967295u) || markmask == 0) + return -IPSET_ERR_INVALID_MARKMASK; + } +#endif hsize = sizeof(*h); #ifdef IP_SET_HASH_WITH_NETS @@ -1071,6 +1111,9 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #ifdef IP_SET_HASH_WITH_NETMASK h->netmask = netmask; #endif +#ifdef IP_SET_HASH_WITH_MARKMASK + h->markmask = markmask; +#endif get_random_bytes(&h->initval, sizeof(h->initval)); set->timeout = IPSET_NO_TIMEOUT; diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index e65fc2423d56..dd40607f878e 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -25,7 +25,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 Counters support */ -#define IPSET_TYPE_REV_MAX 2 /* Comments support */ +/* 2 Comments support */ +#define IPSET_TYPE_REV_MAX 3 /* Forceadd support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c new file mode 100644 index 000000000000..4eff0a297254 --- /dev/null +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -0,0 +1,321 @@ +/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * Copyright (C) 2013 Smoothwall Ltd. <vytas.dauksa@smoothwall.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* Kernel module implementing an IP set type: the hash:ip,mark type */ + +#include <linux/jhash.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/random.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/netlink.h> +#include <net/tcp.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_hash.h> + +#define IPSET_TYPE_REV_MIN 0 +#define IPSET_TYPE_REV_MAX 1 /* Forceadd support */ + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>"); +IP_SET_MODULE_DESC("hash:ip,mark", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); +MODULE_ALIAS("ip_set_hash:ip,mark"); + +/* Type specific function prefix */ +#define HTYPE hash_ipmark +#define IP_SET_HASH_WITH_MARKMASK + +/* IPv4 variant */ + +/* Member elements */ +struct hash_ipmark4_elem { + __be32 ip; + __u32 mark; +}; + +/* Common functions */ + +static inline bool +hash_ipmark4_data_equal(const struct hash_ipmark4_elem *ip1, + const struct hash_ipmark4_elem *ip2, + u32 *multi) +{ + return ip1->ip == ip2->ip && + ip1->mark == ip2->mark; +} + +static bool +hash_ipmark4_data_list(struct sk_buff *skb, + const struct hash_ipmark4_elem *data) +{ + if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || + nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return 1; +} + +static inline void +hash_ipmark4_data_next(struct hash_ipmark4_elem *next, + const struct hash_ipmark4_elem *d) +{ + next->ip = d->ip; +} + +#define MTYPE hash_ipmark4 +#define PF 4 +#define HOST_MASK 32 +#define HKEY_DATALEN sizeof(struct hash_ipmark4_elem) +#include "ip_set_hash_gen.h" + +static int +hash_ipmark4_kadt(struct ip_set *set, const struct sk_buff *skb, + const struct xt_action_param *par, + enum ipset_adt adt, struct ip_set_adt_opt *opt) +{ + const struct hash_ipmark *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipmark4_elem e = { }; + struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); + + e.mark = skb->mark; + e.mark &= h->markmask; + + ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); + return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); +} + +static int +hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) +{ + const struct hash_ipmark *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipmark4_elem e = { }; + struct ip_set_ext ext = IP_SET_INIT_UEXT(set); + u32 ip, ip_to = 0; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) || + ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK])); + e.mark &= h->markmask; + + if (adt == IPSET_TEST || + !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) { + ret = adtfn(set, &e, &ext, &ext, flags); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + ip_to = ip = ntohl(e.ip); + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); + if (ret) + return ret; + if (ip > ip_to) + swap(ip, ip_to); + } else if (tb[IPSET_ATTR_CIDR]) { + u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + + if (!cidr || cidr > 32) + return -IPSET_ERR_INVALID_CIDR; + ip_set_mask_from_to(ip, ip_to, cidr); + } + + if (retried) + ip = ntohl(h->next.ip); + for (; !before(ip_to, ip); ip++) { + e.ip = htonl(ip); + ret = adtfn(set, &e, &ext, &ext, flags); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + return ret; +} + +/* IPv6 variant */ + +struct hash_ipmark6_elem { + union nf_inet_addr ip; + __u32 mark; +}; + +/* Common functions */ + +static inline bool +hash_ipmark6_data_equal(const struct hash_ipmark6_elem *ip1, + const struct hash_ipmark6_elem *ip2, + u32 *multi) +{ + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && + ip1->mark == ip2->mark; +} + +static bool +hash_ipmark6_data_list(struct sk_buff *skb, + const struct hash_ipmark6_elem *data) +{ + if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || + nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark))) + goto nla_put_failure; + return 0; + +nla_put_failure: + return 1; +} + +static inline void +hash_ipmark6_data_next(struct hash_ipmark4_elem *next, + const struct hash_ipmark6_elem *d) +{ +} + +#undef MTYPE +#undef PF +#undef HOST_MASK +#undef HKEY_DATALEN + +#define MTYPE hash_ipmark6 +#define PF 6 +#define HOST_MASK 128 +#define HKEY_DATALEN sizeof(struct hash_ipmark6_elem) +#define IP_SET_EMIT_CREATE +#include "ip_set_hash_gen.h" + + +static int +hash_ipmark6_kadt(struct ip_set *set, const struct sk_buff *skb, + const struct xt_action_param *par, + enum ipset_adt adt, struct ip_set_adt_opt *opt) +{ + const struct hash_ipmark *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipmark6_elem e = { }; + struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); + + e.mark = skb->mark; + e.mark &= h->markmask; + + ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); + return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); +} + +static int +hash_ipmark6_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) +{ + const struct hash_ipmark *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_ipmark6_elem e = { }; + struct ip_set_ext ext = IP_SET_INIT_UEXT(set); + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) || + tb[IPSET_ATTR_IP_TO] || + tb[IPSET_ATTR_CIDR])) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) || + ip_set_get_extensions(set, tb, &ext); + if (ret) + return ret; + + e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK])); + e.mark &= h->markmask; + + if (adt == IPSET_TEST) { + ret = adtfn(set, &e, &ext, &ext, flags); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + ret = adtfn(set, &e, &ext, &ext, flags); + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + + return ret; +} + +static struct ip_set_type hash_ipmark_type __read_mostly = { + .name = "hash:ip,mark", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP | IPSET_TYPE_MARK, + .dimension = IPSET_DIM_TWO, + .family = NFPROTO_UNSPEC, + .revision_min = IPSET_TYPE_REV_MIN, + .revision_max = IPSET_TYPE_REV_MAX, + .create = hash_ipmark_create, + .create_policy = { + [IPSET_ATTR_MARKMASK] = { .type = NLA_U32 }, + [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, + [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, + [IPSET_ATTR_MARK] = { .type = NLA_U32 }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, + [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, + [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING }, + }, + .me = THIS_MODULE, +}; + +static int __init +hash_ipmark_init(void) +{ + return ip_set_type_register(&hash_ipmark_type); +} + +static void __exit +hash_ipmark_fini(void) +{ + ip_set_type_unregister(&hash_ipmark_type); +} + +module_init(hash_ipmark_init); +module_exit(hash_ipmark_fini); diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 525a595dd1fe..7597b82a8b03 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -27,7 +27,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Counters support added */ -#define IPSET_TYPE_REV_MAX 3 /* Comments support added */ +/* 3 Comments support added */ +#define IPSET_TYPE_REV_MAX 4 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index f5636631466e..672655ffd573 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -27,7 +27,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Counters support added */ -#define IPSET_TYPE_REV_MAX 3 /* Comments support added */ +/* 3 Comments support added */ +#define IPSET_TYPE_REV_MAX 4 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 5d87fe8a41ff..7308d84f9277 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -29,7 +29,8 @@ /* 2 Range as input support for IPv4 added */ /* 3 nomatch flag support added */ /* 4 Counters support added */ -#define IPSET_TYPE_REV_MAX 5 /* Comments support added */ +/* 5 Comments support added */ +#define IPSET_TYPE_REV_MAX 6 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 8295cf4f9fdc..4c7d495783a3 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -26,7 +26,8 @@ /* 1 Range as input support for IPv4 added */ /* 2 nomatch flag support added */ /* 3 Counters support added */ -#define IPSET_TYPE_REV_MAX 4 /* Comments support added */ +/* 4 Comments support added */ +#define IPSET_TYPE_REV_MAX 5 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index b827a0f1f351..db2606805b35 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -27,7 +27,8 @@ /* 1 nomatch flag support added */ /* 2 /0 support added */ /* 3 Counters support added */ -#define IPSET_TYPE_REV_MAX 4 /* Comments support added */ +/* 4 Comments support added */ +#define IPSET_TYPE_REV_MAX 5 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 6226803fc490..3e99987e4bf2 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -24,7 +24,7 @@ #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 -#define IPSET_TYPE_REV_MAX 0 +#define IPSET_TYPE_REV_MAX 1 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>"); @@ -112,10 +112,10 @@ hash_netnet4_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void @@ -334,10 +334,10 @@ hash_netnet6_data_list(struct sk_buff *skb, (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; - return 0; + return false; nla_put_failure: - return 1; + return true; } static inline void diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 7097fb0141bf..1c645fbd09c7 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -28,7 +28,8 @@ /* 2 Range as input support for IPv4 added */ /* 3 nomatch flag support added */ /* 4 Counters support added */ -#define IPSET_TYPE_REV_MAX 5 /* Comments support added */ +/* 5 Comments support added */ +#define IPSET_TYPE_REV_MAX 6 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 703d1192a6a2..c0d2ba73f8b2 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -25,7 +25,8 @@ #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 -#define IPSET_TYPE_REV_MAX 0 /* Comments support added */ +/* 0 Comments support added */ +#define IPSET_TYPE_REV_MAX 1 /* Forceadd support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>"); diff --git a/net/netfilter/ipset/pfxlen.c b/net/netfilter/ipset/pfxlen.c index 4f29fa97044b..04d15fdc99ee 100644 --- a/net/netfilter/ipset/pfxlen.c +++ b/net/netfilter/ipset/pfxlen.c @@ -7,8 +7,8 @@ #define E(a, b, c, d) \ {.ip6 = { \ - __constant_htonl(a), __constant_htonl(b), \ - __constant_htonl(c), __constant_htonl(d), \ + htonl(a), htonl(b), \ + htonl(c), htonl(d), \ } } /* diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 35be035ee0ce..c42e83d2751c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2177,10 +2177,10 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) __u64 inbytes, outbytes; do { - start = u64_stats_fetch_begin_bh(&u->syncp); + start = u64_stats_fetch_begin_irq(&u->syncp); inbytes = u->ustats.inbytes; outbytes = u->ustats.outbytes; - } while (u64_stats_fetch_retry_bh(&u->syncp, start)); + } while (u64_stats_fetch_retry_irq(&u->syncp, start)); seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n", i, u->ustats.conns, u->ustats.inpkts, @@ -3580,7 +3580,7 @@ out: } -static const struct genl_ops ip_vs_genl_ops[] __read_mostly = { +static const struct genl_ops ip_vs_genl_ops[] = { { .cmd = IPVS_CMD_NEW_SERVICE, .flags = GENL_ADMIN_PERM, diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index ca056a331e60..547ff33c1efd 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -238,7 +238,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc) spin_lock_bh(&svc->sched_lock); tbl->dead = 1; - for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) { + for (i = 0; i < IP_VS_LBLC_TAB_SIZE; i++) { hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) { ip_vs_lblc_del(en); atomic_dec(&tbl->entries); @@ -265,7 +265,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) unsigned long now = jiffies; int i, j; - for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) { + for (i = 0, j = tbl->rover; i < IP_VS_LBLC_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLC_TAB_MASK; spin_lock(&svc->sched_lock); @@ -321,7 +321,7 @@ static void ip_vs_lblc_check_expire(unsigned long data) if (goal > tbl->max_size/2) goal = tbl->max_size/2; - for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) { + for (i = 0, j = tbl->rover; i < IP_VS_LBLC_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLC_TAB_MASK; spin_lock(&svc->sched_lock); @@ -340,7 +340,7 @@ static void ip_vs_lblc_check_expire(unsigned long data) tbl->rover = j; out: - mod_timer(&tbl->periodic_timer, jiffies+CHECK_EXPIRE_INTERVAL); + mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL); } @@ -363,7 +363,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) /* * Initialize the hash buckets */ - for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) { + for (i = 0; i < IP_VS_LBLC_TAB_SIZE; i++) { INIT_HLIST_HEAD(&tbl->bucket[i]); } tbl->max_size = IP_VS_LBLC_TAB_SIZE*16; @@ -536,8 +536,7 @@ out: /* * IPVS LBLC Scheduler structure */ -static struct ip_vs_scheduler ip_vs_lblc_scheduler = -{ +static struct ip_vs_scheduler ip_vs_lblc_scheduler = { .name = "lblc", .refcnt = ATOMIC_INIT(0), .module = THIS_MODULE, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 356bef519fe5..6dba48efe01e 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -60,8 +60,59 @@ int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct, const struct nlattr *attr) __read_mostly; EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook); -DEFINE_SPINLOCK(nf_conntrack_lock); -EXPORT_SYMBOL_GPL(nf_conntrack_lock); +__cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; +EXPORT_SYMBOL_GPL(nf_conntrack_locks); + +__cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock); +EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock); + +static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2) +{ + h1 %= CONNTRACK_LOCKS; + h2 %= CONNTRACK_LOCKS; + spin_unlock(&nf_conntrack_locks[h1]); + if (h1 != h2) + spin_unlock(&nf_conntrack_locks[h2]); +} + +/* return true if we need to recompute hashes (in case hash table was resized) */ +static bool nf_conntrack_double_lock(struct net *net, unsigned int h1, + unsigned int h2, unsigned int sequence) +{ + h1 %= CONNTRACK_LOCKS; + h2 %= CONNTRACK_LOCKS; + if (h1 <= h2) { + spin_lock(&nf_conntrack_locks[h1]); + if (h1 != h2) + spin_lock_nested(&nf_conntrack_locks[h2], + SINGLE_DEPTH_NESTING); + } else { + spin_lock(&nf_conntrack_locks[h2]); + spin_lock_nested(&nf_conntrack_locks[h1], + SINGLE_DEPTH_NESTING); + } + if (read_seqcount_retry(&net->ct.generation, sequence)) { + nf_conntrack_double_unlock(h1, h2); + return true; + } + return false; +} + +static void nf_conntrack_all_lock(void) +{ + int i; + + for (i = 0; i < CONNTRACK_LOCKS; i++) + spin_lock_nested(&nf_conntrack_locks[i], i); +} + +static void nf_conntrack_all_unlock(void) +{ + int i; + + for (i = 0; i < CONNTRACK_LOCKS; i++) + spin_unlock(&nf_conntrack_locks[i]); +} unsigned int nf_conntrack_htable_size __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); @@ -192,6 +243,50 @@ clean_from_lists(struct nf_conn *ct) nf_ct_remove_expectations(ct); } +/* must be called with local_bh_disable */ +static void nf_ct_add_to_dying_list(struct nf_conn *ct) +{ + struct ct_pcpu *pcpu; + + /* add this conntrack to the (per cpu) dying list */ + ct->cpu = smp_processor_id(); + pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu); + + spin_lock(&pcpu->lock); + hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &pcpu->dying); + spin_unlock(&pcpu->lock); +} + +/* must be called with local_bh_disable */ +static void nf_ct_add_to_unconfirmed_list(struct nf_conn *ct) +{ + struct ct_pcpu *pcpu; + + /* add this conntrack to the (per cpu) unconfirmed list */ + ct->cpu = smp_processor_id(); + pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu); + + spin_lock(&pcpu->lock); + hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &pcpu->unconfirmed); + spin_unlock(&pcpu->lock); +} + +/* must be called with local_bh_disable */ +static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct) +{ + struct ct_pcpu *pcpu; + + /* We overload first tuple to link into unconfirmed or dying list.*/ + pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu); + + spin_lock(&pcpu->lock); + BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode)); + hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + spin_unlock(&pcpu->lock); +} + static void destroy_conntrack(struct nf_conntrack *nfct) { @@ -203,9 +298,6 @@ destroy_conntrack(struct nf_conntrack *nfct) NF_CT_ASSERT(atomic_read(&nfct->use) == 0); NF_CT_ASSERT(!timer_pending(&ct->timeout)); - /* To make sure we don't get any weird locking issues here: - * destroy_conntrack() MUST NOT be called with a write lock - * to nf_conntrack_lock!!! -HW */ rcu_read_lock(); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); if (l4proto && l4proto->destroy) @@ -213,19 +305,18 @@ destroy_conntrack(struct nf_conntrack *nfct) rcu_read_unlock(); - spin_lock_bh(&nf_conntrack_lock); + local_bh_disable(); /* Expectations will have been removed in clean_from_lists, * except TFTP can create an expectation on the first packet, * before connection is in the list, so we need to clean here, - * too. */ + * too. + */ nf_ct_remove_expectations(ct); - /* We overload first tuple to link into unconfirmed or dying list.*/ - BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode)); - hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + nf_ct_del_from_dying_or_unconfirmed_list(ct); NF_CT_STAT_INC(net, delete); - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); if (ct->master) nf_ct_put(ct->master); @@ -237,17 +328,28 @@ destroy_conntrack(struct nf_conntrack *nfct) static void nf_ct_delete_from_lists(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); + unsigned int hash, reply_hash; + u16 zone = nf_ct_zone(ct); + unsigned int sequence; nf_ct_helper_destroy(ct); - spin_lock_bh(&nf_conntrack_lock); - /* Inside lock so preempt is disabled on module removal path. - * Otherwise we can get spurious warnings. */ - NF_CT_STAT_INC(net, delete_list); + + local_bh_disable(); + do { + sequence = read_seqcount_begin(&net->ct.generation); + hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + reply_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); + clean_from_lists(ct); - /* add this conntrack to the dying list */ - hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &net->ct.dying); - spin_unlock_bh(&nf_conntrack_lock); + nf_conntrack_double_unlock(hash, reply_hash); + + nf_ct_add_to_dying_list(ct); + + NF_CT_STAT_INC(net, delete_list); + local_bh_enable(); } static void death_by_event(unsigned long ul_conntrack) @@ -331,8 +433,6 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, * Warning : * - Caller must take a reference on returned object * and recheck nf_ct_tuple_equal(tuple, &h->tuple) - * OR - * - Caller must lock nf_conntrack_lock before calling this function */ static struct nf_conntrack_tuple_hash * ____nf_conntrack_find(struct net *net, u16 zone, @@ -408,32 +508,36 @@ EXPORT_SYMBOL_GPL(nf_conntrack_find_get); static void __nf_conntrack_hash_insert(struct nf_conn *ct, unsigned int hash, - unsigned int repl_hash) + unsigned int reply_hash) { struct net *net = nf_ct_net(ct); hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, &net->ct.hash[hash]); hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode, - &net->ct.hash[repl_hash]); + &net->ct.hash[reply_hash]); } int nf_conntrack_hash_check_insert(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); - unsigned int hash, repl_hash; + unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; u16 zone; + unsigned int sequence; zone = nf_ct_zone(ct); - hash = hash_conntrack(net, zone, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(net, zone, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - spin_lock_bh(&nf_conntrack_lock); + local_bh_disable(); + do { + sequence = read_seqcount_begin(&net->ct.generation); + hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + reply_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); /* See if there's one in the list already, including reverse */ hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) @@ -441,7 +545,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) &h->tuple) && zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; - hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) + hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, &h->tuple) && zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) @@ -451,15 +555,16 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) smp_wmb(); /* The caller holds a reference to this object */ atomic_set(&ct->ct_general.use, 2); - __nf_conntrack_hash_insert(ct, hash, repl_hash); + __nf_conntrack_hash_insert(ct, hash, reply_hash); + nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert); - spin_unlock_bh(&nf_conntrack_lock); - + local_bh_enable(); return 0; out: + nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert_failed); - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); return -EEXIST; } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); @@ -467,15 +572,22 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); /* deletion from this larval template list happens via nf_ct_put() */ void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl) { + struct ct_pcpu *pcpu; + __set_bit(IPS_TEMPLATE_BIT, &tmpl->status); __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); nf_conntrack_get(&tmpl->ct_general); - spin_lock_bh(&nf_conntrack_lock); + /* add this conntrack to the (per cpu) tmpl list */ + local_bh_disable(); + tmpl->cpu = smp_processor_id(); + pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu); + + spin_lock(&pcpu->lock); /* Overload tuple linked list to put us in template list. */ hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &net->ct.tmpl); - spin_unlock_bh(&nf_conntrack_lock); + &pcpu->tmpl); + spin_unlock_bh(&pcpu->lock); } EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); @@ -483,7 +595,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); int __nf_conntrack_confirm(struct sk_buff *skb) { - unsigned int hash, repl_hash; + unsigned int hash, reply_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conn_help *help; @@ -492,6 +604,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) enum ip_conntrack_info ctinfo; struct net *net; u16 zone; + unsigned int sequence; ct = nf_ct_get(skb, &ctinfo); net = nf_ct_net(ct); @@ -504,31 +617,37 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_ACCEPT; zone = nf_ct_zone(ct); - /* reuse the hash saved before */ - hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; - hash = hash_bucket(hash, net); - repl_hash = hash_conntrack(net, zone, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + local_bh_disable(); + + do { + sequence = read_seqcount_begin(&net->ct.generation); + /* reuse the hash saved before */ + hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; + hash = hash_bucket(hash, net); + reply_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + + } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence)); /* We're not in hash table, and we refuse to set up related - connections for unconfirmed conns. But packet copies and - REJECT will give spurious warnings here. */ + * connections for unconfirmed conns. But packet copies and + * REJECT will give spurious warnings here. + */ /* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */ /* No external references means no one else could have - confirmed us. */ + * confirmed us. + */ NF_CT_ASSERT(!nf_ct_is_confirmed(ct)); pr_debug("Confirming conntrack %p\n", ct); - - spin_lock_bh(&nf_conntrack_lock); - /* We have to check the DYING flag inside the lock to prevent a race against nf_ct_get_next_corpse() possibly called from user context, else we insert an already 'dead' hash, blocking further use of that particular connection -JM */ if (unlikely(nf_ct_is_dying(ct))) { - spin_unlock_bh(&nf_conntrack_lock); + nf_conntrack_double_unlock(hash, reply_hash); + local_bh_enable(); return NF_ACCEPT; } @@ -540,14 +659,13 @@ __nf_conntrack_confirm(struct sk_buff *skb) &h->tuple) && zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; - hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) + hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, &h->tuple) && zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; - /* Remove from unconfirmed list */ - hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + nf_ct_del_from_dying_or_unconfirmed_list(ct); /* Timer relative to confirmation time, not original setting time, otherwise we'd get timer wrap in @@ -570,9 +688,10 @@ __nf_conntrack_confirm(struct sk_buff *skb) * guarantee that no other CPU can find the conntrack before the above * stores are visible. */ - __nf_conntrack_hash_insert(ct, hash, repl_hash); + __nf_conntrack_hash_insert(ct, hash, reply_hash); + nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert); - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); help = nfct_help(ct); if (help && help->helper) @@ -583,8 +702,9 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_ACCEPT; out: + nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert_failed); - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); return NF_DROP; } EXPORT_SYMBOL_GPL(__nf_conntrack_confirm); @@ -627,39 +747,48 @@ EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken); /* There's a small race here where we may free a just-assured connection. Too bad: we're in trouble anyway. */ -static noinline int early_drop(struct net *net, unsigned int hash) +static noinline int early_drop(struct net *net, unsigned int _hash) { /* Use oldest entry, which is roughly LRU */ struct nf_conntrack_tuple_hash *h; struct nf_conn *ct = NULL, *tmp; struct hlist_nulls_node *n; - unsigned int i, cnt = 0; + unsigned int i = 0, cnt = 0; int dropped = 0; + unsigned int hash, sequence; + spinlock_t *lockp; - rcu_read_lock(); - for (i = 0; i < net->ct.htable_size; i++) { + local_bh_disable(); +restart: + sequence = read_seqcount_begin(&net->ct.generation); + hash = hash_bucket(_hash, net); + for (; i < net->ct.htable_size; i++) { + lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS]; + spin_lock(lockp); + if (read_seqcount_retry(&net->ct.generation, sequence)) { + spin_unlock(lockp); + goto restart; + } hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { tmp = nf_ct_tuplehash_to_ctrack(h); - if (!test_bit(IPS_ASSURED_BIT, &tmp->status)) + if (!test_bit(IPS_ASSURED_BIT, &tmp->status) && + !nf_ct_is_dying(tmp) && + atomic_inc_not_zero(&tmp->ct_general.use)) { ct = tmp; + break; + } cnt++; } - if (ct != NULL) { - if (likely(!nf_ct_is_dying(ct) && - atomic_inc_not_zero(&ct->ct_general.use))) - break; - else - ct = NULL; - } + hash = (hash + 1) % net->ct.htable_size; + spin_unlock(lockp); - if (cnt >= NF_CT_EVICTION_RANGE) + if (ct || cnt >= NF_CT_EVICTION_RANGE) break; - hash = (hash + 1) % net->ct.htable_size; } - rcu_read_unlock(); + local_bh_enable(); if (!ct) return dropped; @@ -708,7 +837,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone, if (nf_conntrack_max && unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) { - if (!early_drop(net, hash_bucket(hash, net))) { + if (!early_drop(net, hash)) { atomic_dec(&net->ct.count); net_warn_ratelimited("nf_conntrack: table full, dropping packet\n"); return ERR_PTR(-ENOMEM); @@ -805,7 +934,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conn_help *help; struct nf_conntrack_tuple repl_tuple; struct nf_conntrack_ecache *ecache; - struct nf_conntrack_expect *exp; + struct nf_conntrack_expect *exp = NULL; u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; struct nf_conn_timeout *timeout_ext; unsigned int *timeouts; @@ -849,42 +978,44 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, ecache ? ecache->expmask : 0, GFP_ATOMIC); - spin_lock_bh(&nf_conntrack_lock); - exp = nf_ct_find_expectation(net, zone, tuple); - if (exp) { - pr_debug("conntrack: expectation arrives ct=%p exp=%p\n", - ct, exp); - /* Welcome, Mr. Bond. We've been expecting you... */ - __set_bit(IPS_EXPECTED_BIT, &ct->status); - ct->master = exp->master; - if (exp->helper) { - help = nf_ct_helper_ext_add(ct, exp->helper, - GFP_ATOMIC); - if (help) - rcu_assign_pointer(help->helper, exp->helper); - } + local_bh_disable(); + if (net->ct.expect_count) { + spin_lock(&nf_conntrack_expect_lock); + exp = nf_ct_find_expectation(net, zone, tuple); + if (exp) { + pr_debug("conntrack: expectation arrives ct=%p exp=%p\n", + ct, exp); + /* Welcome, Mr. Bond. We've been expecting you... */ + __set_bit(IPS_EXPECTED_BIT, &ct->status); + /* exp->master safe, refcnt bumped in nf_ct_find_expectation */ + ct->master = exp->master; + if (exp->helper) { + help = nf_ct_helper_ext_add(ct, exp->helper, + GFP_ATOMIC); + if (help) + rcu_assign_pointer(help->helper, exp->helper); + } #ifdef CONFIG_NF_CONNTRACK_MARK - ct->mark = exp->master->mark; + ct->mark = exp->master->mark; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK - ct->secmark = exp->master->secmark; + ct->secmark = exp->master->secmark; #endif - nf_conntrack_get(&ct->master->ct_general); - NF_CT_STAT_INC(net, expect_new); - } else { + NF_CT_STAT_INC(net, expect_new); + } + spin_unlock(&nf_conntrack_expect_lock); + } + if (!exp) { __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC); NF_CT_STAT_INC(net, new); } /* Now it is inserted into the unconfirmed list, bump refcount */ nf_conntrack_get(&ct->ct_general); + nf_ct_add_to_unconfirmed_list(ct); - /* Overload tuple linked list to put us in unconfirmed list. */ - hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &net->ct.unconfirmed); - - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); if (exp) { if (exp->expectfn) @@ -1254,27 +1385,42 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct hlist_nulls_node *n; + int cpu; + spinlock_t *lockp; - spin_lock_bh(&nf_conntrack_lock); for (; *bucket < net->ct.htable_size; (*bucket)++) { - hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { - if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) - continue; + lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS]; + local_bh_disable(); + spin_lock(lockp); + if (*bucket < net->ct.htable_size) { + hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { + if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) + continue; + ct = nf_ct_tuplehash_to_ctrack(h); + if (iter(ct, data)) + goto found; + } + } + spin_unlock(lockp); + local_bh_enable(); + } + + for_each_possible_cpu(cpu) { + struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + + spin_lock_bh(&pcpu->lock); + hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) - goto found; + set_bit(IPS_DYING_BIT, &ct->status); } + spin_unlock_bh(&pcpu->lock); } - hlist_nulls_for_each_entry(h, n, &net->ct.unconfirmed, hnnode) { - ct = nf_ct_tuplehash_to_ctrack(h); - if (iter(ct, data)) - set_bit(IPS_DYING_BIT, &ct->status); - } - spin_unlock_bh(&nf_conntrack_lock); return NULL; found: atomic_inc(&ct->ct_general.use); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock(lockp); + local_bh_enable(); return ct; } @@ -1323,14 +1469,19 @@ static void nf_ct_release_dying_list(struct net *net) struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct hlist_nulls_node *n; + int cpu; - spin_lock_bh(&nf_conntrack_lock); - hlist_nulls_for_each_entry(h, n, &net->ct.dying, hnnode) { - ct = nf_ct_tuplehash_to_ctrack(h); - /* never fails to remove them, no listeners at this point */ - nf_ct_kill(ct); + for_each_possible_cpu(cpu) { + struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + + spin_lock_bh(&pcpu->lock); + hlist_nulls_for_each_entry(h, n, &pcpu->dying, hnnode) { + ct = nf_ct_tuplehash_to_ctrack(h); + /* never fails to remove them, no listeners at this point */ + nf_ct_kill(ct); + } + spin_unlock_bh(&pcpu->lock); } - spin_unlock_bh(&nf_conntrack_lock); } static int untrack_refs(void) @@ -1417,6 +1568,7 @@ i_see_dead_people: kmem_cache_destroy(net->ct.nf_conntrack_cachep); kfree(net->ct.slabname); free_percpu(net->ct.stat); + free_percpu(net->ct.pcpu_lists); } } @@ -1469,12 +1621,16 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) if (!hash) return -ENOMEM; + local_bh_disable(); + nf_conntrack_all_lock(); + write_seqcount_begin(&init_net.ct.generation); + /* Lookups in the old hash might happen in parallel, which means we * might get false negatives during connection lookup. New connections * created because of a false negative won't make it into the hash - * though since that required taking the lock. + * though since that required taking the locks. */ - spin_lock_bh(&nf_conntrack_lock); + for (i = 0; i < init_net.ct.htable_size; i++) { while (!hlist_nulls_empty(&init_net.ct.hash[i])) { h = hlist_nulls_entry(init_net.ct.hash[i].first, @@ -1491,7 +1647,10 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) init_net.ct.htable_size = nf_conntrack_htable_size = hashsize; init_net.ct.hash = hash; - spin_unlock_bh(&nf_conntrack_lock); + + write_seqcount_end(&init_net.ct.generation); + nf_conntrack_all_unlock(); + local_bh_enable(); nf_ct_free_hashtable(old_hash, old_size); return 0; @@ -1513,7 +1672,10 @@ EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or); int nf_conntrack_init_start(void) { int max_factor = 8; - int ret, cpu; + int i, ret, cpu; + + for (i = 0; i < CONNTRACK_LOCKS; i++) + spin_lock_init(&nf_conntrack_locks[i]); /* Idea from tcp.c: use 1/16384 of memory. On i386: 32MB * machine has 512 buckets. >= 1GB machines have 16384 buckets. */ @@ -1629,37 +1791,43 @@ void nf_conntrack_init_end(void) int nf_conntrack_init_net(struct net *net) { - int ret; + int ret = -ENOMEM; + int cpu; atomic_set(&net->ct.count, 0); - INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL); - INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL); - INIT_HLIST_NULLS_HEAD(&net->ct.tmpl, TEMPLATE_NULLS_VAL); - net->ct.stat = alloc_percpu(struct ip_conntrack_stat); - if (!net->ct.stat) { - ret = -ENOMEM; + + net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu); + if (!net->ct.pcpu_lists) goto err_stat; + + for_each_possible_cpu(cpu) { + struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + + spin_lock_init(&pcpu->lock); + INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL); + INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL); + INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL); } + net->ct.stat = alloc_percpu(struct ip_conntrack_stat); + if (!net->ct.stat) + goto err_pcpu_lists; + net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net); - if (!net->ct.slabname) { - ret = -ENOMEM; + if (!net->ct.slabname) goto err_slabname; - } net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname, sizeof(struct nf_conn), 0, SLAB_DESTROY_BY_RCU, NULL); if (!net->ct.nf_conntrack_cachep) { printk(KERN_ERR "Unable to create nf_conn slab cache\n"); - ret = -ENOMEM; goto err_cache; } net->ct.htable_size = nf_conntrack_htable_size; net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1); if (!net->ct.hash) { - ret = -ENOMEM; printk(KERN_ERR "Unable to create nf_conntrack_hash\n"); goto err_hash; } @@ -1701,6 +1869,8 @@ err_cache: kfree(net->ct.slabname); err_slabname: free_percpu(net->ct.stat); +err_pcpu_lists: + free_percpu(net->ct.pcpu_lists); err_stat: return ret; } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 4fd1ca94fd4a..f87e8f68ad45 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -66,9 +66,9 @@ static void nf_ct_expectation_timed_out(unsigned long ul_expect) { struct nf_conntrack_expect *exp = (void *)ul_expect; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); nf_ct_unlink_expect(exp); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); nf_ct_expect_put(exp); } @@ -155,6 +155,18 @@ nf_ct_find_expectation(struct net *net, u16 zone, if (!nf_ct_is_confirmed(exp->master)) return NULL; + /* Avoid race with other CPUs, that for exp->master ct, is + * about to invoke ->destroy(), or nf_ct_delete() via timeout + * or early_drop(). + * + * The atomic_inc_not_zero() check tells: If that fails, we + * know that the ct is being destroyed. If it succeeds, we + * can be sure the ct cannot disappear underneath. + */ + if (unlikely(nf_ct_is_dying(exp->master) || + !atomic_inc_not_zero(&exp->master->ct_general.use))) + return NULL; + if (exp->flags & NF_CT_EXPECT_PERMANENT) { atomic_inc(&exp->use); return exp; @@ -162,6 +174,8 @@ nf_ct_find_expectation(struct net *net, u16 zone, nf_ct_unlink_expect(exp); return exp; } + /* Undo exp->master refcnt increase, if del_timer() failed */ + nf_ct_put(exp->master); return NULL; } @@ -177,12 +191,14 @@ void nf_ct_remove_expectations(struct nf_conn *ct) if (!help) return; + spin_lock_bh(&nf_conntrack_expect_lock); hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); } } + spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_remove_expectations); @@ -217,12 +233,12 @@ static inline int expect_matches(const struct nf_conntrack_expect *a, /* Generally a bad idea to call this: could have matched already. */ void nf_ct_unexpect_related(struct nf_conntrack_expect *exp) { - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_unexpect_related); @@ -335,7 +351,7 @@ static int nf_ct_expect_insert(struct nf_conntrack_expect *exp) setup_timer(&exp->timeout, nf_ct_expectation_timed_out, (unsigned long)exp); helper = rcu_dereference_protected(master_help->helper, - lockdep_is_held(&nf_conntrack_lock)); + lockdep_is_held(&nf_conntrack_expect_lock)); if (helper) { exp->timeout.expires = jiffies + helper->expect_policy[exp->class].timeout * HZ; @@ -395,7 +411,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) } /* Will be over limit? */ helper = rcu_dereference_protected(master_help->helper, - lockdep_is_held(&nf_conntrack_lock)); + lockdep_is_held(&nf_conntrack_expect_lock)); if (helper) { p = &helper->expect_policy[expect->class]; if (p->max_expected && @@ -417,12 +433,12 @@ out: return ret; } -int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, +int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, u32 portid, int report) { int ret; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); ret = __nf_ct_expect_check(expect); if (ret <= 0) goto out; @@ -430,11 +446,11 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, ret = nf_ct_expect_insert(expect); if (ret < 0) goto out; - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report); return ret; out: - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); return ret; } EXPORT_SYMBOL_GPL(nf_ct_expect_related_report); diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 70866d192efc..3a3a60b126e0 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1476,7 +1476,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, nf_ct_refresh(ct, skb, info->timeout * HZ); /* Set expect timeout */ - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); exp = find_expect(ct, &ct->tuplehash[dir].tuple.dst.u3, info->sig_port[!dir]); if (exp) { @@ -1486,7 +1486,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, nf_ct_dump_tuple(&exp->tuple); set_expect_timeout(exp, info->timeout); } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } return 0; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 974a2a4adefa..5b3eae7d4c9a 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -250,16 +250,14 @@ out: } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); +/* appropiate ct lock protecting must be taken by caller */ static inline int unhelp(struct nf_conntrack_tuple_hash *i, const struct nf_conntrack_helper *me) { struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); struct nf_conn_help *help = nfct_help(ct); - if (help && rcu_dereference_protected( - help->helper, - lockdep_is_held(&nf_conntrack_lock) - ) == me) { + if (help && rcu_dereference_raw(help->helper) == me) { nf_conntrack_event(IPCT_HELPER, ct); RCU_INIT_POINTER(help->helper, NULL); } @@ -284,17 +282,17 @@ static LIST_HEAD(nf_ct_helper_expectfn_list); void nf_ct_helper_expectfn_register(struct nf_ct_helper_expectfn *n) { - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); list_add_rcu(&n->head, &nf_ct_helper_expectfn_list); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_register); void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n) { - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); list_del_rcu(&n->head); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister); @@ -396,15 +394,17 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, const struct hlist_node *next; const struct hlist_nulls_node *nn; unsigned int i; + int cpu; /* Get rid of expectations */ + spin_lock_bh(&nf_conntrack_expect_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], hnode) { struct nf_conn_help *help = nfct_help(exp->master); if ((rcu_dereference_protected( help->helper, - lockdep_is_held(&nf_conntrack_lock) + lockdep_is_held(&nf_conntrack_expect_lock) ) == me || exp->helper == me) && del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); @@ -412,14 +412,27 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, } } } + spin_unlock_bh(&nf_conntrack_expect_lock); /* Get rid of expecteds, set helpers to NULL. */ - hlist_nulls_for_each_entry(h, nn, &net->ct.unconfirmed, hnnode) - unhelp(h, me); - for (i = 0; i < net->ct.htable_size; i++) { - hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) + for_each_possible_cpu(cpu) { + struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + + spin_lock_bh(&pcpu->lock); + hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode) unhelp(h, me); + spin_unlock_bh(&pcpu->lock); + } + local_bh_disable(); + for (i = 0; i < net->ct.htable_size; i++) { + spin_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + if (i < net->ct.htable_size) { + hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) + unhelp(h, me); + } + spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); } + local_bh_enable(); } void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) @@ -437,10 +450,8 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) synchronize_rcu(); rtnl_lock(); - spin_lock_bh(&nf_conntrack_lock); for_each_net(net) __nf_conntrack_helper_unregister(me, net); - spin_unlock_bh(&nf_conntrack_lock); rtnl_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index b9f0e0374322..ccc46fa5edbc 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -764,14 +764,23 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; int res; + spinlock_t *lockp; + #ifdef CONFIG_NF_CONNTRACK_MARK const struct ctnetlink_dump_filter *filter = cb->data; #endif - spin_lock_bh(&nf_conntrack_lock); last = (struct nf_conn *)cb->args[1]; + + local_bh_disable(); for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) { restart: + lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS]; + spin_lock(lockp); + if (cb->args[0] >= net->ct.htable_size) { + spin_unlock(lockp); + goto out; + } hlist_nulls_for_each_entry(h, n, &net->ct.hash[cb->args[0]], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) @@ -803,16 +812,18 @@ restart: if (res < 0) { nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; + spin_unlock(lockp); goto out; } } + spin_unlock(lockp); if (cb->args[1]) { cb->args[1] = 0; goto restart; } } out: - spin_unlock_bh(&nf_conntrack_lock); + local_bh_enable(); if (last) nf_ct_put(last); @@ -966,7 +977,6 @@ ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, return 0; } -#define __CTA_LABELS_MAX_LENGTH ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE) static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_TUPLE_ORIG] = { .type = NLA_NESTED }, [CTA_TUPLE_REPLY] = { .type = NLA_NESTED }, @@ -984,9 +994,9 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_ZONE] = { .type = NLA_U16 }, [CTA_MARK_MASK] = { .type = NLA_U32 }, [CTA_LABELS] = { .type = NLA_BINARY, - .len = __CTA_LABELS_MAX_LENGTH }, + .len = NF_CT_LABELS_MAX_SIZE }, [CTA_LABELS_MASK] = { .type = NLA_BINARY, - .len = __CTA_LABELS_MAX_LENGTH }, + .len = NF_CT_LABELS_MAX_SIZE }, }; static int @@ -1138,50 +1148,65 @@ static int ctnetlink_done_list(struct netlink_callback *cb) } static int -ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, - struct hlist_nulls_head *list) +ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying) { - struct nf_conn *ct, *last; + struct nf_conn *ct, *last = NULL; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; int res; + int cpu; + struct hlist_nulls_head *list; + struct net *net = sock_net(skb->sk); if (cb->args[2]) return 0; - spin_lock_bh(&nf_conntrack_lock); - last = (struct nf_conn *)cb->args[1]; -restart: - hlist_nulls_for_each_entry(h, n, list, hnnode) { - ct = nf_ct_tuplehash_to_ctrack(h); - if (l3proto && nf_ct_l3num(ct) != l3proto) + if (cb->args[0] == nr_cpu_ids) + return 0; + + for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { + struct ct_pcpu *pcpu; + + if (!cpu_possible(cpu)) continue; - if (cb->args[1]) { - if (ct != last) + + pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); + spin_lock_bh(&pcpu->lock); + last = (struct nf_conn *)cb->args[1]; + list = dying ? &pcpu->dying : &pcpu->unconfirmed; +restart: + hlist_nulls_for_each_entry(h, n, list, hnnode) { + ct = nf_ct_tuplehash_to_ctrack(h); + if (l3proto && nf_ct_l3num(ct) != l3proto) continue; - cb->args[1] = 0; - } - rcu_read_lock(); - res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NFNL_MSG_TYPE(cb->nlh->nlmsg_type), - ct); - rcu_read_unlock(); - if (res < 0) { - nf_conntrack_get(&ct->ct_general); - cb->args[1] = (unsigned long)ct; - goto out; + if (cb->args[1]) { + if (ct != last) + continue; + cb->args[1] = 0; + } + rcu_read_lock(); + res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NFNL_MSG_TYPE(cb->nlh->nlmsg_type), + ct); + rcu_read_unlock(); + if (res < 0) { + nf_conntrack_get(&ct->ct_general); + cb->args[1] = (unsigned long)ct; + spin_unlock_bh(&pcpu->lock); + goto out; + } } + if (cb->args[1]) { + cb->args[1] = 0; + goto restart; + } else + cb->args[2] = 1; + spin_unlock_bh(&pcpu->lock); } - if (cb->args[1]) { - cb->args[1] = 0; - goto restart; - } else - cb->args[2] = 1; out: - spin_unlock_bh(&nf_conntrack_lock); if (last) nf_ct_put(last); @@ -1191,9 +1216,7 @@ out: static int ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = sock_net(skb->sk); - - return ctnetlink_dump_list(skb, cb, &net->ct.dying); + return ctnetlink_dump_list(skb, cb, true); } static int @@ -1215,9 +1238,7 @@ ctnetlink_get_ct_dying(struct sock *ctnl, struct sk_buff *skb, static int ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = sock_net(skb->sk); - - return ctnetlink_dump_list(skb, cb, &net->ct.unconfirmed); + return ctnetlink_dump_list(skb, cb, false); } static int @@ -1361,14 +1382,14 @@ ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) nf_ct_protonum(ct)); if (helper == NULL) { #ifdef CONFIG_MODULES - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); if (request_module("nfct-helper-%s", helpname) < 0) { - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); return -EOPNOTSUPP; } - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper) @@ -1804,9 +1825,9 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, err = -EEXIST; ct = nf_ct_tuplehash_to_ctrack(h); if (!(nlh->nlmsg_flags & NLM_F_EXCL)) { - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); err = ctnetlink_change_conntrack(ct, cda); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); if (err == 0) { nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | @@ -2135,9 +2156,9 @@ ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct) if (ret < 0) return ret; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); ret = ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); return ret; } @@ -2692,13 +2713,13 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, } /* after list removal, usage count == 1 */ - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); if (del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_expect_put(exp); } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); /* have to put what we 'get' above. * after this line usage count == 0 */ nf_ct_expect_put(exp); @@ -2707,7 +2728,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, struct nf_conn_help *m_help; /* delete all expectations for this helper */ - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], @@ -2722,10 +2743,10 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, } } } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } else { /* This basically means we have to flush everything*/ - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], @@ -2738,7 +2759,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, } } } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } return 0; @@ -2964,11 +2985,11 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, if (err < 0) return err; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); exp = __nf_ct_expect_find(net, zone, &tuple); if (!exp) { - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { err = ctnetlink_create_expect(net, zone, cda, @@ -2982,7 +3003,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, err = -EEXIST; if (!(nlh->nlmsg_flags & NLM_F_EXCL)) err = ctnetlink_change_expect(exp, cda); - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); return err; } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 466410eaa482..4c3ba1c8d682 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -800,7 +800,7 @@ static int refresh_signalling_expectation(struct nf_conn *ct, struct hlist_node *next; int found = 0; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if (exp->class != SIP_EXPECT_SIGNALLING || !nf_inet_addr_cmp(&exp->tuple.dst.u3, addr) || @@ -815,7 +815,7 @@ static int refresh_signalling_expectation(struct nf_conn *ct, found = 1; break; } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); return found; } @@ -825,7 +825,7 @@ static void flush_expectations(struct nf_conn *ct, bool media) struct nf_conntrack_expect *exp; struct hlist_node *next; - spin_lock_bh(&nf_conntrack_lock); + spin_lock_bh(&nf_conntrack_expect_lock); hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if ((exp->class != SIP_EXPECT_SIGNALLING) ^ media) continue; @@ -836,7 +836,7 @@ static void flush_expectations(struct nf_conn *ct, bool media) if (!media) break; } - spin_unlock_bh(&nf_conntrack_lock); + spin_unlock_bh(&nf_conntrack_expect_lock); } static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index adce01e8bb57..33045a562297 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -794,9 +794,8 @@ nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr) stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); if (chain->stats) { - /* nfnl_lock is held, add some nfnl function for this, later */ struct nft_stats __percpu *oldstats = - rcu_dereference_protected(chain->stats, 1); + nft_dereference(chain->stats); rcu_assign_pointer(chain->stats, newstats); synchronize_rcu(); @@ -1254,10 +1253,11 @@ err1: return err; } -static void nf_tables_expr_destroy(struct nft_expr *expr) +static void nf_tables_expr_destroy(const struct nft_ctx *ctx, + struct nft_expr *expr) { if (expr->ops->destroy) - expr->ops->destroy(expr); + expr->ops->destroy(ctx, expr); module_put(expr->ops->type->owner); } @@ -1296,6 +1296,8 @@ static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { [NFTA_RULE_EXPRESSIONS] = { .type = NLA_NESTED }, [NFTA_RULE_COMPAT] = { .type = NLA_NESTED }, [NFTA_RULE_POSITION] = { .type = NLA_U64 }, + [NFTA_RULE_USERDATA] = { .type = NLA_BINARY, + .len = NFT_USERDATA_MAXLEN }, }; static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq, @@ -1348,6 +1350,10 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, u32 portid, u32 seq, } nla_nest_end(skb, list); + if (rule->ulen && + nla_put(skb, NFTA_RULE_USERDATA, rule->ulen, nft_userdata(rule))) + goto nla_put_failure; + return nlmsg_end(skb, nlh); nla_put_failure: @@ -1531,7 +1537,8 @@ err: return err; } -static void nf_tables_rule_destroy(struct nft_rule *rule) +static void nf_tables_rule_destroy(const struct nft_ctx *ctx, + struct nft_rule *rule) { struct nft_expr *expr; @@ -1541,7 +1548,7 @@ static void nf_tables_rule_destroy(struct nft_rule *rule) */ expr = nft_expr_first(rule); while (expr->ops && expr != nft_expr_last(rule)) { - nf_tables_expr_destroy(expr); + nf_tables_expr_destroy(ctx, expr); expr = nft_expr_next(expr); } kfree(rule); @@ -1552,7 +1559,7 @@ static void nf_tables_rule_destroy(struct nft_rule *rule) static struct nft_expr_info *info; static struct nft_rule_trans * -nf_tables_trans_add(struct nft_rule *rule, const struct nft_ctx *ctx) +nf_tables_trans_add(struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_rule_trans *rupd; @@ -1560,11 +1567,8 @@ nf_tables_trans_add(struct nft_rule *rule, const struct nft_ctx *ctx) if (rupd == NULL) return NULL; - rupd->chain = ctx->chain; - rupd->table = ctx->table; + rupd->ctx = *ctx; rupd->rule = rule; - rupd->family = ctx->afi->family; - rupd->nlh = ctx->nlh; list_add_tail(&rupd->list, &ctx->net->nft.commit_list); return rupd; @@ -1584,7 +1588,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, struct nft_expr *expr; struct nft_ctx ctx; struct nlattr *tmp; - unsigned int size, i, n; + unsigned int size, i, n, ulen = 0; int err, rem; bool create; u64 handle, pos_handle; @@ -1650,8 +1654,11 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, } } + if (nla[NFTA_RULE_USERDATA]) + ulen = nla_len(nla[NFTA_RULE_USERDATA]); + err = -ENOMEM; - rule = kzalloc(sizeof(*rule) + size, GFP_KERNEL); + rule = kzalloc(sizeof(*rule) + size + ulen, GFP_KERNEL); if (rule == NULL) goto err1; @@ -1659,6 +1666,10 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, rule->handle = handle; rule->dlen = size; + rule->ulen = ulen; + + if (ulen) + nla_memcpy(nft_userdata(rule), nla[NFTA_RULE_USERDATA], ulen); expr = nft_expr_first(rule); for (i = 0; i < n; i++) { @@ -1671,7 +1682,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_REPLACE) { if (nft_rule_is_active_next(net, old_rule)) { - repl = nf_tables_trans_add(old_rule, &ctx); + repl = nf_tables_trans_add(&ctx, old_rule); if (repl == NULL) { err = -ENOMEM; goto err2; @@ -1694,7 +1705,7 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb, list_add_rcu(&rule->list, &chain->rules); } - if (nf_tables_trans_add(rule, &ctx) == NULL) { + if (nf_tables_trans_add(&ctx, rule) == NULL) { err = -ENOMEM; goto err3; } @@ -1709,7 +1720,7 @@ err3: kfree(repl); } err2: - nf_tables_rule_destroy(rule); + nf_tables_rule_destroy(&ctx, rule); err1: for (i = 0; i < n; i++) { if (info[i].ops != NULL) @@ -1723,7 +1734,7 @@ nf_tables_delrule_one(struct nft_ctx *ctx, struct nft_rule *rule) { /* You cannot delete the same rule twice */ if (nft_rule_is_active_next(ctx->net, rule)) { - if (nf_tables_trans_add(rule, ctx) == NULL) + if (nf_tables_trans_add(ctx, rule) == NULL) return -ENOMEM; nft_rule_disactivate_next(ctx->net, rule); return 0; @@ -1819,10 +1830,10 @@ static int nf_tables_commit(struct sk_buff *skb) */ if (nft_rule_is_active(net, rupd->rule)) { nft_rule_clear(net, rupd->rule); - nf_tables_rule_notify(skb, rupd->nlh, rupd->table, - rupd->chain, rupd->rule, - NFT_MSG_NEWRULE, 0, - rupd->family); + nf_tables_rule_notify(skb, rupd->ctx.nlh, + rupd->ctx.table, rupd->ctx.chain, + rupd->rule, NFT_MSG_NEWRULE, 0, + rupd->ctx.afi->family); list_del(&rupd->list); kfree(rupd); continue; @@ -1830,9 +1841,10 @@ static int nf_tables_commit(struct sk_buff *skb) /* This rule is in the past, get rid of it */ list_del_rcu(&rupd->rule->list); - nf_tables_rule_notify(skb, rupd->nlh, rupd->table, rupd->chain, + nf_tables_rule_notify(skb, rupd->ctx.nlh, + rupd->ctx.table, rupd->ctx.chain, rupd->rule, NFT_MSG_DELRULE, 0, - rupd->family); + rupd->ctx.afi->family); } /* Make sure we don't see any packet traversing old rules */ @@ -1840,7 +1852,7 @@ static int nf_tables_commit(struct sk_buff *skb) /* Now we can safely release unused old rules */ list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - nf_tables_rule_destroy(rupd->rule); + nf_tables_rule_destroy(&rupd->ctx, rupd->rule); list_del(&rupd->list); kfree(rupd); } @@ -1869,7 +1881,7 @@ static int nf_tables_abort(struct sk_buff *skb) synchronize_rcu(); list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - nf_tables_rule_destroy(rupd->rule); + nf_tables_rule_destroy(&rupd->ctx, rupd->rule); list_del(&rupd->list); kfree(rupd); } @@ -2430,8 +2442,7 @@ err1: static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { list_del(&set->list); - if (!(set->flags & NFT_SET_ANONYMOUS)) - nf_tables_set_notify(ctx, set, NFT_MSG_DELSET); + nf_tables_set_notify(ctx, set, NFT_MSG_DELSET); set->ops->destroy(set); module_put(set->ops->owner); @@ -3175,9 +3186,16 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict) { - case NF_ACCEPT: - case NF_DROP: - case NF_QUEUE: + default: + switch (data->verdict & NF_VERDICT_MASK) { + case NF_ACCEPT: + case NF_DROP: + case NF_QUEUE: + break; + default: + return -EINVAL; + } + /* fall through */ case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: @@ -3198,8 +3216,6 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->chain = chain; desc->len = sizeof(data); break; - default: - return -EINVAL; } desc->type = NFT_DATA_VERDICT; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 046aa13b4fea..e8138da4c14f 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -61,6 +61,14 @@ void nfnl_unlock(__u8 subsys_id) } EXPORT_SYMBOL_GPL(nfnl_unlock); +#ifdef CONFIG_PROVE_LOCKING +int lockdep_nfnl_is_held(u8 subsys_id) +{ + return lockdep_is_held(&table[subsys_id].mutex); +} +EXPORT_SYMBOL_GPL(lockdep_nfnl_is_held); +#endif + int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n) { nfnl_lock(n->subsys_id); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index a155d19a225e..d292c8d286eb 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -28,8 +28,6 @@ #include <linux/proc_fs.h> #include <linux/security.h> #include <linux/list.h> -#include <linux/jhash.h> -#include <linux/random.h> #include <linux/slab.h> #include <net/sock.h> #include <net/netfilter/nf_log.h> @@ -75,7 +73,6 @@ struct nfulnl_instance { }; #define INSTANCE_BUCKETS 16 -static unsigned int hash_init; static int nfnl_log_net_id __read_mostly; @@ -1067,11 +1064,6 @@ static int __init nfnetlink_log_init(void) { int status = -ENOMEM; - /* it's not really all that important to have a random value, so - * we can do this from the init function, even if there hasn't - * been that much entropy yet */ - get_random_bytes(&hash_init, sizeof(hash_init)); - netlink_register_notifier(&nfulnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfulnl_subsys); if (status < 0) { diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 82cb8236f8a1..8a779be832fb 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -192,7 +192,7 @@ err: } static void -nft_target_destroy(const struct nft_expr *expr) +nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_target *target = expr->ops->data; @@ -379,7 +379,7 @@ err: } static void -nft_match_destroy(const struct nft_expr *expr) +nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_match *match = expr->ops->data; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 46e275403838..bd0d41e69341 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -19,15 +19,15 @@ #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_labels.h> struct nft_ct { enum nft_ct_keys key:8; enum ip_conntrack_dir dir:8; - union{ + union { enum nft_registers dreg:8; enum nft_registers sreg:8; }; - uint8_t family; }; static void nft_ct_get_eval(const struct nft_expr *expr, @@ -97,6 +97,26 @@ static void nft_ct_get_eval(const struct nft_expr *expr, goto err; strncpy((char *)dest->data, helper->name, sizeof(dest->data)); return; +#ifdef CONFIG_NF_CONNTRACK_LABELS + case NFT_CT_LABELS: { + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + unsigned int size; + + if (!labels) { + memset(dest->data, 0, sizeof(dest->data)); + return; + } + + BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE > sizeof(dest->data)); + size = labels->words * sizeof(long); + + memcpy(dest->data, labels->bits, size); + if (size < sizeof(dest->data)) + memset(((char *) dest->data) + size, 0, + sizeof(dest->data) - size); + return; + } +#endif } tuple = &ct->tuplehash[priv->dir].tuple; @@ -221,6 +241,9 @@ static int nft_ct_init_validate_get(const struct nft_expr *expr, #ifdef CONFIG_NF_CONNTRACK_SECMARK case NFT_CT_SECMARK: #endif +#ifdef CONFIG_NF_CONNTRACK_LABELS + case NFT_CT_LABELS: +#endif case NFT_CT_EXPIRATION: case NFT_CT_HELPER: if (tb[NFTA_CT_DIRECTION] != NULL) @@ -292,16 +315,13 @@ static int nft_ct_init(const struct nft_ctx *ctx, if (err < 0) return err; - priv->family = ctx->afi->family; - return 0; } -static void nft_ct_destroy(const struct nft_expr *expr) +static void nft_ct_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { - struct nft_ct *priv = nft_expr_priv(expr); - - nft_ct_l3proto_module_put(priv->family); + nft_ct_l3proto_module_put(ctx->afi->family); } static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 3d3f8fce10a5..3b1ad876d6b0 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -14,21 +14,34 @@ #include <linux/list.h> #include <linux/jhash.h> #include <linux/netlink.h> +#include <linux/vmalloc.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> +#define NFT_HASH_MIN_SIZE 4 + struct nft_hash { - struct hlist_head *hash; - unsigned int hsize; + struct nft_hash_table __rcu *tbl; +}; + +struct nft_hash_table { + unsigned int size; + unsigned int elements; + struct nft_hash_elem __rcu *buckets[]; }; struct nft_hash_elem { - struct hlist_node hnode; - struct nft_data key; - struct nft_data data[]; + struct nft_hash_elem __rcu *next; + struct nft_data key; + struct nft_data data[]; }; +#define nft_hash_for_each_entry(i, head) \ + for (i = nft_dereference(head); i != NULL; i = nft_dereference(i->next)) +#define nft_hash_for_each_entry_rcu(i, head) \ + for (i = rcu_dereference(head); i != NULL; i = rcu_dereference(i->next)) + static u32 nft_hash_rnd __read_mostly; static bool nft_hash_rnd_initted __read_mostly; @@ -38,7 +51,7 @@ static unsigned int nft_hash_data(const struct nft_data *data, unsigned int h; h = jhash(data->data, len, nft_hash_rnd); - return ((u64)h * hsize) >> 32; + return h & (hsize - 1); } static bool nft_hash_lookup(const struct nft_set *set, @@ -46,11 +59,12 @@ static bool nft_hash_lookup(const struct nft_set *set, struct nft_data *data) { const struct nft_hash *priv = nft_set_priv(set); + const struct nft_hash_table *tbl = rcu_dereference(priv->tbl); const struct nft_hash_elem *he; unsigned int h; - h = nft_hash_data(key, priv->hsize, set->klen); - hlist_for_each_entry(he, &priv->hash[h], hnode) { + h = nft_hash_data(key, tbl->size, set->klen); + nft_hash_for_each_entry_rcu(he, tbl->buckets[h]) { if (nft_data_cmp(&he->key, key, set->klen)) continue; if (set->flags & NFT_SET_MAP) @@ -60,19 +74,148 @@ static bool nft_hash_lookup(const struct nft_set *set, return false; } -static void nft_hash_elem_destroy(const struct nft_set *set, - struct nft_hash_elem *he) +static void nft_hash_tbl_free(const struct nft_hash_table *tbl) { - nft_data_uninit(&he->key, NFT_DATA_VALUE); - if (set->flags & NFT_SET_MAP) - nft_data_uninit(he->data, set->dtype); - kfree(he); + if (is_vmalloc_addr(tbl)) + vfree(tbl); + else + kfree(tbl); +} + +static struct nft_hash_table *nft_hash_tbl_alloc(unsigned int nbuckets) +{ + struct nft_hash_table *tbl; + size_t size; + + size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]); + tbl = kzalloc(size, GFP_KERNEL | __GFP_REPEAT | __GFP_NOWARN); + if (tbl == NULL) + tbl = vzalloc(size); + if (tbl == NULL) + return NULL; + tbl->size = nbuckets; + + return tbl; +} + +static void nft_hash_chain_unzip(const struct nft_set *set, + const struct nft_hash_table *ntbl, + struct nft_hash_table *tbl, unsigned int n) +{ + struct nft_hash_elem *he, *last, *next; + unsigned int h; + + he = nft_dereference(tbl->buckets[n]); + if (he == NULL) + return; + h = nft_hash_data(&he->key, ntbl->size, set->klen); + + /* Find last element of first chain hashing to bucket h */ + last = he; + nft_hash_for_each_entry(he, he->next) { + if (nft_hash_data(&he->key, ntbl->size, set->klen) != h) + break; + last = he; + } + + /* Unlink first chain from the old table */ + RCU_INIT_POINTER(tbl->buckets[n], last->next); + + /* If end of chain reached, done */ + if (he == NULL) + return; + + /* Find first element of second chain hashing to bucket h */ + next = NULL; + nft_hash_for_each_entry(he, he->next) { + if (nft_hash_data(&he->key, ntbl->size, set->klen) != h) + continue; + next = he; + break; + } + + /* Link the two chains */ + RCU_INIT_POINTER(last->next, next); +} + +static int nft_hash_tbl_expand(const struct nft_set *set, struct nft_hash *priv) +{ + struct nft_hash_table *tbl = nft_dereference(priv->tbl), *ntbl; + struct nft_hash_elem *he; + unsigned int i, h; + bool complete; + + ntbl = nft_hash_tbl_alloc(tbl->size * 2); + if (ntbl == NULL) + return -ENOMEM; + + /* Link new table's buckets to first element in the old table + * hashing to the new bucket. + */ + for (i = 0; i < ntbl->size; i++) { + h = i < tbl->size ? i : i - tbl->size; + nft_hash_for_each_entry(he, tbl->buckets[h]) { + if (nft_hash_data(&he->key, ntbl->size, set->klen) != i) + continue; + RCU_INIT_POINTER(ntbl->buckets[i], he); + break; + } + } + ntbl->elements = tbl->elements; + + /* Publish new table */ + rcu_assign_pointer(priv->tbl, ntbl); + + /* Unzip interleaved hash chains */ + do { + /* Wait for readers to use new table/unzipped chains */ + synchronize_rcu(); + + complete = true; + for (i = 0; i < tbl->size; i++) { + nft_hash_chain_unzip(set, ntbl, tbl, i); + if (tbl->buckets[i] != NULL) + complete = false; + } + } while (!complete); + + nft_hash_tbl_free(tbl); + return 0; +} + +static int nft_hash_tbl_shrink(const struct nft_set *set, struct nft_hash *priv) +{ + struct nft_hash_table *tbl = nft_dereference(priv->tbl), *ntbl; + struct nft_hash_elem __rcu **pprev; + unsigned int i; + + ntbl = nft_hash_tbl_alloc(tbl->size / 2); + if (ntbl == NULL) + return -ENOMEM; + + for (i = 0; i < ntbl->size; i++) { + ntbl->buckets[i] = tbl->buckets[i]; + + for (pprev = &ntbl->buckets[i]; *pprev != NULL; + pprev = &nft_dereference(*pprev)->next) + ; + RCU_INIT_POINTER(*pprev, tbl->buckets[i + ntbl->size]); + } + ntbl->elements = tbl->elements; + + /* Publish new table */ + rcu_assign_pointer(priv->tbl, ntbl); + synchronize_rcu(); + + nft_hash_tbl_free(tbl); + return 0; } static int nft_hash_insert(const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_table *tbl = nft_dereference(priv->tbl); struct nft_hash_elem *he; unsigned int size, h; @@ -91,33 +234,66 @@ static int nft_hash_insert(const struct nft_set *set, if (set->flags & NFT_SET_MAP) nft_data_copy(he->data, &elem->data); - h = nft_hash_data(&he->key, priv->hsize, set->klen); - hlist_add_head_rcu(&he->hnode, &priv->hash[h]); + h = nft_hash_data(&he->key, tbl->size, set->klen); + RCU_INIT_POINTER(he->next, tbl->buckets[h]); + rcu_assign_pointer(tbl->buckets[h], he); + tbl->elements++; + + /* Expand table when exceeding 75% load */ + if (tbl->elements > tbl->size / 4 * 3) + nft_hash_tbl_expand(set, priv); + return 0; } +static void nft_hash_elem_destroy(const struct nft_set *set, + struct nft_hash_elem *he) +{ + nft_data_uninit(&he->key, NFT_DATA_VALUE); + if (set->flags & NFT_SET_MAP) + nft_data_uninit(he->data, set->dtype); + kfree(he); +} + static void nft_hash_remove(const struct nft_set *set, const struct nft_set_elem *elem) { - struct nft_hash_elem *he = elem->cookie; + struct nft_hash *priv = nft_set_priv(set); + struct nft_hash_table *tbl = nft_dereference(priv->tbl); + struct nft_hash_elem *he, __rcu **pprev; - hlist_del_rcu(&he->hnode); + pprev = elem->cookie; + he = nft_dereference((*pprev)); + + RCU_INIT_POINTER(*pprev, he->next); + synchronize_rcu(); kfree(he); + tbl->elements--; + + /* Shrink table beneath 30% load */ + if (tbl->elements < tbl->size * 3 / 10 && + tbl->size > NFT_HASH_MIN_SIZE) + nft_hash_tbl_shrink(set, priv); } static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem) { const struct nft_hash *priv = nft_set_priv(set); + const struct nft_hash_table *tbl = nft_dereference(priv->tbl); + struct nft_hash_elem __rcu * const *pprev; struct nft_hash_elem *he; unsigned int h; - h = nft_hash_data(&elem->key, priv->hsize, set->klen); - hlist_for_each_entry(he, &priv->hash[h], hnode) { - if (nft_data_cmp(&he->key, &elem->key, set->klen)) + h = nft_hash_data(&elem->key, tbl->size, set->klen); + pprev = &tbl->buckets[h]; + nft_hash_for_each_entry(he, tbl->buckets[h]) { + if (nft_data_cmp(&he->key, &elem->key, set->klen)) { + pprev = &he->next; continue; + } - elem->cookie = he; - elem->flags = 0; + elem->cookie = (void *)pprev; + elem->flags = 0; if (set->flags & NFT_SET_MAP) nft_data_copy(&elem->data, he->data); return 0; @@ -129,12 +305,13 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set, struct nft_set_iter *iter) { const struct nft_hash *priv = nft_set_priv(set); + const struct nft_hash_table *tbl = nft_dereference(priv->tbl); const struct nft_hash_elem *he; struct nft_set_elem elem; unsigned int i; - for (i = 0; i < priv->hsize; i++) { - hlist_for_each_entry(he, &priv->hash[i], hnode) { + for (i = 0; i < tbl->size; i++) { + nft_hash_for_each_entry(he, tbl->buckets[i]) { if (iter->count < iter->skip) goto cont; @@ -161,43 +338,35 @@ static int nft_hash_init(const struct nft_set *set, const struct nlattr * const tb[]) { struct nft_hash *priv = nft_set_priv(set); - unsigned int cnt, i; + struct nft_hash_table *tbl; if (unlikely(!nft_hash_rnd_initted)) { get_random_bytes(&nft_hash_rnd, 4); nft_hash_rnd_initted = true; } - /* Aim for a load factor of 0.75 */ - // FIXME: temporarily broken until we have set descriptions - cnt = 100; - cnt = cnt * 4 / 3; - - priv->hash = kcalloc(cnt, sizeof(struct hlist_head), GFP_KERNEL); - if (priv->hash == NULL) + tbl = nft_hash_tbl_alloc(NFT_HASH_MIN_SIZE); + if (tbl == NULL) return -ENOMEM; - priv->hsize = cnt; - - for (i = 0; i < cnt; i++) - INIT_HLIST_HEAD(&priv->hash[i]); - + RCU_INIT_POINTER(priv->tbl, tbl); return 0; } static void nft_hash_destroy(const struct nft_set *set) { const struct nft_hash *priv = nft_set_priv(set); - const struct hlist_node *next; - struct nft_hash_elem *elem; + const struct nft_hash_table *tbl = nft_dereference(priv->tbl); + struct nft_hash_elem *he, *next; unsigned int i; - for (i = 0; i < priv->hsize; i++) { - hlist_for_each_entry_safe(elem, next, &priv->hash[i], hnode) { - hlist_del(&elem->hnode); - nft_hash_elem_destroy(set, elem); + for (i = 0; i < tbl->size; i++) { + for (he = nft_dereference(tbl->buckets[i]); he != NULL; + he = next) { + next = nft_dereference(he->next); + nft_hash_elem_destroy(set, he); } } - kfree(priv->hash); + kfree(tbl); } static struct nft_set_ops nft_hash_ops __read_mostly = { diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index f169501f1ad4..810385eb7249 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -70,7 +70,8 @@ err1: return err; } -static void nft_immediate_destroy(const struct nft_expr *expr) +static void nft_immediate_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); return nft_data_uninit(&priv->data, nft_dreg_to_type(priv->dreg)); diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 26c5154e05f3..10cfb156cdf4 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -74,7 +74,8 @@ static int nft_log_init(const struct nft_ctx *ctx, return 0; } -static void nft_log_destroy(const struct nft_expr *expr) +static void nft_log_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { struct nft_log *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index bb4ef4cccb6e..7fd2bea8aa23 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -89,11 +89,12 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return 0; } -static void nft_lookup_destroy(const struct nft_expr *expr) +static void nft_lookup_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { struct nft_lookup *priv = nft_expr_priv(expr); - nf_tables_unbind_set(NULL, priv->set, &priv->binding); + nf_tables_unbind_set(ctx, priv->set, &priv->binding); } static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index d3b1ffe26181..a0195d28bcfc 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -31,8 +31,8 @@ struct nft_nat { enum nft_registers sreg_addr_max:8; enum nft_registers sreg_proto_min:8; enum nft_registers sreg_proto_max:8; - int family; - enum nf_nat_manip_type type; + enum nf_nat_manip_type type:8; + u8 family; }; static void nft_nat_eval(const struct nft_expr *expr, @@ -88,6 +88,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_nat *priv = nft_expr_priv(expr); + u32 family; int err; if (tb[NFTA_NAT_TYPE] == NULL) @@ -107,9 +108,12 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (tb[NFTA_NAT_FAMILY] == NULL) return -EINVAL; - priv->family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY])); - if (priv->family != AF_INET && priv->family != AF_INET6) - return -EINVAL; + family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY])); + if (family != AF_INET && family != AF_INET6) + return -EAFNOSUPPORT; + if (family != ctx->afi->family) + return -EOPNOTSUPP; + priv->family = family; if (tb[NFTA_NAT_REG_ADDR_MIN]) { priv->sreg_addr_min = ntohl(nla_get_be32( @@ -202,13 +206,7 @@ static struct nft_expr_type nft_nat_type __read_mostly = { static int __init nft_nat_module_init(void) { - int err; - - err = nft_register_expr(&nft_nat_type); - if (err < 0) - return err; - - return 0; + return nft_register_expr(&nft_nat_type); } static void __exit nft_nat_module_exit(void) diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c index 3228d7f24eb4..4973cbddc446 100644 --- a/net/netfilter/xt_AUDIT.c +++ b/net/netfilter/xt_AUDIT.c @@ -146,11 +146,11 @@ audit_tg(struct sk_buff *skb, const struct xt_action_param *par) if (par->family == NFPROTO_BRIDGE) { switch (eth_hdr(skb)->h_proto) { - case __constant_htons(ETH_P_IP): + case htons(ETH_P_IP): audit_ip4(ab, skb); break; - case __constant_htons(ETH_P_IPV6): + case htons(ETH_P_IPV6): audit_ip6(ab, skb); break; } diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index c40b2695633b..458464e7bd7a 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -19,6 +19,7 @@ #include <linux/jhash.h> #include <linux/slab.h> #include <linux/list.h> +#include <linux/rbtree.h> #include <linux/module.h> #include <linux/random.h> #include <linux/skbuff.h> @@ -31,6 +32,10 @@ #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_zones.h> +#define CONNLIMIT_SLOTS 32 +#define CONNLIMIT_LOCK_SLOTS 32 +#define CONNLIMIT_GC_MAX_NODES 8 + /* we will save the tuples of all connections we care about */ struct xt_connlimit_conn { struct hlist_node node; @@ -38,16 +43,26 @@ struct xt_connlimit_conn { union nf_inet_addr addr; }; +struct xt_connlimit_rb { + struct rb_node node; + struct hlist_head hhead; /* connections/hosts in same subnet */ + union nf_inet_addr addr; /* search key */ +}; + struct xt_connlimit_data { - struct hlist_head iphash[256]; - spinlock_t lock; + struct rb_root climit_root4[CONNLIMIT_SLOTS]; + struct rb_root climit_root6[CONNLIMIT_SLOTS]; + spinlock_t locks[CONNLIMIT_LOCK_SLOTS]; }; static u_int32_t connlimit_rnd __read_mostly; +static struct kmem_cache *connlimit_rb_cachep __read_mostly; +static struct kmem_cache *connlimit_conn_cachep __read_mostly; static inline unsigned int connlimit_iphash(__be32 addr) { - return jhash_1word((__force __u32)addr, connlimit_rnd) & 0xFF; + return jhash_1word((__force __u32)addr, + connlimit_rnd) % CONNLIMIT_SLOTS; } static inline unsigned int @@ -60,7 +75,8 @@ connlimit_iphash6(const union nf_inet_addr *addr, for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i) res.ip6[i] = addr->ip6[i] & mask->ip6[i]; - return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6), connlimit_rnd) & 0xFF; + return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6), + connlimit_rnd) % CONNLIMIT_SLOTS; } static inline bool already_closed(const struct nf_conn *conn) @@ -72,13 +88,14 @@ static inline bool already_closed(const struct nf_conn *conn) return 0; } -static inline unsigned int +static int same_source_net(const union nf_inet_addr *addr, const union nf_inet_addr *mask, const union nf_inet_addr *u3, u_int8_t family) { if (family == NFPROTO_IPV4) { - return (addr->ip & mask->ip) == (u3->ip & mask->ip); + return ntohl(addr->ip & mask->ip) - + ntohl(u3->ip & mask->ip); } else { union nf_inet_addr lh, rh; unsigned int i; @@ -88,89 +105,205 @@ same_source_net(const union nf_inet_addr *addr, rh.ip6[i] = u3->ip6[i] & mask->ip6[i]; } - return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6)) == 0; + return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6)); } } -static int count_them(struct net *net, - struct xt_connlimit_data *data, +static bool add_hlist(struct hlist_head *head, const struct nf_conntrack_tuple *tuple, - const union nf_inet_addr *addr, - const union nf_inet_addr *mask, - u_int8_t family) + const union nf_inet_addr *addr) +{ + struct xt_connlimit_conn *conn; + + conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC); + if (conn == NULL) + return false; + conn->tuple = *tuple; + conn->addr = *addr; + hlist_add_head(&conn->node, head); + return true; +} + +static unsigned int check_hlist(struct net *net, + struct hlist_head *head, + const struct nf_conntrack_tuple *tuple, + bool *addit) { const struct nf_conntrack_tuple_hash *found; struct xt_connlimit_conn *conn; struct hlist_node *n; struct nf_conn *found_ct; - struct hlist_head *hash; - bool addit = true; - int matches = 0; - - if (family == NFPROTO_IPV6) - hash = &data->iphash[connlimit_iphash6(addr, mask)]; - else - hash = &data->iphash[connlimit_iphash(addr->ip & mask->ip)]; + unsigned int length = 0; + *addit = true; rcu_read_lock(); /* check the saved connections */ - hlist_for_each_entry_safe(conn, n, hash, node) { + hlist_for_each_entry_safe(conn, n, head, node) { found = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE, &conn->tuple); - found_ct = NULL; + if (found == NULL) { + hlist_del(&conn->node); + kmem_cache_free(connlimit_conn_cachep, conn); + continue; + } - if (found != NULL) - found_ct = nf_ct_tuplehash_to_ctrack(found); + found_ct = nf_ct_tuplehash_to_ctrack(found); - if (found_ct != NULL && - nf_ct_tuple_equal(&conn->tuple, tuple) && - !already_closed(found_ct)) + if (nf_ct_tuple_equal(&conn->tuple, tuple)) { /* * Just to be sure we have it only once in the list. * We should not see tuples twice unless someone hooks * this into a table without "-p tcp --syn". */ - addit = false; - - if (found == NULL) { - /* this one is gone */ - hlist_del(&conn->node); - kfree(conn); - continue; - } - - if (already_closed(found_ct)) { + *addit = false; + } else if (already_closed(found_ct)) { /* * we do not care about connections which are * closed already -> ditch it */ nf_ct_put(found_ct); hlist_del(&conn->node); - kfree(conn); + kmem_cache_free(connlimit_conn_cachep, conn); continue; } - if (same_source_net(addr, mask, &conn->addr, family)) - /* same source network -> be counted! */ - ++matches; nf_ct_put(found_ct); + length++; } rcu_read_unlock(); - if (addit) { - /* save the new connection in our list */ - conn = kmalloc(sizeof(*conn), GFP_ATOMIC); - if (conn == NULL) - return -ENOMEM; - conn->tuple = *tuple; - conn->addr = *addr; - hlist_add_head(&conn->node, hash); - ++matches; + return length; +} + +static void tree_nodes_free(struct rb_root *root, + struct xt_connlimit_rb *gc_nodes[], + unsigned int gc_count) +{ + struct xt_connlimit_rb *rbconn; + + while (gc_count) { + rbconn = gc_nodes[--gc_count]; + rb_erase(&rbconn->node, root); + kmem_cache_free(connlimit_rb_cachep, rbconn); + } +} + +static unsigned int +count_tree(struct net *net, struct rb_root *root, + const struct nf_conntrack_tuple *tuple, + const union nf_inet_addr *addr, const union nf_inet_addr *mask, + u8 family) +{ + struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES]; + struct rb_node **rbnode, *parent; + struct xt_connlimit_rb *rbconn; + struct xt_connlimit_conn *conn; + unsigned int gc_count; + bool no_gc = false; + + restart: + gc_count = 0; + parent = NULL; + rbnode = &(root->rb_node); + while (*rbnode) { + int diff; + bool addit; + + rbconn = container_of(*rbnode, struct xt_connlimit_rb, node); + + parent = *rbnode; + diff = same_source_net(addr, mask, &rbconn->addr, family); + if (diff < 0) { + rbnode = &((*rbnode)->rb_left); + } else if (diff > 0) { + rbnode = &((*rbnode)->rb_right); + } else { + /* same source network -> be counted! */ + unsigned int count; + count = check_hlist(net, &rbconn->hhead, tuple, &addit); + + tree_nodes_free(root, gc_nodes, gc_count); + if (!addit) + return count; + + if (!add_hlist(&rbconn->hhead, tuple, addr)) + return 0; /* hotdrop */ + + return count + 1; + } + + if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes)) + continue; + + /* only used for GC on hhead, retval and 'addit' ignored */ + check_hlist(net, &rbconn->hhead, tuple, &addit); + if (hlist_empty(&rbconn->hhead)) + gc_nodes[gc_count++] = rbconn; + } + + if (gc_count) { + no_gc = true; + tree_nodes_free(root, gc_nodes, gc_count); + /* tree_node_free before new allocation permits + * allocator to re-use newly free'd object. + * + * This is a rare event; in most cases we will find + * existing node to re-use. (or gc_count is 0). + */ + goto restart; + } + + /* no match, need to insert new node */ + rbconn = kmem_cache_alloc(connlimit_rb_cachep, GFP_ATOMIC); + if (rbconn == NULL) + return 0; + + conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC); + if (conn == NULL) { + kmem_cache_free(connlimit_rb_cachep, rbconn); + return 0; + } + + conn->tuple = *tuple; + conn->addr = *addr; + rbconn->addr = *addr; + + INIT_HLIST_HEAD(&rbconn->hhead); + hlist_add_head(&conn->node, &rbconn->hhead); + + rb_link_node(&rbconn->node, parent, rbnode); + rb_insert_color(&rbconn->node, root); + return 1; +} + +static int count_them(struct net *net, + struct xt_connlimit_data *data, + const struct nf_conntrack_tuple *tuple, + const union nf_inet_addr *addr, + const union nf_inet_addr *mask, + u_int8_t family) +{ + struct rb_root *root; + int count; + u32 hash; + + if (family == NFPROTO_IPV6) { + hash = connlimit_iphash6(addr, mask); + root = &data->climit_root6[hash]; + } else { + hash = connlimit_iphash(addr->ip & mask->ip); + root = &data->climit_root4[hash]; } - return matches; + spin_lock_bh(&data->locks[hash % CONNLIMIT_LOCK_SLOTS]); + + count = count_tree(net, root, tuple, addr, mask, family); + + spin_unlock_bh(&data->locks[hash % CONNLIMIT_LOCK_SLOTS]); + + return count; } static bool @@ -183,7 +316,7 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) const struct nf_conntrack_tuple *tuple_ptr = &tuple; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; - int connections; + unsigned int connections; ct = nf_ct_get(skb, &ctinfo); if (ct != NULL) @@ -202,12 +335,9 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) iph->daddr : iph->saddr; } - spin_lock_bh(&info->data->lock); connections = count_them(net, info->data, tuple_ptr, &addr, &info->mask, par->family); - spin_unlock_bh(&info->data->lock); - - if (connections < 0) + if (connections == 0) /* kmalloc failed, drop it entirely */ goto hotdrop; @@ -247,29 +377,47 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) return -ENOMEM; } - spin_lock_init(&info->data->lock); - for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) - INIT_HLIST_HEAD(&info->data->iphash[i]); + for (i = 0; i < ARRAY_SIZE(info->data->locks); ++i) + spin_lock_init(&info->data->locks[i]); + + for (i = 0; i < ARRAY_SIZE(info->data->climit_root4); ++i) + info->data->climit_root4[i] = RB_ROOT; + for (i = 0; i < ARRAY_SIZE(info->data->climit_root6); ++i) + info->data->climit_root6[i] = RB_ROOT; return 0; } -static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) +static void destroy_tree(struct rb_root *r) { - const struct xt_connlimit_info *info = par->matchinfo; struct xt_connlimit_conn *conn; + struct xt_connlimit_rb *rbconn; struct hlist_node *n; - struct hlist_head *hash = info->data->iphash; + struct rb_node *node; + + while ((node = rb_first(r)) != NULL) { + rbconn = container_of(node, struct xt_connlimit_rb, node); + + rb_erase(node, r); + + hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node) + kmem_cache_free(connlimit_conn_cachep, conn); + + kmem_cache_free(connlimit_rb_cachep, rbconn); + } +} + +static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) +{ + const struct xt_connlimit_info *info = par->matchinfo; unsigned int i; nf_ct_l3proto_module_put(par->family); - for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) { - hlist_for_each_entry_safe(conn, n, &hash[i], node) { - hlist_del(&conn->node); - kfree(conn); - } - } + for (i = 0; i < ARRAY_SIZE(info->data->climit_root4); ++i) + destroy_tree(&info->data->climit_root4[i]); + for (i = 0; i < ARRAY_SIZE(info->data->climit_root6); ++i) + destroy_tree(&info->data->climit_root6[i]); kfree(info->data); } @@ -287,12 +435,37 @@ static struct xt_match connlimit_mt_reg __read_mostly = { static int __init connlimit_mt_init(void) { - return xt_register_match(&connlimit_mt_reg); + int ret; + + BUILD_BUG_ON(CONNLIMIT_LOCK_SLOTS > CONNLIMIT_SLOTS); + BUILD_BUG_ON((CONNLIMIT_SLOTS % CONNLIMIT_LOCK_SLOTS) != 0); + + connlimit_conn_cachep = kmem_cache_create("xt_connlimit_conn", + sizeof(struct xt_connlimit_conn), + 0, 0, NULL); + if (!connlimit_conn_cachep) + return -ENOMEM; + + connlimit_rb_cachep = kmem_cache_create("xt_connlimit_rb", + sizeof(struct xt_connlimit_rb), + 0, 0, NULL); + if (!connlimit_rb_cachep) { + kmem_cache_destroy(connlimit_conn_cachep); + return -ENOMEM; + } + ret = xt_register_match(&connlimit_mt_reg); + if (ret != 0) { + kmem_cache_destroy(connlimit_conn_cachep); + kmem_cache_destroy(connlimit_rb_cachep); + } + return ret; } static void __exit connlimit_mt_exit(void) { xt_unregister_match(&connlimit_mt_reg); + kmem_cache_destroy(connlimit_conn_cachep); + kmem_cache_destroy(connlimit_rb_cachep); } module_init(connlimit_mt_init); diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c index a4c7561698c5..89d53104c6b3 100644 --- a/net/netfilter/xt_ipcomp.c +++ b/net/netfilter/xt_ipcomp.c @@ -60,7 +60,7 @@ static bool comp_mt(const struct sk_buff *skb, struct xt_action_param *par) } return spi_match(compinfo->spis[0], compinfo->spis[1], - ntohl(chdr->cpi << 16), + ntohs(chdr->cpi), !!(compinfo->invflags & XT_IPCOMP_INV_SPI)); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 04748ab649c2..c2d585c4f7c5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1460,7 +1460,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nlk->netlink_bind && nlk->groups[0]) { int i; - for (i=0; i<nlk->ngroups; i++) { + for (i = 0; i < nlk->ngroups; i++) { if (test_bit(i, nlk->groups)) nlk->netlink_bind(i); } @@ -2343,6 +2343,11 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, } #endif + /* Record the max length of recvmsg() calls for future allocations */ + nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len); + nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len, + 16384); + copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; @@ -2549,7 +2554,7 @@ __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int fla struct nlmsghdr *nlh; int size = nlmsg_msg_size(len); - nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size)); + nlh = (struct nlmsghdr *)skb_put(skb, NLMSG_ALIGN(size)); nlh->nlmsg_type = type; nlh->nlmsg_len = size; nlh->nlmsg_flags = flags; @@ -2587,7 +2592,27 @@ static int netlink_dump(struct sock *sk) if (!netlink_rx_is_mmaped(sk) && atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; - skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL); + + /* NLMSG_GOODSIZE is small to avoid high order allocations being + * required, but it makes sense to _attempt_ a 16K bytes allocation + * to reduce number of system calls on dump operations, if user + * ever provided a big enough buffer. + */ + if (alloc_size < nlk->max_recvmsg_len) { + skb = netlink_alloc_skb(sk, + nlk->max_recvmsg_len, + nlk->portid, + GFP_KERNEL | + __GFP_NOWARN | + __GFP_NORETRY); + /* available room should be exact amount to avoid MSG_TRUNC */ + if (skb) + skb_reserve(skb, skb_tailroom(skb) - + nlk->max_recvmsg_len); + } + if (!skb) + skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, + GFP_KERNEL); if (!skb) goto errout_skb; netlink_skb_set_owner_r(skb, sk); diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index acbd774eeb7c..ed13a790b00e 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -31,6 +31,7 @@ struct netlink_sock { u32 ngroups; unsigned long *groups; unsigned long state; + size_t max_recvmsg_len; wait_queue_head_t wait; bool cb_running; struct netlink_callback cb; diff --git a/net/nfc/core.c b/net/nfc/core.c index ca1e65f4b133..819b87702b70 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -280,9 +280,6 @@ static struct nfc_target *nfc_find_target(struct nfc_dev *dev, u32 target_idx) { int i; - if (dev->n_targets == 0) - return NULL; - for (i = 0; i < dev->n_targets; i++) { if (dev->targets[i].idx == target_idx) return &dev->targets[i]; @@ -546,9 +543,9 @@ error: struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx) { - struct nfc_se *se, *n; + struct nfc_se *se; - list_for_each_entry_safe(se, n, &dev->secure_elements, list) + list_for_each_entry(se, &dev->secure_elements, list) if (se->idx == se_idx) return se; @@ -655,9 +652,6 @@ int nfc_set_remote_general_bytes(struct nfc_dev *dev, u8 *gb, u8 gb_len) { pr_debug("dev_name=%s gb_len=%d\n", dev_name(&dev->dev), gb_len); - if (gb_len > NFC_MAX_GT_LEN) - return -EINVAL; - return nfc_llcp_set_remote_gb(dev, gb, gb_len); } EXPORT_SYMBOL(nfc_set_remote_general_bytes); diff --git a/net/nfc/digital.h b/net/nfc/digital.h index 08b29b55ea63..3759add68b1b 100644 --- a/net/nfc/digital.h +++ b/net/nfc/digital.h @@ -72,6 +72,12 @@ void digital_poll_next_tech(struct nfc_digital_dev *ddev); int digital_in_send_sens_req(struct nfc_digital_dev *ddev, u8 rf_tech); int digital_in_send_sensf_req(struct nfc_digital_dev *ddev, u8 rf_tech); +int digital_in_send_iso15693_inv_req(struct nfc_digital_dev *ddev, u8 rf_tech); + +int digital_in_iso_dep_pull_sod(struct nfc_digital_dev *ddev, + struct sk_buff *skb); +int digital_in_iso_dep_push_sod(struct nfc_digital_dev *ddev, + struct sk_buff *skb); int digital_target_found(struct nfc_digital_dev *ddev, struct nfc_target *target, u8 protocol); diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index c129d1571ca6..e01e15dbf1ab 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -25,6 +25,8 @@ #define DIGITAL_PROTO_NFCF_RF_TECH \ (NFC_PROTO_FELICA_MASK | NFC_PROTO_NFC_DEP_MASK) +#define DIGITAL_PROTO_ISO15693_RF_TECH NFC_PROTO_ISO15693_MASK + struct digital_cmd { struct list_head queue; @@ -331,6 +333,18 @@ int digital_target_found(struct nfc_digital_dev *ddev, } break; + case NFC_PROTO_ISO15693: + framing = NFC_DIGITAL_FRAMING_ISO15693_T5T; + check_crc = digital_skb_check_crc_b; + add_crc = digital_skb_add_crc_b; + break; + + case NFC_PROTO_ISO14443: + framing = NFC_DIGITAL_FRAMING_NFCA_T4T; + check_crc = digital_skb_check_crc_a; + add_crc = digital_skb_add_crc_a; + break; + default: pr_err("Invalid protocol %d\n", protocol); return -EINVAL; @@ -461,7 +475,7 @@ static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols, digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106A, digital_in_send_sens_req); - if (im_protocols & DIGITAL_PROTO_NFCF_RF_TECH) { + if (matching_im_protocols & DIGITAL_PROTO_NFCF_RF_TECH) { digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_212F, digital_in_send_sensf_req); @@ -469,7 +483,11 @@ static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols, digital_in_send_sensf_req); } - if (tm_protocols & NFC_PROTO_NFC_DEP_MASK) { + if (matching_im_protocols & DIGITAL_PROTO_ISO15693_RF_TECH) + digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_ISO15693, + digital_in_send_iso15693_inv_req); + + if (matching_tm_protocols & NFC_PROTO_NFC_DEP_MASK) { if (ddev->ops->tg_listen_mdaa) { digital_add_poll_tech(ddev, 0, digital_tg_listen_mdaa); @@ -607,20 +625,30 @@ static void digital_in_send_complete(struct nfc_digital_dev *ddev, void *arg, if (IS_ERR(resp)) { rc = PTR_ERR(resp); + resp = NULL; goto done; } - if (ddev->curr_protocol == NFC_PROTO_MIFARE) + if (ddev->curr_protocol == NFC_PROTO_MIFARE) { rc = digital_in_recv_mifare_res(resp); - else - rc = ddev->skb_check_crc(resp); + /* crc check is done in digital_in_recv_mifare_res() */ + goto done; + } + if (ddev->curr_protocol == NFC_PROTO_ISO14443) { + rc = digital_in_iso_dep_pull_sod(ddev, resp); + if (rc) + goto done; + } + + rc = ddev->skb_check_crc(resp); + +done: if (rc) { kfree_skb(resp); resp = NULL; } -done: data_exch->cb(data_exch->cb_context, resp, rc); kfree(data_exch); @@ -632,6 +660,7 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, { struct nfc_digital_dev *ddev = nfc_get_drvdata(nfc_dev); struct digital_data_exch *data_exch; + int rc; data_exch = kzalloc(sizeof(struct digital_data_exch), GFP_KERNEL); if (!data_exch) { @@ -642,13 +671,27 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, data_exch->cb = cb; data_exch->cb_context = cb_context; - if (ddev->curr_protocol == NFC_PROTO_NFC_DEP) - return digital_in_send_dep_req(ddev, target, skb, data_exch); + if (ddev->curr_protocol == NFC_PROTO_NFC_DEP) { + rc = digital_in_send_dep_req(ddev, target, skb, data_exch); + goto exit; + } + + if (ddev->curr_protocol == NFC_PROTO_ISO14443) { + rc = digital_in_iso_dep_push_sod(ddev, skb); + if (rc) + goto exit; + } ddev->skb_add_crc(skb); - return digital_in_send_cmd(ddev, skb, 500, digital_in_send_complete, - data_exch); + rc = digital_in_send_cmd(ddev, skb, 500, digital_in_send_complete, + data_exch); + +exit: + if (rc) + kfree(data_exch); + + return rc; } static struct nfc_ops digital_nfc_ops = { @@ -700,6 +743,10 @@ struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops, ddev->protocols |= NFC_PROTO_FELICA_MASK; if (supported_protocols & NFC_PROTO_NFC_DEP_MASK) ddev->protocols |= NFC_PROTO_NFC_DEP_MASK; + if (supported_protocols & NFC_PROTO_ISO15693_MASK) + ddev->protocols |= NFC_PROTO_ISO15693_MASK; + if (supported_protocols & NFC_PROTO_ISO14443_MASK) + ddev->protocols |= NFC_PROTO_ISO14443_MASK; ddev->tx_headroom = tx_headroom + DIGITAL_MAX_HEADER_LEN; ddev->tx_tailroom = tx_tailroom + DIGITAL_CRC_LEN; diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c index 251c8c753ebe..278c3fed27e0 100644 --- a/net/nfc/digital_technology.c +++ b/net/nfc/digital_technology.c @@ -30,6 +30,7 @@ #define DIGITAL_SEL_RES_NFCID1_COMPLETE(sel_res) (!((sel_res) & 0x04)) #define DIGITAL_SEL_RES_IS_T2T(sel_res) (!((sel_res) & 0x60)) +#define DIGITAL_SEL_RES_IS_T4T(sel_res) ((sel_res) & 0x20) #define DIGITAL_SEL_RES_IS_NFC_DEP(sel_res) ((sel_res) & 0x40) #define DIGITAL_SENS_RES_IS_T1T(sens_res) (((sens_res) & 0x0C00) == 0x0C00) @@ -51,6 +52,34 @@ #define DIGITAL_SENSF_REQ_RC_SC 1 #define DIGITAL_SENSF_REQ_RC_AP 2 +#define DIGITAL_CMD_ISO15693_INVENTORY_REQ 0x01 + +#define DIGITAL_ISO15693_REQ_FLAG_DATA_RATE BIT(1) +#define DIGITAL_ISO15693_REQ_FLAG_INVENTORY BIT(2) +#define DIGITAL_ISO15693_REQ_FLAG_NB_SLOTS BIT(5) +#define DIGITAL_ISO15693_RES_FLAG_ERROR BIT(0) +#define DIGITAL_ISO15693_RES_IS_VALID(flags) \ + (!((flags) & DIGITAL_ISO15693_RES_FLAG_ERROR)) + +#define DIGITAL_ISO_DEP_I_PCB 0x02 +#define DIGITAL_ISO_DEP_PNI(pni) ((pni) & 0x01) + +#define DIGITAL_ISO_DEP_PCB_TYPE(pcb) ((pcb) & 0xC0) + +#define DIGITAL_ISO_DEP_I_BLOCK 0x00 + +#define DIGITAL_ISO_DEP_BLOCK_HAS_DID(pcb) ((pcb) & 0x08) + +static const u8 digital_ats_fsc[] = { + 16, 24, 32, 40, 48, 64, 96, 128, +}; + +#define DIGITAL_ATS_FSCI(t0) ((t0) & 0x0F) +#define DIGITAL_ATS_MAX_FSC 256 + +#define DIGITAL_RATS_BYTE1 0xE0 +#define DIGITAL_RATS_PARAM 0x80 + struct digital_sdd_res { u8 nfcid1[4]; u8 bcc; @@ -82,9 +111,127 @@ struct digital_sensf_res { u8 rd[2]; } __packed; +struct digital_iso15693_inv_req { + u8 flags; + u8 cmd; + u8 mask_len; + u64 mask; +} __packed; + +struct digital_iso15693_inv_res { + u8 flags; + u8 dsfid; + u64 uid; +} __packed; + static int digital_in_send_sdd_req(struct nfc_digital_dev *ddev, struct nfc_target *target); +int digital_in_iso_dep_pull_sod(struct nfc_digital_dev *ddev, + struct sk_buff *skb) +{ + u8 pcb; + u8 block_type; + + if (skb->len < 1) + return -EIO; + + pcb = *skb->data; + block_type = DIGITAL_ISO_DEP_PCB_TYPE(pcb); + + /* No support fo R-block nor S-block */ + if (block_type != DIGITAL_ISO_DEP_I_BLOCK) { + pr_err("ISO_DEP R-block and S-block not supported\n"); + return -EIO; + } + + if (DIGITAL_ISO_DEP_BLOCK_HAS_DID(pcb)) { + pr_err("DID field in ISO_DEP PCB not supported\n"); + return -EIO; + } + + skb_pull(skb, 1); + + return 0; +} + +int digital_in_iso_dep_push_sod(struct nfc_digital_dev *ddev, + struct sk_buff *skb) +{ + /* + * Chaining not supported so skb->len + 1 PCB byte + 2 CRC bytes must + * not be greater than remote FSC + */ + if (skb->len + 3 > ddev->target_fsc) + return -EIO; + + skb_push(skb, 1); + + *skb->data = DIGITAL_ISO_DEP_I_PCB | ddev->curr_nfc_dep_pni; + + ddev->curr_nfc_dep_pni = + DIGITAL_ISO_DEP_PNI(ddev->curr_nfc_dep_pni + 1); + + return 0; +} + +static void digital_in_recv_ats(struct nfc_digital_dev *ddev, void *arg, + struct sk_buff *resp) +{ + struct nfc_target *target = arg; + u8 fsdi; + int rc; + + if (IS_ERR(resp)) { + rc = PTR_ERR(resp); + resp = NULL; + goto exit; + } + + if (resp->len < 2) { + rc = -EIO; + goto exit; + } + + fsdi = DIGITAL_ATS_FSCI(resp->data[1]); + if (fsdi >= 8) + ddev->target_fsc = DIGITAL_ATS_MAX_FSC; + else + ddev->target_fsc = digital_ats_fsc[fsdi]; + + ddev->curr_nfc_dep_pni = 0; + + rc = digital_target_found(ddev, target, NFC_PROTO_ISO14443); + +exit: + dev_kfree_skb(resp); + kfree(target); + + if (rc) + digital_poll_next_tech(ddev); +} + +static int digital_in_send_rats(struct nfc_digital_dev *ddev, + struct nfc_target *target) +{ + int rc; + struct sk_buff *skb; + + skb = digital_skb_alloc(ddev, 2); + if (!skb) + return -ENOMEM; + + *skb_put(skb, 1) = DIGITAL_RATS_BYTE1; + *skb_put(skb, 1) = DIGITAL_RATS_PARAM; + + rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_ats, + target); + if (rc) + kfree_skb(skb); + + return rc; +} + static void digital_in_recv_sel_res(struct nfc_digital_dev *ddev, void *arg, struct sk_buff *resp) { @@ -122,8 +269,19 @@ static void digital_in_recv_sel_res(struct nfc_digital_dev *ddev, void *arg, goto exit_free_skb; } + target->sel_res = sel_res; + if (DIGITAL_SEL_RES_IS_T2T(sel_res)) { nfc_proto = NFC_PROTO_MIFARE; + } else if (DIGITAL_SEL_RES_IS_T4T(sel_res)) { + rc = digital_in_send_rats(ddev, target); + if (rc) + goto exit; + /* + * Skip target_found and don't free it for now. This will be + * done when receiving the ATS + */ + goto exit_free_skb; } else if (DIGITAL_SEL_RES_IS_NFC_DEP(sel_res)) { nfc_proto = NFC_PROTO_NFC_DEP; } else { @@ -131,8 +289,6 @@ static void digital_in_recv_sel_res(struct nfc_digital_dev *ddev, void *arg, goto exit; } - target->sel_res = sel_res; - rc = digital_target_found(ddev, target, nfc_proto); exit: @@ -473,6 +629,93 @@ int digital_in_send_sensf_req(struct nfc_digital_dev *ddev, u8 rf_tech) return rc; } +static void digital_in_recv_iso15693_inv_res(struct nfc_digital_dev *ddev, + void *arg, struct sk_buff *resp) +{ + struct digital_iso15693_inv_res *res; + struct nfc_target *target = NULL; + int rc; + + if (IS_ERR(resp)) { + rc = PTR_ERR(resp); + resp = NULL; + goto out_free_skb; + } + + if (resp->len != sizeof(*res)) { + rc = -EIO; + goto out_free_skb; + } + + res = (struct digital_iso15693_inv_res *)resp->data; + + if (!DIGITAL_ISO15693_RES_IS_VALID(res->flags)) { + PROTOCOL_ERR("ISO15693 - 10.3.1"); + rc = -EINVAL; + goto out_free_skb; + } + + target = kzalloc(sizeof(*target), GFP_KERNEL); + if (!target) { + rc = -ENOMEM; + goto out_free_skb; + } + + target->is_iso15693 = 1; + target->iso15693_dsfid = res->dsfid; + memcpy(target->iso15693_uid, &res->uid, sizeof(target->iso15693_uid)); + + rc = digital_target_found(ddev, target, NFC_PROTO_ISO15693); + + kfree(target); + +out_free_skb: + dev_kfree_skb(resp); + + if (rc) + digital_poll_next_tech(ddev); +} + +int digital_in_send_iso15693_inv_req(struct nfc_digital_dev *ddev, u8 rf_tech) +{ + struct digital_iso15693_inv_req *req; + struct sk_buff *skb; + int rc; + + rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH, + NFC_DIGITAL_RF_TECH_ISO15693); + if (rc) + return rc; + + rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING, + NFC_DIGITAL_FRAMING_ISO15693_INVENTORY); + if (rc) + return rc; + + skb = digital_skb_alloc(ddev, sizeof(*req)); + if (!skb) + return -ENOMEM; + + skb_put(skb, sizeof(*req) - sizeof(req->mask)); /* No mask */ + req = (struct digital_iso15693_inv_req *)skb->data; + + /* Single sub-carrier, high data rate, no AFI, single slot + * Inventory command + */ + req->flags = DIGITAL_ISO15693_REQ_FLAG_DATA_RATE | + DIGITAL_ISO15693_REQ_FLAG_INVENTORY | + DIGITAL_ISO15693_REQ_FLAG_NB_SLOTS; + req->cmd = DIGITAL_CMD_ISO15693_INVENTORY_REQ; + req->mask_len = 0; + + rc = digital_in_send_cmd(ddev, skb, 30, + digital_in_recv_iso15693_inv_res, NULL); + if (rc) + kfree_skb(skb); + + return rc; +} + static int digital_tg_send_sel_res(struct nfc_digital_dev *ddev) { struct sk_buff *skb; diff --git a/net/nfc/hci/llc.c b/net/nfc/hci/llc.c index a07d2b818487..1b90c0531852 100644 --- a/net/nfc/hci/llc.c +++ b/net/nfc/hci/llc.c @@ -20,14 +20,12 @@ #include "llc.h" -static struct list_head llc_engines; +static LIST_HEAD(llc_engines); int nfc_llc_init(void) { int r; - INIT_LIST_HEAD(&llc_engines); - r = nfc_llc_nop_register(); if (r) goto exit; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 6184bd1fba3a..b486f12ae243 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -27,7 +27,7 @@ static u8 llcp_magic[3] = {0x46, 0x66, 0x6d}; -static struct list_head llcp_devices; +static LIST_HEAD(llcp_devices); static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb); @@ -293,9 +293,9 @@ static void nfc_llcp_sdreq_timer(unsigned long data) struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev) { - struct nfc_llcp_local *local, *n; + struct nfc_llcp_local *local; - list_for_each_entry_safe(local, n, &llcp_devices, list) + list_for_each_entry(local, &llcp_devices, list) if (local->dev == dev) return local; @@ -609,14 +609,16 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) { - struct nfc_llcp_local *local = nfc_llcp_find_local(dev); + struct nfc_llcp_local *local; + + if (gb_len < 3 || gb_len > NFC_MAX_GT_LEN) + return -EINVAL; + local = nfc_llcp_find_local(dev); if (local == NULL) { pr_err("No LLCP device\n"); return -ENODEV; } - if (gb_len < 3) - return -EINVAL; memset(local->remote_gb, 0, NFC_MAX_GT_LEN); memcpy(local->remote_gb, gb, gb_len); @@ -1622,8 +1624,6 @@ void nfc_llcp_unregister_device(struct nfc_dev *dev) int __init nfc_llcp_init(void) { - INIT_LIST_HEAD(&llcp_devices); - return nfc_llcp_sock_init(); } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 56db888b1cd5..6c34ac978501 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -74,7 +74,7 @@ static int __nci_request(struct nci_dev *ndev, ndev->req_status = NCI_REQ_PEND; - init_completion(&ndev->req_completion); + reinit_completion(&ndev->req_completion); req(ndev, opt); completion_rc = wait_for_completion_interruptible_timeout(&ndev->req_completion, @@ -709,6 +709,7 @@ struct nci_dev *nci_allocate_device(struct nci_ops *ops, ndev->ops = ops; ndev->tx_headroom = tx_headroom; ndev->tx_tailroom = tx_tailroom; + init_completion(&ndev->req_completion); ndev->nfc_dev = nfc_allocate_device(&nci_nfc_ops, supported_protocols, diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c index f1d426f10cce..ec250e77763a 100644 --- a/net/nfc/nci/spi.c +++ b/net/nfc/nci/spi.c @@ -105,7 +105,7 @@ int nci_spi_send(struct nci_spi *nspi, if (ret != 0 || nspi->acknowledge_mode == NCI_SPI_CRC_DISABLED) goto done; - init_completion(&nspi->req_completion); + reinit_completion(&nspi->req_completion); completion_rc = wait_for_completion_interruptible_timeout( &nspi->req_completion, NCI_SPI_SEND_TIMEOUT); @@ -145,6 +145,7 @@ struct nci_spi *nci_spi_allocate_spi(struct spi_device *spi, nspi->spi = spi; nspi->ndev = ndev; + init_completion(&nspi->req_completion); return nspi; } diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index ebbf6fb88b35..43cb1c17e267 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -94,6 +94,14 @@ static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, target->sensf_res)) goto nla_put_failure; + if (target->is_iso15693) { + if (nla_put_u8(msg, NFC_ATTR_TARGET_ISO15693_DSFID, + target->iso15693_dsfid) || + nla_put(msg, NFC_ATTR_TARGET_ISO15693_UID, + sizeof(target->iso15693_uid), target->iso15693_uid)) + goto nla_put_failure; + } + return genlmsg_end(msg, hdr); nla_put_failure: diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 270b77dfac30..a3276e3c4feb 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -256,10 +256,10 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb) out: /* Update datapath statistics. */ - u64_stats_update_begin(&stats->sync); + u64_stats_update_begin(&stats->syncp); (*stats_counter)++; stats->n_mask_hit += n_mask_hit; - u64_stats_update_end(&stats->sync); + u64_stats_update_end(&stats->syncp); } static struct genl_family dp_packet_genl_family = { @@ -295,9 +295,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, err: stats = this_cpu_ptr(dp->stats_percpu); - u64_stats_update_begin(&stats->sync); + u64_stats_update_begin(&stats->syncp); stats->n_lost++; - u64_stats_update_end(&stats->sync); + u64_stats_update_end(&stats->syncp); return err; } @@ -610,9 +610,9 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats, percpu_stats = per_cpu_ptr(dp->stats_percpu, i); do { - start = u64_stats_fetch_begin_bh(&percpu_stats->sync); + start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); local_stats = *percpu_stats; - } while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start)); + } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); stats->n_hit += local_stats.n_hit; stats->n_missed += local_stats.n_missed; @@ -1219,18 +1219,12 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) if (err) goto err_free_dp; - dp->stats_percpu = alloc_percpu(struct dp_stats_percpu); + dp->stats_percpu = netdev_alloc_pcpu_stats(struct dp_stats_percpu); if (!dp->stats_percpu) { err = -ENOMEM; goto err_destroy_table; } - for_each_possible_cpu(i) { - struct dp_stats_percpu *dpath_stats; - dpath_stats = per_cpu_ptr(dp->stats_percpu, i); - u64_stats_init(&dpath_stats->sync); - } - dp->ports = kmalloc(DP_VPORT_HASH_BUCKETS * sizeof(struct hlist_head), GFP_KERNEL); if (!dp->ports) { diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 6be9fbb5e9cb..05317380fc03 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -55,7 +55,7 @@ struct dp_stats_percpu { u64 n_missed; u64 n_lost; u64 n_mask_hit; - struct u64_stats_sync sync; + struct u64_stats_sync syncp; }; /** diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 208dd9a26dd1..42c0f4a0b78c 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -121,7 +121,6 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, { struct vport *vport; size_t alloc_size; - int i; alloc_size = sizeof(struct vport); if (priv_size) { @@ -139,19 +138,12 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, vport->ops = ops; INIT_HLIST_NODE(&vport->dp_hash_node); - vport->percpu_stats = alloc_percpu(struct pcpu_sw_netstats); + vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!vport->percpu_stats) { kfree(vport); return ERR_PTR(-ENOMEM); } - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *vport_stats; - vport_stats = per_cpu_ptr(vport->percpu_stats, i); - u64_stats_init(&vport_stats->syncp); - } - - spin_lock_init(&vport->stats_lock); return vport; @@ -285,9 +277,9 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) percpu_stats = per_cpu_ptr(vport->percpu_stats, i); do { - start = u64_stats_fetch_begin_bh(&percpu_stats->syncp); + start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); local_stats = *percpu_stats; - } while (u64_stats_fetch_retry_bh(&percpu_stats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); stats->rx_bytes += local_stats.rx_bytes; stats->rx_packets += local_stats.rx_packets; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 48a6a93db296..01039d2b1695 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -243,40 +243,40 @@ static int packet_direct_xmit(struct sk_buff *skb) const struct net_device_ops *ops = dev->netdev_ops; netdev_features_t features; struct netdev_queue *txq; + int ret = NETDEV_TX_BUSY; u16 queue_map; - int ret; if (unlikely(!netif_running(dev) || - !netif_carrier_ok(dev))) { - kfree_skb(skb); - return NET_XMIT_DROP; - } + !netif_carrier_ok(dev))) + goto drop; features = netif_skb_features(skb); if (skb_needs_linearize(skb, features) && - __skb_linearize(skb)) { - kfree_skb(skb); - return NET_XMIT_DROP; - } + __skb_linearize(skb)) + goto drop; queue_map = skb_get_queue_mapping(skb); txq = netdev_get_tx_queue(dev, queue_map); - __netif_tx_lock_bh(txq); - if (unlikely(netif_xmit_frozen_or_stopped(txq))) { - ret = NETDEV_TX_BUSY; - kfree_skb(skb); - goto out; + local_bh_disable(); + + HARD_TX_LOCK(dev, txq, smp_processor_id()); + if (!netif_xmit_frozen_or_stopped(txq)) { + ret = ops->ndo_start_xmit(skb, dev); + if (ret == NETDEV_TX_OK) + txq_trans_update(txq); } + HARD_TX_UNLOCK(dev, txq); - ret = ops->ndo_start_xmit(skb, dev); - if (likely(dev_xmit_complete(ret))) - txq_trans_update(txq); - else + local_bh_enable(); + + if (!dev_xmit_complete(ret)) kfree_skb(skb); -out: - __netif_tx_unlock_bh(txq); + return ret; +drop: + kfree_skb(skb); + return NET_XMIT_DROP; } static struct net_device *packet_cached_dev_get(struct packet_sock *po) @@ -1277,7 +1277,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_scale(skb->rxhash, num); + return reciprocal_scale(skb_get_hash(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, @@ -1362,7 +1362,6 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, if (!skb) return 0; } - skb_get_hash(skb); idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: @@ -2257,8 +2256,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(!(dev->flags & IFF_UP))) goto out_put; - reserve = dev->hard_header_len; - + reserve = dev->hard_header_len + VLAN_HLEN; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); @@ -2285,8 +2283,19 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_status; tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, - addr, hlen); + addr, hlen); + if (tp_len > dev->mtu + dev->hard_header_len) { + struct ethhdr *ehdr; + /* Earlier code assumed this would be a VLAN pkt, + * double-check this now that we have the actual + * packet in hand. + */ + skb_reset_mac_header(skb); + ehdr = eth_hdr(skb); + if (ehdr->h_proto != htons(ETH_P_8021Q)) + tp_len = -EMSGSIZE; + } if (unlikely(tp_len < 0)) { if (po->tp_loss) { __packet_set_status(po, ph, diff --git a/net/rds/iw.c b/net/rds/iw.c index 7826d46baa70..589935661d66 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr) ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); /* due to this, we will claim to support IB devices unless we check node_type. */ - if (ret || cm_id->device->node_type != RDMA_NODE_RNIC) + if (ret || !cm_id->device || + cm_id->device->node_type != RDMA_NODE_RNIC) ret = -EADDRNOTAVAIL; rdsdebug("addr %pI4 ret %d node type %d\n", diff --git a/net/rfkill/core.c b/net/rfkill/core.c index ed7e0b4e7f90..b3b16c070a7f 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -789,7 +789,8 @@ void rfkill_resume_polling(struct rfkill *rfkill) if (!rfkill->ops->poll) return; - schedule_work(&rfkill->poll_work.work); + queue_delayed_work(system_power_efficient_wq, + &rfkill->poll_work, 0); } EXPORT_SYMBOL(rfkill_resume_polling); @@ -894,7 +895,8 @@ static void rfkill_poll(struct work_struct *work) */ rfkill->ops->poll(rfkill, rfkill->data); - schedule_delayed_work(&rfkill->poll_work, + queue_delayed_work(system_power_efficient_wq, + &rfkill->poll_work, round_jiffies_relative(POLL_INTERVAL)); } @@ -958,7 +960,8 @@ int __must_check rfkill_register(struct rfkill *rfkill) INIT_WORK(&rfkill->sync_work, rfkill_sync_work); if (rfkill->ops->poll) - schedule_delayed_work(&rfkill->poll_work, + queue_delayed_work(system_power_efficient_wq, + &rfkill->poll_work, round_jiffies_relative(POLL_INTERVAL)); if (!rfkill->persistent || rfkill_epo_lock_active) { diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index d1c3429b69ed..ec126f91276b 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -20,9 +20,8 @@ af-rxrpc-y := \ ar-skbuff.o \ ar-transport.o -ifeq ($(CONFIG_PROC_FS),y) -af-rxrpc-y += ar-proc.o -endif +af-rxrpc-$(CONFIG_PROC_FS) += ar-proc.o +af-rxrpc-$(CONFIG_SYSCTL) += sysctl.o obj-$(CONFIG_AF_RXRPC) += af-rxrpc.o diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index e61aa6001c65..7b1670489638 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -838,6 +838,12 @@ static int __init af_rxrpc_init(void) goto error_key_type_s; } + ret = rxrpc_sysctl_init(); + if (ret < 0) { + printk(KERN_CRIT "RxRPC: Cannot register sysctls\n"); + goto error_sysctls; + } + #ifdef CONFIG_PROC_FS proc_create("rxrpc_calls", 0, init_net.proc_net, &rxrpc_call_seq_fops); proc_create("rxrpc_conns", 0, init_net.proc_net, @@ -845,6 +851,8 @@ static int __init af_rxrpc_init(void) #endif return 0; +error_sysctls: + unregister_key_type(&key_type_rxrpc_s); error_key_type_s: unregister_key_type(&key_type_rxrpc); error_key_type: @@ -865,6 +873,7 @@ error_call_jar: static void __exit af_rxrpc_exit(void) { _enter(""); + rxrpc_sysctl_exit(); unregister_key_type(&key_type_rxrpc_s); unregister_key_type(&key_type_rxrpc); sock_unregister(PF_RXRPC); diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c index cd97a0ce48d8..c6be17a959a6 100644 --- a/net/rxrpc/ar-ack.c +++ b/net/rxrpc/ar-ack.c @@ -19,7 +19,49 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -static unsigned int rxrpc_ack_defer = 1; +/* + * How long to wait before scheduling ACK generation after seeing a + * packet with RXRPC_REQUEST_ACK set (in jiffies). + */ +unsigned rxrpc_requested_ack_delay = 1; + +/* + * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). + * + * We use this when we've received new data packets. If those packets aren't + * all consumed within this time we will send a DELAY ACK if an ACK was not + * requested to let the sender know it doesn't need to resend. + */ +unsigned rxrpc_soft_ack_delay = 1 * HZ; + +/* + * How long to wait before scheduling an ACK with subtype IDLE (in jiffies). + * + * We use this when we've consumed some previously soft-ACK'd packets when + * further packets aren't immediately received to decide when to send an IDLE + * ACK let the other end know that it can free up its Tx buffer space. + */ +unsigned rxrpc_idle_ack_delay = 0.5 * HZ; + +/* + * Receive window size in packets. This indicates the maximum number of + * unconsumed received packets we're willing to retain in memory. Once this + * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further + * packets. + */ +unsigned rxrpc_rx_window_size = 32; + +/* + * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet + * made by gluing normal packets together that we're willing to handle. + */ +unsigned rxrpc_rx_mtu = 5692; + +/* + * The maximum number of fragments in a received jumbo packet that we tell the + * sender that we're willing to handle. + */ +unsigned rxrpc_rx_jumbo_max = 4; static const char *rxrpc_acks(u8 reason) { @@ -82,24 +124,23 @@ void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, switch (ack_reason) { case RXRPC_ACK_DELAY: _debug("run delay timer"); - call->ack_timer.expires = jiffies + rxrpc_ack_timeout * HZ; - add_timer(&call->ack_timer); - return; + expiry = rxrpc_soft_ack_delay; + goto run_timer; case RXRPC_ACK_IDLE: if (!immediate) { _debug("run defer timer"); - expiry = 1; + expiry = rxrpc_idle_ack_delay; goto run_timer; } goto cancel_timer; case RXRPC_ACK_REQUESTED: - if (!rxrpc_ack_defer) + expiry = rxrpc_requested_ack_delay; + if (!expiry) goto cancel_timer; if (!immediate || serial == cpu_to_be32(1)) { _debug("run defer timer"); - expiry = rxrpc_ack_defer; goto run_timer; } @@ -1174,11 +1215,11 @@ send_ACK: mtu = call->conn->trans->peer->if_mtu; mtu -= call->conn->trans->peer->hdrsize; ackinfo.maxMTU = htonl(mtu); - ackinfo.rwind = htonl(32); + ackinfo.rwind = htonl(rxrpc_rx_window_size); /* permit the peer to send us jumbo packets if it wants to */ - ackinfo.rxMTU = htonl(5692); - ackinfo.jumbo_max = htonl(4); + ackinfo.rxMTU = htonl(rxrpc_rx_mtu); + ackinfo.jumbo_max = htonl(rxrpc_rx_jumbo_max); hdr.serial = htonl(atomic_inc_return(&call->conn->serial)); _proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }", diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/ar-call.c index a3bbb360a3f9..a9e05db0f5d5 100644 --- a/net/rxrpc/ar-call.c +++ b/net/rxrpc/ar-call.c @@ -12,10 +12,22 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/circ_buf.h> +#include <linux/hashtable.h> +#include <linux/spinlock_types.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include "ar-internal.h" +/* + * Maximum lifetime of a call (in jiffies). + */ +unsigned rxrpc_max_call_lifetime = 60 * HZ; + +/* + * Time till dead call expires after last use (in jiffies). + */ +unsigned rxrpc_dead_call_expiry = 2 * HZ; + const char *const rxrpc_call_states[] = { [RXRPC_CALL_CLIENT_SEND_REQUEST] = "ClSndReq", [RXRPC_CALL_CLIENT_AWAIT_REPLY] = "ClAwtRpl", @@ -38,8 +50,6 @@ const char *const rxrpc_call_states[] = { struct kmem_cache *rxrpc_call_jar; LIST_HEAD(rxrpc_calls); DEFINE_RWLOCK(rxrpc_call_lock); -static unsigned int rxrpc_call_max_lifetime = 60; -static unsigned int rxrpc_dead_call_timeout = 2; static void rxrpc_destroy_call(struct work_struct *work); static void rxrpc_call_life_expired(unsigned long _call); @@ -47,6 +57,145 @@ static void rxrpc_dead_call_expired(unsigned long _call); static void rxrpc_ack_time_expired(unsigned long _call); static void rxrpc_resend_time_expired(unsigned long _call); +static DEFINE_SPINLOCK(rxrpc_call_hash_lock); +static DEFINE_HASHTABLE(rxrpc_call_hash, 10); + +/* + * Hash function for rxrpc_call_hash + */ +static unsigned long rxrpc_call_hashfunc( + u8 clientflag, + __be32 cid, + __be32 call_id, + __be32 epoch, + __be16 service_id, + sa_family_t proto, + void *localptr, + unsigned int addr_size, + const u8 *peer_addr) +{ + const u16 *p; + unsigned int i; + unsigned long key; + u32 hcid = ntohl(cid); + + _enter(""); + + key = (unsigned long)localptr; + /* We just want to add up the __be32 values, so forcing the + * cast should be okay. + */ + key += (__force u32)epoch; + key += (__force u16)service_id; + key += (__force u32)call_id; + key += (hcid & RXRPC_CIDMASK) >> RXRPC_CIDSHIFT; + key += hcid & RXRPC_CHANNELMASK; + key += clientflag; + key += proto; + /* Step through the peer address in 16-bit portions for speed */ + for (i = 0, p = (const u16 *)peer_addr; i < addr_size >> 1; i++, p++) + key += *p; + _leave(" key = 0x%lx", key); + return key; +} + +/* + * Add a call to the hashtable + */ +static void rxrpc_call_hash_add(struct rxrpc_call *call) +{ + unsigned long key; + unsigned int addr_size = 0; + + _enter(""); + switch (call->proto) { + case AF_INET: + addr_size = sizeof(call->peer_ip.ipv4_addr); + break; + case AF_INET6: + addr_size = sizeof(call->peer_ip.ipv6_addr); + break; + default: + break; + } + key = rxrpc_call_hashfunc(call->in_clientflag, call->cid, + call->call_id, call->epoch, + call->service_id, call->proto, + call->conn->trans->local, addr_size, + call->peer_ip.ipv6_addr); + /* Store the full key in the call */ + call->hash_key = key; + spin_lock(&rxrpc_call_hash_lock); + hash_add_rcu(rxrpc_call_hash, &call->hash_node, key); + spin_unlock(&rxrpc_call_hash_lock); + _leave(""); +} + +/* + * Remove a call from the hashtable + */ +static void rxrpc_call_hash_del(struct rxrpc_call *call) +{ + _enter(""); + spin_lock(&rxrpc_call_hash_lock); + hash_del_rcu(&call->hash_node); + spin_unlock(&rxrpc_call_hash_lock); + _leave(""); +} + +/* + * Find a call in the hashtable and return it, or NULL if it + * isn't there. + */ +struct rxrpc_call *rxrpc_find_call_hash( + u8 clientflag, + __be32 cid, + __be32 call_id, + __be32 epoch, + __be16 service_id, + void *localptr, + sa_family_t proto, + const u8 *peer_addr) +{ + unsigned long key; + unsigned int addr_size = 0; + struct rxrpc_call *call = NULL; + struct rxrpc_call *ret = NULL; + + _enter(""); + switch (proto) { + case AF_INET: + addr_size = sizeof(call->peer_ip.ipv4_addr); + break; + case AF_INET6: + addr_size = sizeof(call->peer_ip.ipv6_addr); + break; + default: + break; + } + + key = rxrpc_call_hashfunc(clientflag, cid, call_id, epoch, + service_id, proto, localptr, addr_size, + peer_addr); + hash_for_each_possible_rcu(rxrpc_call_hash, call, hash_node, key) { + if (call->hash_key == key && + call->call_id == call_id && + call->cid == cid && + call->in_clientflag == clientflag && + call->service_id == service_id && + call->proto == proto && + call->local == localptr && + memcmp(call->peer_ip.ipv6_addr, peer_addr, + addr_size) == 0 && + call->epoch == epoch) { + ret = call; + break; + } + } + _leave(" = %p", ret); + return ret; +} + /* * allocate a new call */ @@ -91,7 +240,7 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) call->rx_data_expect = 1; call->rx_data_eaten = 0; call->rx_first_oos = 0; - call->ackr_win_top = call->rx_data_eaten + 1 + RXRPC_MAXACKS; + call->ackr_win_top = call->rx_data_eaten + 1 + rxrpc_rx_window_size; call->creation_jif = jiffies; return call; } @@ -128,11 +277,31 @@ static struct rxrpc_call *rxrpc_alloc_client_call( return ERR_PTR(ret); } + /* Record copies of information for hashtable lookup */ + call->proto = rx->proto; + call->local = trans->local; + switch (call->proto) { + case AF_INET: + call->peer_ip.ipv4_addr = + trans->peer->srx.transport.sin.sin_addr.s_addr; + break; + case AF_INET6: + memcpy(call->peer_ip.ipv6_addr, + trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8, + sizeof(call->peer_ip.ipv6_addr)); + break; + } + call->epoch = call->conn->epoch; + call->service_id = call->conn->service_id; + call->in_clientflag = call->conn->in_clientflag; + /* Add the new call to the hashtable */ + rxrpc_call_hash_add(call); + spin_lock(&call->conn->trans->peer->lock); list_add(&call->error_link, &call->conn->trans->peer->error_targets); spin_unlock(&call->conn->trans->peer->lock); - call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ; + call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime; add_timer(&call->lifetimer); _leave(" = %p", call); @@ -320,9 +489,12 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, parent = *p; call = rb_entry(parent, struct rxrpc_call, conn_node); - if (call_id < call->call_id) + /* The tree is sorted in order of the __be32 value without + * turning it into host order. + */ + if ((__force u32)call_id < (__force u32)call->call_id) p = &(*p)->rb_left; - else if (call_id > call->call_id) + else if ((__force u32)call_id > (__force u32)call->call_id) p = &(*p)->rb_right; else goto old_call; @@ -347,9 +519,31 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, list_add_tail(&call->link, &rxrpc_calls); write_unlock_bh(&rxrpc_call_lock); + /* Record copies of information for hashtable lookup */ + call->proto = rx->proto; + call->local = conn->trans->local; + switch (call->proto) { + case AF_INET: + call->peer_ip.ipv4_addr = + conn->trans->peer->srx.transport.sin.sin_addr.s_addr; + break; + case AF_INET6: + memcpy(call->peer_ip.ipv6_addr, + conn->trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8, + sizeof(call->peer_ip.ipv6_addr)); + break; + default: + break; + } + call->epoch = conn->epoch; + call->service_id = conn->service_id; + call->in_clientflag = conn->in_clientflag; + /* Add the new call to the hashtable */ + rxrpc_call_hash_add(call); + _net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id); - call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ; + call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime; add_timer(&call->lifetimer); _leave(" = %p {%d} [new]", call, call->debug_id); return call; @@ -533,7 +727,7 @@ void rxrpc_release_call(struct rxrpc_call *call) del_timer_sync(&call->resend_timer); del_timer_sync(&call->ack_timer); del_timer_sync(&call->lifetimer); - call->deadspan.expires = jiffies + rxrpc_dead_call_timeout * HZ; + call->deadspan.expires = jiffies + rxrpc_dead_call_expiry; add_timer(&call->deadspan); _leave(""); @@ -665,6 +859,9 @@ static void rxrpc_cleanup_call(struct rxrpc_call *call) rxrpc_put_connection(call->conn); } + /* Remove the call from the hash */ + rxrpc_call_hash_del(call); + if (call->acks_window) { _debug("kill Tx window %d", CIRC_CNT(call->acks_head, call->acks_tail, diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c index 7bf5b5b9e8b9..6631f4f1e39b 100644 --- a/net/rxrpc/ar-connection.c +++ b/net/rxrpc/ar-connection.c @@ -18,11 +18,15 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" +/* + * Time till a connection expires after last use (in seconds). + */ +unsigned rxrpc_connection_expiry = 10 * 60; + static void rxrpc_connection_reaper(struct work_struct *work); LIST_HEAD(rxrpc_connections); DEFINE_RWLOCK(rxrpc_connection_lock); -static unsigned long rxrpc_connection_timeout = 10 * 60; static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper); /* @@ -862,7 +866,7 @@ static void rxrpc_connection_reaper(struct work_struct *work) spin_lock(&conn->trans->client_lock); write_lock(&conn->trans->conn_lock); - reap_time = conn->put_time + rxrpc_connection_timeout; + reap_time = conn->put_time + rxrpc_connection_expiry; if (atomic_read(&conn->usage) > 0) { ; @@ -916,7 +920,7 @@ void __exit rxrpc_destroy_all_connections(void) { _enter(""); - rxrpc_connection_timeout = 0; + rxrpc_connection_expiry = 0; cancel_delayed_work(&rxrpc_connection_reap); rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c index a9206087b4d7..db57458c824c 100644 --- a/net/rxrpc/ar-error.c +++ b/net/rxrpc/ar-error.c @@ -83,6 +83,7 @@ void rxrpc_UDP_error_report(struct sock *sk) if (mtu == 0) { /* they didn't give us a size, estimate one */ + mtu = peer->if_mtu; if (mtu > 1500) { mtu >>= 1; if (mtu < 1500) diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index 529572f18d1f..73742647c135 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -25,8 +25,6 @@ #include <net/net_namespace.h> #include "ar-internal.h" -unsigned long rxrpc_ack_timeout = 1; - const char *rxrpc_pkts[] = { "?00", "DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG", @@ -349,8 +347,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) * it */ if (sp->hdr.flags & RXRPC_REQUEST_ACK) { _proto("ACK Requested on %%%u", serial); - rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, - !(sp->hdr.flags & RXRPC_MORE_PACKETS)); + rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, false); } switch (sp->hdr.type) { @@ -526,36 +523,38 @@ protocol_error: * post an incoming packet to the appropriate call/socket to deal with * - must get rid of the sk_buff, either by freeing it or by queuing it */ -static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn, +static void rxrpc_post_packet_to_call(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp; - struct rxrpc_call *call; - struct rb_node *p; - __be32 call_id; - - _enter("%p,%p", conn, skb); - read_lock_bh(&conn->lock); + _enter("%p,%p", call, skb); sp = rxrpc_skb(skb); - /* look at extant calls by channel number first */ - call = conn->channels[ntohl(sp->hdr.cid) & RXRPC_CHANNELMASK]; - if (!call || call->call_id != sp->hdr.callNumber) - goto call_not_extant; - _debug("extant call [%d]", call->state); - ASSERTCMP(call->conn, ==, conn); read_lock(&call->state_lock); switch (call->state) { case RXRPC_CALL_LOCALLY_ABORTED: - if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events)) + if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events)) { rxrpc_queue_call(call); + goto free_unlock; + } case RXRPC_CALL_REMOTELY_ABORTED: case RXRPC_CALL_NETWORK_ERROR: case RXRPC_CALL_DEAD: + goto dead_call; + case RXRPC_CALL_COMPLETE: + case RXRPC_CALL_CLIENT_FINAL_ACK: + /* complete server call */ + if (call->conn->in_clientflag) + goto dead_call; + /* resend last packet of a completed call */ + _debug("final ack again"); + rxrpc_get_call(call); + set_bit(RXRPC_CALL_ACK_FINAL, &call->events); + rxrpc_queue_call(call); goto free_unlock; default: break; @@ -563,7 +562,6 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn, read_unlock(&call->state_lock); rxrpc_get_call(call); - read_unlock_bh(&conn->lock); if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && sp->hdr.flags & RXRPC_JUMBO_PACKET) @@ -574,78 +572,16 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn, rxrpc_put_call(call); goto done; -call_not_extant: - /* search the completed calls in case what we're dealing with is - * there */ - _debug("call not extant"); - - call_id = sp->hdr.callNumber; - p = conn->calls.rb_node; - while (p) { - call = rb_entry(p, struct rxrpc_call, conn_node); - - if (call_id < call->call_id) - p = p->rb_left; - else if (call_id > call->call_id) - p = p->rb_right; - else - goto found_completed_call; - } - dead_call: - /* it's a either a really old call that we no longer remember or its a - * new incoming call */ - read_unlock_bh(&conn->lock); - - if (sp->hdr.flags & RXRPC_CLIENT_INITIATED && - sp->hdr.seq == cpu_to_be32(1)) { - _debug("incoming call"); - skb_queue_tail(&conn->trans->local->accept_queue, skb); - rxrpc_queue_work(&conn->trans->local->acceptor); - goto done; - } - - _debug("dead call"); - skb->priority = RX_CALL_DEAD; - rxrpc_reject_packet(conn->trans->local, skb); - goto done; - - /* resend last packet of a completed call - * - client calls may have been aborted or ACK'd - * - server calls may have been aborted - */ -found_completed_call: - _debug("completed call"); - - if (atomic_read(&call->usage) == 0) - goto dead_call; - - /* synchronise any state changes */ - read_lock(&call->state_lock); - ASSERTIFCMP(call->state != RXRPC_CALL_CLIENT_FINAL_ACK, - call->state, >=, RXRPC_CALL_COMPLETE); - - if (call->state == RXRPC_CALL_LOCALLY_ABORTED || - call->state == RXRPC_CALL_REMOTELY_ABORTED || - call->state == RXRPC_CALL_DEAD) { - read_unlock(&call->state_lock); - goto dead_call; - } - - if (call->conn->in_clientflag) { - read_unlock(&call->state_lock); - goto dead_call; /* complete server call */ + if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { + skb->priority = RX_CALL_DEAD; + rxrpc_reject_packet(call->conn->trans->local, skb); + goto unlock; } - - _debug("final ack again"); - rxrpc_get_call(call); - set_bit(RXRPC_CALL_ACK_FINAL, &call->events); - rxrpc_queue_call(call); - free_unlock: - read_unlock(&call->state_lock); - read_unlock_bh(&conn->lock); rxrpc_free_skb(skb); +unlock: + read_unlock(&call->state_lock); done: _leave(""); } @@ -664,17 +600,42 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, rxrpc_queue_conn(conn); } +static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local, + struct sk_buff *skb, + struct rxrpc_skb_priv *sp) +{ + struct rxrpc_peer *peer; + struct rxrpc_transport *trans; + struct rxrpc_connection *conn; + + peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr, + udp_hdr(skb)->source); + if (IS_ERR(peer)) + goto cant_find_conn; + + trans = rxrpc_find_transport(local, peer); + rxrpc_put_peer(peer); + if (!trans) + goto cant_find_conn; + + conn = rxrpc_find_connection(trans, &sp->hdr); + rxrpc_put_transport(trans); + if (!conn) + goto cant_find_conn; + + return conn; +cant_find_conn: + return NULL; +} + /* * handle data received on the local endpoint * - may be called in interrupt context */ void rxrpc_data_ready(struct sock *sk, int count) { - struct rxrpc_connection *conn; - struct rxrpc_transport *trans; struct rxrpc_skb_priv *sp; struct rxrpc_local *local; - struct rxrpc_peer *peer; struct sk_buff *skb; int ret; @@ -749,27 +710,34 @@ void rxrpc_data_ready(struct sock *sk, int count) (sp->hdr.callNumber == 0 || sp->hdr.seq == 0)) goto bad_message; - peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr, udp_hdr(skb)->source); - if (IS_ERR(peer)) - goto cant_route_call; + if (sp->hdr.callNumber == 0) { + /* This is a connection-level packet. These should be + * fairly rare, so the extra overhead of looking them up the + * old-fashioned way doesn't really hurt */ + struct rxrpc_connection *conn; - trans = rxrpc_find_transport(local, peer); - rxrpc_put_peer(peer); - if (!trans) - goto cant_route_call; + conn = rxrpc_conn_from_local(local, skb, sp); + if (!conn) + goto cant_route_call; - conn = rxrpc_find_connection(trans, &sp->hdr); - rxrpc_put_transport(trans); - if (!conn) - goto cant_route_call; - - _debug("CONN %p {%d}", conn, conn->debug_id); - - if (sp->hdr.callNumber == 0) + _debug("CONN %p {%d}", conn, conn->debug_id); rxrpc_post_packet_to_conn(conn, skb); - else - rxrpc_post_packet_to_call(conn, skb); - rxrpc_put_connection(conn); + rxrpc_put_connection(conn); + } else { + struct rxrpc_call *call; + u8 in_clientflag = 0; + + if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) + in_clientflag = RXRPC_CLIENT_INITIATED; + call = rxrpc_find_call_hash(in_clientflag, sp->hdr.cid, + sp->hdr.callNumber, sp->hdr.epoch, + sp->hdr.serviceId, local, AF_INET, + (u8 *)&ip_hdr(skb)->saddr); + if (call) + rxrpc_post_packet_to_call(call, skb); + else + goto cant_route_call; + } rxrpc_put_local(local); return; @@ -790,8 +758,10 @@ cant_route_call: skb->priority = RX_CALL_DEAD; } - _debug("reject"); - rxrpc_reject_packet(local, skb); + if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { + _debug("reject type %d",sp->hdr.type); + rxrpc_reject_packet(local, skb); + } rxrpc_put_local(local); _leave(" [no call]"); return; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5f43675ee1df..c831d44b0841 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -396,9 +396,20 @@ struct rxrpc_call { #define RXRPC_ACKR_WINDOW_ASZ DIV_ROUND_UP(RXRPC_MAXACKS, BITS_PER_LONG) unsigned long ackr_window[RXRPC_ACKR_WINDOW_ASZ + 1]; + struct hlist_node hash_node; + unsigned long hash_key; /* Full hash key */ + u8 in_clientflag; /* Copy of conn->in_clientflag for hashing */ + struct rxrpc_local *local; /* Local endpoint. Used for hashing. */ + sa_family_t proto; /* Frame protocol */ /* the following should all be in net order */ __be32 cid; /* connection ID + channel index */ __be32 call_id; /* call ID on connection */ + __be32 epoch; /* epoch of this connection */ + __be16 service_id; /* service ID */ + union { /* Peer IP address for hashing */ + __be32 ipv4_addr; + __u8 ipv6_addr[16]; /* Anticipates eventual IPv6 support */ + } peer_ip; }; /* @@ -433,6 +444,13 @@ int rxrpc_reject_call(struct rxrpc_sock *); /* * ar-ack.c */ +extern unsigned rxrpc_requested_ack_delay; +extern unsigned rxrpc_soft_ack_delay; +extern unsigned rxrpc_idle_ack_delay; +extern unsigned rxrpc_rx_window_size; +extern unsigned rxrpc_rx_mtu; +extern unsigned rxrpc_rx_jumbo_max; + void __rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool); void rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool); void rxrpc_process_call(struct work_struct *); @@ -440,10 +458,14 @@ void rxrpc_process_call(struct work_struct *); /* * ar-call.c */ +extern unsigned rxrpc_max_call_lifetime; +extern unsigned rxrpc_dead_call_expiry; extern struct kmem_cache *rxrpc_call_jar; extern struct list_head rxrpc_calls; extern rwlock_t rxrpc_call_lock; +struct rxrpc_call *rxrpc_find_call_hash(u8, __be32, __be32, __be32, + __be16, void *, sa_family_t, const u8 *); struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *, struct rxrpc_transport *, struct rxrpc_conn_bundle *, @@ -460,6 +482,7 @@ void __exit rxrpc_destroy_all_calls(void); /* * ar-connection.c */ +extern unsigned rxrpc_connection_expiry; extern struct list_head rxrpc_connections; extern rwlock_t rxrpc_connection_lock; @@ -493,7 +516,6 @@ void rxrpc_UDP_error_handler(struct work_struct *); /* * ar-input.c */ -extern unsigned long rxrpc_ack_timeout; extern const char *rxrpc_pkts[]; void rxrpc_data_ready(struct sock *, int); @@ -504,6 +526,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *); * ar-local.c */ extern rwlock_t rxrpc_local_lock; + struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *); void rxrpc_put_local(struct rxrpc_local *); void __exit rxrpc_destroy_all_locals(void); @@ -522,7 +545,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t, /* * ar-output.c */ -extern int rxrpc_resend_timeout; +extern unsigned rxrpc_resend_timeout; int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *); int rxrpc_client_sendmsg(struct kiocb *, struct rxrpc_sock *, @@ -572,6 +595,8 @@ void rxrpc_packet_destructor(struct sk_buff *); /* * ar-transport.c */ +extern unsigned rxrpc_transport_expiry; + struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *, struct rxrpc_peer *, gfp_t); void rxrpc_put_transport(struct rxrpc_transport *); @@ -580,6 +605,17 @@ struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *, struct rxrpc_peer *); /* + * sysctl.c + */ +#ifdef CONFIG_SYSCTL +extern int __init rxrpc_sysctl_init(void); +extern void rxrpc_sysctl_exit(void); +#else +static inline int __init rxrpc_sysctl_init(void) { return 0; } +static inline void rxrpc_sysctl_exit(void) {} +#endif + +/* * debug tracing */ extern unsigned int rxrpc_debug; diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index d0e8f1c1898a..0b4b9a79f5ab 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -18,7 +18,10 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -int rxrpc_resend_timeout = 4; +/* + * Time till packet resend (in jiffies). + */ +unsigned rxrpc_resend_timeout = 4 * HZ; static int rxrpc_send_data(struct kiocb *iocb, struct rxrpc_sock *rx, @@ -487,7 +490,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, ntohl(sp->hdr.serial), ntohl(sp->hdr.seq)); sp->need_resend = false; - sp->resend_at = jiffies + rxrpc_resend_timeout * HZ; + sp->resend_at = jiffies + rxrpc_resend_timeout; if (!test_and_set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags)) { _debug("run timer"); call->resend_timer.expires = sp->resend_at; @@ -666,6 +669,7 @@ static int rxrpc_send_data(struct kiocb *iocb, /* add the packet to the send queue if it's now full */ if (sp->remain <= 0 || (segment == 0 && !more)) { struct rxrpc_connection *conn = call->conn; + uint32_t seq; size_t pad; /* pad out if we're using security */ @@ -678,11 +682,12 @@ static int rxrpc_send_data(struct kiocb *iocb, memset(skb_put(skb, pad), 0, pad); } + seq = atomic_inc_return(&call->sequence); + sp->hdr.epoch = conn->epoch; sp->hdr.cid = call->cid; sp->hdr.callNumber = call->call_id; - sp->hdr.seq = - htonl(atomic_inc_return(&call->sequence)); + sp->hdr.seq = htonl(seq); sp->hdr.serial = htonl(atomic_inc_return(&conn->serial)); sp->hdr.type = RXRPC_PACKET_TYPE_DATA; @@ -697,6 +702,8 @@ static int rxrpc_send_data(struct kiocb *iocb, else if (CIRC_SPACE(call->acks_head, call->acks_tail, call->acks_winsz) > 1) sp->hdr.flags |= RXRPC_MORE_PACKETS; + if (more && seq & 1) + sp->hdr.flags |= RXRPC_REQUEST_ACK; ret = rxrpc_secure_packet( call, skb, skb->mark, diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 34b5490dde65..e9aaa65c0778 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -180,16 +180,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, if (copy > len - copied) copy = len - copied; - if (skb->ip_summed == CHECKSUM_UNNECESSARY || - skb->ip_summed == CHECKSUM_PARTIAL) { - ret = skb_copy_datagram_iovec(skb, offset, - msg->msg_iov, copy); - } else { - ret = skb_copy_and_csum_datagram_iovec(skb, offset, - msg->msg_iov); - if (ret == -EINVAL) - goto csum_copy_error; - } + ret = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copy); if (ret < 0) goto copy_error; @@ -348,20 +339,6 @@ copy_error: _leave(" = %d", ret); return ret; -csum_copy_error: - _debug("csum error"); - release_sock(&rx->sk); - if (continue_call) - rxrpc_put_call(continue_call); - rxrpc_kill_skb(skb); - if (!(flags & MSG_PEEK)) { - if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) - BUG(); - } - skb_kill_datagram(&rx->sk, skb, flags); - rxrpc_put_call(call); - return -EAGAIN; - wait_interrupted: ret = sock_intr_errno(timeo); wait_error: diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/ar-skbuff.c index de755e04d29c..4cfab49e329d 100644 --- a/net/rxrpc/ar-skbuff.c +++ b/net/rxrpc/ar-skbuff.c @@ -83,9 +83,14 @@ static void rxrpc_hard_ACK_data(struct rxrpc_call *call, rxrpc_request_final_ACK(call); } else if (atomic_dec_and_test(&call->ackr_not_idle) && test_and_clear_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags)) { + /* We previously soft-ACK'd some received packets that have now + * been consumed, so send a hard-ACK if no more packets are + * immediately forthcoming to allow the transmitter to free up + * its Tx bufferage. + */ _debug("send Rx idle ACK"); __rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, sp->hdr.serial, - true); + false); } spin_unlock_bh(&call->lock); diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c index 92df566930b9..1976dec84f29 100644 --- a/net/rxrpc/ar-transport.c +++ b/net/rxrpc/ar-transport.c @@ -17,11 +17,15 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" +/* + * Time after last use at which transport record is cleaned up. + */ +unsigned rxrpc_transport_expiry = 3600 * 24; + static void rxrpc_transport_reaper(struct work_struct *work); static LIST_HEAD(rxrpc_transports); static DEFINE_RWLOCK(rxrpc_transport_lock); -static unsigned long rxrpc_transport_timeout = 3600 * 24; static DECLARE_DELAYED_WORK(rxrpc_transport_reap, rxrpc_transport_reaper); /* @@ -235,7 +239,7 @@ static void rxrpc_transport_reaper(struct work_struct *work) if (likely(atomic_read(&trans->usage) > 0)) continue; - reap_time = trans->put_time + rxrpc_transport_timeout; + reap_time = trans->put_time + rxrpc_transport_expiry; if (reap_time <= now) list_move_tail(&trans->link, &graveyard); else if (reap_time < earliest) @@ -271,7 +275,7 @@ void __exit rxrpc_destroy_all_transports(void) { _enter(""); - rxrpc_transport_timeout = 0; + rxrpc_transport_expiry = 0; cancel_delayed_work(&rxrpc_transport_reap); rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0); diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c new file mode 100644 index 000000000000..50a98a910eb1 --- /dev/null +++ b/net/rxrpc/sysctl.c @@ -0,0 +1,146 @@ +/* sysctls for configuring RxRPC operating parameters + * + * Copyright (C) 2014 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/sysctl.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +static struct ctl_table_header *rxrpc_sysctl_reg_table; +static const unsigned zero = 0; +static const unsigned one = 1; +static const unsigned four = 4; +static const unsigned n_65535 = 65535; +static const unsigned n_max_acks = RXRPC_MAXACKS; + +/* + * RxRPC operating parameters. + * + * See Documentation/networking/rxrpc.txt and the variable definitions for more + * information on the individual parameters. + */ +static struct ctl_table rxrpc_sysctl_table[] = { + /* Values measured in milliseconds */ + { + .procname = "req_ack_delay", + .data = &rxrpc_requested_ack_delay, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&zero, + }, + { + .procname = "soft_ack_delay", + .data = &rxrpc_soft_ack_delay, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, + { + .procname = "idle_ack_delay", + .data = &rxrpc_idle_ack_delay, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, + { + .procname = "resend_timeout", + .data = &rxrpc_resend_timeout, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, + + /* Values measured in seconds but used in jiffies */ + { + .procname = "max_call_lifetime", + .data = &rxrpc_max_call_lifetime, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + .extra1 = (void *)&one, + }, + { + .procname = "dead_call_expiry", + .data = &rxrpc_dead_call_expiry, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + .extra1 = (void *)&one, + }, + + /* Values measured in seconds */ + { + .procname = "connection_expiry", + .data = &rxrpc_connection_expiry, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + }, + { + .procname = "transport_expiry", + .data = &rxrpc_transport_expiry, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + }, + + /* Non-time values */ + { + .procname = "rx_window_size", + .data = &rxrpc_rx_window_size, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + .extra2 = (void *)&n_max_acks, + }, + { + .procname = "rx_mtu", + .data = &rxrpc_rx_mtu, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + .extra1 = (void *)&n_65535, + }, + { + .procname = "rx_jumbo_max", + .data = &rxrpc_rx_jumbo_max, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + .extra2 = (void *)&four, + }, + + { } +}; + +int __init rxrpc_sysctl_init(void) +{ + rxrpc_sysctl_reg_table = register_net_sysctl(&init_net, "net/rxrpc", + rxrpc_sysctl_table); + if (!rxrpc_sysctl_reg_table) + return -ENOMEM; + return 0; +} + +void rxrpc_sysctl_exit(void) +{ + if (rxrpc_sysctl_reg_table) + unregister_net_sysctl_table(rxrpc_sysctl_reg_table); +} diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 72bdc7166345..8a5ba5add4bc 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -27,8 +27,11 @@ #include <net/act_api.h> #include <net/netlink.h> -void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) +void tcf_hash_destroy(struct tc_action *a) { + struct tcf_common *p = a->priv; + struct tcf_hashinfo *hinfo = a->ops->hinfo; + spin_lock_bh(&hinfo->lock); hlist_del(&p->tcfc_head); spin_unlock_bh(&hinfo->lock); @@ -42,18 +45,22 @@ void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) } EXPORT_SYMBOL(tcf_hash_destroy); -int tcf_hash_release(struct tcf_common *p, int bind, - struct tcf_hashinfo *hinfo) +int tcf_hash_release(struct tc_action *a, int bind) { + struct tcf_common *p = a->priv; int ret = 0; if (p) { if (bind) p->tcfc_bindcnt--; + else if (p->tcfc_bindcnt > 0) + return -EPERM; p->tcfc_refcnt--; if (p->tcfc_bindcnt <= 0 && p->tcfc_refcnt <= 0) { - tcf_hash_destroy(p, hinfo); + if (a->ops->cleanup) + a->ops->cleanup(a, bind); + tcf_hash_destroy(a); ret = 1; } } @@ -118,6 +125,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) struct tcf_common *p; struct nlattr *nest; int i = 0, n_i = 0; + int ret = -EINVAL; nest = nla_nest_start(skb, a->order); if (nest == NULL) @@ -127,10 +135,13 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) for (i = 0; i < (hinfo->hmask + 1); i++) { head = &hinfo->htab[tcf_hash(i, hinfo->hmask)]; hlist_for_each_entry_safe(p, n, head, tcfc_head) { - if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) { + a->priv = p; + ret = tcf_hash_release(a, 0); + if (ret == ACT_P_DELETED) { module_put(a->ops->owner); n_i++; - } + } else if (ret < 0) + goto nla_put_failure; } } if (nla_put_u32(skb, TCA_FCNT, n_i)) @@ -140,7 +151,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) return n_i; nla_put_failure: nla_nest_cancel(skb, nest); - return -EINVAL; + return ret; } static int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, @@ -198,7 +209,7 @@ int tcf_hash_search(struct tc_action *a, u32 index) } EXPORT_SYMBOL(tcf_hash_search); -struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind) +int tcf_hash_check(u32 index, struct tc_action *a, int bind) { struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = NULL; @@ -207,19 +218,30 @@ struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind) p->tcfc_bindcnt++; p->tcfc_refcnt++; a->priv = p; + return 1; } - return p; + return 0; } EXPORT_SYMBOL(tcf_hash_check); -struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, - struct tc_action *a, int size, int bind) +void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est) +{ + struct tcf_common *pc = a->priv; + if (est) + gen_kill_estimator(&pc->tcfc_bstats, + &pc->tcfc_rate_est); + kfree_rcu(pc, tcfc_rcu); +} +EXPORT_SYMBOL(tcf_hash_cleanup); + +int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, + int size, int bind) { struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = kzalloc(size, GFP_KERNEL); if (unlikely(!p)) - return ERR_PTR(-ENOMEM); + return -ENOMEM; p->tcfc_refcnt = 1; if (bind) p->tcfc_bindcnt = 1; @@ -234,17 +256,19 @@ struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, &p->tcfc_lock, est); if (err) { kfree(p); - return ERR_PTR(err); + return err; } } a->priv = (void *) p; - return p; + return 0; } EXPORT_SYMBOL(tcf_hash_create); -void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo) +void tcf_hash_insert(struct tc_action *a) { + struct tcf_common *p = a->priv; + struct tcf_hashinfo *hinfo = a->ops->hinfo; unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask); spin_lock_bh(&hinfo->lock); @@ -256,12 +280,13 @@ EXPORT_SYMBOL(tcf_hash_insert); static LIST_HEAD(act_base); static DEFINE_RWLOCK(act_mod_lock); -int tcf_register_action(struct tc_action_ops *act) +int tcf_register_action(struct tc_action_ops *act, unsigned int mask) { struct tc_action_ops *a; + int err; - /* Must supply act, dump, cleanup and init */ - if (!act->act || !act->dump || !act->cleanup || !act->init) + /* Must supply act, dump and init */ + if (!act->act || !act->dump || !act->init) return -EINVAL; /* Supply defaults */ @@ -270,10 +295,21 @@ int tcf_register_action(struct tc_action_ops *act) if (!act->walk) act->walk = tcf_generic_walker; + act->hinfo = kmalloc(sizeof(struct tcf_hashinfo), GFP_KERNEL); + if (!act->hinfo) + return -ENOMEM; + err = tcf_hashinfo_init(act->hinfo, mask); + if (err) { + kfree(act->hinfo); + return err; + } + write_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { write_unlock(&act_mod_lock); + tcf_hashinfo_destroy(act->hinfo); + kfree(act->hinfo); return -EEXIST; } } @@ -292,6 +328,8 @@ int tcf_unregister_action(struct tc_action_ops *act) list_for_each_entry(a, &act_base, head) { if (a == act) { list_del(&act->head); + tcf_hashinfo_destroy(act->hinfo); + kfree(act->hinfo); err = 0; break; } @@ -368,16 +406,21 @@ exec_done: } EXPORT_SYMBOL(tcf_action_exec); -void tcf_action_destroy(struct list_head *actions, int bind) +int tcf_action_destroy(struct list_head *actions, int bind) { struct tc_action *a, *tmp; + int ret = 0; list_for_each_entry_safe(a, tmp, actions, list) { - if (a->ops->cleanup(a, bind) == ACT_P_DELETED) + ret = tcf_hash_release(a, bind); + if (ret == ACT_P_DELETED) module_put(a->ops->owner); + else if (ret < 0) + return ret; list_del(&a->list); kfree(a); } + return ret; } int @@ -642,6 +685,20 @@ act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, return rtnl_unicast(skb, net, portid); } +static struct tc_action *create_a(int i) +{ + struct tc_action *act; + + act = kzalloc(sizeof(*act), GFP_KERNEL); + if (act == NULL) { + pr_debug("create_a: failed to alloc!\n"); + return NULL; + } + act->order = i; + INIT_LIST_HEAD(&act->list); + return act; +} + static struct tc_action * tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) { @@ -661,11 +718,10 @@ tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) index = nla_get_u32(tb[TCA_ACT_INDEX]); err = -ENOMEM; - a = kzalloc(sizeof(struct tc_action), GFP_KERNEL); + a = create_a(0); if (a == NULL) goto err_out; - INIT_LIST_HEAD(&a->list); err = -EINVAL; a->ops = tc_lookup_action(tb[TCA_ACT_KIND]); if (a->ops == NULL) /* could happen in batch of actions */ @@ -695,20 +751,6 @@ static void cleanup_a(struct list_head *actions) } } -static struct tc_action *create_a(int i) -{ - struct tc_action *act; - - act = kzalloc(sizeof(*act), GFP_KERNEL); - if (act == NULL) { - pr_debug("create_a: failed to alloc!\n"); - return NULL; - } - act->order = i; - INIT_LIST_HEAD(&act->list); - return act; -} - static int tca_action_flush(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid) { @@ -720,18 +762,12 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, struct nlattr *nest; struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; - struct tc_action *a = create_a(0); + struct tc_action a; int err = -ENOMEM; - if (a == NULL) { - pr_debug("tca_action_flush: couldnt create tc_action\n"); - return err; - } - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { pr_debug("tca_action_flush: failed skb alloc\n"); - kfree(a); return err; } @@ -743,8 +779,10 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, err = -EINVAL; kind = tb[TCA_ACT_KIND]; - a->ops = tc_lookup_action(kind); - if (a->ops == NULL) /*some idjot trying to flush unknown action */ + memset(&a, 0, sizeof(struct tc_action)); + INIT_LIST_HEAD(&a.list); + a.ops = tc_lookup_action(kind); + if (a.ops == NULL) /*some idjot trying to flush unknown action */ goto err_out; nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); @@ -759,7 +797,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, if (nest == NULL) goto out_module_put; - err = a->ops->walk(skb, &dcb, RTM_DELACTION, a); + err = a.ops->walk(skb, &dcb, RTM_DELACTION, &a); if (err < 0) goto out_module_put; if (err == 0) @@ -769,8 +807,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, nlh->nlmsg_len = skb_tail_pointer(skb) - b; nlh->nlmsg_flags |= NLM_F_ROOT; - module_put(a->ops->owner); - kfree(a); + module_put(a.ops->owner); err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); if (err > 0) @@ -779,11 +816,10 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, return err; out_module_put: - module_put(a->ops->owner); + module_put(a.ops->owner); err_out: noflush_out: kfree_skb(skb); - kfree(a); return err; } @@ -805,7 +841,11 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, } /* now do the delete */ - tcf_action_destroy(actions, 0); + ret = tcf_action_destroy(actions, 0); + if (ret < 0) { + kfree_skb(skb); + return ret; + } ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 2210187c45c2..edbf40dac709 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -37,7 +37,6 @@ #include <net/tc_act/tc_csum.h> #define CSUM_TAB_MASK 15 -static struct tcf_hashinfo csum_hash_info; static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, @@ -48,7 +47,6 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, { struct nlattr *tb[TCA_CSUM_MAX + 1]; struct tc_csum *parm; - struct tcf_common *pc; struct tcf_csum *p; int ret = 0, err; @@ -63,38 +61,31 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + if (ret) + return ret; ret = ACT_P_CREATED; } else { if (bind)/* dont override defaults */ return 0; - tcf_hash_release(pc, bind, a->ops->hinfo); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; } - p = to_tcf_csum(pc); + p = to_tcf_csum(a); spin_lock_bh(&p->tcf_lock); p->tcf_action = parm->action; p->update_flags = parm->update_flags; spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_csum_cleanup(struct tc_action *a, int bind) -{ - struct tcf_csum *p = a->priv; - return tcf_hash_release(&p->common, bind, &csum_hash_info); -} - /** * tcf_csum_skb_nextlayer - Get next layer pointer * @skb: sk_buff to use @@ -569,12 +560,10 @@ nla_put_failure: static struct tc_action_ops act_csum_ops = { .kind = "csum", - .hinfo = &csum_hash_info, .type = TCA_ACT_CSUM, .owner = THIS_MODULE, .act = tcf_csum, .dump = tcf_csum_dump, - .cleanup = tcf_csum_cleanup, .init = tcf_csum_init, }; @@ -583,11 +572,7 @@ MODULE_LICENSE("GPL"); static int __init csum_init_module(void) { - int err = tcf_hashinfo_init(&csum_hash_info, CSUM_TAB_MASK); - if (err) - return err; - - return tcf_register_action(&act_csum_ops); + return tcf_register_action(&act_csum_ops, CSUM_TAB_MASK); } static void __exit csum_cleanup_module(void) diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index a0eed30d5811..d6bcbd9f7791 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -24,7 +24,6 @@ #include <net/tc_act/tc_gact.h> #define GACT_TAB_MASK 15 -static struct tcf_hashinfo gact_hash_info; #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) @@ -57,7 +56,6 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *tb[TCA_GACT_MAX + 1]; struct tc_gact *parm; struct tcf_gact *gact; - struct tcf_common *pc; int ret = 0; int err; #ifdef CONFIG_GACT_PROB @@ -86,21 +84,20 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } #endif - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind); + if (ret) + return ret; ret = ACT_P_CREATED; } else { if (bind)/* dont override defaults */ return 0; - tcf_hash_release(pc, bind, a->ops->hinfo); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; } - gact = to_gact(pc); + gact = to_gact(a); spin_lock_bh(&gact->tcf_lock); gact->tcf_action = parm->action; @@ -113,19 +110,10 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, #endif spin_unlock_bh(&gact->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_gact_cleanup(struct tc_action *a, int bind) -{ - struct tcf_gact *gact = a->priv; - - if (gact) - return tcf_hash_release(&gact->common, bind, a->ops->hinfo); - return 0; -} - static int tcf_gact(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -191,12 +179,10 @@ nla_put_failure: static struct tc_action_ops act_gact_ops = { .kind = "gact", - .hinfo = &gact_hash_info, .type = TCA_ACT_GACT, .owner = THIS_MODULE, .act = tcf_gact, .dump = tcf_gact_dump, - .cleanup = tcf_gact_cleanup, .init = tcf_gact_init, }; @@ -206,21 +192,17 @@ MODULE_LICENSE("GPL"); static int __init gact_init_module(void) { - int err = tcf_hashinfo_init(&gact_hash_info, GACT_TAB_MASK); - if (err) - return err; #ifdef CONFIG_GACT_PROB pr_info("GACT probability on\n"); #else pr_info("GACT probability NOT on\n"); #endif - return tcf_register_action(&act_gact_ops); + return tcf_register_action(&act_gact_ops, GACT_TAB_MASK); } static void __exit gact_cleanup_module(void) { tcf_unregister_action(&act_gact_ops); - tcf_hashinfo_destroy(&gact_hash_info); } module_init(gact_init_module); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 0a6d62174027..8a64a0734aee 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -29,7 +29,6 @@ #define IPT_TAB_MASK 15 -static struct tcf_hashinfo ipt_hash_info; static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook) { @@ -69,22 +68,12 @@ static void ipt_destroy_target(struct xt_entry_target *t) module_put(par.target->me); } -static int tcf_ipt_release(struct tcf_ipt *ipt, int bind) +static void tcf_ipt_release(struct tc_action *a, int bind) { - int ret = 0; - if (ipt) { - if (bind) - ipt->tcf_bindcnt--; - ipt->tcf_refcnt--; - if (ipt->tcf_bindcnt <= 0 && ipt->tcf_refcnt <= 0) { - ipt_destroy_target(ipt->tcfi_t); - kfree(ipt->tcfi_tname); - kfree(ipt->tcfi_t); - tcf_hash_destroy(&ipt->common, &ipt_hash_info); - ret = ACT_P_DELETED; - } - } - return ret; + struct tcf_ipt *ipt = to_ipt(a); + ipt_destroy_target(ipt->tcfi_t); + kfree(ipt->tcfi_tname); + kfree(ipt->tcfi_t); } static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { @@ -99,7 +88,6 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, { struct nlattr *tb[TCA_IPT_MAX + 1]; struct tcf_ipt *ipt; - struct tcf_common *pc; struct xt_entry_target *td, *t; char *tname; int ret = 0, err; @@ -125,21 +113,20 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (tb[TCA_IPT_INDEX] != NULL) index = nla_get_u32(tb[TCA_IPT_INDEX]); - pc = tcf_hash_check(index, a, bind); - if (!pc) { - pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(index, a, bind) ) { + ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind); + if (ret) + return ret; ret = ACT_P_CREATED; } else { if (bind)/* dont override defaults */ return 0; - tcf_ipt_release(to_ipt(pc), bind); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; } - ipt = to_ipt(pc); + ipt = to_ipt(a); hook = nla_get_u32(tb[TCA_IPT_HOOK]); @@ -170,7 +157,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, ipt->tcfi_hook = hook; spin_unlock_bh(&ipt->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; err3: @@ -178,21 +165,11 @@ err3: err2: kfree(tname); err1: - if (ret == ACT_P_CREATED) { - if (est) - gen_kill_estimator(&pc->tcfc_bstats, - &pc->tcfc_rate_est); - kfree_rcu(pc, tcfc_rcu); - } + if (ret == ACT_P_CREATED) + tcf_hash_cleanup(a, est); return err; } -static int tcf_ipt_cleanup(struct tc_action *a, int bind) -{ - struct tcf_ipt *ipt = a->priv; - return tcf_ipt_release(ipt, bind); -} - static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -284,23 +261,21 @@ nla_put_failure: static struct tc_action_ops act_ipt_ops = { .kind = "ipt", - .hinfo = &ipt_hash_info, .type = TCA_ACT_IPT, .owner = THIS_MODULE, .act = tcf_ipt, .dump = tcf_ipt_dump, - .cleanup = tcf_ipt_cleanup, + .cleanup = tcf_ipt_release, .init = tcf_ipt_init, }; static struct tc_action_ops act_xt_ops = { .kind = "xt", - .hinfo = &ipt_hash_info, .type = TCA_ACT_XT, .owner = THIS_MODULE, .act = tcf_ipt, .dump = tcf_ipt_dump, - .cleanup = tcf_ipt_cleanup, + .cleanup = tcf_ipt_release, .init = tcf_ipt_init, }; @@ -311,20 +286,16 @@ MODULE_ALIAS("act_xt"); static int __init ipt_init_module(void) { - int ret1, ret2, err; - err = tcf_hashinfo_init(&ipt_hash_info, IPT_TAB_MASK); - if (err) - return err; + int ret1, ret2; - ret1 = tcf_register_action(&act_xt_ops); + ret1 = tcf_register_action(&act_xt_ops, IPT_TAB_MASK); if (ret1 < 0) printk("Failed to load xt action\n"); - ret2 = tcf_register_action(&act_ipt_ops); + ret2 = tcf_register_action(&act_ipt_ops, IPT_TAB_MASK); if (ret2 < 0) printk("Failed to load ipt action\n"); if (ret1 < 0 && ret2 < 0) { - tcf_hashinfo_destroy(&ipt_hash_info); return ret1; } else return 0; @@ -334,7 +305,6 @@ static void __exit ipt_cleanup_module(void) { tcf_unregister_action(&act_xt_ops); tcf_unregister_action(&act_ipt_ops); - tcf_hashinfo_destroy(&ipt_hash_info); } module_init(ipt_init_module); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 0b2c6d39d396..4f912c0e225b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -31,23 +31,13 @@ #define MIRRED_TAB_MASK 7 static LIST_HEAD(mirred_list); -static struct tcf_hashinfo mirred_hash_info; -static int tcf_mirred_release(struct tcf_mirred *m, int bind) +static void tcf_mirred_release(struct tc_action *a, int bind) { - if (m) { - if (bind) - m->tcf_bindcnt--; - m->tcf_refcnt--; - if (!m->tcf_bindcnt && m->tcf_refcnt <= 0) { - list_del(&m->tcfm_list); - if (m->tcfm_dev) - dev_put(m->tcfm_dev); - tcf_hash_destroy(&m->common, &mirred_hash_info); - return 1; - } - } - return 0; + struct tcf_mirred *m = to_mirred(a); + list_del(&m->tcfm_list); + if (m->tcfm_dev) + dev_put(m->tcfm_dev); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { @@ -61,7 +51,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *tb[TCA_MIRRED_MAX + 1]; struct tc_mirred *parm; struct tcf_mirred *m; - struct tcf_common *pc; struct net_device *dev; int ret, ok_push = 0; @@ -101,21 +90,20 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, dev = NULL; } - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { + if (!tcf_hash_check(parm->index, a, bind)) { if (dev == NULL) return -EINVAL; - pc = tcf_hash_create(parm->index, est, a, sizeof(*m), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + ret = tcf_hash_create(parm->index, est, a, sizeof(*m), bind); + if (ret) + return ret; ret = ACT_P_CREATED; } else { if (!ovr) { - tcf_mirred_release(to_mirred(pc), bind); + tcf_hash_release(a, bind); return -EEXIST; } } - m = to_mirred(pc); + m = to_mirred(a); spin_lock_bh(&m->tcf_lock); m->tcf_action = parm->action; @@ -131,21 +119,12 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&m->tcf_lock); if (ret == ACT_P_CREATED) { list_add(&m->tcfm_list, &mirred_list); - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); } return ret; } -static int tcf_mirred_cleanup(struct tc_action *a, int bind) -{ - struct tcf_mirred *m = a->priv; - - if (m) - return tcf_mirred_release(m, bind); - return 0; -} - static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -254,12 +233,11 @@ static struct notifier_block mirred_device_notifier = { static struct tc_action_ops act_mirred_ops = { .kind = "mirred", - .hinfo = &mirred_hash_info, .type = TCA_ACT_MIRRED, .owner = THIS_MODULE, .act = tcf_mirred, .dump = tcf_mirred_dump, - .cleanup = tcf_mirred_cleanup, + .cleanup = tcf_mirred_release, .init = tcf_mirred_init, }; @@ -273,19 +251,13 @@ static int __init mirred_init_module(void) if (err) return err; - err = tcf_hashinfo_init(&mirred_hash_info, MIRRED_TAB_MASK); - if (err) { - unregister_netdevice_notifier(&mirred_device_notifier); - return err; - } pr_info("Mirror/redirect action on\n"); - return tcf_register_action(&act_mirred_ops); + return tcf_register_action(&act_mirred_ops, MIRRED_TAB_MASK); } static void __exit mirred_cleanup_module(void) { tcf_unregister_action(&act_mirred_ops); - tcf_hashinfo_destroy(&mirred_hash_info); unregister_netdevice_notifier(&mirred_device_notifier); } diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 81f0404bb335..270a030d5fd0 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -31,8 +31,6 @@ #define NAT_TAB_MASK 15 -static struct tcf_hashinfo nat_hash_info; - static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { [TCA_NAT_PARMS] = { .len = sizeof(struct tc_nat) }, }; @@ -44,7 +42,6 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_nat *parm; int ret = 0, err; struct tcf_nat *p; - struct tcf_common *pc; if (nla == NULL) return -EINVAL; @@ -57,20 +54,19 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + if (ret) + return ret; ret = ACT_P_CREATED; } else { if (bind) return 0; - tcf_hash_release(pc, bind, a->ops->hinfo); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; } - p = to_tcf_nat(pc); + p = to_tcf_nat(a); spin_lock_bh(&p->tcf_lock); p->old_addr = parm->old_addr; @@ -82,18 +78,11 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_nat_cleanup(struct tc_action *a, int bind) -{ - struct tcf_nat *p = a->priv; - - return tcf_hash_release(&p->common, bind, &nat_hash_info); -} - static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -293,12 +282,10 @@ nla_put_failure: static struct tc_action_ops act_nat_ops = { .kind = "nat", - .hinfo = &nat_hash_info, .type = TCA_ACT_NAT, .owner = THIS_MODULE, .act = tcf_nat, .dump = tcf_nat_dump, - .cleanup = tcf_nat_cleanup, .init = tcf_nat_init, }; @@ -307,16 +294,12 @@ MODULE_LICENSE("GPL"); static int __init nat_init_module(void) { - int err = tcf_hashinfo_init(&nat_hash_info, NAT_TAB_MASK); - if (err) - return err; - return tcf_register_action(&act_nat_ops); + return tcf_register_action(&act_nat_ops, NAT_TAB_MASK); } static void __exit nat_cleanup_module(void) { tcf_unregister_action(&act_nat_ops); - tcf_hashinfo_destroy(&nat_hash_info); } module_init(nat_init_module); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index be3f0f6875bb..5f9bcb2e080b 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -25,8 +25,6 @@ #define PEDIT_TAB_MASK 15 -static struct tcf_hashinfo pedit_hash_info; - static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, }; @@ -39,7 +37,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct tc_pedit *parm; int ret = 0, err; struct tcf_pedit *p; - struct tcf_common *pc; struct tc_pedit_key *keys = NULL; int ksize; @@ -57,26 +54,22 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (nla_len(tb[TCA_PEDIT_PARMS]) < sizeof(*parm) + ksize) return -EINVAL; - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { + if (!tcf_hash_check(parm->index, a, bind)) { if (!parm->nkeys) return -EINVAL; - pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); - p = to_pedit(pc); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + if (ret) + return ret; + p = to_pedit(a); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { - if (est) - gen_kill_estimator(&pc->tcfc_bstats, - &pc->tcfc_rate_est); - kfree_rcu(pc, tcfc_rcu); + tcf_hash_cleanup(a, est); return -ENOMEM; } ret = ACT_P_CREATED; } else { - p = to_pedit(pc); - tcf_hash_release(pc, bind, a->ops->hinfo); + p = to_pedit(a); + tcf_hash_release(a, bind); if (bind) return 0; if (!ovr) @@ -100,22 +93,15 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, memcpy(p->tcfp_keys, parm->keys, ksize); spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_pedit_cleanup(struct tc_action *a, int bind) +static void tcf_pedit_cleanup(struct tc_action *a, int bind) { struct tcf_pedit *p = a->priv; - - if (p) { - struct tc_pedit_key *keys = p->tcfp_keys; - if (tcf_hash_release(&p->common, bind, &pedit_hash_info)) { - kfree(keys); - return 1; - } - } - return 0; + struct tc_pedit_key *keys = p->tcfp_keys; + kfree(keys); } static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, @@ -230,7 +216,6 @@ nla_put_failure: static struct tc_action_ops act_pedit_ops = { .kind = "pedit", - .hinfo = &pedit_hash_info, .type = TCA_ACT_PEDIT, .owner = THIS_MODULE, .act = tcf_pedit, @@ -245,15 +230,11 @@ MODULE_LICENSE("GPL"); static int __init pedit_init_module(void) { - int err = tcf_hashinfo_init(&pedit_hash_info, PEDIT_TAB_MASK); - if (err) - return err; - return tcf_register_action(&act_pedit_ops); + return tcf_register_action(&act_pedit_ops, PEDIT_TAB_MASK); } static void __exit pedit_cleanup_module(void) { - tcf_hashinfo_destroy(&pedit_hash_info); tcf_unregister_action(&act_pedit_ops); } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 1778209a332f..0566e4606a4a 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -41,7 +41,6 @@ struct tcf_police { container_of(pc, struct tcf_police, common) #define POL_TAB_MASK 15 -static struct tcf_hashinfo police_hash_info; /* old policer structure from before tc actions */ struct tc_police_compat { @@ -234,7 +233,7 @@ override: police->tcfp_t_c = ktime_to_ns(ktime_get()); police->tcf_index = parm->index ? parm->index : - tcf_hash_new_index(a->ops->hinfo); + tcf_hash_new_index(hinfo); h = tcf_hash(police->tcf_index, POL_TAB_MASK); spin_lock_bh(&hinfo->lock); hlist_add_head(&police->tcf_head, &hinfo->htab[h]); @@ -253,14 +252,6 @@ failure: return err; } -static int tcf_act_police_cleanup(struct tc_action *a, int bind) -{ - struct tcf_police *p = a->priv; - if (p) - return tcf_hash_release(&p->common, bind, &police_hash_info); - return 0; -} - static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -357,12 +348,10 @@ MODULE_LICENSE("GPL"); static struct tc_action_ops act_police_ops = { .kind = "police", - .hinfo = &police_hash_info, .type = TCA_ID_POLICE, .owner = THIS_MODULE, .act = tcf_act_police, .dump = tcf_act_police_dump, - .cleanup = tcf_act_police_cleanup, .init = tcf_act_police_locate, .walk = tcf_act_police_walker }; @@ -370,19 +359,12 @@ static struct tc_action_ops act_police_ops = { static int __init police_init_module(void) { - int err = tcf_hashinfo_init(&police_hash_info, POL_TAB_MASK); - if (err) - return err; - err = tcf_register_action(&act_police_ops); - if (err) - tcf_hashinfo_destroy(&police_hash_info); - return err; + return tcf_register_action(&act_police_ops, POL_TAB_MASK); } static void __exit police_cleanup_module(void) { - tcf_hashinfo_destroy(&police_hash_info); tcf_unregister_action(&act_police_ops); } diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 8ef2f1fcbfba..992c2317ce88 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -25,7 +25,6 @@ #include <net/tc_act/tc_defact.h> #define SIMP_TAB_MASK 7 -static struct tcf_hashinfo simp_hash_info; #define SIMP_MAX_DATA 32 static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, @@ -47,20 +46,10 @@ static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, return d->tcf_action; } -static int tcf_simp_release(struct tcf_defact *d, int bind) +static void tcf_simp_release(struct tc_action *a, int bind) { - int ret = 0; - if (d) { - if (bind) - d->tcf_bindcnt--; - d->tcf_refcnt--; - if (d->tcf_bindcnt <= 0 && d->tcf_refcnt <= 0) { - kfree(d->tcfd_defdata); - tcf_hash_destroy(&d->common, &simp_hash_info); - ret = 1; - } - } - return ret; + struct tcf_defact *d = to_defact(a); + kfree(d->tcfd_defdata); } static int alloc_defdata(struct tcf_defact *d, char *defdata) @@ -94,7 +83,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *tb[TCA_DEF_MAX + 1]; struct tc_defact *parm; struct tcf_defact *d; - struct tcf_common *pc; char *defdata; int ret = 0, err; @@ -114,29 +102,25 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_DEF_PARMS]); defdata = nla_data(tb[TCA_DEF_DATA]); - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); + if (ret) + return ret; - d = to_defact(pc); + d = to_defact(a); ret = alloc_defdata(d, defdata); if (ret < 0) { - if (est) - gen_kill_estimator(&pc->tcfc_bstats, - &pc->tcfc_rate_est); - kfree_rcu(pc, tcfc_rcu); + tcf_hash_cleanup(a, est); return ret; } d->tcf_action = parm->action; ret = ACT_P_CREATED; } else { - d = to_defact(pc); + d = to_defact(a); if (bind) return 0; - tcf_simp_release(d, bind); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; @@ -144,19 +128,10 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, } if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_simp_cleanup(struct tc_action *a, int bind) -{ - struct tcf_defact *d = a->priv; - - if (d) - return tcf_simp_release(d, bind); - return 0; -} - static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -187,12 +162,11 @@ nla_put_failure: static struct tc_action_ops act_simp_ops = { .kind = "simple", - .hinfo = &simp_hash_info, .type = TCA_ACT_SIMP, .owner = THIS_MODULE, .act = tcf_simp, .dump = tcf_simp_dump, - .cleanup = tcf_simp_cleanup, + .cleanup = tcf_simp_release, .init = tcf_simp_init, }; @@ -202,23 +176,15 @@ MODULE_LICENSE("GPL"); static int __init simp_init_module(void) { - int err, ret; - err = tcf_hashinfo_init(&simp_hash_info, SIMP_TAB_MASK); - if (err) - return err; - - ret = tcf_register_action(&act_simp_ops); + int ret; + ret = tcf_register_action(&act_simp_ops, SIMP_TAB_MASK); if (!ret) pr_info("Simple TC action Loaded\n"); - else - tcf_hashinfo_destroy(&simp_hash_info); - return ret; } static void __exit simp_cleanup_module(void) { - tcf_hashinfo_destroy(&simp_hash_info); tcf_unregister_action(&act_simp_ops); } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 98725080b5aa..fcfeeaf838be 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -28,7 +28,6 @@ #include <net/tc_act/tc_skbedit.h> #define SKBEDIT_TAB_MASK 15 -static struct tcf_hashinfo skbedit_hash_info; static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) @@ -65,7 +64,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; struct tcf_skbedit *d; - struct tcf_common *pc; u32 flags = 0, *priority = NULL, *mark = NULL; u16 *queue_mapping = NULL; int ret = 0, err; @@ -100,19 +98,18 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_SKBEDIT_PARMS]); - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); + if (ret) + return ret; - d = to_skbedit(pc); + d = to_skbedit(a); ret = ACT_P_CREATED; } else { - d = to_skbedit(pc); + d = to_skbedit(a); if (bind) return 0; - tcf_hash_release(pc, bind, a->ops->hinfo); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; } @@ -132,19 +129,10 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&d->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_skbedit_cleanup(struct tc_action *a, int bind) -{ - struct tcf_skbedit *d = a->priv; - - if (d) - return tcf_hash_release(&d->common, bind, &skbedit_hash_info); - return 0; -} - static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -186,12 +174,10 @@ nla_put_failure: static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", - .hinfo = &skbedit_hash_info, .type = TCA_ACT_SKBEDIT, .owner = THIS_MODULE, .act = tcf_skbedit, .dump = tcf_skbedit_dump, - .cleanup = tcf_skbedit_cleanup, .init = tcf_skbedit_init, }; @@ -201,15 +187,11 @@ MODULE_LICENSE("GPL"); static int __init skbedit_init_module(void) { - int err = tcf_hashinfo_init(&skbedit_hash_info, SKBEDIT_TAB_MASK); - if (err) - return err; - return tcf_register_action(&act_skbedit_ops); + return tcf_register_action(&act_skbedit_ops, SKBEDIT_TAB_MASK); } static void __exit skbedit_cleanup_module(void) { - tcf_hashinfo_destroy(&skbedit_hash_info); tcf_unregister_action(&act_skbedit_ops); } diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index a366537f82c6..63a3ce75c02e 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -29,11 +29,11 @@ #include <net/act_api.h> #include <net/pkt_cls.h> -#define HTSIZE (PAGE_SIZE/sizeof(struct fw_filter *)) +#define HTSIZE 256 struct fw_head { - struct fw_filter *ht[HTSIZE]; - u32 mask; + u32 mask; + struct fw_filter *ht[HTSIZE]; }; struct fw_filter { @@ -46,30 +46,11 @@ struct fw_filter { struct tcf_exts exts; }; -static inline int fw_hash(u32 handle) +static u32 fw_hash(u32 handle) { - if (HTSIZE == 4096) - return ((handle >> 24) & 0xFFF) ^ - ((handle >> 12) & 0xFFF) ^ - (handle & 0xFFF); - else if (HTSIZE == 2048) - return ((handle >> 22) & 0x7FF) ^ - ((handle >> 11) & 0x7FF) ^ - (handle & 0x7FF); - else if (HTSIZE == 1024) - return ((handle >> 20) & 0x3FF) ^ - ((handle >> 10) & 0x3FF) ^ - (handle & 0x3FF); - else if (HTSIZE == 512) - return (handle >> 27) ^ - ((handle >> 18) & 0x1FF) ^ - ((handle >> 9) & 0x1FF) ^ - (handle & 0x1FF); - else if (HTSIZE == 256) { - u8 *t = (u8 *) &handle; - return t[0] ^ t[1] ^ t[2] ^ t[3]; - } else - return handle & (HTSIZE - 1); + handle ^= (handle >> 16); + handle ^= (handle >> 8); + return handle % HTSIZE; } static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index a07d55e75698..a0b84e0e22de 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1304,6 +1304,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, struct gnet_dump d; struct qdisc_size_table *stab; + cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; @@ -1435,9 +1436,9 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) s_idx = cb->args[0]; s_q_idx = q_idx = cb->args[1]; - rcu_read_lock(); idx = 0; - for_each_netdev_rcu(net, dev) { + ASSERT_RTNL(); + for_each_netdev(net, dev) { struct netdev_queue *dev_queue; if (idx < s_idx) @@ -1460,8 +1461,6 @@ cont: } done: - rcu_read_unlock(); - cb->args[0] = idx; cb->args[1] = q_idx; @@ -1618,6 +1617,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, struct gnet_dump d; const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; + cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 1f9c31411f19..8449b337f9e3 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -623,8 +623,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, if (nla_put_u32(skb, TCA_ATM_EXCESS, 0)) goto nla_put_failure; } - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 2f80d01d42a6..ead526467cca 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1563,8 +1563,7 @@ static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb) goto nla_put_failure; if (cbq_dump_attr(skb, &q->link) < 0) goto nla_put_failure; - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); @@ -1599,8 +1598,7 @@ cbq_dump_class(struct Qdisc *sch, unsigned long arg, goto nla_put_failure; if (cbq_dump_attr(skb, cl) < 0) goto nla_put_failure; - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 21e251766eb1..23c682b42f99 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -781,8 +781,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log)) goto nla_put_failure; - nla_nest_end(skb, opts); - return skb->len; + return nla_nest_end(skb, opts); nla_put_failure: return -1; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index ba5bc929eac7..0bf432c782c1 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -450,8 +450,7 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) q->flows_cnt)) goto nla_put_failure; - nla_nest_end(skb, opts); - return skb->len; + return nla_nest_end(skb, opts); nla_put_failure: return -1; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index e82e43b69c33..e1543b03e39d 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -310,6 +310,7 @@ void netif_carrier_on(struct net_device *dev) if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; + atomic_inc(&dev->carrier_changes); linkwatch_fire_event(dev); if (netif_running(dev)) __netdev_watchdog_up(dev); @@ -328,6 +329,7 @@ void netif_carrier_off(struct net_device *dev) if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; + atomic_inc(&dev->carrier_changes); linkwatch_fire_event(dev); } } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index c4075610502c..ec8aeaac1dd7 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1353,8 +1353,7 @@ hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, goto nla_put_failure; if (hfsc_dump_curves(skb, cl) < 0) goto nla_put_failure; - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 647680b1c625..edee03d922e2 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -691,8 +691,7 @@ static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_HHF_NON_HH_WEIGHT, q->hhf_non_hh_weight)) goto nla_put_failure; - nla_nest_end(skb, opts); - return skb->len; + return nla_nest_end(skb, opts); nla_put_failure: return -1; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 722e137df244..9f949abcacef 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1062,12 +1062,13 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) { - spinlock_t *root_lock = qdisc_root_sleeping_lock(sch); struct htb_sched *q = qdisc_priv(sch); struct nlattr *nest; struct tc_htb_glob gopt; - spin_lock_bh(root_lock); + /* Its safe to not acquire qdisc lock. As we hold RTNL, + * no change can happen on the qdisc parameters. + */ gopt.direct_pkts = q->direct_pkts; gopt.version = HTB_VER; @@ -1081,13 +1082,10 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) || nla_put_u32(skb, TCA_HTB_DIRECT_QLEN, q->direct_qlen)) goto nla_put_failure; - nla_nest_end(skb, nest); - spin_unlock_bh(root_lock); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: - spin_unlock_bh(root_lock); nla_nest_cancel(skb, nest); return -1; } @@ -1096,11 +1094,12 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { struct htb_class *cl = (struct htb_class *)arg; - spinlock_t *root_lock = qdisc_root_sleeping_lock(sch); struct nlattr *nest; struct tc_htb_opt opt; - spin_lock_bh(root_lock); + /* Its safe to not acquire qdisc lock. As we hold RTNL, + * no change can happen on the class parameters. + */ tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT; tcm->tcm_handle = cl->common.classid; if (!cl->level && cl->un.leaf.q) @@ -1128,12 +1127,9 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, nla_put_u64(skb, TCA_HTB_CEIL64, cl->ceil.rate_bytes_ps)) goto nla_put_failure; - nla_nest_end(skb, nest); - spin_unlock_bh(root_lock); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: - spin_unlock_bh(root_lock); nla_nest_cancel(skb, nest); return -1; } diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index bce1665239b8..62871c14e1f9 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -100,8 +100,7 @@ static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb) nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index de1059af6da1..f1669a00f571 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -117,6 +117,11 @@ struct netem_sched_data { LOST_IN_BURST_PERIOD, } _4_state_model; + enum { + GOOD_STATE = 1, + BAD_STATE, + } GE_state_model; + /* Correlated Loss Generation models */ struct clgstate { /* state of the Markov chain */ @@ -272,15 +277,15 @@ static bool loss_gilb_ell(struct netem_sched_data *q) struct clgstate *clg = &q->clg; switch (clg->state) { - case 1: + case GOOD_STATE: if (prandom_u32() < clg->a1) - clg->state = 2; + clg->state = BAD_STATE; if (prandom_u32() < clg->a4) return true; break; - case 2: + case BAD_STATE: if (prandom_u32() < clg->a2) - clg->state = 1; + clg->state = GOOD_STATE; if (prandom_u32() > clg->a3) return true; } @@ -689,9 +694,8 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) return 0; } -static void get_correlation(struct Qdisc *sch, const struct nlattr *attr) +static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); const struct tc_netem_corr *c = nla_data(attr); init_crandom(&q->delay_cor, c->delay_corr); @@ -699,27 +703,24 @@ static void get_correlation(struct Qdisc *sch, const struct nlattr *attr) init_crandom(&q->dup_cor, c->dup_corr); } -static void get_reorder(struct Qdisc *sch, const struct nlattr *attr) +static void get_reorder(struct netem_sched_data *q, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); const struct tc_netem_reorder *r = nla_data(attr); q->reorder = r->probability; init_crandom(&q->reorder_cor, r->correlation); } -static void get_corrupt(struct Qdisc *sch, const struct nlattr *attr) +static void get_corrupt(struct netem_sched_data *q, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); const struct tc_netem_corrupt *r = nla_data(attr); q->corrupt = r->probability; init_crandom(&q->corrupt_cor, r->correlation); } -static void get_rate(struct Qdisc *sch, const struct nlattr *attr) +static void get_rate(struct netem_sched_data *q, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); const struct tc_netem_rate *r = nla_data(attr); q->rate = r->rate; @@ -732,9 +733,8 @@ static void get_rate(struct Qdisc *sch, const struct nlattr *attr) q->cell_size_reciprocal = (struct reciprocal_value) { 0 }; } -static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) +static int get_loss_clg(struct netem_sched_data *q, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); const struct nlattr *la; int rem; @@ -752,7 +752,7 @@ static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) q->loss_model = CLG_4_STATES; - q->clg.state = 1; + q->clg.state = TX_IN_GAP_PERIOD; q->clg.a1 = gi->p13; q->clg.a2 = gi->p31; q->clg.a3 = gi->p32; @@ -770,7 +770,7 @@ static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) } q->loss_model = CLG_GILB_ELL; - q->clg.state = 1; + q->clg.state = GOOD_STATE; q->clg.a1 = ge->p; q->clg.a2 = ge->r; q->clg.a3 = ge->h; @@ -821,6 +821,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; struct tc_netem_qopt *qopt; + struct clgstate old_clg; + int old_loss_model = CLG_RANDOM; int ret; if (opt == NULL) @@ -831,6 +833,33 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) if (ret < 0) return ret; + /* backup q->clg and q->loss_model */ + old_clg = q->clg; + old_loss_model = q->loss_model; + + if (tb[TCA_NETEM_LOSS]) { + ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); + if (ret) { + q->loss_model = old_loss_model; + return ret; + } + } else { + q->loss_model = CLG_RANDOM; + } + + if (tb[TCA_NETEM_DELAY_DIST]) { + ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]); + if (ret) { + /* recover clg and loss_model, in case of + * q->clg and q->loss_model were modified + * in get_loss_clg() + */ + q->clg = old_clg; + q->loss_model = old_loss_model; + return ret; + } + } + sch->limit = qopt->limit; q->latency = qopt->latency; @@ -848,22 +877,16 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) q->reorder = ~0; if (tb[TCA_NETEM_CORR]) - get_correlation(sch, tb[TCA_NETEM_CORR]); - - if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]); - if (ret) - return ret; - } + get_correlation(q, tb[TCA_NETEM_CORR]); if (tb[TCA_NETEM_REORDER]) - get_reorder(sch, tb[TCA_NETEM_REORDER]); + get_reorder(q, tb[TCA_NETEM_REORDER]); if (tb[TCA_NETEM_CORRUPT]) - get_corrupt(sch, tb[TCA_NETEM_CORRUPT]); + get_corrupt(q, tb[TCA_NETEM_CORRUPT]); if (tb[TCA_NETEM_RATE]) - get_rate(sch, tb[TCA_NETEM_RATE]); + get_rate(q, tb[TCA_NETEM_RATE]); if (tb[TCA_NETEM_RATE64]) q->rate = max_t(u64, q->rate, @@ -872,10 +895,6 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); - q->loss_model = CLG_RANDOM; - if (tb[TCA_NETEM_LOSS]) - ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]); - return ret; } diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 4f505a006896..18ff63433709 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -101,12 +101,11 @@ struct tbf_sched_data { /* Parameters */ u32 limit; /* Maximal length of backlog: bytes */ + u32 max_size; s64 buffer; /* Token bucket depth/rate: MUST BE >= MTU/B */ s64 mtu; - u32 max_size; struct psched_ratecfg rate; struct psched_ratecfg peak; - bool peak_present; /* Variables */ s64 tokens; /* Current number of B tokens */ @@ -222,6 +221,11 @@ static unsigned int tbf_drop(struct Qdisc *sch) return len; } +static bool tbf_peak_present(const struct tbf_sched_data *q) +{ + return q->peak.rate_bytes_ps; +} + static struct sk_buff *tbf_dequeue(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -238,7 +242,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch) now = ktime_to_ns(ktime_get()); toks = min_t(s64, now - q->t_c, q->buffer); - if (q->peak_present) { + if (tbf_peak_present(q)) { ptoks = toks + q->ptokens; if (ptoks > q->mtu) ptoks = q->mtu; @@ -366,6 +370,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) } else { max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu)); } + } else { + memset(&peak, 0, sizeof(peak)); } if (max_size < psched_mtu(qdisc_dev(sch))) @@ -410,12 +416,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) q->ptokens = q->mtu; memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg)); - if (qopt->peakrate.rate) { - memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg)); - q->peak_present = true; - } else { - q->peak_present = false; - } + memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg)); sch_tree_unlock(sch); err = 0; @@ -458,7 +459,7 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) opt.limit = q->limit; psched_ratecfg_getrate(&opt.rate, &q->rate); - if (q->peak_present) + if (tbf_peak_present(q)) psched_ratecfg_getrate(&opt.peakrate, &q->peak); else memset(&opt.peakrate, 0, sizeof(opt.peakrate)); @@ -469,13 +470,12 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) if (q->rate.rate_bytes_ps >= (1ULL << 32) && nla_put_u64(skb, TCA_TBF_RATE64, q->rate.rate_bytes_ps)) goto nla_put_failure; - if (q->peak_present && + if (tbf_peak_present(q) && q->peak.rate_bytes_ps >= (1ULL << 32) && nla_put_u64(skb, TCA_TBF_PRATE64, q->peak.rate_bytes_ps)) goto nla_put_failure; - nla_nest_end(skb, nest); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index ee13d28d39d1..4f6d6f9d1274 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1319,8 +1319,7 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc) break; } - if (trans_next != NULL) - asoc->peer.retran_path = trans_next; + asoc->peer.retran_path = trans_next; pr_debug("%s: association:%p updated new path to addr:%pISpc\n", __func__, asoc, &asoc->peer.retran_path->ipaddr.sa); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index d0810dc5f079..1d348d15b33d 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -652,5 +652,4 @@ void sctp_transport_immediate_rtx(struct sctp_transport *t) if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto)) sctp_transport_hold(t); } - return; } diff --git a/net/socket.c b/net/socket.c index a19ae1968d37..1b1e7e6a960f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -72,6 +72,7 @@ #include <linux/if_bridge.h> #include <linux/if_frad.h> #include <linux/if_vlan.h> +#include <linux/ptp_classify.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/cache.h> @@ -594,7 +595,7 @@ void sock_release(struct socket *sock) } if (rcu_dereference_protected(sock->wq, 1)->fasync_list) - printk(KERN_ERR "sock_release: fasync list not empty!\n"); + pr_err("%s: fasync list not empty!\n", __func__); if (test_bit(SOCK_EXTERNALLY_ALLOCATED, &sock->flags)) return; @@ -1266,8 +1267,8 @@ int __sock_create(struct net *net, int family, int type, int protocol, static int warned; if (!warned) { warned = 1; - printk(KERN_INFO "%s uses obsolete (PF_INET,SOCK_PACKET)\n", - current->comm); + pr_info("%s uses obsolete (PF_INET,SOCK_PACKET)\n", + current->comm); } family = PF_PACKET; } @@ -2600,8 +2601,7 @@ int sock_register(const struct net_proto_family *ops) int err; if (ops->family >= NPROTO) { - printk(KERN_CRIT "protocol %d >= NPROTO(%d)\n", ops->family, - NPROTO); + pr_crit("protocol %d >= NPROTO(%d)\n", ops->family, NPROTO); return -ENOBUFS; } @@ -2615,7 +2615,7 @@ int sock_register(const struct net_proto_family *ops) } spin_unlock(&net_family_lock); - printk(KERN_INFO "NET: Registered protocol family %d\n", ops->family); + pr_info("NET: Registered protocol family %d\n", ops->family); return err; } EXPORT_SYMBOL(sock_register); @@ -2643,7 +2643,7 @@ void sock_unregister(int family) synchronize_rcu(); - printk(KERN_INFO "NET: Unregistered protocol family %d\n", family); + pr_info("NET: Unregistered protocol family %d\n", family); } EXPORT_SYMBOL(sock_unregister); @@ -2686,9 +2686,7 @@ static int __init sock_init(void) goto out; #endif -#ifdef CONFIG_NETWORK_PHY_TIMESTAMPING - skb_timestamping_init(); -#endif + ptp_classifier_init(); out: return err; diff --git a/net/tipc/addr.h b/net/tipc/addr.h index 60b00ab93d74..a74acf9ee804 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -37,6 +37,8 @@ #ifndef _TIPC_ADDR_H #define _TIPC_ADDR_H +#include "core.h" + #define TIPC_ZONE_MASK 0xff000000u #define TIPC_CLUSTER_MASK 0xfffff000u diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index bf860d9e75af..95ab5ef92920 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -41,9 +41,9 @@ #include "bcast.h" #include "name_distr.h" -#define MAX_PKT_DEFAULT_MCAST 1500 /* bcast link max packet size (fixed) */ - -#define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */ +#define MAX_PKT_DEFAULT_MCAST 1500 /* bcast link max packet size (fixed) */ +#define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */ +#define BCBEARER MAX_BEARERS /** * struct tipc_bcbearer_pair - a pair of bearers used by broadcast link @@ -356,9 +356,9 @@ static void bclink_peek_nack(struct tipc_msg *msg) } /* - * tipc_bclink_send_msg - broadcast a packet to all nodes in cluster + * tipc_bclink_xmit - broadcast a packet to all nodes in cluster */ -int tipc_bclink_send_msg(struct sk_buff *buf) +int tipc_bclink_xmit(struct sk_buff *buf) { int res; @@ -370,7 +370,7 @@ int tipc_bclink_send_msg(struct sk_buff *buf) goto exit; } - res = tipc_link_send_buf(bcl, buf); + res = __tipc_link_xmit(bcl, buf); if (likely(res >= 0)) { bclink_set_last_sent(); bcl->stats.queue_sz_counts++; @@ -399,19 +399,18 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) */ if (((seqno - tipc_own_addr) % TIPC_MIN_LINK_WIN) == 0) { - tipc_link_send_proto_msg( - node->active_links[node->addr & 1], - STATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(node->active_links[node->addr & 1], + STATE_MSG, 0, 0, 0, 0, 0); bcl->stats.sent_acks++; } } /** - * tipc_bclink_recv_pkt - receive a broadcast packet, and deliver upwards + * tipc_bclink_rcv - receive a broadcast packet, and deliver upwards * * tipc_net_lock is read_locked, no other locks set */ -void tipc_bclink_recv_pkt(struct sk_buff *buf) +void tipc_bclink_rcv(struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); struct tipc_node *node; @@ -468,7 +467,7 @@ receive: spin_unlock_bh(&bc_lock); tipc_node_unlock(node); if (likely(msg_mcast(msg))) - tipc_port_recv_mcast(buf, NULL); + tipc_port_mcast_rcv(buf, NULL); else kfree_skb(buf); } else if (msg_user(msg) == MSG_BUNDLER) { @@ -478,12 +477,12 @@ receive: bcl->stats.recv_bundled += msg_msgcnt(msg); spin_unlock_bh(&bc_lock); tipc_node_unlock(node); - tipc_link_recv_bundle(buf); + tipc_link_bundle_rcv(buf); } else if (msg_user(msg) == MSG_FRAGMENTER) { int ret; - ret = tipc_link_recv_fragment(&node->bclink.reasm_head, - &node->bclink.reasm_tail, - &buf); + ret = tipc_link_frag_rcv(&node->bclink.reasm_head, + &node->bclink.reasm_tail, + &buf); if (ret == LINK_REASM_ERROR) goto unlock; spin_lock_bh(&bc_lock); @@ -503,7 +502,7 @@ receive: bclink_accept_pkt(node, seqno); spin_unlock_bh(&bc_lock); tipc_node_unlock(node); - tipc_named_recv(buf); + tipc_named_rcv(buf); } else { spin_lock_bh(&bc_lock); bclink_accept_pkt(node, seqno); @@ -669,9 +668,8 @@ void tipc_bcbearer_sort(void) memset(bp_temp, 0, sizeof(bcbearer->bpairs_temp)); for (b_index = 0; b_index < MAX_BEARERS; b_index++) { - struct tipc_bearer *b = &tipc_bearers[b_index]; - - if (!b->active || !b->nodes.count) + struct tipc_bearer *b = bearer_list[b_index]; + if (!b || !b->nodes.count) continue; if (!bp_temp[b->priority].primary) @@ -785,8 +783,8 @@ void tipc_bclink_init(void) bcl->owner = &bclink->node; bcl->max_pkt = MAX_PKT_DEFAULT_MCAST; tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT); - spin_lock_init(&bcbearer->bearer.lock); bcl->b_ptr = &bcbearer->bearer; + bearer_list[BCBEARER] = &bcbearer->bearer; bcl->state = WORKING_WORKING; strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME); } @@ -797,6 +795,7 @@ void tipc_bclink_stop(void) tipc_link_purge_queues(bcl); spin_unlock_bh(&bc_lock); + bearer_list[BCBEARER] = NULL; memset(bclink, 0, sizeof(*bclink)); memset(bcbearer, 0, sizeof(*bcbearer)); } diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 6ee587b469fd..a80ef54b818e 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -90,8 +90,8 @@ void tipc_bclink_add_node(u32 addr); void tipc_bclink_remove_node(u32 addr); struct tipc_node *tipc_bclink_retransmit_to(void); void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked); -int tipc_bclink_send_msg(struct sk_buff *buf); -void tipc_bclink_recv_pkt(struct sk_buff *buf); +int tipc_bclink_xmit(struct sk_buff *buf); +void tipc_bclink_rcv(struct sk_buff *buf); u32 tipc_bclink_get_last_sent(void); u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr); void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 574b86193b15..3fef7eb776dc 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -49,9 +49,9 @@ static struct tipc_media * const media_info_array[] = { NULL }; -struct tipc_bearer tipc_bearers[MAX_BEARERS]; +struct tipc_bearer *bearer_list[MAX_BEARERS + 1]; -static void bearer_disable(struct tipc_bearer *b_ptr); +static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down); /** * tipc_media_find - locates specified media object by name @@ -177,8 +177,9 @@ struct tipc_bearer *tipc_bearer_find(const char *name) struct tipc_bearer *b_ptr; u32 i; - for (i = 0, b_ptr = tipc_bearers; i < MAX_BEARERS; i++, b_ptr++) { - if (b_ptr->active && (!strcmp(b_ptr->name, name))) + for (i = 0; i < MAX_BEARERS; i++) { + b_ptr = bearer_list[i]; + if (b_ptr && (!strcmp(b_ptr->name, name))) return b_ptr; } return NULL; @@ -200,8 +201,10 @@ struct sk_buff *tipc_bearer_get_names(void) read_lock_bh(&tipc_net_lock); for (i = 0; media_info_array[i] != NULL; i++) { for (j = 0; j < MAX_BEARERS; j++) { - b = &tipc_bearers[j]; - if (b->active && (b->media == media_info_array[i])) { + b = bearer_list[j]; + if (!b) + continue; + if (b->media == media_info_array[i]) { tipc_cfg_append_tlv(buf, TIPC_TLV_BEARER_NAME, b->name, strlen(b->name) + 1); @@ -284,16 +287,17 @@ restart: bearer_id = MAX_BEARERS; with_this_prio = 1; for (i = MAX_BEARERS; i-- != 0; ) { - if (!tipc_bearers[i].active) { + b_ptr = bearer_list[i]; + if (!b_ptr) { bearer_id = i; continue; } - if (!strcmp(name, tipc_bearers[i].name)) { + if (!strcmp(name, b_ptr->name)) { pr_warn("Bearer <%s> rejected, already enabled\n", name); goto exit; } - if ((tipc_bearers[i].priority == priority) && + if ((b_ptr->priority == priority) && (++with_this_prio > 2)) { if (priority-- == 0) { pr_warn("Bearer <%s> rejected, duplicate priority\n", @@ -311,7 +315,11 @@ restart: goto exit; } - b_ptr = &tipc_bearers[bearer_id]; + b_ptr = kzalloc(sizeof(*b_ptr), GFP_ATOMIC); + if (!b_ptr) { + res = -ENOMEM; + goto exit; + } strcpy(b_ptr->name, name); b_ptr->media = m_ptr; res = m_ptr->enable_media(b_ptr); @@ -324,19 +332,20 @@ restart: b_ptr->identity = bearer_id; b_ptr->tolerance = m_ptr->tolerance; b_ptr->window = m_ptr->window; + b_ptr->domain = disc_domain; b_ptr->net_plane = bearer_id + 'A'; - b_ptr->active = 1; b_ptr->priority = priority; - INIT_LIST_HEAD(&b_ptr->links); - spin_lock_init(&b_ptr->lock); - res = tipc_disc_create(b_ptr, &b_ptr->bcast_addr, disc_domain); + res = tipc_disc_create(b_ptr, &b_ptr->bcast_addr); if (res) { - bearer_disable(b_ptr); + bearer_disable(b_ptr, false); pr_warn("Bearer <%s> rejected, discovery object creation failed\n", name); goto exit; } + + bearer_list[bearer_id] = b_ptr; + pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n", name, tipc_addr_string_fill(addr_string, disc_domain), priority); @@ -350,20 +359,11 @@ exit: */ static int tipc_reset_bearer(struct tipc_bearer *b_ptr) { - struct tipc_link *l_ptr; - struct tipc_link *temp_l_ptr; - read_lock_bh(&tipc_net_lock); pr_info("Resetting bearer <%s>\n", b_ptr->name); - spin_lock_bh(&b_ptr->lock); - list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { - struct tipc_node *n_ptr = l_ptr->owner; - - spin_lock_bh(&n_ptr->lock); - tipc_link_reset(l_ptr); - spin_unlock_bh(&n_ptr->lock); - } - spin_unlock_bh(&b_ptr->lock); + tipc_disc_delete(b_ptr->link_req); + tipc_link_reset_list(b_ptr->identity); + tipc_disc_create(b_ptr, &b_ptr->bcast_addr); read_unlock_bh(&tipc_net_lock); return 0; } @@ -373,26 +373,24 @@ static int tipc_reset_bearer(struct tipc_bearer *b_ptr) * * Note: This routine assumes caller holds tipc_net_lock. */ -static void bearer_disable(struct tipc_bearer *b_ptr) +static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down) { - struct tipc_link *l_ptr; - struct tipc_link *temp_l_ptr; - struct tipc_link_req *temp_req; + u32 i; pr_info("Disabling bearer <%s>\n", b_ptr->name); - spin_lock_bh(&b_ptr->lock); b_ptr->media->disable_media(b_ptr); - list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { - tipc_link_delete(l_ptr); - } - temp_req = b_ptr->link_req; - b_ptr->link_req = NULL; - spin_unlock_bh(&b_ptr->lock); - if (temp_req) - tipc_disc_delete(temp_req); + tipc_link_delete_list(b_ptr->identity, shutting_down); + if (b_ptr->link_req) + tipc_disc_delete(b_ptr->link_req); - memset(b_ptr, 0, sizeof(struct tipc_bearer)); + for (i = 0; i < MAX_BEARERS; i++) { + if (b_ptr == bearer_list[i]) { + bearer_list[i] = NULL; + break; + } + } + kfree(b_ptr); } int tipc_disable_bearer(const char *name) @@ -406,7 +404,7 @@ int tipc_disable_bearer(const char *name) pr_warn("Attempt to disable unknown bearer <%s>\n", name); res = -EINVAL; } else { - bearer_disable(b_ptr); + bearer_disable(b_ptr, false); res = 0; } write_unlock_bh(&tipc_net_lock); @@ -585,7 +583,11 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, break; case NETDEV_DOWN: case NETDEV_CHANGEMTU: + tipc_reset_bearer(b_ptr); + break; case NETDEV_CHANGEADDR: + tipc_l2_media_addr_set(b_ptr, &b_ptr->addr, + (char *)dev->dev_addr); tipc_reset_bearer(b_ptr); break; case NETDEV_UNREGISTER: @@ -599,7 +601,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, } static struct packet_type tipc_packet_type __read_mostly = { - .type = __constant_htons(ETH_P_TIPC), + .type = htons(ETH_P_TIPC), .func = tipc_l2_rcv_msg, }; @@ -627,10 +629,14 @@ void tipc_bearer_cleanup(void) void tipc_bearer_stop(void) { + struct tipc_bearer *b_ptr; u32 i; for (i = 0; i < MAX_BEARERS; i++) { - if (tipc_bearers[i].active) - bearer_disable(&tipc_bearers[i]); + b_ptr = bearer_list[i]; + if (b_ptr) { + bearer_disable(b_ptr, true); + bearer_list[i] = NULL; + } } } diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 4f5db9ad5bf6..ba48145e871d 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -107,10 +107,8 @@ struct tipc_media { /** * struct tipc_bearer - Generic TIPC bearer structure - * @dev: ptr to associated network device - * @usr_handle: pointer to additional media-specific information about bearer + * @media_ptr: pointer to additional media-specific information about bearer * @mtu: max packet size bearer can support - * @lock: spinlock for controlling access to bearer * @addr: media-specific address associated with bearer * @name: bearer name (format = media:interface) * @media: ptr to media structure associated with bearer @@ -118,10 +116,9 @@ struct tipc_media { * @priority: default link priority for bearer * @window: default window size for bearer * @tolerance: default link tolerance for bearer + * @domain: network domain to which links can be established * @identity: array index of this bearer within TIPC bearer array * @link_req: ptr to (optional) structure making periodic link setup requests - * @links: list of non-congested links associated with bearer - * @active: non-zero if bearer structure is represents a bearer * @net_plane: network plane ('A' through 'H') currently associated with bearer * @nodes: indicates which nodes in cluster can be reached through bearer * @@ -134,16 +131,14 @@ struct tipc_bearer { u32 mtu; /* initalized by media */ struct tipc_media_addr addr; /* initalized by media */ char name[TIPC_MAX_BEARER_NAME]; - spinlock_t lock; struct tipc_media *media; struct tipc_media_addr bcast_addr; u32 priority; u32 window; u32 tolerance; + u32 domain; u32 identity; struct tipc_link_req *link_req; - struct list_head links; - int active; char net_plane; struct tipc_node_map nodes; }; @@ -155,7 +150,7 @@ struct tipc_bearer_names { struct tipc_link; -extern struct tipc_bearer tipc_bearers[]; +extern struct tipc_bearer *bearer_list[]; /* * TIPC routines available to supported media types diff --git a/net/tipc/config.c b/net/tipc/config.c index e6d721692ae0..4b981c053823 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -43,13 +43,11 @@ #define REPLY_TRUNCATED "<truncated>\n" static DEFINE_MUTEX(config_mutex); -static struct tipc_server cfgsrv; static const void *req_tlv_area; /* request message TLV area */ static int req_tlv_space; /* request message TLV area size */ static int rep_headroom; /* reply message headroom to use */ - struct sk_buff *tipc_cfg_reply_alloc(int payload_size) { struct sk_buff *buf; @@ -185,18 +183,6 @@ static struct sk_buff *cfg_set_own_addr(void) return tipc_cfg_reply_none(); } -static struct sk_buff *cfg_set_remote_mng(void) -{ - u32 value; - - if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) - return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); - - value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - tipc_remote_management = (value != 0); - return tipc_cfg_reply_none(); -} - static struct sk_buff *cfg_set_max_ports(void) { u32 value; @@ -247,21 +233,10 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area /* Check command authorization */ if (likely(in_own_node(orig_node))) { /* command is permitted */ - } else if (cmd >= 0x8000) { + } else { rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (cannot be done remotely)"); goto exit; - } else if (!tipc_remote_management) { - rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NO_REMOTE); - goto exit; - } else if (cmd >= 0x4000) { - u32 domain = 0; - - if ((tipc_nametbl_translate(TIPC_ZM_SRV, 0, &domain) == 0) || - (domain != orig_node)) { - rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_ZONE_MSTR); - goto exit; - } } /* Call appropriate processing routine */ @@ -310,18 +285,12 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SET_NODE_ADDR: rep_tlv_buf = cfg_set_own_addr(); break; - case TIPC_CMD_SET_REMOTE_MNG: - rep_tlv_buf = cfg_set_remote_mng(); - break; case TIPC_CMD_SET_MAX_PORTS: rep_tlv_buf = cfg_set_max_ports(); break; case TIPC_CMD_SET_NETID: rep_tlv_buf = cfg_set_netid(); break; - case TIPC_CMD_GET_REMOTE_MNG: - rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_remote_management); - break; case TIPC_CMD_GET_MAX_PORTS: rep_tlv_buf = tipc_cfg_reply_unsigned(tipc_max_ports); break; @@ -345,6 +314,8 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area case TIPC_CMD_SET_MAX_PUBL: case TIPC_CMD_GET_MAX_PUBL: case TIPC_CMD_SET_LOG_SIZE: + case TIPC_CMD_SET_REMOTE_MNG: + case TIPC_CMD_GET_REMOTE_MNG: case TIPC_CMD_DUMP_LOG: rep_tlv_buf = tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (obsolete command)"); @@ -369,75 +340,3 @@ exit: mutex_unlock(&config_mutex); return rep_tlv_buf; } - -static void cfg_conn_msg_event(int conid, struct sockaddr_tipc *addr, - void *usr_data, void *buf, size_t len) -{ - struct tipc_cfg_msg_hdr *req_hdr; - struct tipc_cfg_msg_hdr *rep_hdr; - struct sk_buff *rep_buf; - - /* Validate configuration message header (ignore invalid message) */ - req_hdr = (struct tipc_cfg_msg_hdr *)buf; - if ((len < sizeof(*req_hdr)) || - (len != TCM_ALIGN(ntohl(req_hdr->tcm_len))) || - (ntohs(req_hdr->tcm_flags) != TCM_F_REQUEST)) { - pr_warn("Invalid configuration message discarded\n"); - return; - } - - /* Generate reply for request (if can't, return request) */ - rep_buf = tipc_cfg_do_cmd(addr->addr.id.node, ntohs(req_hdr->tcm_type), - buf + sizeof(*req_hdr), - len - sizeof(*req_hdr), - BUF_HEADROOM + MAX_H_SIZE + sizeof(*rep_hdr)); - if (rep_buf) { - skb_push(rep_buf, sizeof(*rep_hdr)); - rep_hdr = (struct tipc_cfg_msg_hdr *)rep_buf->data; - memcpy(rep_hdr, req_hdr, sizeof(*rep_hdr)); - rep_hdr->tcm_len = htonl(rep_buf->len); - rep_hdr->tcm_flags &= htons(~TCM_F_REQUEST); - tipc_conn_sendmsg(&cfgsrv, conid, addr, rep_buf->data, - rep_buf->len); - kfree_skb(rep_buf); - } -} - -static struct sockaddr_tipc cfgsrv_addr __read_mostly = { - .family = AF_TIPC, - .addrtype = TIPC_ADDR_NAMESEQ, - .addr.nameseq.type = TIPC_CFG_SRV, - .addr.nameseq.lower = 0, - .addr.nameseq.upper = 0, - .scope = TIPC_ZONE_SCOPE -}; - -static struct tipc_server cfgsrv __read_mostly = { - .saddr = &cfgsrv_addr, - .imp = TIPC_CRITICAL_IMPORTANCE, - .type = SOCK_RDM, - .max_rcvbuf_size = 64 * 1024, - .name = "cfg_server", - .tipc_conn_recvmsg = cfg_conn_msg_event, - .tipc_conn_new = NULL, - .tipc_conn_shutdown = NULL -}; - -int tipc_cfg_init(void) -{ - return tipc_server_start(&cfgsrv); -} - -void tipc_cfg_reinit(void) -{ - tipc_server_stop(&cfgsrv); - - cfgsrv_addr.addr.nameseq.lower = tipc_own_addr; - cfgsrv_addr.addr.nameseq.upper = tipc_own_addr; - tipc_server_start(&cfgsrv); -} - -void tipc_cfg_stop(void) -{ - tipc_server_stop(&cfgsrv); -} diff --git a/net/tipc/config.h b/net/tipc/config.h index 1f252f3fa058..47b1bf181612 100644 --- a/net/tipc/config.h +++ b/net/tipc/config.h @@ -64,9 +64,4 @@ static inline struct sk_buff *tipc_cfg_reply_ultra_string(char *string) struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *req_tlv_area, int req_tlv_space, int headroom); - -int tipc_cfg_init(void); -void tipc_cfg_reinit(void); -void tipc_cfg_stop(void); - #endif diff --git a/net/tipc/core.c b/net/tipc/core.c index 80c20647b3d2..50d57429ebca 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -1,7 +1,7 @@ /* * net/tipc/core.c: TIPC module code * - * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2003-2006, 2013, Ericsson AB * Copyright (c) 2005-2006, 2010-2013, Wind River Systems * All rights reserved. * @@ -50,7 +50,6 @@ int tipc_random __read_mostly; u32 tipc_own_addr __read_mostly; int tipc_max_ports __read_mostly; int tipc_net_id __read_mostly; -int tipc_remote_management __read_mostly; int sysctl_tipc_rmem[3] __read_mostly; /* min/default/max */ /** @@ -85,7 +84,6 @@ static void tipc_core_stop(void) tipc_net_stop(); tipc_bearer_cleanup(); tipc_netlink_stop(); - tipc_cfg_stop(); tipc_subscr_stop(); tipc_nametbl_stop(); tipc_ref_table_stop(); @@ -130,18 +128,12 @@ static int tipc_core_start(void) if (err) goto out_subscr; - err = tipc_cfg_init(); - if (err) - goto out_cfg; - err = tipc_bearer_setup(); if (err) goto out_bearer; return 0; out_bearer: - tipc_cfg_stop(); -out_cfg: tipc_subscr_stop(); out_subscr: tipc_unregister_sysctl(); @@ -166,7 +158,6 @@ static int __init tipc_init(void) pr_info("Activated (version " TIPC_MOD_VER ")\n"); tipc_own_addr = 0; - tipc_remote_management = 1; tipc_max_ports = CONFIG_TIPC_PORTS; tipc_net_id = 4711; diff --git a/net/tipc/core.h b/net/tipc/core.h index 4dfe137587bb..8985bbcb942b 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -79,7 +79,6 @@ int tipc_snprintf(char *buf, int len, const char *fmt, ...); extern u32 tipc_own_addr __read_mostly; extern int tipc_max_ports __read_mostly; extern int tipc_net_id __read_mostly; -extern int tipc_remote_management __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; /* diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 412ff41b8611..542fe3413dc4 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -48,7 +48,6 @@ * struct tipc_link_req - information about an ongoing link setup request * @bearer: bearer issuing requests * @dest: destination address for request messages - * @domain: network domain to which links can be established * @num_nodes: number of nodes currently discovered (i.e. with an active link) * @lock: spinlock for controlling access to requests * @buf: request message to be (repeatedly) sent @@ -58,7 +57,6 @@ struct tipc_link_req { struct tipc_bearer *bearer; struct tipc_media_addr dest; - u32 domain; int num_nodes; spinlock_t lock; struct sk_buff *buf; @@ -69,14 +67,13 @@ struct tipc_link_req { /** * tipc_disc_init_msg - initialize a link setup message * @type: message type (request or response) - * @dest_domain: network domain of node(s) which should respond to message * @b_ptr: ptr to bearer issuing message */ -static struct sk_buff *tipc_disc_init_msg(u32 type, u32 dest_domain, - struct tipc_bearer *b_ptr) +static struct sk_buff *tipc_disc_init_msg(u32 type, struct tipc_bearer *b_ptr) { struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE); struct tipc_msg *msg; + u32 dest_domain = b_ptr->domain; if (buf) { msg = buf_msg(buf); @@ -110,11 +107,11 @@ static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr, } /** - * tipc_disc_recv_msg - handle incoming link setup message (request or response) + * tipc_disc_rcv - handle incoming link setup message (request or response) * @buf: buffer containing message * @b_ptr: bearer that message arrived on */ -void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) +void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr) { struct tipc_node *n_ptr; struct tipc_link *link; @@ -149,7 +146,7 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) } if (!tipc_in_scope(dest, tipc_own_addr)) return; - if (!tipc_in_scope(b_ptr->link_req->domain, orig)) + if (!tipc_in_scope(b_ptr->domain, orig)) return; /* Locate structure corresponding to requesting node */ @@ -242,7 +239,7 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) link_fully_up = link_working_working(link); if ((type == DSC_REQ_MSG) && !link_fully_up) { - rbuf = tipc_disc_init_msg(DSC_RESP_MSG, orig, b_ptr); + rbuf = tipc_disc_init_msg(DSC_RESP_MSG, b_ptr); if (rbuf) { tipc_bearer_send(b_ptr, rbuf, &media_addr); kfree_skb(rbuf); @@ -306,7 +303,7 @@ static void disc_timeout(struct tipc_link_req *req) spin_lock_bh(&req->lock); /* Stop searching if only desired node has been found */ - if (tipc_node(req->domain) && req->num_nodes) { + if (tipc_node(req->bearer->domain) && req->num_nodes) { req->timer_intv = TIPC_LINK_REQ_INACTIVE; goto exit; } @@ -342,8 +339,7 @@ exit: * * Returns 0 if successful, otherwise -errno. */ -int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest, - u32 dest_domain) +int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest) { struct tipc_link_req *req; @@ -351,7 +347,7 @@ int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest, if (!req) return -ENOMEM; - req->buf = tipc_disc_init_msg(DSC_REQ_MSG, dest_domain, b_ptr); + req->buf = tipc_disc_init_msg(DSC_REQ_MSG, b_ptr); if (!req->buf) { kfree(req); return -ENOMSG; @@ -359,7 +355,6 @@ int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest, memcpy(&req->dest, dest, sizeof(*dest)); req->bearer = b_ptr; - req->domain = dest_domain; req->num_nodes = 0; req->timer_intv = TIPC_LINK_REQ_INIT; spin_lock_init(&req->lock); diff --git a/net/tipc/discover.h b/net/tipc/discover.h index 75b67c403aa3..07f34729459d 100644 --- a/net/tipc/discover.h +++ b/net/tipc/discover.h @@ -39,11 +39,10 @@ struct tipc_link_req; -int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest, - u32 dest_domain); +int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest); void tipc_disc_delete(struct tipc_link_req *req); void tipc_disc_add_dest(struct tipc_link_req *req); void tipc_disc_remove_dest(struct tipc_link_req *req); -void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr); +void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr); #endif diff --git a/net/tipc/link.c b/net/tipc/link.c index da6018beb6eb..c5190ab75290 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -77,19 +77,19 @@ static const char *link_unk_evt = "Unknown link event "; static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, struct sk_buff *buf); -static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf); -static int tipc_link_tunnel_rcv(struct tipc_link **l_ptr, +static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf); +static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr, struct sk_buff **buf); static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance); -static int link_send_sections_long(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destnode); +static int tipc_link_iovec_long_xmit(struct tipc_port *sender, + struct iovec const *msg_sect, + unsigned int len, u32 destnode); static void link_state_event(struct tipc_link *l_ptr, u32 event); static void link_reset_statistics(struct tipc_link *l_ptr); static void link_print(struct tipc_link *l_ptr, const char *str); -static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf); -static void tipc_link_send_sync(struct tipc_link *l); -static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf); +static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf); +static void tipc_link_sync_xmit(struct tipc_link *l); +static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf); /* * Simple link routines @@ -147,11 +147,6 @@ int tipc_link_is_active(struct tipc_link *l_ptr) /** * link_timeout - handle expiration of link timer * @l_ptr: pointer to link - * - * This routine must not grab "tipc_net_lock" to avoid a potential deadlock conflict - * with tipc_link_delete(). (There is no risk that the node will be deleted by - * another thread because tipc_link_delete() always cancels the link timer before - * tipc_node_delete() is called.) */ static void link_timeout(struct tipc_link *l_ptr) { @@ -213,8 +208,8 @@ static void link_set_timer(struct tipc_link *l_ptr, u32 time) * Returns pointer to link. */ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, - struct tipc_bearer *b_ptr, - const struct tipc_media_addr *media_addr) + struct tipc_bearer *b_ptr, + const struct tipc_media_addr *media_addr) { struct tipc_link *l_ptr; struct tipc_msg *msg; @@ -279,41 +274,44 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, k_init_timer(&l_ptr->timer, (Handler)link_timeout, (unsigned long)l_ptr); - list_add_tail(&l_ptr->link_list, &b_ptr->links); link_state_event(l_ptr, STARTING_EVT); return l_ptr; } -/** - * tipc_link_delete - delete a link - * @l_ptr: pointer to link - * - * Note: 'tipc_net_lock' is write_locked, bearer is locked. - * This routine must not grab the node lock until after link timer cancellation - * to avoid a potential deadlock situation. - */ -void tipc_link_delete(struct tipc_link *l_ptr) +void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down) { - if (!l_ptr) { - pr_err("Attempt to delete non-existent link\n"); - return; - } - - k_cancel_timer(&l_ptr->timer); + struct tipc_link *l_ptr; + struct tipc_node *n_ptr; - tipc_node_lock(l_ptr->owner); - tipc_link_reset(l_ptr); - tipc_node_detach_link(l_ptr->owner, l_ptr); - tipc_link_purge_queues(l_ptr); - list_del_init(&l_ptr->link_list); - tipc_node_unlock(l_ptr->owner); - k_term_timer(&l_ptr->timer); - kfree(l_ptr); + rcu_read_lock(); + list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { + spin_lock_bh(&n_ptr->lock); + l_ptr = n_ptr->links[bearer_id]; + if (l_ptr) { + tipc_link_reset(l_ptr); + if (shutting_down || !tipc_node_is_up(n_ptr)) { + tipc_node_detach_link(l_ptr->owner, l_ptr); + tipc_link_reset_fragments(l_ptr); + spin_unlock_bh(&n_ptr->lock); + + /* Nobody else can access this link now: */ + del_timer_sync(&l_ptr->timer); + kfree(l_ptr); + } else { + /* Detach/delete when failover is finished: */ + l_ptr->flags |= LINK_STOPPED; + spin_unlock_bh(&n_ptr->lock); + del_timer_sync(&l_ptr->timer); + } + continue; + } + spin_unlock_bh(&n_ptr->lock); + } + rcu_read_unlock(); } - /** * link_schedule_port - schedule port for deferred sending * @l_ptr: pointer to link @@ -330,8 +328,6 @@ static int link_schedule_port(struct tipc_link *l_ptr, u32 origport, u32 sz) spin_lock_bh(&tipc_port_list_lock); p_ptr = tipc_port_lock(origport); if (p_ptr) { - if (!p_ptr->wakeup) - goto exit; if (!list_empty(&p_ptr->wait_list)) goto exit; p_ptr->congested = 1; @@ -366,7 +362,7 @@ void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all) list_del_init(&p_ptr->wait_list); spin_lock_bh(p_ptr->lock); p_ptr->congested = 0; - p_ptr->wakeup(p_ptr); + tipc_port_wakeup(p_ptr); win -= p_ptr->waiting_pkts; spin_unlock_bh(p_ptr->lock); } @@ -461,6 +457,21 @@ void tipc_link_reset(struct tipc_link *l_ptr) link_reset_statistics(l_ptr); } +void tipc_link_reset_list(unsigned int bearer_id) +{ + struct tipc_link *l_ptr; + struct tipc_node *n_ptr; + + rcu_read_lock(); + list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { + spin_lock_bh(&n_ptr->lock); + l_ptr = n_ptr->links[bearer_id]; + if (l_ptr) + tipc_link_reset(l_ptr); + spin_unlock_bh(&n_ptr->lock); + } + rcu_read_unlock(); +} static void link_activate(struct tipc_link *l_ptr) { @@ -479,7 +490,10 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) struct tipc_link *other; u32 cont_intv = l_ptr->continuity_interval; - if (!l_ptr->started && (event != STARTING_EVT)) + if (l_ptr->flags & LINK_STOPPED) + return; + + if (!(l_ptr->flags & LINK_STARTED) && (event != STARTING_EVT)) return; /* Not yet. */ /* Check whether changeover is going on */ @@ -499,12 +513,12 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) if (l_ptr->next_in_no != l_ptr->checkpoint) { l_ptr->checkpoint = l_ptr->next_in_no; if (tipc_bclink_acks_missing(l_ptr->owner)) { - tipc_link_send_proto_msg(l_ptr, STATE_MSG, - 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; } else if (l_ptr->max_pkt < l_ptr->max_pkt_target) { - tipc_link_send_proto_msg(l_ptr, STATE_MSG, - 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, + 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; } link_set_timer(l_ptr, cont_intv); @@ -512,7 +526,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) } l_ptr->state = WORKING_UNKNOWN; l_ptr->fsm_msg_cnt = 0; - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv / 4); break; @@ -522,7 +536,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) tipc_link_reset(l_ptr); l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; - tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -544,7 +559,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) tipc_link_reset(l_ptr); l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; - tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -554,14 +570,14 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->fsm_msg_cnt = 0; l_ptr->checkpoint = l_ptr->next_in_no; if (tipc_bclink_acks_missing(l_ptr->owner)) { - tipc_link_send_proto_msg(l_ptr, STATE_MSG, - 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; } link_set_timer(l_ptr, cont_intv); } else if (l_ptr->fsm_msg_cnt < l_ptr->abort_limit) { - tipc_link_send_proto_msg(l_ptr, STATE_MSG, - 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, + 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv / 4); } else { /* Link has failed */ @@ -570,8 +586,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) tipc_link_reset(l_ptr); l_ptr->state = RESET_UNKNOWN; l_ptr->fsm_msg_cnt = 0; - tipc_link_send_proto_msg(l_ptr, RESET_MSG, - 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, RESET_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); } @@ -591,24 +607,25 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->state = WORKING_WORKING; l_ptr->fsm_msg_cnt = 0; link_activate(l_ptr); - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; if (l_ptr->owner->working_links == 1) - tipc_link_send_sync(l_ptr); + tipc_link_sync_xmit(l_ptr); link_set_timer(l_ptr, cont_intv); break; case RESET_MSG: l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; - tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, + 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; case STARTING_EVT: - l_ptr->started = 1; + l_ptr->flags |= LINK_STARTED; /* fall through */ case TIMEOUT_EVT: - tipc_link_send_proto_msg(l_ptr, RESET_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -626,16 +643,17 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->state = WORKING_WORKING; l_ptr->fsm_msg_cnt = 0; link_activate(l_ptr); - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; if (l_ptr->owner->working_links == 1) - tipc_link_send_sync(l_ptr); + tipc_link_sync_xmit(l_ptr); link_set_timer(l_ptr, cont_intv); break; case RESET_MSG: break; case TIMEOUT_EVT: - tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -721,11 +739,11 @@ static void link_add_chain_to_outqueue(struct tipc_link *l_ptr, } /* - * tipc_link_send_buf() is the 'full path' for messages, called from - * inside TIPC when the 'fast path' in tipc_send_buf + * tipc_link_xmit() is the 'full path' for messages, called from + * inside TIPC when the 'fast path' in tipc_send_xmit * has failed, and from link_send() */ -int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) +int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); u32 size = msg_size(msg); @@ -753,7 +771,7 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) /* Fragmentation needed ? */ if (size > max_packet) - return link_send_long_buf(l_ptr, buf); + return tipc_link_frag_xmit(l_ptr, buf); /* Packet can be queued or sent. */ if (likely(!link_congested(l_ptr))) { @@ -797,11 +815,11 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) } /* - * tipc_link_send(): same as tipc_link_send_buf(), but the link to use has - * not been selected yet, and the the owner node is not locked + * tipc_link_xmit(): same as __tipc_link_xmit(), but the link to use + * has not been selected yet, and the the owner node is not locked * Called by TIPC internal users, e.g. the name distributor */ -int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) +int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector) { struct tipc_link *l_ptr; struct tipc_node *n_ptr; @@ -813,7 +831,7 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) tipc_node_lock(n_ptr); l_ptr = n_ptr->active_links[selector & 1]; if (l_ptr) - res = tipc_link_send_buf(l_ptr, buf); + res = __tipc_link_xmit(l_ptr, buf); else kfree_skb(buf); tipc_node_unlock(n_ptr); @@ -825,14 +843,14 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) } /* - * tipc_link_send_sync - synchronize broadcast link endpoints. + * tipc_link_sync_xmit - synchronize broadcast link endpoints. * * Give a newly added peer node the sequence number where it should * start receiving and acking broadcast packets. * * Called with node locked */ -static void tipc_link_send_sync(struct tipc_link *l) +static void tipc_link_sync_xmit(struct tipc_link *l) { struct sk_buff *buf; struct tipc_msg *msg; @@ -849,14 +867,14 @@ static void tipc_link_send_sync(struct tipc_link *l) } /* - * tipc_link_recv_sync - synchronize broadcast link endpoints. + * tipc_link_sync_rcv - synchronize broadcast link endpoints. * Receive the sequence number where we should start receiving and * acking broadcast packets from a newly added peer node, and open * up for reception of such packets. * * Called with node locked */ -static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf) +static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); @@ -866,7 +884,7 @@ static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf) } /* - * tipc_link_send_names - send name table entries to new neighbor + * tipc_link_names_xmit - send name table entries to new neighbor * * Send routine for bulk delivery of name table messages when contact * with a new neighbor occurs. No link congestion checking is performed @@ -874,7 +892,7 @@ static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf) * small enough not to require fragmentation. * Called without any locks held. */ -void tipc_link_send_names(struct list_head *message_list, u32 dest) +void tipc_link_names_xmit(struct list_head *message_list, u32 dest) { struct tipc_node *n_ptr; struct tipc_link *l_ptr; @@ -909,13 +927,13 @@ void tipc_link_send_names(struct list_head *message_list, u32 dest) } /* - * link_send_buf_fast: Entry for data messages where the + * tipc_link_xmit_fast: Entry for data messages where the * destination link is known and the header is complete, * inclusive total message length. Very time critical. * Link is locked. Returns user data length. */ -static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf, - u32 *used_max_pkt) +static int tipc_link_xmit_fast(struct tipc_link *l_ptr, struct sk_buff *buf, + u32 *used_max_pkt) { struct tipc_msg *msg = buf_msg(buf); int res = msg_data_sz(msg); @@ -931,18 +949,18 @@ static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf, else *used_max_pkt = l_ptr->max_pkt; } - return tipc_link_send_buf(l_ptr, buf); /* All other cases */ + return __tipc_link_xmit(l_ptr, buf); /* All other cases */ } /* - * tipc_link_send_sections_fast: Entry for messages where the + * tipc_link_iovec_xmit_fast: Entry for messages where the * destination processor is known and the header is complete, * except for total message length. * Returns user data length or errno. */ -int tipc_link_send_sections_fast(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destaddr) +int tipc_link_iovec_xmit_fast(struct tipc_port *sender, + struct iovec const *msg_sect, + unsigned int len, u32 destaddr) { struct tipc_msg *hdr = &sender->phdr; struct tipc_link *l_ptr; @@ -968,8 +986,8 @@ again: l_ptr = node->active_links[selector]; if (likely(l_ptr)) { if (likely(buf)) { - res = link_send_buf_fast(l_ptr, buf, - &sender->max_pkt); + res = tipc_link_xmit_fast(l_ptr, buf, + &sender->max_pkt); exit: tipc_node_unlock(node); read_unlock_bh(&tipc_net_lock); @@ -995,24 +1013,21 @@ exit: if ((msg_hdr_sz(hdr) + res) <= sender->max_pkt) goto again; - return link_send_sections_long(sender, msg_sect, len, - destaddr); + return tipc_link_iovec_long_xmit(sender, msg_sect, + len, destaddr); } tipc_node_unlock(node); } read_unlock_bh(&tipc_net_lock); /* Couldn't find a link to the destination node */ - if (buf) - return tipc_reject_msg(buf, TIPC_ERR_NO_NODE); - if (res >= 0) - return tipc_port_reject_sections(sender, hdr, msg_sect, - len, TIPC_ERR_NO_NODE); - return res; + kfree_skb(buf); + tipc_port_iovec_reject(sender, hdr, msg_sect, len, TIPC_ERR_NO_NODE); + return -ENETUNREACH; } /* - * link_send_sections_long(): Entry for long messages where the + * tipc_link_iovec_long_xmit(): Entry for long messages where the * destination node is known and the header is complete, * inclusive total message length. * Link and bearer congestion status have been checked to be ok, @@ -1025,9 +1040,9 @@ exit: * * Returns user data length or errno. */ -static int link_send_sections_long(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destaddr) +static int tipc_link_iovec_long_xmit(struct tipc_port *sender, + struct iovec const *msg_sect, + unsigned int len, u32 destaddr) { struct tipc_link *l_ptr; struct tipc_node *node; @@ -1146,8 +1161,9 @@ error: } else { reject: kfree_skb_list(buf_chain); - return tipc_port_reject_sections(sender, hdr, msg_sect, - len, TIPC_ERR_NO_NODE); + tipc_port_iovec_reject(sender, hdr, msg_sect, len, + TIPC_ERR_NO_NODE); + return -ENETUNREACH; } /* Append chain of fragments to send queue & send them */ @@ -1441,15 +1457,10 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) u32 seq_no; u32 ackd; u32 released = 0; - int type; head = head->next; buf->next = NULL; - /* Ensure bearer is still enabled */ - if (unlikely(!b_ptr->active)) - goto discard; - /* Ensure message is well-formed */ if (unlikely(!link_recv_buf_validate(buf))) goto discard; @@ -1463,9 +1474,9 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) if (unlikely(msg_non_seq(msg))) { if (msg_user(msg) == LINK_CONFIG) - tipc_disc_recv_msg(buf, b_ptr); + tipc_disc_rcv(buf, b_ptr); else - tipc_bclink_recv_pkt(buf); + tipc_bclink_rcv(buf); continue; } @@ -1489,7 +1500,7 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) if ((n_ptr->block_setup & WAIT_PEER_DOWN) && msg_user(msg) == LINK_PROTOCOL && (msg_type(msg) == RESET_MSG || - msg_type(msg) == ACTIVATE_MSG) && + msg_type(msg) == ACTIVATE_MSG) && !msg_redundant_link(msg)) n_ptr->block_setup &= ~WAIT_PEER_DOWN; @@ -1508,7 +1519,6 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) while ((crs != l_ptr->next_out) && less_eq(buf_seqno(crs), ackd)) { struct sk_buff *next = crs->next; - kfree_skb(crs); crs = next; released++; @@ -1521,18 +1531,19 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) /* Try sending any messages link endpoint has pending */ if (unlikely(l_ptr->next_out)) tipc_link_push_queue(l_ptr); + if (unlikely(!list_empty(&l_ptr->waiting_ports))) tipc_link_wakeup_ports(l_ptr, 0); + if (unlikely(++l_ptr->unacked_window >= TIPC_MIN_LINK_WIN)) { l_ptr->stats.sent_acks++; - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); } - /* Now (finally!) process the incoming message */ -protocol_check: + /* Process the incoming packet */ if (unlikely(!link_working_working(l_ptr))) { if (msg_user(msg) == LINK_PROTOCOL) { - link_recv_proto_msg(l_ptr, buf); + tipc_link_proto_rcv(l_ptr, buf); head = link_insert_deferred_queue(l_ptr, head); tipc_node_unlock(n_ptr); continue; @@ -1561,67 +1572,65 @@ protocol_check: l_ptr->next_in_no++; if (unlikely(l_ptr->oldest_deferred_in)) head = link_insert_deferred_queue(l_ptr, head); -deliver: - if (likely(msg_isdata(msg))) { - tipc_node_unlock(n_ptr); - tipc_port_recv_msg(buf); - continue; + + /* Deliver packet/message to correct user: */ + if (unlikely(msg_user(msg) == CHANGEOVER_PROTOCOL)) { + if (!tipc_link_tunnel_rcv(n_ptr, &buf)) { + tipc_node_unlock(n_ptr); + continue; + } + msg = buf_msg(buf); + } else if (msg_user(msg) == MSG_FRAGMENTER) { + int rc; + + l_ptr->stats.recv_fragments++; + rc = tipc_link_frag_rcv(&l_ptr->reasm_head, + &l_ptr->reasm_tail, + &buf); + if (rc == LINK_REASM_COMPLETE) { + l_ptr->stats.recv_fragmented++; + msg = buf_msg(buf); + } else { + if (rc == LINK_REASM_ERROR) + tipc_link_reset(l_ptr); + tipc_node_unlock(n_ptr); + continue; + } } + switch (msg_user(msg)) { - int ret; + case TIPC_LOW_IMPORTANCE: + case TIPC_MEDIUM_IMPORTANCE: + case TIPC_HIGH_IMPORTANCE: + case TIPC_CRITICAL_IMPORTANCE: + tipc_node_unlock(n_ptr); + tipc_port_rcv(buf); + continue; case MSG_BUNDLER: l_ptr->stats.recv_bundles++; l_ptr->stats.recv_bundled += msg_msgcnt(msg); tipc_node_unlock(n_ptr); - tipc_link_recv_bundle(buf); + tipc_link_bundle_rcv(buf); continue; case NAME_DISTRIBUTOR: n_ptr->bclink.recv_permitted = true; tipc_node_unlock(n_ptr); - tipc_named_recv(buf); - continue; - case BCAST_PROTOCOL: - tipc_link_recv_sync(n_ptr, buf); - tipc_node_unlock(n_ptr); + tipc_named_rcv(buf); continue; case CONN_MANAGER: tipc_node_unlock(n_ptr); - tipc_port_recv_proto_msg(buf); + tipc_port_proto_rcv(buf); continue; - case MSG_FRAGMENTER: - l_ptr->stats.recv_fragments++; - ret = tipc_link_recv_fragment(&l_ptr->reasm_head, - &l_ptr->reasm_tail, - &buf); - if (ret == LINK_REASM_COMPLETE) { - l_ptr->stats.recv_fragmented++; - msg = buf_msg(buf); - goto deliver; - } - if (ret == LINK_REASM_ERROR) - tipc_link_reset(l_ptr); - tipc_node_unlock(n_ptr); - continue; - case CHANGEOVER_PROTOCOL: - type = msg_type(msg); - if (tipc_link_tunnel_rcv(&l_ptr, &buf)) { - msg = buf_msg(buf); - seq_no = msg_seqno(msg); - if (type == ORIGINAL_MSG) - goto deliver; - goto protocol_check; - } + case BCAST_PROTOCOL: + tipc_link_sync_rcv(n_ptr, buf); break; default: kfree_skb(buf); - buf = NULL; break; } tipc_node_unlock(n_ptr); - tipc_net_route_msg(buf); continue; unlock_discard: - tipc_node_unlock(n_ptr); discard: kfree_skb(buf); @@ -1688,7 +1697,7 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, u32 seq_no = buf_seqno(buf); if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) { - link_recv_proto_msg(l_ptr, buf); + tipc_link_proto_rcv(l_ptr, buf); return; } @@ -1711,7 +1720,7 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, l_ptr->stats.deferred_recv++; TIPC_SKB_CB(buf)->deferred = true; if ((l_ptr->deferred_inqueue_sz % 16) == 1) - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); } else l_ptr->stats.duplicates++; } @@ -1719,9 +1728,8 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, /* * Send protocol message to the other endpoint. */ -void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, - int probe_msg, u32 gap, u32 tolerance, - u32 priority, u32 ack_mtu) +void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, + u32 gap, u32 tolerance, u32 priority, u32 ack_mtu) { struct sk_buff *buf = NULL; struct tipc_msg *msg = l_ptr->pmsg; @@ -1820,7 +1828,7 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, * Note that network plane id propagates through the network, and may * change at any time. The node with lowest address rules */ -static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) +static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf) { u32 rec_gap = 0; u32 max_pkt_info; @@ -1939,8 +1947,8 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) msg_last_bcast(msg)); if (rec_gap || (msg_probe(msg))) { - tipc_link_send_proto_msg(l_ptr, STATE_MSG, - 0, rec_gap, 0, 0, max_pkt_ack); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, rec_gap, 0, + 0, max_pkt_ack); } if (msg_seq_gap(msg)) { l_ptr->stats.recv_nacks++; @@ -1979,7 +1987,7 @@ static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr, } skb_copy_to_linear_data(buf, tunnel_hdr, INT_H_SIZE); skb_copy_to_linear_data_offset(buf, INT_H_SIZE, msg, length); - tipc_link_send_buf(tunnel, buf); + __tipc_link_xmit(tunnel, buf); } @@ -2012,7 +2020,7 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) if (buf) { skb_copy_to_linear_data(buf, &tunnel_hdr, INT_H_SIZE); msg_set_size(&tunnel_hdr, INT_H_SIZE); - tipc_link_send_buf(tunnel, buf); + __tipc_link_xmit(tunnel, buf); } else { pr_warn("%sunable to send changeover msg\n", link_co_err); @@ -2046,7 +2054,7 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) } } -/* tipc_link_dup_send_queue(): A second link has become active. Tunnel a +/* tipc_link_dup_queue_xmit(): A second link has become active. Tunnel a * duplicate of the first link's send queue via the new link. This way, we * are guaranteed that currently queued packets from a socket are delivered * before future traffic from the same socket, even if this is using the @@ -2055,7 +2063,7 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) * and sequence order is preserved per sender/receiver socket pair. * Owner node is locked. */ -void tipc_link_dup_send_queue(struct tipc_link *l_ptr, +void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *tunnel) { struct sk_buff *iter; @@ -2085,7 +2093,7 @@ void tipc_link_dup_send_queue(struct tipc_link *l_ptr, skb_copy_to_linear_data(outbuf, &tunnel_hdr, INT_H_SIZE); skb_copy_to_linear_data_offset(outbuf, INT_H_SIZE, iter->data, length); - tipc_link_send_buf(tunnel, outbuf); + __tipc_link_xmit(tunnel, outbuf); if (!tipc_link_is_up(l_ptr)) return; iter = iter->next; @@ -2112,89 +2120,114 @@ static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) return eb; } -/* tipc_link_tunnel_rcv(): Receive a tunneled packet, sent - * via other link as result of a failover (ORIGINAL_MSG) or - * a new active link (DUPLICATE_MSG). Failover packets are - * returned to the active link for delivery upwards. + + +/* tipc_link_dup_rcv(): Receive a tunnelled DUPLICATE_MSG packet. + * Owner node is locked. + */ +static void tipc_link_dup_rcv(struct tipc_link *l_ptr, + struct sk_buff *t_buf) +{ + struct sk_buff *buf; + + if (!tipc_link_is_up(l_ptr)) + return; + + buf = buf_extract(t_buf, INT_H_SIZE); + if (buf == NULL) { + pr_warn("%sfailed to extract inner dup pkt\n", link_co_err); + return; + } + + /* Add buffer to deferred queue, if applicable: */ + link_handle_out_of_seq_msg(l_ptr, buf); +} + +/* tipc_link_failover_rcv(): Receive a tunnelled ORIGINAL_MSG packet * Owner node is locked. */ -static int tipc_link_tunnel_rcv(struct tipc_link **l_ptr, - struct sk_buff **buf) +static struct sk_buff *tipc_link_failover_rcv(struct tipc_link *l_ptr, + struct sk_buff *t_buf) { - struct sk_buff *tunnel_buf = *buf; - struct tipc_link *dest_link; + struct tipc_msg *t_msg = buf_msg(t_buf); + struct sk_buff *buf = NULL; struct tipc_msg *msg; - struct tipc_msg *tunnel_msg = buf_msg(tunnel_buf); - u32 msg_typ = msg_type(tunnel_msg); - u32 msg_count = msg_msgcnt(tunnel_msg); - u32 bearer_id = msg_bearer_id(tunnel_msg); - if (bearer_id >= MAX_BEARERS) - goto exit; - dest_link = (*l_ptr)->owner->links[bearer_id]; - if (!dest_link) - goto exit; - if (dest_link == *l_ptr) { - pr_err("Unexpected changeover message on link <%s>\n", - (*l_ptr)->name); - goto exit; - } - *l_ptr = dest_link; - msg = msg_get_wrapped(tunnel_msg); + if (tipc_link_is_up(l_ptr)) + tipc_link_reset(l_ptr); - if (msg_typ == DUPLICATE_MSG) { - if (less(msg_seqno(msg), mod(dest_link->next_in_no))) - goto exit; - *buf = buf_extract(tunnel_buf, INT_H_SIZE); - if (*buf == NULL) { - pr_warn("%sduplicate msg dropped\n", link_co_err); + /* First failover packet? */ + if (l_ptr->exp_msg_count == START_CHANGEOVER) + l_ptr->exp_msg_count = msg_msgcnt(t_msg); + + /* Should there be an inner packet? */ + if (l_ptr->exp_msg_count) { + l_ptr->exp_msg_count--; + buf = buf_extract(t_buf, INT_H_SIZE); + if (buf == NULL) { + pr_warn("%sno inner failover pkt\n", link_co_err); goto exit; } - kfree_skb(tunnel_buf); - return 1; - } + msg = buf_msg(buf); - /* First original message ?: */ - if (tipc_link_is_up(dest_link)) { - pr_info("%s<%s>, changeover initiated by peer\n", link_rst_msg, - dest_link->name); - tipc_link_reset(dest_link); - dest_link->exp_msg_count = msg_count; - if (!msg_count) - goto exit; - } else if (dest_link->exp_msg_count == START_CHANGEOVER) { - dest_link->exp_msg_count = msg_count; - if (!msg_count) + if (less(msg_seqno(msg), l_ptr->reset_checkpoint)) { + kfree_skb(buf); + buf = NULL; goto exit; + } + if (msg_user(msg) == MSG_FRAGMENTER) { + l_ptr->stats.recv_fragments++; + tipc_link_frag_rcv(&l_ptr->reasm_head, + &l_ptr->reasm_tail, + &buf); + } + } +exit: + if ((l_ptr->exp_msg_count == 0) && (l_ptr->flags & LINK_STOPPED)) { + tipc_node_detach_link(l_ptr->owner, l_ptr); + kfree(l_ptr); } + return buf; +} - /* Receive original message */ - if (dest_link->exp_msg_count == 0) { - pr_warn("%sgot too many tunnelled messages\n", link_co_err); +/* tipc_link_tunnel_rcv(): Receive a tunnelled packet, sent + * via other link as result of a failover (ORIGINAL_MSG) or + * a new active link (DUPLICATE_MSG). Failover packets are + * returned to the active link for delivery upwards. + * Owner node is locked. + */ +static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr, + struct sk_buff **buf) +{ + struct sk_buff *t_buf = *buf; + struct tipc_link *l_ptr; + struct tipc_msg *t_msg = buf_msg(t_buf); + u32 bearer_id = msg_bearer_id(t_msg); + + *buf = NULL; + + if (bearer_id >= MAX_BEARERS) goto exit; - } - dest_link->exp_msg_count--; - if (less(msg_seqno(msg), dest_link->reset_checkpoint)) { + + l_ptr = n_ptr->links[bearer_id]; + if (!l_ptr) goto exit; - } else { - *buf = buf_extract(tunnel_buf, INT_H_SIZE); - if (*buf != NULL) { - kfree_skb(tunnel_buf); - return 1; - } else { - pr_warn("%soriginal msg dropped\n", link_co_err); - } - } + + if (msg_type(t_msg) == DUPLICATE_MSG) + tipc_link_dup_rcv(l_ptr, t_buf); + else if (msg_type(t_msg) == ORIGINAL_MSG) + *buf = tipc_link_failover_rcv(l_ptr, t_buf); + else + pr_warn("%sunknown tunnel pkt received\n", link_co_err); exit: - *buf = NULL; - kfree_skb(tunnel_buf); - return 0; + kfree_skb(t_buf); + return *buf != NULL; } /* * Bundler functionality: */ -void tipc_link_recv_bundle(struct sk_buff *buf) +void tipc_link_bundle_rcv(struct sk_buff *buf) { u32 msgcount = msg_msgcnt(buf_msg(buf)); u32 pos = INT_H_SIZE; @@ -2217,11 +2250,11 @@ void tipc_link_recv_bundle(struct sk_buff *buf) */ /* - * link_send_long_buf: Entry for buffers needing fragmentation. + * tipc_link_frag_xmit: Entry for buffers needing fragmentation. * The buffer is complete, inclusive total message length. * Returns user data length. */ -static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) +static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf) { struct sk_buff *buf_chain = NULL; struct sk_buff *buf_chain_tail = (struct sk_buff *)&buf_chain; @@ -2284,12 +2317,11 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) return dsz; } -/* - * tipc_link_recv_fragment(): Called with node lock on. Returns +/* tipc_link_frag_rcv(): Called with node lock on. Returns * the reassembled buffer if message is complete. */ -int tipc_link_recv_fragment(struct sk_buff **head, struct sk_buff **tail, - struct sk_buff **fbuf) +int tipc_link_frag_rcv(struct sk_buff **head, struct sk_buff **tail, + struct sk_buff **fbuf) { struct sk_buff *frag = *fbuf; struct tipc_msg *msg = buf_msg(frag); @@ -2303,6 +2335,7 @@ int tipc_link_recv_fragment(struct sk_buff **head, struct sk_buff **tail, goto out_free; *head = frag; skb_frag_list_init(*head); + *fbuf = NULL; return 0; } else if (*head && skb_try_coalesce(*head, frag, &headstolen, &delta)) { @@ -2322,10 +2355,12 @@ int tipc_link_recv_fragment(struct sk_buff **head, struct sk_buff **tail, *tail = *head = NULL; return LINK_REASM_COMPLETE; } + *fbuf = NULL; return 0; out_free: pr_warn_ratelimited("Link unable to reassemble fragmented message\n"); kfree_skb(*fbuf); + *fbuf = NULL; return LINK_REASM_ERROR; } @@ -2359,35 +2394,41 @@ void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window) l_ptr->queue_limit[MSG_FRAGMENTER] = 4000; } -/** - * link_find_link - locate link by name - * @name: ptr to link name string - * @node: ptr to area to be filled with ptr to associated node - * +/* tipc_link_find_owner - locate owner node of link by link's name + * @name: pointer to link name string + * @bearer_id: pointer to index in 'node->links' array where the link was found. * Caller must hold 'tipc_net_lock' to ensure node and bearer are not deleted; * this also prevents link deletion. * - * Returns pointer to link (or 0 if invalid link name). + * Returns pointer to node owning the link, or 0 if no matching link is found. */ -static struct tipc_link *link_find_link(const char *name, - struct tipc_node **node) +static struct tipc_node *tipc_link_find_owner(const char *link_name, + unsigned int *bearer_id) { struct tipc_link *l_ptr; struct tipc_node *n_ptr; + struct tipc_node *found_node = 0; int i; - list_for_each_entry(n_ptr, &tipc_node_list, list) { + *bearer_id = 0; + rcu_read_lock(); + list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { + tipc_node_lock(n_ptr); for (i = 0; i < MAX_BEARERS; i++) { l_ptr = n_ptr->links[i]; - if (l_ptr && !strcmp(l_ptr->name, name)) - goto found; + if (l_ptr && !strcmp(l_ptr->name, link_name)) { + *bearer_id = i; + found_node = n_ptr; + break; + } } + tipc_node_unlock(n_ptr); + if (found_node) + break; } - l_ptr = NULL; - n_ptr = NULL; -found: - *node = n_ptr; - return l_ptr; + rcu_read_unlock(); + + return found_node; } /** @@ -2429,32 +2470,33 @@ static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) struct tipc_link *l_ptr; struct tipc_bearer *b_ptr; struct tipc_media *m_ptr; + int bearer_id; int res = 0; - l_ptr = link_find_link(name, &node); - if (l_ptr) { - /* - * acquire node lock for tipc_link_send_proto_msg(). - * see "TIPC locking policy" in net.c. - */ + node = tipc_link_find_owner(name, &bearer_id); + if (node) { tipc_node_lock(node); - switch (cmd) { - case TIPC_CMD_SET_LINK_TOL: - link_set_supervision_props(l_ptr, new_value); - tipc_link_send_proto_msg(l_ptr, - STATE_MSG, 0, 0, new_value, 0, 0); - break; - case TIPC_CMD_SET_LINK_PRI: - l_ptr->priority = new_value; - tipc_link_send_proto_msg(l_ptr, - STATE_MSG, 0, 0, 0, new_value, 0); - break; - case TIPC_CMD_SET_LINK_WINDOW: - tipc_link_set_queue_limits(l_ptr, new_value); - break; - default: - res = -EINVAL; - break; + l_ptr = node->links[bearer_id]; + + if (l_ptr) { + switch (cmd) { + case TIPC_CMD_SET_LINK_TOL: + link_set_supervision_props(l_ptr, new_value); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, + new_value, 0, 0); + break; + case TIPC_CMD_SET_LINK_PRI: + l_ptr->priority = new_value; + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, + 0, new_value, 0); + break; + case TIPC_CMD_SET_LINK_WINDOW: + tipc_link_set_queue_limits(l_ptr, new_value); + break; + default: + res = -EINVAL; + break; + } } tipc_node_unlock(node); return res; @@ -2549,6 +2591,7 @@ struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_ char *link_name; struct tipc_link *l_ptr; struct tipc_node *node; + unsigned int bearer_id; if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME)) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); @@ -2559,15 +2602,19 @@ struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_ return tipc_cfg_reply_error_string("link not found"); return tipc_cfg_reply_none(); } - read_lock_bh(&tipc_net_lock); - l_ptr = link_find_link(link_name, &node); - if (!l_ptr) { + node = tipc_link_find_owner(link_name, &bearer_id); + if (!node) { read_unlock_bh(&tipc_net_lock); return tipc_cfg_reply_error_string("link not found"); } - tipc_node_lock(node); + l_ptr = node->links[bearer_id]; + if (!l_ptr) { + tipc_node_unlock(node); + read_unlock_bh(&tipc_net_lock); + return tipc_cfg_reply_error_string("link not found"); + } link_reset_statistics(l_ptr); tipc_node_unlock(node); read_unlock_bh(&tipc_net_lock); @@ -2597,18 +2644,27 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size) struct tipc_node *node; char *status; u32 profile_total = 0; + unsigned int bearer_id; int ret; if (!strcmp(name, tipc_bclink_name)) return tipc_bclink_stats(buf, buf_size); read_lock_bh(&tipc_net_lock); - l = link_find_link(name, &node); - if (!l) { + node = tipc_link_find_owner(name, &bearer_id); + if (!node) { read_unlock_bh(&tipc_net_lock); return 0; } tipc_node_lock(node); + + l = node->links[bearer_id]; + if (!l) { + tipc_node_unlock(node); + read_unlock_bh(&tipc_net_lock); + return 0; + } + s = &l->stats; if (tipc_link_is_active(l)) diff --git a/net/tipc/link.h b/net/tipc/link.h index 3b6aa65b608c..8c0b49b5b2ee 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -1,7 +1,7 @@ /* * net/tipc/link.h: Include file for TIPC link code * - * Copyright (c) 1995-2006, Ericsson AB + * Copyright (c) 1995-2006, 2013, Ericsson AB * Copyright (c) 2004-2005, 2010-2011, Wind River Systems * All rights reserved. * @@ -40,27 +40,28 @@ #include "msg.h" #include "node.h" -/* - * Link reassembly status codes +/* Link reassembly status codes */ #define LINK_REASM_ERROR -1 #define LINK_REASM_COMPLETE 1 -/* - * Out-of-range value for link sequence numbers +/* Out-of-range value for link sequence numbers */ #define INVALID_LINK_SEQ 0x10000 -/* - * Link states +/* Link working states */ #define WORKING_WORKING 560810u #define WORKING_UNKNOWN 560811u #define RESET_UNKNOWN 560812u #define RESET_RESET 560813u -/* - * Starting value for maximum packet size negotiation on unicast links +/* Link endpoint execution states + */ +#define LINK_STARTED 0x0001 +#define LINK_STOPPED 0x0002 + +/* Starting value for maximum packet size negotiation on unicast links * (unless bearer MTU is less) */ #define MAX_PKT_DEFAULT 1500 @@ -102,8 +103,7 @@ struct tipc_stats { * @media_addr: media address to use when sending messages over link * @timer: link timer * @owner: pointer to peer node - * @link_list: adjacent links in bearer's list of links - * @started: indicates if link has been started + * @flags: execution state flags for link endpoint instance * @checkpoint: reference point for triggering link continuity checking * @peer_session: link session # being used by peer end of link * @peer_bearer_id: bearer id used by link's peer endpoint @@ -149,10 +149,9 @@ struct tipc_link { struct tipc_media_addr media_addr; struct timer_list timer; struct tipc_node *owner; - struct list_head link_list; /* Management and link supervision data */ - int started; + unsigned int flags; u32 checkpoint; u32 peer_session; u32 peer_bearer_id; @@ -215,10 +214,9 @@ struct tipc_port; struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, struct tipc_bearer *b_ptr, const struct tipc_media_addr *media_addr); -void tipc_link_delete(struct tipc_link *l_ptr); +void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down); void tipc_link_failover_send_queue(struct tipc_link *l_ptr); -void tipc_link_dup_send_queue(struct tipc_link *l_ptr, - struct tipc_link *dest); +void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *dest); void tipc_link_reset_fragments(struct tipc_link *l_ptr); int tipc_link_is_up(struct tipc_link *l_ptr); int tipc_link_is_active(struct tipc_link *l_ptr); @@ -231,23 +229,24 @@ struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space); void tipc_link_reset(struct tipc_link *l_ptr); -int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector); -void tipc_link_send_names(struct list_head *message_list, u32 dest); +void tipc_link_reset_list(unsigned int bearer_id); +int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector); +void tipc_link_names_xmit(struct list_head *message_list, u32 dest); +int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf); int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf); u32 tipc_link_get_max_pkt(u32 dest, u32 selector); -int tipc_link_send_sections_fast(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destnode); -void tipc_link_recv_bundle(struct sk_buff *buf); -int tipc_link_recv_fragment(struct sk_buff **reasm_head, - struct sk_buff **reasm_tail, - struct sk_buff **fbuf); -void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, int prob, - u32 gap, u32 tolerance, u32 priority, - u32 acked_mtu); +int tipc_link_iovec_xmit_fast(struct tipc_port *sender, + struct iovec const *msg_sect, + unsigned int len, u32 destnode); +void tipc_link_bundle_rcv(struct sk_buff *buf); +int tipc_link_frag_rcv(struct sk_buff **reasm_head, + struct sk_buff **reasm_tail, + struct sk_buff **fbuf); +void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob, + u32 gap, u32 tolerance, u32 priority, u32 acked_mtu); void tipc_link_push_queue(struct tipc_link *l_ptr); u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail, - struct sk_buff *buf); + struct sk_buff *buf); void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all); void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window); void tipc_link_retransmit(struct tipc_link *l_ptr, diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index e0d08055754e..aff8041dc157 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -131,16 +131,24 @@ static void named_cluster_distribute(struct sk_buff *buf) { struct sk_buff *buf_copy; struct tipc_node *n_ptr; + struct tipc_link *l_ptr; - list_for_each_entry(n_ptr, &tipc_node_list, list) { - if (tipc_node_active_links(n_ptr)) { + rcu_read_lock(); + list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { + spin_lock_bh(&n_ptr->lock); + l_ptr = n_ptr->active_links[n_ptr->addr & 1]; + if (l_ptr) { buf_copy = skb_copy(buf, GFP_ATOMIC); - if (!buf_copy) + if (!buf_copy) { + spin_unlock_bh(&n_ptr->lock); break; + } msg_set_destnode(buf_msg(buf_copy), n_ptr->addr); - tipc_link_send(buf_copy, n_ptr->addr, n_ptr->addr); + __tipc_link_xmit(l_ptr, buf_copy); } + spin_unlock_bh(&n_ptr->lock); } + rcu_read_unlock(); kfree_skb(buf); } @@ -262,7 +270,7 @@ void tipc_named_node_up(unsigned long nodearg) named_distribute(&message_list, node, &publ_zone, max_item_buf); read_unlock_bh(&tipc_nametbl_lock); - tipc_link_send_names(&message_list, node); + tipc_link_names_xmit(&message_list, node); } /** @@ -293,9 +301,9 @@ static void named_purge_publ(struct publication *publ) } /** - * tipc_named_recv - process name table update message sent by another node + * tipc_named_rcv - process name table update message sent by another node */ -void tipc_named_recv(struct sk_buff *buf) +void tipc_named_rcv(struct sk_buff *buf) { struct publication *publ; struct tipc_msg *msg = buf_msg(buf); diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h index 1e41bdd4f255..9b312ccfd43e 100644 --- a/net/tipc/name_distr.h +++ b/net/tipc/name_distr.h @@ -42,7 +42,7 @@ void tipc_named_publish(struct publication *publ); void tipc_named_withdraw(struct publication *publ); void tipc_named_node_up(unsigned long node); -void tipc_named_recv(struct sk_buff *buf); +void tipc_named_rcv(struct sk_buff *buf); void tipc_named_reinit(void); #endif diff --git a/net/tipc/net.c b/net/tipc/net.c index 7d305ecc09c2..0374a817631e 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -146,19 +146,19 @@ void tipc_net_route_msg(struct sk_buff *buf) if (tipc_in_scope(dnode, tipc_own_addr)) { if (msg_isdata(msg)) { if (msg_mcast(msg)) - tipc_port_recv_mcast(buf, NULL); + tipc_port_mcast_rcv(buf, NULL); else if (msg_destport(msg)) - tipc_port_recv_msg(buf); + tipc_port_rcv(buf); else net_route_named_msg(buf); return; } switch (msg_user(msg)) { case NAME_DISTRIBUTOR: - tipc_named_recv(buf); + tipc_named_rcv(buf); break; case CONN_MANAGER: - tipc_port_recv_proto_msg(buf); + tipc_port_proto_rcv(buf); break; default: kfree_skb(buf); @@ -168,7 +168,7 @@ void tipc_net_route_msg(struct sk_buff *buf) /* Handle message for another node */ skb_trim(buf, msg_size(msg)); - tipc_link_send(buf, dnode, msg_link_selector(msg)); + tipc_link_xmit(buf, dnode, msg_link_selector(msg)); } void tipc_net_start(u32 addr) @@ -182,8 +182,6 @@ void tipc_net_start(u32 addr) tipc_bclink_init(); write_unlock_bh(&tipc_net_lock); - tipc_cfg_reinit(); - pr_info("Started in network mode\n"); pr_info("Own node address %s, network identity %u\n", tipc_addr_string_fill(addr_string, tipc_own_addr), tipc_net_id); @@ -191,15 +189,14 @@ void tipc_net_start(u32 addr) void tipc_net_stop(void) { - struct tipc_node *node, *t_node; - if (!tipc_own_addr) return; + write_lock_bh(&tipc_net_lock); tipc_bearer_stop(); tipc_bclink_stop(); - list_for_each_entry_safe(node, t_node, &tipc_node_list, list) - tipc_node_delete(node); + tipc_node_stop(); write_unlock_bh(&tipc_net_lock); + pr_info("Left network mode\n"); } diff --git a/net/tipc/node.c b/net/tipc/node.c index efe4d41bf11b..1d3a4999a70f 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2,7 +2,7 @@ * net/tipc/node.c: TIPC node management routines * * Copyright (c) 2000-2006, 2012 Ericsson AB - * Copyright (c) 2005-2006, 2010-2011, Wind River Systems + * Copyright (c) 2005-2006, 2010-2014, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -44,13 +44,11 @@ static void node_lost_contact(struct tipc_node *n_ptr); static void node_established_contact(struct tipc_node *n_ptr); -static DEFINE_SPINLOCK(node_create_lock); - static struct hlist_head node_htable[NODE_HTABLE_SIZE]; LIST_HEAD(tipc_node_list); static u32 tipc_num_nodes; - -static atomic_t tipc_num_links = ATOMIC_INIT(0); +static u32 tipc_num_links; +static DEFINE_SPINLOCK(node_list_lock); /* * A trivial power-of-two bitmask technique is used for speed, since this @@ -73,37 +71,26 @@ struct tipc_node *tipc_node_find(u32 addr) if (unlikely(!in_own_cluster_exact(addr))) return NULL; - hlist_for_each_entry(node, &node_htable[tipc_hashfn(addr)], hash) { - if (node->addr == addr) + rcu_read_lock(); + hlist_for_each_entry_rcu(node, &node_htable[tipc_hashfn(addr)], hash) { + if (node->addr == addr) { + rcu_read_unlock(); return node; + } } + rcu_read_unlock(); return NULL; } -/** - * tipc_node_create - create neighboring node - * - * Currently, this routine is called by neighbor discovery code, which holds - * net_lock for reading only. We must take node_create_lock to ensure a node - * isn't created twice if two different bearers discover the node at the same - * time. (It would be preferable to switch to holding net_lock in write mode, - * but this is a non-trivial change.) - */ struct tipc_node *tipc_node_create(u32 addr) { struct tipc_node *n_ptr, *temp_node; - spin_lock_bh(&node_create_lock); - - n_ptr = tipc_node_find(addr); - if (n_ptr) { - spin_unlock_bh(&node_create_lock); - return n_ptr; - } + spin_lock_bh(&node_list_lock); n_ptr = kzalloc(sizeof(*n_ptr), GFP_ATOMIC); if (!n_ptr) { - spin_unlock_bh(&node_create_lock); + spin_unlock_bh(&node_list_lock); pr_warn("Node creation failed, no memory\n"); return NULL; } @@ -114,31 +101,41 @@ struct tipc_node *tipc_node_create(u32 addr) INIT_LIST_HEAD(&n_ptr->list); INIT_LIST_HEAD(&n_ptr->nsub); - hlist_add_head(&n_ptr->hash, &node_htable[tipc_hashfn(addr)]); + hlist_add_head_rcu(&n_ptr->hash, &node_htable[tipc_hashfn(addr)]); - list_for_each_entry(temp_node, &tipc_node_list, list) { + list_for_each_entry_rcu(temp_node, &tipc_node_list, list) { if (n_ptr->addr < temp_node->addr) break; } - list_add_tail(&n_ptr->list, &temp_node->list); + list_add_tail_rcu(&n_ptr->list, &temp_node->list); n_ptr->block_setup = WAIT_PEER_DOWN; n_ptr->signature = INVALID_NODE_SIG; tipc_num_nodes++; - spin_unlock_bh(&node_create_lock); + spin_unlock_bh(&node_list_lock); return n_ptr; } -void tipc_node_delete(struct tipc_node *n_ptr) +static void tipc_node_delete(struct tipc_node *n_ptr) { - list_del(&n_ptr->list); - hlist_del(&n_ptr->hash); - kfree(n_ptr); + list_del_rcu(&n_ptr->list); + hlist_del_rcu(&n_ptr->hash); + kfree_rcu(n_ptr, rcu); tipc_num_nodes--; } +void tipc_node_stop(void) +{ + struct tipc_node *node, *t_node; + + spin_lock_bh(&node_list_lock); + list_for_each_entry_safe(node, t_node, &tipc_node_list, list) + tipc_node_delete(node); + spin_unlock_bh(&node_list_lock); +} + /** * tipc_node_link_up - handle addition of link * @@ -162,7 +159,7 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) pr_info("New link <%s> becomes standby\n", l_ptr->name); return; } - tipc_link_dup_send_queue(active[0], l_ptr); + tipc_link_dup_queue_xmit(active[0], l_ptr); if (l_ptr->priority == active[0]->priority) { active[0] = l_ptr; return; @@ -243,15 +240,25 @@ int tipc_node_is_up(struct tipc_node *n_ptr) void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) { n_ptr->links[l_ptr->b_ptr->identity] = l_ptr; - atomic_inc(&tipc_num_links); + spin_lock_bh(&node_list_lock); + tipc_num_links++; + spin_unlock_bh(&node_list_lock); n_ptr->link_cnt++; } void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) { - n_ptr->links[l_ptr->b_ptr->identity] = NULL; - atomic_dec(&tipc_num_links); - n_ptr->link_cnt--; + int i; + + for (i = 0; i < MAX_BEARERS; i++) { + if (l_ptr != n_ptr->links[i]) + continue; + n_ptr->links[i] = NULL; + spin_lock_bh(&node_list_lock); + tipc_num_links--; + spin_unlock_bh(&node_list_lock); + n_ptr->link_cnt--; + } } static void node_established_contact(struct tipc_node *n_ptr) @@ -335,27 +342,28 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (network address)"); - read_lock_bh(&tipc_net_lock); + spin_lock_bh(&node_list_lock); if (!tipc_num_nodes) { - read_unlock_bh(&tipc_net_lock); + spin_unlock_bh(&node_list_lock); return tipc_cfg_reply_none(); } /* For now, get space for all other nodes */ payload_size = TLV_SPACE(sizeof(node_info)) * tipc_num_nodes; if (payload_size > 32768u) { - read_unlock_bh(&tipc_net_lock); + spin_unlock_bh(&node_list_lock); return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (too many nodes)"); } + spin_unlock_bh(&node_list_lock); + buf = tipc_cfg_reply_alloc(payload_size); - if (!buf) { - read_unlock_bh(&tipc_net_lock); + if (!buf) return NULL; - } /* Add TLVs for all nodes in scope */ - list_for_each_entry(n_ptr, &tipc_node_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { if (!tipc_in_scope(domain, n_ptr->addr)) continue; node_info.addr = htonl(n_ptr->addr); @@ -363,8 +371,7 @@ struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space) tipc_cfg_append_tlv(buf, TIPC_TLV_NODE_INFO, &node_info, sizeof(node_info)); } - - read_unlock_bh(&tipc_net_lock); + rcu_read_unlock(); return buf; } @@ -387,21 +394,19 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) if (!tipc_own_addr) return tipc_cfg_reply_none(); - read_lock_bh(&tipc_net_lock); - + spin_lock_bh(&node_list_lock); /* Get space for all unicast links + broadcast link */ - payload_size = TLV_SPACE(sizeof(link_info)) * - (atomic_read(&tipc_num_links) + 1); + payload_size = TLV_SPACE((sizeof(link_info)) * (tipc_num_links + 1)); if (payload_size > 32768u) { - read_unlock_bh(&tipc_net_lock); + spin_unlock_bh(&node_list_lock); return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (too many links)"); } + spin_unlock_bh(&node_list_lock); + buf = tipc_cfg_reply_alloc(payload_size); - if (!buf) { - read_unlock_bh(&tipc_net_lock); + if (!buf) return NULL; - } /* Add TLV for broadcast link */ link_info.dest = htonl(tipc_cluster_mask(tipc_own_addr)); @@ -410,7 +415,8 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) tipc_cfg_append_tlv(buf, TIPC_TLV_LINK_INFO, &link_info, sizeof(link_info)); /* Add TLVs for any other links in scope */ - list_for_each_entry(n_ptr, &tipc_node_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) { u32 i; if (!tipc_in_scope(domain, n_ptr->addr)) @@ -427,7 +433,6 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) } tipc_node_unlock(n_ptr); } - - read_unlock_bh(&tipc_net_lock); + rcu_read_unlock(); return buf; } diff --git a/net/tipc/node.h b/net/tipc/node.h index 63e2e8ead2fe..7cbb8cec1a93 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -2,7 +2,7 @@ * net/tipc/node.h: Include file for TIPC node management routines * * Copyright (c) 2000-2006, Ericsson AB - * Copyright (c) 2005, 2010-2011, Wind River Systems + * Copyright (c) 2005, 2010-2014, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -66,6 +66,7 @@ * @link_cnt: number of links to node * @signature: node instance identifier * @bclink: broadcast-related info + * @rcu: rcu struct for tipc_node * @acked: sequence # of last outbound b'cast message acknowledged by node * @last_in: sequence # of last in-sequence b'cast message received from node * @last_sent: sequence # of last b'cast message sent by node @@ -89,6 +90,7 @@ struct tipc_node { int working_links; int block_setup; u32 signature; + struct rcu_head rcu; struct { u32 acked; u32 last_in; @@ -107,7 +109,7 @@ extern struct list_head tipc_node_list; struct tipc_node *tipc_node_find(u32 addr); struct tipc_node *tipc_node_create(u32 addr); -void tipc_node_delete(struct tipc_node *n_ptr); +void tipc_node_stop(void); void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr); diff --git a/net/tipc/port.c b/net/tipc/port.c index b742b2654525..5c14c7801ee6 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -1,7 +1,7 @@ /* * net/tipc/port.c: TIPC port code * - * Copyright (c) 1992-2007, Ericsson AB + * Copyright (c) 1992-2007, 2014, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -38,6 +38,7 @@ #include "config.h" #include "port.h" #include "name_table.h" +#include "socket.h" /* Connection management: */ #define PROBING_INTERVAL 3600000 /* [ms] => 1 h */ @@ -54,17 +55,6 @@ static struct sk_buff *port_build_self_abort_msg(struct tipc_port *, u32 err); static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *, u32 err); static void port_timeout(unsigned long ref); - -static u32 port_peernode(struct tipc_port *p_ptr) -{ - return msg_destnode(&p_ptr->phdr); -} - -static u32 port_peerport(struct tipc_port *p_ptr) -{ - return msg_destport(&p_ptr->phdr); -} - /** * tipc_port_peer_msg - verify message was sent by connected port's peer * @@ -76,33 +66,32 @@ int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg) u32 peernode; u32 orignode; - if (msg_origport(msg) != port_peerport(p_ptr)) + if (msg_origport(msg) != tipc_port_peerport(p_ptr)) return 0; orignode = msg_orignode(msg); - peernode = port_peernode(p_ptr); + peernode = tipc_port_peernode(p_ptr); return (orignode == peernode) || (!orignode && (peernode == tipc_own_addr)) || (!peernode && (orignode == tipc_own_addr)); } /** - * tipc_multicast - send a multicast message to local and remote destinations + * tipc_port_mcast_xmit - send a multicast message to local and remote + * destinations */ -int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, - struct iovec const *msg_sect, unsigned int len) +int tipc_port_mcast_xmit(struct tipc_port *oport, + struct tipc_name_seq const *seq, + struct iovec const *msg_sect, + unsigned int len) { struct tipc_msg *hdr; struct sk_buff *buf; struct sk_buff *ibuf = NULL; struct tipc_port_list dports = {0, NULL, }; - struct tipc_port *oport = tipc_port_deref(ref); int ext_targets; int res; - if (unlikely(!oport)) - return -EINVAL; - /* Create multicast message */ hdr = &oport->phdr; msg_set_type(hdr, TIPC_MCAST_MSG); @@ -131,7 +120,7 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, return -ENOMEM; } } - res = tipc_bclink_send_msg(buf); + res = tipc_bclink_xmit(buf); if ((res < 0) && (dports.count != 0)) kfree_skb(ibuf); } else { @@ -140,7 +129,7 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, if (res >= 0) { if (ibuf) - tipc_port_recv_mcast(ibuf, &dports); + tipc_port_mcast_rcv(ibuf, &dports); } else { tipc_port_list_free(&dports); } @@ -148,11 +137,11 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, } /** - * tipc_port_recv_mcast - deliver multicast message to all destination ports + * tipc_port_mcast_rcv - deliver multicast message to all destination ports * * If there is no port list, perform a lookup to create one */ -void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) +void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp) { struct tipc_msg *msg; struct tipc_port_list dports = {0, NULL, }; @@ -176,7 +165,7 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) msg_set_destnode(msg, tipc_own_addr); if (dp->count == 1) { msg_set_destport(msg, dp->ports[0]); - tipc_port_recv_msg(buf); + tipc_port_rcv(buf); tipc_port_list_free(dp); return; } @@ -191,7 +180,7 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) if ((index == 0) && (cnt != 0)) item = item->next; msg_set_destport(buf_msg(b), item->ports[index]); - tipc_port_recv_msg(b); + tipc_port_rcv(b); } } exit: @@ -199,40 +188,32 @@ exit: tipc_port_list_free(dp); } -/** - * tipc_createport - create a generic TIPC port + +void tipc_port_wakeup(struct tipc_port *port) +{ + tipc_sock_wakeup(tipc_port_to_sock(port)); +} + +/* tipc_port_init - intiate TIPC port and lock it * - * Returns pointer to (locked) TIPC port, or NULL if unable to create it + * Returns obtained reference if initialization is successful, zero otherwise */ -struct tipc_port *tipc_createport(struct sock *sk, - u32 (*dispatcher)(struct tipc_port *, - struct sk_buff *), - void (*wakeup)(struct tipc_port *), - const u32 importance) +u32 tipc_port_init(struct tipc_port *p_ptr, + const unsigned int importance) { - struct tipc_port *p_ptr; struct tipc_msg *msg; u32 ref; - p_ptr = kzalloc(sizeof(*p_ptr), GFP_ATOMIC); - if (!p_ptr) { - pr_warn("Port creation failed, no memory\n"); - return NULL; - } ref = tipc_ref_acquire(p_ptr, &p_ptr->lock); if (!ref) { - pr_warn("Port creation failed, ref. table exhausted\n"); - kfree(p_ptr); - return NULL; + pr_warn("Port registration failed, ref. table exhausted\n"); + return 0; } - p_ptr->sk = sk; p_ptr->max_pkt = MAX_PKT_DEFAULT; p_ptr->ref = ref; INIT_LIST_HEAD(&p_ptr->wait_list); INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list); - p_ptr->dispatcher = dispatcher; - p_ptr->wakeup = wakeup; k_init_timer(&p_ptr->timer, (Handler)port_timeout, ref); INIT_LIST_HEAD(&p_ptr->publications); INIT_LIST_HEAD(&p_ptr->port_list); @@ -248,10 +229,10 @@ struct tipc_port *tipc_createport(struct sock *sk, msg_set_origport(msg, ref); list_add_tail(&p_ptr->port_list, &ports); spin_unlock_bh(&tipc_port_list_lock); - return p_ptr; + return ref; } -int tipc_deleteport(struct tipc_port *p_ptr) +void tipc_port_destroy(struct tipc_port *p_ptr) { struct sk_buff *buf = NULL; @@ -272,67 +253,7 @@ int tipc_deleteport(struct tipc_port *p_ptr) list_del(&p_ptr->wait_list); spin_unlock_bh(&tipc_port_list_lock); k_term_timer(&p_ptr->timer); - kfree(p_ptr); tipc_net_route_msg(buf); - return 0; -} - -static int port_unreliable(struct tipc_port *p_ptr) -{ - return msg_src_droppable(&p_ptr->phdr); -} - -int tipc_portunreliable(u32 ref, unsigned int *isunreliable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - *isunreliable = port_unreliable(p_ptr); - tipc_port_unlock(p_ptr); - return 0; -} - -int tipc_set_portunreliable(u32 ref, unsigned int isunreliable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - msg_set_src_droppable(&p_ptr->phdr, (isunreliable != 0)); - tipc_port_unlock(p_ptr); - return 0; -} - -static int port_unreturnable(struct tipc_port *p_ptr) -{ - return msg_dest_droppable(&p_ptr->phdr); -} - -int tipc_portunreturnable(u32 ref, unsigned int *isunrejectable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - *isunrejectable = port_unreturnable(p_ptr); - tipc_port_unlock(p_ptr); - return 0; -} - -int tipc_set_portunreturnable(u32 ref, unsigned int isunrejectable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - msg_set_dest_droppable(&p_ptr->phdr, (isunrejectable != 0)); - tipc_port_unlock(p_ptr); - return 0; } /* @@ -350,8 +271,8 @@ static struct sk_buff *port_build_proto_msg(struct tipc_port *p_ptr, if (buf) { msg = buf_msg(buf); tipc_msg_init(msg, CONN_MANAGER, type, INT_H_SIZE, - port_peernode(p_ptr)); - msg_set_destport(msg, port_peerport(p_ptr)); + tipc_port_peernode(p_ptr)); + msg_set_destport(msg, tipc_port_peerport(p_ptr)); msg_set_origport(msg, p_ptr->ref); msg_set_msgcnt(msg, ack); } @@ -422,17 +343,17 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) /* send returned message & dispose of rejected message */ src_node = msg_prevnode(msg); if (in_own_node(src_node)) - tipc_port_recv_msg(rbuf); + tipc_port_rcv(rbuf); else - tipc_link_send(rbuf, src_node, msg_link_selector(rmsg)); + tipc_link_xmit(rbuf, src_node, msg_link_selector(rmsg)); exit: kfree_skb(buf); return data_sz; } -int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr, - struct iovec const *msg_sect, unsigned int len, - int err) +int tipc_port_iovec_reject(struct tipc_port *p_ptr, struct tipc_msg *hdr, + struct iovec const *msg_sect, unsigned int len, + int err) { struct sk_buff *buf; int res; @@ -519,7 +440,7 @@ static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *p_ptr, u32 er return buf; } -void tipc_port_recv_proto_msg(struct sk_buff *buf) +void tipc_port_proto_rcv(struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); struct tipc_port *p_ptr; @@ -547,13 +468,12 @@ void tipc_port_recv_proto_msg(struct sk_buff *buf) /* Process protocol message sent by peer */ switch (msg_type(msg)) { case CONN_ACK: - wakeable = tipc_port_congested(p_ptr) && p_ptr->congested && - p_ptr->wakeup; + wakeable = tipc_port_congested(p_ptr) && p_ptr->congested; p_ptr->acked += msg_msgcnt(msg); if (!tipc_port_congested(p_ptr)) { p_ptr->congested = 0; if (wakeable) - p_ptr->wakeup(p_ptr); + tipc_port_wakeup(p_ptr); } break; case CONN_PROBE: @@ -584,8 +504,8 @@ static int port_print(struct tipc_port *p_ptr, char *buf, int len, int full_id) ret = tipc_snprintf(buf, len, "%-10u:", p_ptr->ref); if (p_ptr->connected) { - u32 dport = port_peerport(p_ptr); - u32 destnode = port_peernode(p_ptr); + u32 dport = tipc_port_peerport(p_ptr); + u32 destnode = tipc_port_peernode(p_ptr); ret += tipc_snprintf(buf + ret, len - ret, " connected to <%u.%u.%u:%u>", @@ -673,34 +593,6 @@ void tipc_acknowledge(u32 ref, u32 ack) tipc_net_route_msg(buf); } -int tipc_portimportance(u32 ref, unsigned int *importance) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - *importance = (unsigned int)msg_importance(&p_ptr->phdr); - tipc_port_unlock(p_ptr); - return 0; -} - -int tipc_set_portimportance(u32 ref, unsigned int imp) -{ - struct tipc_port *p_ptr; - - if (imp > TIPC_CRITICAL_IMPORTANCE) - return -EINVAL; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - msg_set_importance(&p_ptr->phdr, (u32)imp); - tipc_port_unlock(p_ptr); - return 0; -} - - int tipc_publish(struct tipc_port *p_ptr, unsigned int scope, struct tipc_name_seq const *seq) { @@ -760,7 +652,7 @@ int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope, return res; } -int tipc_connect(u32 ref, struct tipc_portid const *peer) +int tipc_port_connect(u32 ref, struct tipc_portid const *peer) { struct tipc_port *p_ptr; int res; @@ -768,17 +660,17 @@ int tipc_connect(u32 ref, struct tipc_portid const *peer) p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - res = __tipc_connect(ref, p_ptr, peer); + res = __tipc_port_connect(ref, p_ptr, peer); tipc_port_unlock(p_ptr); return res; } /* - * __tipc_connect - connect to a remote peer + * __tipc_port_connect - connect to a remote peer * * Port must be locked. */ -int __tipc_connect(u32 ref, struct tipc_port *p_ptr, +int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr, struct tipc_portid const *peer) { struct tipc_msg *msg; @@ -815,7 +707,7 @@ exit: * * Port must be locked. */ -int __tipc_disconnect(struct tipc_port *tp_ptr) +int __tipc_port_disconnect(struct tipc_port *tp_ptr) { if (tp_ptr->connected) { tp_ptr->connected = 0; @@ -828,10 +720,10 @@ int __tipc_disconnect(struct tipc_port *tp_ptr) } /* - * tipc_disconnect(): Disconnect port form peer. + * tipc_port_disconnect(): Disconnect port form peer. * This is a node local operation. */ -int tipc_disconnect(u32 ref) +int tipc_port_disconnect(u32 ref) { struct tipc_port *p_ptr; int res; @@ -839,15 +731,15 @@ int tipc_disconnect(u32 ref) p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - res = __tipc_disconnect(p_ptr); + res = __tipc_port_disconnect(p_ptr); tipc_port_unlock(p_ptr); return res; } /* - * tipc_shutdown(): Send a SHUTDOWN msg to peer and disconnect + * tipc_port_shutdown(): Send a SHUTDOWN msg to peer and disconnect */ -int tipc_shutdown(u32 ref) +int tipc_port_shutdown(u32 ref) { struct tipc_port *p_ptr; struct sk_buff *buf = NULL; @@ -859,13 +751,13 @@ int tipc_shutdown(u32 ref) buf = port_build_peer_abort_msg(p_ptr, TIPC_CONN_SHUTDOWN); tipc_port_unlock(p_ptr); tipc_net_route_msg(buf); - return tipc_disconnect(ref); + return tipc_port_disconnect(ref); } /** - * tipc_port_recv_msg - receive message from lower layer and deliver to port user + * tipc_port_rcv - receive message from lower layer and deliver to port user */ -int tipc_port_recv_msg(struct sk_buff *buf) +int tipc_port_rcv(struct sk_buff *buf) { struct tipc_port *p_ptr; struct tipc_msg *msg = buf_msg(buf); @@ -882,7 +774,7 @@ int tipc_port_recv_msg(struct sk_buff *buf) /* validate destination & pass to port, otherwise reject message */ p_ptr = tipc_port_lock(destport); if (likely(p_ptr)) { - err = p_ptr->dispatcher(p_ptr, buf); + err = tipc_sk_rcv(&tipc_port_to_sock(p_ptr)->sk, buf); tipc_port_unlock(p_ptr); if (likely(!err)) return dsz; @@ -894,43 +786,43 @@ int tipc_port_recv_msg(struct sk_buff *buf) } /* - * tipc_port_recv_sections(): Concatenate and deliver sectioned - * message for this node. + * tipc_port_iovec_rcv: Concatenate and deliver sectioned + * message for this node. */ -static int tipc_port_recv_sections(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len) +static int tipc_port_iovec_rcv(struct tipc_port *sender, + struct iovec const *msg_sect, + unsigned int len) { struct sk_buff *buf; int res; res = tipc_msg_build(&sender->phdr, msg_sect, len, MAX_MSG_SIZE, &buf); if (likely(buf)) - tipc_port_recv_msg(buf); + tipc_port_rcv(buf); return res; } /** * tipc_send - send message sections on connection */ -int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len) +int tipc_send(struct tipc_port *p_ptr, + struct iovec const *msg_sect, + unsigned int len) { - struct tipc_port *p_ptr; u32 destnode; int res; - p_ptr = tipc_port_deref(ref); - if (!p_ptr || !p_ptr->connected) + if (!p_ptr->connected) return -EINVAL; p_ptr->congested = 1; if (!tipc_port_congested(p_ptr)) { - destnode = port_peernode(p_ptr); + destnode = tipc_port_peernode(p_ptr); if (likely(!in_own_node(destnode))) - res = tipc_link_send_sections_fast(p_ptr, msg_sect, - len, destnode); + res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len, + destnode); else - res = tipc_port_recv_sections(p_ptr, msg_sect, len); + res = tipc_port_iovec_rcv(p_ptr, msg_sect, len); if (likely(res != -ELINKCONG)) { p_ptr->congested = 0; @@ -939,7 +831,7 @@ int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len) return res; } } - if (port_unreliable(p_ptr)) { + if (tipc_port_unreliable(p_ptr)) { p_ptr->congested = 0; return len; } @@ -949,17 +841,18 @@ int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len) /** * tipc_send2name - send message sections to port name */ -int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, - struct iovec const *msg_sect, unsigned int len) +int tipc_send2name(struct tipc_port *p_ptr, + struct tipc_name const *name, + unsigned int domain, + struct iovec const *msg_sect, + unsigned int len) { - struct tipc_port *p_ptr; struct tipc_msg *msg; u32 destnode = domain; u32 destport; int res; - p_ptr = tipc_port_deref(ref); - if (!p_ptr || p_ptr->connected) + if (p_ptr->connected) return -EINVAL; msg = &p_ptr->phdr; @@ -974,39 +867,39 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, if (likely(destport || destnode)) { if (likely(in_own_node(destnode))) - res = tipc_port_recv_sections(p_ptr, msg_sect, len); + res = tipc_port_iovec_rcv(p_ptr, msg_sect, len); else if (tipc_own_addr) - res = tipc_link_send_sections_fast(p_ptr, msg_sect, - len, destnode); + res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len, + destnode); else - res = tipc_port_reject_sections(p_ptr, msg, msg_sect, - len, TIPC_ERR_NO_NODE); + res = tipc_port_iovec_reject(p_ptr, msg, msg_sect, + len, TIPC_ERR_NO_NODE); if (likely(res != -ELINKCONG)) { if (res > 0) p_ptr->sent++; return res; } - if (port_unreliable(p_ptr)) { + if (tipc_port_unreliable(p_ptr)) return len; - } + return -ELINKCONG; } - return tipc_port_reject_sections(p_ptr, msg, msg_sect, len, - TIPC_ERR_NO_NAME); + return tipc_port_iovec_reject(p_ptr, msg, msg_sect, len, + TIPC_ERR_NO_NAME); } /** * tipc_send2port - send message sections to port identity */ -int tipc_send2port(u32 ref, struct tipc_portid const *dest, - struct iovec const *msg_sect, unsigned int len) +int tipc_send2port(struct tipc_port *p_ptr, + struct tipc_portid const *dest, + struct iovec const *msg_sect, + unsigned int len) { - struct tipc_port *p_ptr; struct tipc_msg *msg; int res; - p_ptr = tipc_port_deref(ref); - if (!p_ptr || p_ptr->connected) + if (p_ptr->connected) return -EINVAL; msg = &p_ptr->phdr; @@ -1017,20 +910,20 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest, msg_set_hdr_sz(msg, BASIC_H_SIZE); if (in_own_node(dest->node)) - res = tipc_port_recv_sections(p_ptr, msg_sect, len); + res = tipc_port_iovec_rcv(p_ptr, msg_sect, len); else if (tipc_own_addr) - res = tipc_link_send_sections_fast(p_ptr, msg_sect, len, - dest->node); + res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len, + dest->node); else - res = tipc_port_reject_sections(p_ptr, msg, msg_sect, len, + res = tipc_port_iovec_reject(p_ptr, msg, msg_sect, len, TIPC_ERR_NO_NODE); if (likely(res != -ELINKCONG)) { if (res > 0) p_ptr->sent++; return res; } - if (port_unreliable(p_ptr)) { + if (tipc_port_unreliable(p_ptr)) return len; - } + return -ELINKCONG; } diff --git a/net/tipc/port.h b/net/tipc/port.h index 34f12bd4074e..a00397393bd1 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -1,7 +1,7 @@ /* * net/tipc/port.h: Include file for TIPC port code * - * Copyright (c) 1994-2007, Ericsson AB + * Copyright (c) 1994-2007, 2014, Ericsson AB * Copyright (c) 2004-2007, 2010-2013, Wind River Systems * All rights reserved. * @@ -48,7 +48,6 @@ /** * struct tipc_port - TIPC port structure - * @sk: pointer to socket handle * @lock: pointer to spinlock for controlling access to port * @connected: non-zero if port is currently connected to a peer port * @conn_type: TIPC type used when connection was established @@ -60,8 +59,6 @@ * @ref: unique reference to port in TIPC object registry * @phdr: preformatted message header used when sending messages * @port_list: adjacent ports in TIPC's global list of ports - * @dispatcher: ptr to routine which handles received messages - * @wakeup: ptr to routine to call when port is no longer congested * @wait_list: adjacent ports in list of ports waiting on link congestion * @waiting_pkts: * @sent: # of non-empty messages sent by port @@ -74,7 +71,6 @@ * @subscription: "node down" subscription used to terminate failed connections */ struct tipc_port { - struct sock *sk; spinlock_t *lock; int connected; u32 conn_type; @@ -86,8 +82,6 @@ struct tipc_port { u32 ref; struct tipc_msg phdr; struct list_head port_list; - u32 (*dispatcher)(struct tipc_port *, struct sk_buff *); - void (*wakeup)(struct tipc_port *); struct list_head wait_list; u32 waiting_pkts; u32 sent; @@ -106,68 +100,71 @@ struct tipc_port_list; /* * TIPC port manipulation routines */ -struct tipc_port *tipc_createport(struct sock *sk, - u32 (*dispatcher)(struct tipc_port *, - struct sk_buff *), - void (*wakeup)(struct tipc_port *), - const u32 importance); +u32 tipc_port_init(struct tipc_port *p_ptr, + const unsigned int importance); int tipc_reject_msg(struct sk_buff *buf, u32 err); void tipc_acknowledge(u32 port_ref, u32 ack); -int tipc_deleteport(struct tipc_port *p_ptr); - -int tipc_portimportance(u32 portref, unsigned int *importance); -int tipc_set_portimportance(u32 portref, unsigned int importance); - -int tipc_portunreliable(u32 portref, unsigned int *isunreliable); -int tipc_set_portunreliable(u32 portref, unsigned int isunreliable); - -int tipc_portunreturnable(u32 portref, unsigned int *isunreturnable); -int tipc_set_portunreturnable(u32 portref, unsigned int isunreturnable); +void tipc_port_destroy(struct tipc_port *p_ptr); int tipc_publish(struct tipc_port *p_ptr, unsigned int scope, struct tipc_name_seq const *name_seq); + int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope, struct tipc_name_seq const *name_seq); -int tipc_connect(u32 portref, struct tipc_portid const *port); +int tipc_port_connect(u32 portref, struct tipc_portid const *port); -int tipc_disconnect(u32 portref); +int tipc_port_disconnect(u32 portref); -int tipc_shutdown(u32 ref); +int tipc_port_shutdown(u32 ref); +void tipc_port_wakeup(struct tipc_port *port); /* * The following routines require that the port be locked on entry */ -int __tipc_disconnect(struct tipc_port *tp_ptr); -int __tipc_connect(u32 ref, struct tipc_port *p_ptr, +int __tipc_port_disconnect(struct tipc_port *tp_ptr); +int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr, struct tipc_portid const *peer); int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg); /* * TIPC messaging routines */ -int tipc_port_recv_msg(struct sk_buff *buf); -int tipc_send(u32 portref, struct iovec const *msg_sect, unsigned int len); - -int tipc_send2name(u32 portref, struct tipc_name const *name, u32 domain, - struct iovec const *msg_sect, unsigned int len); +int tipc_port_rcv(struct sk_buff *buf); + +int tipc_send(struct tipc_port *port, + struct iovec const *msg_sect, + unsigned int len); + +int tipc_send2name(struct tipc_port *port, + struct tipc_name const *name, + u32 domain, + struct iovec const *msg_sect, + unsigned int len); + +int tipc_send2port(struct tipc_port *port, + struct tipc_portid const *dest, + struct iovec const *msg_sect, + unsigned int len); + +int tipc_port_mcast_xmit(struct tipc_port *port, + struct tipc_name_seq const *seq, + struct iovec const *msg, + unsigned int len); + +int tipc_port_iovec_reject(struct tipc_port *p_ptr, + struct tipc_msg *hdr, + struct iovec const *msg_sect, + unsigned int len, + int err); -int tipc_send2port(u32 portref, struct tipc_portid const *dest, - struct iovec const *msg_sect, unsigned int len); - -int tipc_multicast(u32 portref, struct tipc_name_seq const *seq, - struct iovec const *msg, unsigned int len); - -int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr, - struct iovec const *msg_sect, unsigned int len, - int err); struct sk_buff *tipc_port_get_ports(void); -void tipc_port_recv_proto_msg(struct sk_buff *buf); -void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp); +void tipc_port_proto_rcv(struct sk_buff *buf); +void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp); void tipc_port_reinit(void); /** @@ -188,14 +185,53 @@ static inline void tipc_port_unlock(struct tipc_port *p_ptr) spin_unlock_bh(p_ptr->lock); } -static inline struct tipc_port *tipc_port_deref(u32 ref) +static inline int tipc_port_congested(struct tipc_port *p_ptr) { - return (struct tipc_port *)tipc_ref_deref(ref); + return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2); } -static inline int tipc_port_congested(struct tipc_port *p_ptr) + +static inline u32 tipc_port_peernode(struct tipc_port *p_ptr) { - return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2); + return msg_destnode(&p_ptr->phdr); +} + +static inline u32 tipc_port_peerport(struct tipc_port *p_ptr) +{ + return msg_destport(&p_ptr->phdr); +} + +static inline bool tipc_port_unreliable(struct tipc_port *port) +{ + return msg_src_droppable(&port->phdr) != 0; +} + +static inline void tipc_port_set_unreliable(struct tipc_port *port, + bool unreliable) +{ + msg_set_src_droppable(&port->phdr, unreliable ? 1 : 0); +} + +static inline bool tipc_port_unreturnable(struct tipc_port *port) +{ + return msg_dest_droppable(&port->phdr) != 0; +} + +static inline void tipc_port_set_unreturnable(struct tipc_port *port, + bool unreturnable) +{ + msg_set_dest_droppable(&port->phdr, unreturnable ? 1 : 0); +} + + +static inline int tipc_port_importance(struct tipc_port *port) +{ + return msg_importance(&port->phdr); +} + +static inline void tipc_port_set_importance(struct tipc_port *port, int imp) +{ + msg_set_importance(&port->phdr, (u32)imp); } #endif diff --git a/net/tipc/ref.c b/net/tipc/ref.c index de3d593e2fee..3d4ecd754eee 100644 --- a/net/tipc/ref.c +++ b/net/tipc/ref.c @@ -89,7 +89,7 @@ struct ref_table { static struct ref_table tipc_ref_table; -static DEFINE_RWLOCK(ref_table_lock); +static DEFINE_SPINLOCK(ref_table_lock); /** * tipc_ref_table_init - create reference table for objects @@ -159,7 +159,7 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) } /* take a free entry, if available; otherwise initialize a new entry */ - write_lock_bh(&ref_table_lock); + spin_lock_bh(&ref_table_lock); if (tipc_ref_table.first_free) { index = tipc_ref_table.first_free; entry = &(tipc_ref_table.entries[index]); @@ -175,7 +175,7 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) } else { ref = 0; } - write_unlock_bh(&ref_table_lock); + spin_unlock_bh(&ref_table_lock); /* * Grab the lock so no one else can modify this entry @@ -216,7 +216,7 @@ void tipc_ref_discard(u32 ref) index = ref & index_mask; entry = &(tipc_ref_table.entries[index]); - write_lock_bh(&ref_table_lock); + spin_lock_bh(&ref_table_lock); if (!entry->object) { pr_err("Attempt to discard ref. to non-existent obj\n"); @@ -242,7 +242,7 @@ void tipc_ref_discard(u32 ref) tipc_ref_table.last_free = index; exit: - write_unlock_bh(&ref_table_lock); + spin_unlock_bh(&ref_table_lock); } /** @@ -264,20 +264,3 @@ void *tipc_ref_lock(u32 ref) } return NULL; } - - -/** - * tipc_ref_deref - return pointer referenced object (without locking it) - */ -void *tipc_ref_deref(u32 ref) -{ - if (likely(tipc_ref_table.entries)) { - struct reference *entry; - - entry = &tipc_ref_table.entries[ref & - tipc_ref_table.index_mask]; - if (likely(entry->ref == ref)) - return entry->object; - } - return NULL; -} diff --git a/net/tipc/ref.h b/net/tipc/ref.h index 5bc8e7ab84de..d01aa1df63b8 100644 --- a/net/tipc/ref.h +++ b/net/tipc/ref.h @@ -44,6 +44,5 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock); void tipc_ref_discard(u32 ref); void *tipc_ref_lock(u32 ref); -void *tipc_ref_deref(u32 ref); #endif diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 0ed0eaa62f29..29b7f26a12cf 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012 Ericsson AB + * Copyright (c) 2001-2007, 2012-2014, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -38,30 +38,17 @@ #include "port.h" #include <linux/export.h> -#include <net/sock.h> #define SS_LISTENING -1 /* socket is listening */ #define SS_READY -2 /* socket is connectionless */ #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ -struct tipc_sock { - struct sock sk; - struct tipc_port *p; - struct tipc_portid peer_name; - unsigned int conn_timeout; -}; - -#define tipc_sk(sk) ((struct tipc_sock *)(sk)) -#define tipc_sk_port(sk) (tipc_sk(sk)->p) - static int backlog_rcv(struct sock *sk, struct sk_buff *skb); -static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf); -static void wakeupdispatch(struct tipc_port *tport); static void tipc_data_ready(struct sock *sk, int len); static void tipc_write_space(struct sock *sk); -static int release(struct socket *sock); -static int accept(struct socket *sock, struct socket *new_sock, int flags); +static int tipc_release(struct socket *sock); +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -115,6 +102,8 @@ static struct proto tipc_proto_kern; * - port reference */ +#include "socket.h" + /** * advance_rx_queue - discard first buffer in socket receive queue * @@ -150,13 +139,15 @@ static void reject_rx_queue(struct sock *sk) * * Returns 0 on success, errno otherwise */ -static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, - int kern) +static int tipc_sk_create(struct net *net, struct socket *sock, + int protocol, int kern) { const struct proto_ops *ops; socket_state state; struct sock *sk; - struct tipc_port *tp_ptr; + struct tipc_sock *tsk; + struct tipc_port *port; + u32 ref; /* Validate arguments */ if (unlikely(protocol != 0)) @@ -189,10 +180,12 @@ static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, if (sk == NULL) return -ENOMEM; - /* Allocate TIPC port for socket to use */ - tp_ptr = tipc_createport(sk, &dispatch, &wakeupdispatch, - TIPC_LOW_IMPORTANCE); - if (unlikely(!tp_ptr)) { + tsk = tipc_sk(sk); + port = &tsk->port; + + ref = tipc_port_init(port, TIPC_LOW_IMPORTANCE); + if (!ref) { + pr_warn("Socket registration failed, ref. table exhausted\n"); sk_free(sk); return -ENOMEM; } @@ -206,17 +199,14 @@ static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, sk->sk_rcvbuf = sysctl_tipc_rmem[1]; sk->sk_data_ready = tipc_data_ready; sk->sk_write_space = tipc_write_space; - tipc_sk(sk)->p = tp_ptr; tipc_sk(sk)->conn_timeout = CONN_TIMEOUT_DEFAULT; - - spin_unlock_bh(tp_ptr->lock); + tipc_port_unlock(port); if (sock->state == SS_READY) { - tipc_set_portunreturnable(tp_ptr->ref, 1); + tipc_port_set_unreturnable(port, true); if (sock->type == SOCK_DGRAM) - tipc_set_portunreliable(tp_ptr->ref, 1); + tipc_port_set_unreliable(port, true); } - return 0; } @@ -254,7 +244,7 @@ int tipc_sock_create_local(int type, struct socket **res) */ void tipc_sock_release_local(struct socket *sock) { - release(sock); + tipc_release(sock); sock->ops = NULL; sock_release(sock); } @@ -280,7 +270,7 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, if (ret < 0) return ret; - ret = accept(sock, *newsock, flags); + ret = tipc_accept(sock, *newsock, flags); if (ret < 0) { sock_release(*newsock); return ret; @@ -290,7 +280,7 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, } /** - * release - destroy a TIPC socket + * tipc_release - destroy a TIPC socket * @sock: socket to destroy * * This routine cleans up any messages that are still queued on the socket. @@ -305,10 +295,11 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, * * Returns 0 on success, errno otherwise */ -static int release(struct socket *sock) +static int tipc_release(struct socket *sock) { struct sock *sk = sock->sk; - struct tipc_port *tport; + struct tipc_sock *tsk; + struct tipc_port *port; struct sk_buff *buf; int res; @@ -319,7 +310,8 @@ static int release(struct socket *sock) if (sk == NULL) return 0; - tport = tipc_sk_port(sk); + tsk = tipc_sk(sk); + port = &tsk->port; lock_sock(sk); /* @@ -336,17 +328,16 @@ static int release(struct socket *sock) if ((sock->state == SS_CONNECTING) || (sock->state == SS_CONNECTED)) { sock->state = SS_DISCONNECTING; - tipc_disconnect(tport->ref); + tipc_port_disconnect(port->ref); } tipc_reject_msg(buf, TIPC_ERR_NO_PORT); } } - /* - * Delete TIPC port; this ensures no more messages are queued - * (also disconnects an active connection & sends a 'FIN-' to peer) + /* Destroy TIPC port; also disconnects an active connection and + * sends a 'FIN-' to peer. */ - res = tipc_deleteport(tport); + tipc_port_destroy(port); /* Discard any remaining (connection-based) messages in receive queue */ __skb_queue_purge(&sk->sk_receive_queue); @@ -362,7 +353,7 @@ static int release(struct socket *sock) } /** - * bind - associate or disassocate TIPC name(s) with a socket + * tipc_bind - associate or disassocate TIPC name(s) with a socket * @sock: socket structure * @uaddr: socket address describing name(s) and desired operation * @uaddr_len: size of socket address data structure @@ -376,16 +367,17 @@ static int release(struct socket *sock) * NOTE: This routine doesn't need to take the socket lock since it doesn't * access any non-constant socket information. */ -static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) +static int tipc_bind(struct socket *sock, struct sockaddr *uaddr, + int uaddr_len) { struct sock *sk = sock->sk; struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; - struct tipc_port *tport = tipc_sk_port(sock->sk); + struct tipc_sock *tsk = tipc_sk(sk); int res = -EINVAL; lock_sock(sk); if (unlikely(!uaddr_len)) { - res = tipc_withdraw(tport, 0, NULL); + res = tipc_withdraw(&tsk->port, 0, NULL); goto exit; } @@ -413,15 +405,15 @@ static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) } res = (addr->scope > 0) ? - tipc_publish(tport, addr->scope, &addr->addr.nameseq) : - tipc_withdraw(tport, -addr->scope, &addr->addr.nameseq); + tipc_publish(&tsk->port, addr->scope, &addr->addr.nameseq) : + tipc_withdraw(&tsk->port, -addr->scope, &addr->addr.nameseq); exit: release_sock(sk); return res; } /** - * get_name - get port ID of socket or peer socket + * tipc_getname - get port ID of socket or peer socket * @sock: socket structure * @uaddr: area for returned socket address * @uaddr_len: area for returned length of socket address @@ -433,21 +425,21 @@ exit: * accesses socket information that is unchanging (or which changes in * a completely predictable manner). */ -static int get_name(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) +static int tipc_getname(struct socket *sock, struct sockaddr *uaddr, + int *uaddr_len, int peer) { struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; - struct tipc_sock *tsock = tipc_sk(sock->sk); + struct tipc_sock *tsk = tipc_sk(sock->sk); memset(addr, 0, sizeof(*addr)); if (peer) { if ((sock->state != SS_CONNECTED) && ((peer != 2) || (sock->state != SS_DISCONNECTING))) return -ENOTCONN; - addr->addr.id.ref = tsock->peer_name.ref; - addr->addr.id.node = tsock->peer_name.node; + addr->addr.id.ref = tipc_port_peerport(&tsk->port); + addr->addr.id.node = tipc_port_peernode(&tsk->port); } else { - addr->addr.id.ref = tsock->p->ref; + addr->addr.id.ref = tsk->port.ref; addr->addr.id.node = tipc_own_addr; } @@ -461,7 +453,7 @@ static int get_name(struct socket *sock, struct sockaddr *uaddr, } /** - * poll - read and possibly block on pollmask + * tipc_poll - read and possibly block on pollmask * @file: file structure associated with the socket * @sock: socket for which to calculate the poll bits * @wait: ??? @@ -500,22 +492,23 @@ static int get_name(struct socket *sock, struct sockaddr *uaddr, * imply that the operation will succeed, merely that it should be performed * and will not block. */ -static unsigned int poll(struct file *file, struct socket *sock, - poll_table *wait) +static unsigned int tipc_poll(struct file *file, struct socket *sock, + poll_table *wait) { struct sock *sk = sock->sk; + struct tipc_sock *tsk = tipc_sk(sk); u32 mask = 0; sock_poll_wait(file, sk_sleep(sk), wait); switch ((int)sock->state) { case SS_UNCONNECTED: - if (!tipc_sk_port(sk)->congested) + if (!tsk->port.congested) mask |= POLLOUT; break; case SS_READY: case SS_CONNECTED: - if (!tipc_sk_port(sk)->congested) + if (!tsk->port.congested) mask |= POLLOUT; /* fall thru' */ case SS_CONNECTING: @@ -565,7 +558,7 @@ static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); DEFINE_WAIT(wait); int done; @@ -581,14 +574,15 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) return sock_intr_errno(*timeo_p); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - done = sk_wait_event(sk, timeo_p, !tport->congested); + done = sk_wait_event(sk, timeo_p, !tsk->port.congested); finish_wait(sk_sleep(sk), &wait); } while (!done); return 0; } + /** - * send_msg - send message in connectionless manner + * tipc_sendmsg - send message in connectionless manner * @iocb: if NULL, indicates that socket lock is already held * @sock: socket structure * @m: message to send @@ -601,11 +595,12 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) * * Returns the number of bytes sent on success, or errno otherwise */ -static int send_msg(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len) +static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); int needs_conn; long timeo; @@ -632,13 +627,13 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, res = -EISCONN; goto exit; } - if (tport->published) { + if (tsk->port.published) { res = -EOPNOTSUPP; goto exit; } if (dest->addrtype == TIPC_ADDR_NAME) { - tport->conn_type = dest->addr.name.name.type; - tport->conn_instance = dest->addr.name.name.instance; + tsk->port.conn_type = dest->addr.name.name.type; + tsk->port.conn_instance = dest->addr.name.name.instance; } /* Abort any pending connection attempts (very unlikely) */ @@ -651,13 +646,13 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, res = dest_name_check(dest, m); if (res) break; - res = tipc_send2name(tport->ref, + res = tipc_send2name(port, &dest->addr.name.name, dest->addr.name.domain, m->msg_iov, total_len); } else if (dest->addrtype == TIPC_ADDR_ID) { - res = tipc_send2port(tport->ref, + res = tipc_send2port(port, &dest->addr.id, m->msg_iov, total_len); @@ -669,10 +664,10 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, res = dest_name_check(dest, m); if (res) break; - res = tipc_multicast(tport->ref, - &dest->addr.nameseq, - m->msg_iov, - total_len); + res = tipc_port_mcast_xmit(port, + &dest->addr.nameseq, + m->msg_iov, + total_len); } if (likely(res != -ELINKCONG)) { if (needs_conn && (res >= 0)) @@ -693,7 +688,8 @@ exit: static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; DEFINE_WAIT(wait); int done; @@ -712,14 +708,14 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); done = sk_wait_event(sk, timeo_p, - (!tport->congested || !tport->connected)); + (!port->congested || !port->connected)); finish_wait(sk_sleep(sk), &wait); } while (!done); return 0; } /** - * send_packet - send a connection-oriented message + * tipc_send_packet - send a connection-oriented message * @iocb: if NULL, indicates that socket lock is already held * @sock: socket structure * @m: message to send @@ -729,18 +725,18 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) * * Returns the number of bytes sent on success, or errno otherwise */ -static int send_packet(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len) +static int tipc_send_packet(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); int res = -EINVAL; long timeo; /* Handle implied connection establishment */ if (unlikely(dest)) - return send_msg(iocb, sock, m, total_len); + return tipc_sendmsg(iocb, sock, m, total_len); if (total_len > TIPC_MAX_USER_MSG_SIZE) return -EMSGSIZE; @@ -758,7 +754,7 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); do { - res = tipc_send(tport->ref, m->msg_iov, total_len); + res = tipc_send(&tsk->port, m->msg_iov, total_len); if (likely(res != -ELINKCONG)) break; res = tipc_wait_for_sndpkt(sock, &timeo); @@ -772,7 +768,7 @@ exit: } /** - * send_stream - send stream-oriented data + * tipc_send_stream - send stream-oriented data * @iocb: (unused) * @sock: socket structure * @m: data to send @@ -783,11 +779,11 @@ exit: * Returns the number of bytes sent on success (or partial success), * or errno if no data sent */ -static int send_stream(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len) +static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); struct msghdr my_msg; struct iovec my_iov; struct iovec *curr_iov; @@ -804,7 +800,7 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, /* Handle special cases where there is no connection */ if (unlikely(sock->state != SS_CONNECTED)) { if (sock->state == SS_UNCONNECTED) - res = send_packet(NULL, sock, m, total_len); + res = tipc_send_packet(NULL, sock, m, total_len); else res = sock->state == SS_DISCONNECTING ? -EPIPE : -ENOTCONN; goto exit; @@ -835,21 +831,22 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, my_msg.msg_name = NULL; bytes_sent = 0; - hdr_size = msg_hdr_sz(&tport->phdr); + hdr_size = msg_hdr_sz(&tsk->port.phdr); while (curr_iovlen--) { curr_start = curr_iov->iov_base; curr_left = curr_iov->iov_len; while (curr_left) { - bytes_to_send = tport->max_pkt - hdr_size; + bytes_to_send = tsk->port.max_pkt - hdr_size; if (bytes_to_send > TIPC_MAX_USER_MSG_SIZE) bytes_to_send = TIPC_MAX_USER_MSG_SIZE; if (curr_left < bytes_to_send) bytes_to_send = curr_left; my_iov.iov_base = curr_start; my_iov.iov_len = bytes_to_send; - res = send_packet(NULL, sock, &my_msg, bytes_to_send); + res = tipc_send_packet(NULL, sock, &my_msg, + bytes_to_send); if (res < 0) { if (bytes_sent) res = bytes_sent; @@ -870,27 +867,25 @@ exit: /** * auto_connect - complete connection setup to a remote port - * @sock: socket structure + * @tsk: tipc socket structure * @msg: peer's response message * * Returns 0 on success, errno otherwise */ -static int auto_connect(struct socket *sock, struct tipc_msg *msg) +static int auto_connect(struct tipc_sock *tsk, struct tipc_msg *msg) { - struct tipc_sock *tsock = tipc_sk(sock->sk); - struct tipc_port *p_ptr; + struct tipc_port *port = &tsk->port; + struct socket *sock = tsk->sk.sk_socket; + struct tipc_portid peer; - tsock->peer_name.ref = msg_origport(msg); - tsock->peer_name.node = msg_orignode(msg); - p_ptr = tipc_port_deref(tsock->p->ref); - if (!p_ptr) - return -EINVAL; + peer.ref = msg_origport(msg); + peer.node = msg_orignode(msg); - __tipc_connect(tsock->p->ref, p_ptr, &tsock->peer_name); + __tipc_port_connect(port->ref, port, &peer); if (msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE) return -EINVAL; - msg_set_importance(&p_ptr->phdr, (u32)msg_importance(msg)); + msg_set_importance(&port->phdr, (u32)msg_importance(msg)); sock->state = SS_CONNECTED; return 0; } @@ -1021,7 +1016,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo) } /** - * recv_msg - receive packet-oriented message + * tipc_recvmsg - receive packet-oriented message * @iocb: (unused) * @m: descriptor for message info * @buf_len: total size of user buffer area @@ -1032,11 +1027,12 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo) * * Returns size of returned message data, errno otherwise */ -static int recv_msg(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t buf_len, int flags) +static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t buf_len, int flags) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; struct sk_buff *buf; struct tipc_msg *msg; long timeo; @@ -1079,7 +1075,7 @@ restart: set_orig_addr(m, msg); /* Capture ancillary data (optional) */ - res = anc_data_recv(m, msg, tport); + res = anc_data_recv(m, msg, port); if (res) goto exit; @@ -1105,8 +1101,8 @@ restart: /* Consume received message (optional) */ if (likely(!(flags & MSG_PEEK))) { if ((sock->state != SS_READY) && - (++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) - tipc_acknowledge(tport->ref, tport->conn_unacked); + (++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) + tipc_acknowledge(port->ref, port->conn_unacked); advance_rx_queue(sk); } exit: @@ -1115,7 +1111,7 @@ exit: } /** - * recv_stream - receive stream-oriented data + * tipc_recv_stream - receive stream-oriented data * @iocb: (unused) * @m: descriptor for message info * @buf_len: total size of user buffer area @@ -1126,11 +1122,12 @@ exit: * * Returns size of returned message data, errno otherwise */ -static int recv_stream(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t buf_len, int flags) +static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t buf_len, int flags) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; struct sk_buff *buf; struct tipc_msg *msg; long timeo; @@ -1175,7 +1172,7 @@ restart: /* Optionally capture sender's address & ancillary data of first msg */ if (sz_copied == 0) { set_orig_addr(m, msg); - res = anc_data_recv(m, msg, tport); + res = anc_data_recv(m, msg, port); if (res) goto exit; } @@ -1213,8 +1210,8 @@ restart: /* Consume received message (optional) */ if (likely(!(flags & MSG_PEEK))) { - if (unlikely(++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) - tipc_acknowledge(tport->ref, tport->conn_unacked); + if (unlikely(++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) + tipc_acknowledge(port->ref, port->conn_unacked); advance_rx_queue(sk); } @@ -1266,17 +1263,19 @@ static void tipc_data_ready(struct sock *sk, int len) /** * filter_connect - Handle all incoming messages for a connection-based socket - * @tsock: TIPC socket + * @tsk: TIPC socket * @msg: message * * Returns TIPC error status code and socket error status code * once it encounters some errors */ -static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) +static u32 filter_connect(struct tipc_sock *tsk, struct sk_buff **buf) { - struct socket *sock = tsock->sk.sk_socket; + struct sock *sk = &tsk->sk; + struct tipc_port *port = &tsk->port; + struct socket *sock = sk->sk_socket; struct tipc_msg *msg = buf_msg(*buf); - struct sock *sk = &tsock->sk; + u32 retval = TIPC_ERR_NO_PORT; int res; @@ -1286,10 +1285,10 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) switch ((int)sock->state) { case SS_CONNECTED: /* Accept only connection-based messages sent by peer */ - if (msg_connected(msg) && tipc_port_peer_msg(tsock->p, msg)) { + if (msg_connected(msg) && tipc_port_peer_msg(port, msg)) { if (unlikely(msg_errcode(msg))) { sock->state = SS_DISCONNECTING; - __tipc_disconnect(tsock->p); + __tipc_port_disconnect(port); } retval = TIPC_OK; } @@ -1306,7 +1305,7 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) if (unlikely(!msg_connected(msg))) break; - res = auto_connect(sock, msg); + res = auto_connect(tsk, msg); if (res) { sock->state = SS_DISCONNECTING; sk->sk_err = -res; @@ -1385,6 +1384,7 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) { struct socket *sock = sk->sk_socket; + struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *msg = buf_msg(buf); unsigned int limit = rcvbuf_limit(sk, buf); u32 res = TIPC_OK; @@ -1397,7 +1397,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) if (msg_connected(msg)) return TIPC_ERR_NO_PORT; } else { - res = filter_connect(tipc_sk(sk), &buf); + res = filter_connect(tsk, &buf); if (res != TIPC_OK || buf == NULL) return res; } @@ -1435,17 +1435,16 @@ static int backlog_rcv(struct sock *sk, struct sk_buff *buf) } /** - * dispatch - handle incoming message - * @tport: TIPC port that received message + * tipc_sk_rcv - handle incoming message + * @sk: socket receiving message * @buf: message * * Called with port lock already taken. * * Returns TIPC error status code (TIPC_OK if message is not to be rejected) */ -static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) +u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf) { - struct sock *sk = tport->sk; u32 res; /* @@ -1468,19 +1467,6 @@ static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) return res; } -/** - * wakeupdispatch - wake up port after congestion - * @tport: port to wakeup - * - * Called with port lock already taken. - */ -static void wakeupdispatch(struct tipc_port *tport) -{ - struct sock *sk = tport->sk; - - sk->sk_write_space(sk); -} - static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) { struct sock *sk = sock->sk; @@ -1504,7 +1490,7 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) } /** - * connect - establish a connection to another TIPC port + * tipc_connect - establish a connection to another TIPC port * @sock: socket structure * @dest: socket address for destination port * @destlen: size of socket address data structure @@ -1512,8 +1498,8 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) * * Returns 0 on success, errno otherwise */ -static int connect(struct socket *sock, struct sockaddr *dest, int destlen, - int flags) +static int tipc_connect(struct socket *sock, struct sockaddr *dest, + int destlen, int flags) { struct sock *sk = sock->sk; struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest; @@ -1554,7 +1540,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, if (!timeout) m.msg_flags = MSG_DONTWAIT; - res = send_msg(NULL, sock, &m, 0); + res = tipc_sendmsg(NULL, sock, &m, 0); if ((res < 0) && (res != -EWOULDBLOCK)) goto exit; @@ -1585,13 +1571,13 @@ exit: } /** - * listen - allow socket to listen for incoming connections + * tipc_listen - allow socket to listen for incoming connections * @sock: socket structure * @len: (unused) * * Returns 0 on success, errno otherwise */ -static int listen(struct socket *sock, int len) +static int tipc_listen(struct socket *sock, int len) { struct sock *sk = sock->sk; int res; @@ -1646,20 +1632,20 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) } /** - * accept - wait for connection request + * tipc_accept - wait for connection request * @sock: listening socket * @newsock: new socket that is to be connected * @flags: file-related flags associated with socket * * Returns 0 on success, errno otherwise */ -static int accept(struct socket *sock, struct socket *new_sock, int flags) +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) { struct sock *new_sk, *sk = sock->sk; struct sk_buff *buf; - struct tipc_sock *new_tsock; - struct tipc_port *new_tport; + struct tipc_port *new_port; struct tipc_msg *msg; + struct tipc_portid peer; u32 new_ref; long timeo; int res; @@ -1670,7 +1656,6 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) res = -EINVAL; goto exit; } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); res = tipc_wait_for_accept(sock, timeo); if (res) @@ -1683,9 +1668,8 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) goto exit; new_sk = new_sock->sk; - new_tsock = tipc_sk(new_sk); - new_tport = new_tsock->p; - new_ref = new_tport->ref; + new_port = &tipc_sk(new_sk)->port; + new_ref = new_port->ref; msg = buf_msg(buf); /* we lock on new_sk; but lockdep sees the lock on sk */ @@ -1698,15 +1682,15 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) reject_rx_queue(new_sk); /* Connect new socket to it's peer */ - new_tsock->peer_name.ref = msg_origport(msg); - new_tsock->peer_name.node = msg_orignode(msg); - tipc_connect(new_ref, &new_tsock->peer_name); + peer.ref = msg_origport(msg); + peer.node = msg_orignode(msg); + tipc_port_connect(new_ref, &peer); new_sock->state = SS_CONNECTED; - tipc_set_portimportance(new_ref, msg_importance(msg)); + tipc_port_set_importance(new_port, msg_importance(msg)); if (msg_named(msg)) { - new_tport->conn_type = msg_nametype(msg); - new_tport->conn_instance = msg_nameinst(msg); + new_port->conn_type = msg_nametype(msg); + new_port->conn_instance = msg_nameinst(msg); } /* @@ -1717,21 +1701,20 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) struct msghdr m = {NULL,}; advance_rx_queue(sk); - send_packet(NULL, new_sock, &m, 0); + tipc_send_packet(NULL, new_sock, &m, 0); } else { __skb_dequeue(&sk->sk_receive_queue); __skb_queue_head(&new_sk->sk_receive_queue, buf); skb_set_owner_r(buf, new_sk); } release_sock(new_sk); - exit: release_sock(sk); return res; } /** - * shutdown - shutdown socket connection + * tipc_shutdown - shutdown socket connection * @sock: socket structure * @how: direction to close (must be SHUT_RDWR) * @@ -1739,10 +1722,11 @@ exit: * * Returns 0 on success, errno otherwise */ -static int shutdown(struct socket *sock, int how) +static int tipc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; struct sk_buff *buf; int res; @@ -1763,10 +1747,10 @@ restart: kfree_skb(buf); goto restart; } - tipc_disconnect(tport->ref); + tipc_port_disconnect(port->ref); tipc_reject_msg(buf, TIPC_CONN_SHUTDOWN); } else { - tipc_shutdown(tport->ref); + tipc_port_shutdown(port->ref); } sock->state = SS_DISCONNECTING; @@ -1792,7 +1776,7 @@ restart: } /** - * setsockopt - set socket option + * tipc_setsockopt - set socket option * @sock: socket structure * @lvl: option level * @opt: option identifier @@ -1804,11 +1788,12 @@ restart: * * Returns 0 on success, errno otherwise */ -static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov, - unsigned int ol) +static int tipc_setsockopt(struct socket *sock, int lvl, int opt, + char __user *ov, unsigned int ol) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; u32 value; int res; @@ -1826,16 +1811,16 @@ static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov, switch (opt) { case TIPC_IMPORTANCE: - res = tipc_set_portimportance(tport->ref, value); + tipc_port_set_importance(port, value); break; case TIPC_SRC_DROPPABLE: if (sock->type != SOCK_STREAM) - res = tipc_set_portunreliable(tport->ref, value); + tipc_port_set_unreliable(port, value); else res = -ENOPROTOOPT; break; case TIPC_DEST_DROPPABLE: - res = tipc_set_portunreturnable(tport->ref, value); + tipc_port_set_unreturnable(port, value); break; case TIPC_CONN_TIMEOUT: tipc_sk(sk)->conn_timeout = value; @@ -1851,7 +1836,7 @@ static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov, } /** - * getsockopt - get socket option + * tipc_getsockopt - get socket option * @sock: socket structure * @lvl: option level * @opt: option identifier @@ -1863,11 +1848,12 @@ static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov, * * Returns 0 on success, errno otherwise */ -static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov, - int __user *ol) +static int tipc_getsockopt(struct socket *sock, int lvl, int opt, + char __user *ov, int __user *ol) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; int len; u32 value; int res; @@ -1884,13 +1870,13 @@ static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov, switch (opt) { case TIPC_IMPORTANCE: - res = tipc_portimportance(tport->ref, &value); + value = tipc_port_importance(port); break; case TIPC_SRC_DROPPABLE: - res = tipc_portunreliable(tport->ref, &value); + value = tipc_port_unreliable(port); break; case TIPC_DEST_DROPPABLE: - res = tipc_portunreturnable(tport->ref, &value); + value = tipc_port_unreturnable(port); break; case TIPC_CONN_TIMEOUT: value = tipc_sk(sk)->conn_timeout; @@ -1925,20 +1911,20 @@ static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov, static const struct proto_ops msg_ops = { .owner = THIS_MODULE, .family = AF_TIPC, - .release = release, - .bind = bind, - .connect = connect, + .release = tipc_release, + .bind = tipc_bind, + .connect = tipc_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, - .getname = get_name, - .poll = poll, + .getname = tipc_getname, + .poll = tipc_poll, .ioctl = sock_no_ioctl, .listen = sock_no_listen, - .shutdown = shutdown, - .setsockopt = setsockopt, - .getsockopt = getsockopt, - .sendmsg = send_msg, - .recvmsg = recv_msg, + .shutdown = tipc_shutdown, + .setsockopt = tipc_setsockopt, + .getsockopt = tipc_getsockopt, + .sendmsg = tipc_sendmsg, + .recvmsg = tipc_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage }; @@ -1946,20 +1932,20 @@ static const struct proto_ops msg_ops = { static const struct proto_ops packet_ops = { .owner = THIS_MODULE, .family = AF_TIPC, - .release = release, - .bind = bind, - .connect = connect, + .release = tipc_release, + .bind = tipc_bind, + .connect = tipc_connect, .socketpair = sock_no_socketpair, - .accept = accept, - .getname = get_name, - .poll = poll, + .accept = tipc_accept, + .getname = tipc_getname, + .poll = tipc_poll, .ioctl = sock_no_ioctl, - .listen = listen, - .shutdown = shutdown, - .setsockopt = setsockopt, - .getsockopt = getsockopt, - .sendmsg = send_packet, - .recvmsg = recv_msg, + .listen = tipc_listen, + .shutdown = tipc_shutdown, + .setsockopt = tipc_setsockopt, + .getsockopt = tipc_getsockopt, + .sendmsg = tipc_send_packet, + .recvmsg = tipc_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage }; @@ -1967,20 +1953,20 @@ static const struct proto_ops packet_ops = { static const struct proto_ops stream_ops = { .owner = THIS_MODULE, .family = AF_TIPC, - .release = release, - .bind = bind, - .connect = connect, + .release = tipc_release, + .bind = tipc_bind, + .connect = tipc_connect, .socketpair = sock_no_socketpair, - .accept = accept, - .getname = get_name, - .poll = poll, + .accept = tipc_accept, + .getname = tipc_getname, + .poll = tipc_poll, .ioctl = sock_no_ioctl, - .listen = listen, - .shutdown = shutdown, - .setsockopt = setsockopt, - .getsockopt = getsockopt, - .sendmsg = send_stream, - .recvmsg = recv_stream, + .listen = tipc_listen, + .shutdown = tipc_shutdown, + .setsockopt = tipc_setsockopt, + .getsockopt = tipc_getsockopt, + .sendmsg = tipc_send_stream, + .recvmsg = tipc_recv_stream, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage }; diff --git a/net/tipc/socket.h b/net/tipc/socket.h new file mode 100644 index 000000000000..74e5c7f195a6 --- /dev/null +++ b/net/tipc/socket.h @@ -0,0 +1,72 @@ +/* net/tipc/socket.h: Include file for TIPC socket code + * + * Copyright (c) 2014, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_SOCK_H +#define _TIPC_SOCK_H + +#include "port.h" +#include <net/sock.h> + +/** + * struct tipc_sock - TIPC socket structure + * @sk: socket - interacts with 'port' and with user via the socket API + * @port: port - interacts with 'sk' and with the rest of the TIPC stack + * @peer_name: the peer of the connection, if any + * @conn_timeout: the time we can wait for an unresponded setup request + */ + +struct tipc_sock { + struct sock sk; + struct tipc_port port; + unsigned int conn_timeout; +}; + +static inline struct tipc_sock *tipc_sk(const struct sock *sk) +{ + return container_of(sk, struct tipc_sock, sk); +} + +static inline struct tipc_sock *tipc_port_to_sock(const struct tipc_port *port) +{ + return container_of(port, struct tipc_sock, port); +} + +static inline void tipc_sock_wakeup(struct tipc_sock *tsk) +{ + tsk->sk.sk_write_space(&tsk->sk); +} + +u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf); + +#endif diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 11ee4ed04f73..3e02ade508d8 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -7,7 +7,7 @@ static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, - struct net_device *dev) + struct net_device *dev, bool notify) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; @@ -27,22 +27,24 @@ static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, err = rdev_stop_ap(rdev, dev); if (!err) { wdev->beacon_interval = 0; - wdev->channel = NULL; + memset(&wdev->chandef, 0, sizeof(wdev->chandef)); wdev->ssid_len = 0; rdev_set_qos_map(rdev, dev, NULL); + if (notify) + nl80211_send_ap_stopped(wdev); } return err; } int cfg80211_stop_ap(struct cfg80211_registered_device *rdev, - struct net_device *dev) + struct net_device *dev, bool notify) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; wdev_lock(wdev); - err = __cfg80211_stop_ap(rdev, dev); + err = __cfg80211_stop_ap(rdev, dev, notify); wdev_unlock(wdev); return err; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 78559b5bbd1f..9c9501a35fb5 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -490,6 +490,62 @@ static bool cfg80211_chandef_dfs_available(struct wiphy *wiphy, return r; } +static unsigned int cfg80211_get_chans_dfs_cac_time(struct wiphy *wiphy, + u32 center_freq, + u32 bandwidth) +{ + struct ieee80211_channel *c; + u32 start_freq, end_freq, freq; + unsigned int dfs_cac_ms = 0; + + start_freq = cfg80211_get_start_freq(center_freq, bandwidth); + end_freq = cfg80211_get_end_freq(center_freq, bandwidth); + + for (freq = start_freq; freq <= end_freq; freq += 20) { + c = ieee80211_get_channel(wiphy, freq); + if (!c) + return 0; + + if (c->flags & IEEE80211_CHAN_DISABLED) + return 0; + + if (!(c->flags & IEEE80211_CHAN_RADAR)) + continue; + + if (c->dfs_cac_ms > dfs_cac_ms) + dfs_cac_ms = c->dfs_cac_ms; + } + + return dfs_cac_ms; +} + +unsigned int +cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef) +{ + int width; + unsigned int t1 = 0, t2 = 0; + + if (WARN_ON(!cfg80211_chandef_valid(chandef))) + return 0; + + width = cfg80211_chandef_get_width(chandef); + if (width < 0) + return 0; + + t1 = cfg80211_get_chans_dfs_cac_time(wiphy, + chandef->center_freq1, + width); + + if (!chandef->center_freq2) + return t1; + + t2 = cfg80211_get_chans_dfs_cac_time(wiphy, + chandef->center_freq2, + width); + + return max(t1, t2); +} static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, u32 center_freq, u32 bandwidth, @@ -642,7 +698,8 @@ int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev, void cfg80211_get_chan_state(struct wireless_dev *wdev, struct ieee80211_channel **chan, - enum cfg80211_chan_mode *chanmode) + enum cfg80211_chan_mode *chanmode, + u8 *radar_detect) { *chan = NULL; *chanmode = CHAN_MODE_UNDEFINED; @@ -660,6 +717,11 @@ cfg80211_get_chan_state(struct wireless_dev *wdev, !wdev->ibss_dfs_possible) ? CHAN_MODE_SHARED : CHAN_MODE_EXCLUSIVE; + + /* consider worst-case - IBSS can try to return to the + * original user-specified channel as creator */ + if (wdev->ibss_dfs_possible) + *radar_detect |= BIT(wdev->chandef.width); return; } break; @@ -674,33 +736,36 @@ cfg80211_get_chan_state(struct wireless_dev *wdev, case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: if (wdev->cac_started) { - *chan = wdev->channel; + *chan = wdev->chandef.chan; *chanmode = CHAN_MODE_SHARED; + *radar_detect |= BIT(wdev->chandef.width); } else if (wdev->beacon_interval) { - *chan = wdev->channel; + *chan = wdev->chandef.chan; *chanmode = CHAN_MODE_SHARED; + + if (cfg80211_chandef_dfs_required(wdev->wiphy, + &wdev->chandef)) + *radar_detect |= BIT(wdev->chandef.width); } return; case NL80211_IFTYPE_MESH_POINT: if (wdev->mesh_id_len) { - *chan = wdev->channel; + *chan = wdev->chandef.chan; *chanmode = CHAN_MODE_SHARED; + + if (cfg80211_chandef_dfs_required(wdev->wiphy, + &wdev->chandef)) + *radar_detect |= BIT(wdev->chandef.width); } return; case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_WDS: - /* these interface types don't really have a channel */ - return; case NL80211_IFTYPE_P2P_DEVICE: - if (wdev->wiphy->features & - NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL) - *chanmode = CHAN_MODE_EXCLUSIVE; + /* these interface types don't really have a channel */ return; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: WARN_ON(1); } - - return; } diff --git a/net/wireless/core.c b/net/wireless/core.c index a3bf18d11609..086cddd03ba6 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -737,7 +737,7 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev) } EXPORT_SYMBOL(cfg80211_unregister_wdev); -static struct device_type wiphy_type = { +static const struct device_type wiphy_type = { .name = "wlan", }; @@ -783,7 +783,7 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev, break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: - cfg80211_stop_ap(rdev, dev); + cfg80211_stop_ap(rdev, dev, true); break; default: break; diff --git a/net/wireless/core.h b/net/wireless/core.h index f1d193b557b6..5b1fdcadd469 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -166,7 +166,6 @@ static inline void wdev_unlock(struct wireless_dev *wdev) mutex_unlock(&wdev->mtx); } -#define ASSERT_RDEV_LOCK(rdev) ASSERT_RTNL() #define ASSERT_WDEV_LOCK(wdev) lockdep_assert_held(&(wdev)->mtx) static inline bool cfg80211_has_monitors_only(struct cfg80211_registered_device *rdev) @@ -211,6 +210,7 @@ struct cfg80211_event { } dc; struct { u8 bssid[ETH_ALEN]; + struct ieee80211_channel *channel; } ij; }; }; @@ -245,10 +245,6 @@ void cfg80211_bss_age(struct cfg80211_registered_device *dev, unsigned long age_secs); /* IBSS */ -int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, - struct net_device *dev, - struct cfg80211_ibss_params *params, - struct cfg80211_cached_keys *connkeys); int cfg80211_join_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ibss_params *params, @@ -258,7 +254,8 @@ int __cfg80211_leave_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev, bool nowext); int cfg80211_leave_ibss(struct cfg80211_registered_device *rdev, struct net_device *dev, bool nowext); -void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid); +void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, + struct ieee80211_channel *channel); int cfg80211_ibss_wext_join(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); @@ -281,7 +278,7 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev, /* AP */ int cfg80211_stop_ap(struct cfg80211_registered_device *rdev, - struct net_device *dev); + struct net_device *dev, bool notify); /* MLME */ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, @@ -400,6 +397,9 @@ void cfg80211_set_dfs_state(struct wiphy *wiphy, void cfg80211_dfs_channels_update_work(struct work_struct *work); +unsigned int +cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef); static inline int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, @@ -443,7 +443,8 @@ static inline unsigned int elapsed_jiffies_msecs(unsigned long start) void cfg80211_get_chan_state(struct wireless_dev *wdev, struct ieee80211_channel **chan, - enum cfg80211_chan_mode *chanmode); + enum cfg80211_chan_mode *chanmode, + u8 *radar_detect); int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef); diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk index 9a8217d2a908..b35da8dc85de 100644 --- a/net/wireless/genregdb.awk +++ b/net/wireless/genregdb.awk @@ -66,6 +66,7 @@ function parse_reg_rule() units = $8 sub(/\)/, "", units) sub(/,/, "", units) + dfs_cac = $9 if (units == "mW") { if (power == 100) { power = 20 @@ -78,7 +79,12 @@ function parse_reg_rule() } else { print "Unknown power value in database!" } + } else { + dfs_cac = $8 } + sub(/,/, "", dfs_cac) + sub(/\(/, "", dfs_cac) + sub(/\)/, "", dfs_cac) flagstr = "" for (i=8; i<=NF; i++) flagstr = flagstr $i @@ -105,11 +111,13 @@ function parse_reg_rule() flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " } else if (flagarray[arg] == "NO-IR") { flags = flags "\n\t\t\tNL80211_RRF_NO_IR | " + } else if (flagarray[arg] == "AUTO-BW") { + flags = flags "\n\t\t\tNL80211_RRF_AUTO_BW | " } } flags = flags "0" - printf "\t\tREG_RULE(%d, %d, %d, %d, %d, %s),\n", start, end, bw, gain, power, flags + printf "\t\tREG_RULE_EXT(%d, %d, %d, %d, %d, %d, %s),\n", start, end, bw, gain, power, dfs_cac, flags rules++ } diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index f911c5f9f903..a6b5bdad039c 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -14,7 +14,8 @@ #include "rdev-ops.h" -void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) +void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, + struct ieee80211_channel *channel) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_bss *bss; @@ -28,8 +29,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) if (!wdev->ssid_len) return; - bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid, - wdev->ssid, wdev->ssid_len, + bss = cfg80211_get_bss(wdev->wiphy, channel, bssid, NULL, 0, WLAN_CAPABILITY_IBSS, WLAN_CAPABILITY_IBSS); if (WARN_ON(!bss)) @@ -54,21 +54,26 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) #endif } -void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) +void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, + struct ieee80211_channel *channel, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; - trace_cfg80211_ibss_joined(dev, bssid); + trace_cfg80211_ibss_joined(dev, bssid, channel); + + if (WARN_ON(!channel)) + return; ev = kzalloc(sizeof(*ev), gfp); if (!ev) return; ev->type = EVENT_IBSS_JOINED; - memcpy(ev->cr.bssid, bssid, ETH_ALEN); + memcpy(ev->ij.bssid, bssid, ETH_ALEN); + ev->ij.channel = channel; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); @@ -77,10 +82,10 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) } EXPORT_SYMBOL(cfg80211_ibss_joined); -int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, - struct net_device *dev, - struct cfg80211_ibss_params *params, - struct cfg80211_cached_keys *connkeys) +static int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_ibss_params *params, + struct cfg80211_cached_keys *connkeys) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct ieee80211_channel *check_chan; @@ -117,17 +122,17 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, wdev->ibss_fixed = params->channel_fixed; wdev->ibss_dfs_possible = params->userspace_handles_dfs; + wdev->chandef = params->chandef; #ifdef CONFIG_CFG80211_WEXT wdev->wext.ibss.chandef = params->chandef; #endif check_chan = params->chandef.chan; if (params->userspace_handles_dfs) { - /* use channel NULL to check for radar even if the current - * channel is not a radar channel - it might decide to change - * to DFS channel later. + /* Check for radar even if the current channel is not + * a radar channel - it might decide to change to DFS + * channel later. */ radar_detect_width = BIT(params->chandef.width); - check_chan = NULL; } err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype, @@ -200,6 +205,7 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext) wdev->current_bss = NULL; wdev->ssid_len = 0; + memset(&wdev->chandef, 0, sizeof(wdev->chandef)); #ifdef CONFIG_CFG80211_WEXT if (!nowext) wdev->wext.ibss.ssid_len = 0; diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index 885862447b63..5af5cc6b2c4c 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -195,7 +195,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, if (!err) { memcpy(wdev->ssid, setup->mesh_id, setup->mesh_id_len); wdev->mesh_id_len = setup->mesh_id_len; - wdev->channel = setup->chandef.chan; + wdev->chandef = setup->chandef; } return err; @@ -236,6 +236,12 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev, if (!netif_running(wdev->netdev)) return -ENETDOWN; + /* cfg80211_can_use_chan() calls + * cfg80211_can_use_iftype_chan() with no radar + * detection, so if we're trying to use a radar + * channel here, something is wrong. + */ + WARN_ON_ONCE(chandef->chan->flags & IEEE80211_CHAN_RADAR); err = cfg80211_can_use_chan(rdev, wdev, chandef->chan, CHAN_MODE_SHARED); if (err) @@ -244,7 +250,7 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev, err = rdev_libertas_set_mesh_channel(rdev, wdev->netdev, chandef->chan); if (!err) - wdev->channel = chandef->chan; + wdev->chandef = *chandef; return err; } @@ -276,7 +282,7 @@ static int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev, err = rdev_leave_mesh(rdev, dev); if (!err) { wdev->mesh_id_len = 0; - wdev->channel = NULL; + memset(&wdev->chandef, 0, sizeof(wdev->chandef)); rdev_set_qos_map(rdev, dev, NULL); } diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 52cca05044a8..c52ff59a3e96 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -772,13 +772,13 @@ void cfg80211_cac_event(struct net_device *netdev, if (WARN_ON(!wdev->cac_started)) return; - if (WARN_ON(!wdev->channel)) + if (WARN_ON(!wdev->chandef.chan)) return; switch (event) { case NL80211_RADAR_CAC_FINISHED: timeout = wdev->cac_start_time + - msecs_to_jiffies(IEEE80211_DFS_MIN_CAC_TIME_MS); + msecs_to_jiffies(wdev->cac_time_ms); WARN_ON(!time_after_eq(jiffies, timeout)); cfg80211_set_dfs_state(wiphy, chandef, NL80211_DFS_AVAILABLE); break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4fe2e6e2bc76..052c1bf8ffac 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -382,6 +382,9 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, [NL80211_ATTR_QOS_MAP] = { .type = NLA_BINARY, .len = IEEE80211_QOS_MAP_LEN_MAX }, + [NL80211_ATTR_MAC_HINT] = { .len = ETH_ALEN }, + [NL80211_ATTR_WIPHY_FREQ_HINT] = { .type = NLA_U32 }, + [NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 }, }; /* policy for the key attributes */ @@ -590,6 +593,10 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_DFS_TIME, time)) goto nla_put_failure; + if (nla_put_u32(msg, + NL80211_FREQUENCY_ATTR_DFS_CAC_TIME, + chan->dfs_cac_ms)) + goto nla_put_failure; } } @@ -855,6 +862,19 @@ static int nl80211_key_allowed(struct wireless_dev *wdev) return 0; } +static struct ieee80211_channel *nl80211_get_valid_chan(struct wiphy *wiphy, + struct nlattr *tb) +{ + struct ieee80211_channel *chan; + + if (tb == NULL) + return NULL; + chan = ieee80211_get_channel(wiphy, nla_get_u32(tb)); + if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) + return NULL; + return chan; +} + static int nl80211_put_iftypes(struct sk_buff *msg, u32 attr, u16 ifmodes) { struct nlattr *nl_modes = nla_nest_start(msg, attr); @@ -1586,6 +1606,12 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev, (nla_put_flag(msg, NL80211_ATTR_SUPPORT_5_MHZ) || nla_put_flag(msg, NL80211_ATTR_SUPPORT_10_MHZ))) goto nla_put_failure; + + if (dev->wiphy.max_ap_assoc_sta && + nla_put_u32(msg, NL80211_ATTR_MAX_AP_ASSOC_STA, + dev->wiphy.max_ap_assoc_sta)) + goto nla_put_failure; + state->split_start++; break; case 11: @@ -2035,10 +2061,12 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) nla_for_each_nested(nl_txq_params, info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS], rem_txq_params) { - nla_parse(tb, NL80211_TXQ_ATTR_MAX, - nla_data(nl_txq_params), - nla_len(nl_txq_params), - txq_params_policy); + result = nla_parse(tb, NL80211_TXQ_ATTR_MAX, + nla_data(nl_txq_params), + nla_len(nl_txq_params), + txq_params_policy); + if (result) + return result; result = parse_txq_params(tb, &txq_params); if (result) return result; @@ -3259,7 +3287,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (!err) { wdev->preset_chandef = params.chandef; wdev->beacon_interval = params.beacon_interval; - wdev->channel = params.chandef.chan; + wdev->chandef = params.chandef; wdev->ssid_len = params.ssid_len; memcpy(wdev->ssid, params.ssid, wdev->ssid_len); } @@ -3304,7 +3332,7 @@ static int nl80211_stop_ap(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; - return cfg80211_stop_ap(rdev, dev); + return cfg80211_stop_ap(rdev, dev, false); } static const struct nla_policy sta_flags_policy[NL80211_STA_FLAG_MAX + 1] = { @@ -3902,8 +3930,8 @@ static struct net_device *get_vlan(struct genl_info *info, return ERR_PTR(ret); } -static struct nla_policy -nl80211_sta_wme_policy[NL80211_STA_WME_MAX + 1] __read_mostly = { +static const struct nla_policy +nl80211_sta_wme_policy[NL80211_STA_WME_MAX + 1] = { [NL80211_STA_WME_UAPSD_QUEUES] = { .type = NLA_U8 }, [NL80211_STA_WME_MAX_SP] = { .type = NLA_U8 }, }; @@ -4590,6 +4618,7 @@ static const struct nla_policy reg_rule_policy[NL80211_REG_RULE_ATTR_MAX + 1] = [NL80211_ATTR_FREQ_RANGE_MAX_BW] = { .type = NLA_U32 }, [NL80211_ATTR_POWER_RULE_MAX_ANT_GAIN] = { .type = NLA_U32 }, [NL80211_ATTR_POWER_RULE_MAX_EIRP] = { .type = NLA_U32 }, + [NL80211_ATTR_DFS_CAC_TIME] = { .type = NLA_U32 }, }; static int parse_reg_rule(struct nlattr *tb[], @@ -4625,6 +4654,10 @@ static int parse_reg_rule(struct nlattr *tb[], power_rule->max_antenna_gain = nla_get_u32(tb[NL80211_ATTR_POWER_RULE_MAX_ANT_GAIN]); + if (tb[NL80211_ATTR_DFS_CAC_TIME]) + reg_rule->dfs_cac_ms = + nla_get_u32(tb[NL80211_ATTR_DFS_CAC_TIME]); + return 0; } @@ -5086,6 +5119,7 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) const struct ieee80211_reg_rule *reg_rule; const struct ieee80211_freq_range *freq_range; const struct ieee80211_power_rule *power_rule; + unsigned int max_bandwidth_khz; reg_rule = ®dom->reg_rules[i]; freq_range = ®_rule->freq_range; @@ -5095,6 +5129,11 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) if (!nl_reg_rule) goto nla_put_failure_rcu; + max_bandwidth_khz = freq_range->max_bandwidth_khz; + if (!max_bandwidth_khz) + max_bandwidth_khz = reg_get_max_bandwidth(regdom, + reg_rule); + if (nla_put_u32(msg, NL80211_ATTR_REG_RULE_FLAGS, reg_rule->flags) || nla_put_u32(msg, NL80211_ATTR_FREQ_RANGE_START, @@ -5102,11 +5141,13 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) nla_put_u32(msg, NL80211_ATTR_FREQ_RANGE_END, freq_range->end_freq_khz) || nla_put_u32(msg, NL80211_ATTR_FREQ_RANGE_MAX_BW, - freq_range->max_bandwidth_khz) || + max_bandwidth_khz) || nla_put_u32(msg, NL80211_ATTR_POWER_RULE_MAX_ANT_GAIN, power_rule->max_antenna_gain) || nla_put_u32(msg, NL80211_ATTR_POWER_RULE_MAX_EIRP, - power_rule->max_eirp)) + power_rule->max_eirp) || + nla_put_u32(msg, NL80211_ATTR_DFS_CAC_TIME, + reg_rule->dfs_cac_ms)) goto nla_put_failure_rcu; nla_nest_end(msg, nl_reg_rule); @@ -5178,9 +5219,11 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) nla_for_each_nested(nl_reg_rule, info->attrs[NL80211_ATTR_REG_RULES], rem_reg_rules) { - nla_parse(tb, NL80211_REG_RULE_ATTR_MAX, - nla_data(nl_reg_rule), nla_len(nl_reg_rule), - reg_rule_policy); + r = nla_parse(tb, NL80211_REG_RULE_ATTR_MAX, + nla_data(nl_reg_rule), nla_len(nl_reg_rule), + reg_rule_policy); + if (r) + goto bad_reg; r = parse_reg_rule(tb, &rd->reg_rules[rule_idx]); if (r) goto bad_reg; @@ -5443,6 +5486,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, enum ieee80211_band band; size_t ie_len; struct nlattr *tb[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1]; + s32 default_match_rssi = NL80211_SCAN_RSSI_THOLD_OFF; if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) || !rdev->ops->sched_scan_start) @@ -5477,11 +5521,40 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (n_ssids > wiphy->max_sched_scan_ssids) return -EINVAL; - if (info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH]) + /* + * First, count the number of 'real' matchsets. Due to an issue with + * the old implementation, matchsets containing only the RSSI attribute + * (NL80211_SCHED_SCAN_MATCH_ATTR_RSSI) are considered as the 'default' + * RSSI for all matchsets, rather than their own matchset for reporting + * all APs with a strong RSSI. This is needed to be compatible with + * older userspace that treated a matchset with only the RSSI as the + * global RSSI for all other matchsets - if there are other matchsets. + */ + if (info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH]) { nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCHED_SCAN_MATCH], - tmp) - n_match_sets++; + tmp) { + struct nlattr *rssi; + + err = nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX, + nla_data(attr), nla_len(attr), + nl80211_match_policy); + if (err) + return err; + /* add other standalone attributes here */ + if (tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID]) { + n_match_sets++; + continue; + } + rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI]; + if (rssi) + default_match_rssi = nla_get_s32(rssi); + } + } + + /* However, if there's no other matchset, add the RSSI one */ + if (!n_match_sets && default_match_rssi != NL80211_SCAN_RSSI_THOLD_OFF) + n_match_sets = 1; if (n_match_sets > wiphy->max_match_sets) return -EINVAL; @@ -5602,11 +5675,22 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, tmp) { struct nlattr *ssid, *rssi; - nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX, - nla_data(attr), nla_len(attr), - nl80211_match_policy); + err = nla_parse(tb, NL80211_SCHED_SCAN_MATCH_ATTR_MAX, + nla_data(attr), nla_len(attr), + nl80211_match_policy); + if (err) + goto out_free; ssid = tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID]; if (ssid) { + if (WARN_ON(i >= n_match_sets)) { + /* this indicates a programming error, + * the loop above should have verified + * things properly + */ + err = -EINVAL; + goto out_free; + } + if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) { err = -EINVAL; goto out_free; @@ -5615,19 +5699,32 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, nla_data(ssid), nla_len(ssid)); request->match_sets[i].ssid.ssid_len = nla_len(ssid); + /* special attribute - old implemenation w/a */ + request->match_sets[i].rssi_thold = + default_match_rssi; + rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI]; + if (rssi) + request->match_sets[i].rssi_thold = + nla_get_s32(rssi); } - rssi = tb[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI]; - if (rssi) - request->rssi_thold = nla_get_u32(rssi); - else - request->rssi_thold = - NL80211_SCAN_RSSI_THOLD_OFF; i++; } + + /* there was no other matchset, so the RSSI one is alone */ + if (i == 0) + request->match_sets[0].rssi_thold = default_match_rssi; + + request->min_rssi_thold = INT_MAX; + for (i = 0; i < n_match_sets; i++) + request->min_rssi_thold = + min(request->match_sets[i].rssi_thold, + request->min_rssi_thold); + } else { + request->min_rssi_thold = NL80211_SCAN_RSSI_THOLD_OFF; } - if (info->attrs[NL80211_ATTR_IE]) { - request->ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); + if (ie_len) { + request->ie_len = ie_len; memcpy((void *)request->ie, nla_data(info->attrs[NL80211_ATTR_IE]), request->ie_len); @@ -5682,6 +5779,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_chan_def chandef; enum nl80211_dfs_regions dfs_region; + unsigned int cac_time_ms; int err; dfs_region = reg_get_dfs_region(wdev->wiphy); @@ -5717,11 +5815,17 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, if (err) return err; - err = rdev->ops->start_radar_detection(&rdev->wiphy, dev, &chandef); + cac_time_ms = cfg80211_chandef_dfs_cac_time(&rdev->wiphy, &chandef); + if (WARN_ON(!cac_time_ms)) + cac_time_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; + + err = rdev->ops->start_radar_detection(&rdev->wiphy, dev, &chandef, + cac_time_ms); if (!err) { - wdev->channel = chandef.chan; + wdev->chandef = chandef; wdev->cac_started = true; wdev->cac_start_time = jiffies; + wdev->cac_time_ms = cac_time_ms; } return err; } @@ -5751,10 +5855,15 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) /* useless if AP is not running */ if (!wdev->beacon_interval) - return -EINVAL; + return -ENOTCONN; break; case NL80211_IFTYPE_ADHOC: + if (!wdev->ssid_len) + return -ENOTCONN; + break; case NL80211_IFTYPE_MESH_POINT: + if (!wdev->mesh_id_len) + return -ENOTCONN; break; default: return -EOPNOTSUPP; @@ -5822,17 +5931,22 @@ skip_beacons: if (!cfg80211_reg_can_beacon(&rdev->wiphy, ¶ms.chandef)) return -EINVAL; - if (dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP || - dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO || - dev->ieee80211_ptr->iftype == NL80211_IFTYPE_ADHOC) { + switch (dev->ieee80211_ptr->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_MESH_POINT: err = cfg80211_chandef_dfs_required(wdev->wiphy, ¶ms.chandef); - if (err < 0) { + if (err < 0) return err; - } else if (err) { + if (err) { radar_detect_width = BIT(params.chandef.width); params.radar_required = true; } + break; + default: + break; } err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype, @@ -6192,9 +6306,9 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); - chan = ieee80211_get_channel(&rdev->wiphy, - nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); - if (!chan || (chan->flags & IEEE80211_CHAN_DISABLED)) + chan = nl80211_get_valid_chan(&rdev->wiphy, + info->attrs[NL80211_ATTR_WIPHY_FREQ]); + if (!chan) return -EINVAL; ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); @@ -6347,9 +6461,9 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); - chan = ieee80211_get_channel(&rdev->wiphy, - nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); - if (!chan || (chan->flags & IEEE80211_CHAN_DISABLED)) + chan = nl80211_get_valid_chan(&rdev->wiphy, + info->attrs[NL80211_ATTR_WIPHY_FREQ]); + if (!chan) return -EINVAL; ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); @@ -6985,6 +7099,9 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_MAC]) connect.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); + else if (info->attrs[NL80211_ATTR_MAC_HINT]) + connect.bssid_hint = + nla_data(info->attrs[NL80211_ATTR_MAC_HINT]); connect.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); connect.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); @@ -7003,11 +7120,14 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { - connect.channel = - ieee80211_get_channel(wiphy, - nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ])); - if (!connect.channel || - connect.channel->flags & IEEE80211_CHAN_DISABLED) + connect.channel = nl80211_get_valid_chan( + wiphy, info->attrs[NL80211_ATTR_WIPHY_FREQ]); + if (!connect.channel) + return -EINVAL; + } else if (info->attrs[NL80211_ATTR_WIPHY_FREQ_HINT]) { + connect.channel_hint = nl80211_get_valid_chan( + wiphy, info->attrs[NL80211_ATTR_WIPHY_FREQ_HINT]); + if (!connect.channel_hint) return -EINVAL; } @@ -7174,6 +7294,7 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info) struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; u8 action_code, dialog_token; + u32 peer_capability = 0; u16 status_code; u8 *peer; @@ -7192,9 +7313,12 @@ static int nl80211_tdls_mgmt(struct sk_buff *skb, struct genl_info *info) action_code = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_ACTION]); status_code = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]); dialog_token = nla_get_u8(info->attrs[NL80211_ATTR_TDLS_DIALOG_TOKEN]); + if (info->attrs[NL80211_ATTR_TDLS_PEER_CAPABILITY]) + peer_capability = + nla_get_u32(info->attrs[NL80211_ATTR_TDLS_PEER_CAPABILITY]); return rdev_tdls_mgmt(rdev, dev, peer, action_code, - dialog_token, status_code, + dialog_token, status_code, peer_capability, nla_data(info->attrs[NL80211_ATTR_IE]), nla_len(info->attrs[NL80211_ATTR_IE])); } @@ -7421,6 +7545,7 @@ static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = { [NL80211_TXRATE_HT] = { .type = NLA_BINARY, .len = NL80211_MAX_SUPP_HT_RATES }, [NL80211_TXRATE_VHT] = { .len = sizeof(struct nl80211_txrate_vht)}, + [NL80211_TXRATE_GI] = { .type = NLA_U8 }, }; static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, @@ -7467,16 +7592,19 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, * directly to the enum ieee80211_band values used in cfg80211. */ BUILD_BUG_ON(NL80211_MAX_SUPP_HT_RATES > IEEE80211_HT_MCS_MASK_LEN * 8); - nla_for_each_nested(tx_rates, info->attrs[NL80211_ATTR_TX_RATES], rem) - { + nla_for_each_nested(tx_rates, info->attrs[NL80211_ATTR_TX_RATES], rem) { enum ieee80211_band band = nla_type(tx_rates); + int err; + if (band < 0 || band >= IEEE80211_NUM_BANDS) return -EINVAL; sband = rdev->wiphy.bands[band]; if (sband == NULL) return -EINVAL; - nla_parse(tb, NL80211_TXRATE_MAX, nla_data(tx_rates), - nla_len(tx_rates), nl80211_txattr_policy); + err = nla_parse(tb, NL80211_TXRATE_MAX, nla_data(tx_rates), + nla_len(tx_rates), nl80211_txattr_policy); + if (err) + return err; if (tb[NL80211_TXRATE_LEGACY]) { mask.control[band].legacy = rateset_to_mask( sband, @@ -7501,6 +7629,12 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb, mask.control[band].vht_mcs)) return -EINVAL; } + if (tb[NL80211_TXRATE_GI]) { + mask.control[band].gi = + nla_get_u8(tb[NL80211_TXRATE_GI]); + if (mask.control[band].gi > NL80211_TXRATE_FORCE_LGI) + return -EINVAL; + } if (mask.control[band].legacy == 0) { /* don't allow empty legacy rates if HT or VHT @@ -7777,8 +7911,8 @@ static int nl80211_get_power_save(struct sk_buff *skb, struct genl_info *info) return err; } -static struct nla_policy -nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] __read_mostly = { +static const struct nla_policy +nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] = { [NL80211_ATTR_CQM_RSSI_THOLD] = { .type = NLA_U32 }, [NL80211_ATTR_CQM_RSSI_HYST] = { .type = NLA_U32 }, [NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT] = { .type = NLA_U32 }, @@ -11107,7 +11241,8 @@ void cfg80211_ch_switch_notify(struct net_device *dev, wdev->iftype != NL80211_IFTYPE_MESH_POINT)) return; - wdev->channel = chandef->chan; + wdev->chandef = *chandef; + wdev->preset_chandef = *chandef; nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL); } EXPORT_SYMBOL(cfg80211_ch_switch_notify); @@ -11621,6 +11756,35 @@ void cfg80211_crit_proto_stopped(struct wireless_dev *wdev, gfp_t gfp) } EXPORT_SYMBOL(cfg80211_crit_proto_stopped); +void nl80211_send_ap_stopped(struct wireless_dev *wdev) +{ + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_STOP_AP); + if (!hdr) + goto out; + + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || + nla_put_u32(msg, NL80211_ATTR_IFINDEX, wdev->netdev->ifindex) || + nla_put_u64(msg, NL80211_ATTR_WDEV, wdev_id(wdev))) + goto out; + + genlmsg_end(msg, hdr); + + genlmsg_multicast_netns(&nl80211_fam, wiphy_net(wiphy), msg, 0, + NL80211_MCGRP_MLME, GFP_KERNEL); + return; + out: + nlmsg_free(msg); +} + /* initialisation/exit functions */ int nl80211_init(void) diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 75799746d845..1e6df9630f42 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -74,6 +74,8 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev, enum nl80211_radar_event event, struct net_device *netdev, gfp_t gfp); +void nl80211_send_ap_stopped(struct wireless_dev *wdev); + void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev); #endif /* __NET_WIRELESS_NL80211_H */ diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index c8e225947adb..74d97d33c938 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -769,13 +769,16 @@ static inline int rdev_set_rekey_data(struct cfg80211_registered_device *rdev, static inline int rdev_tdls_mgmt(struct cfg80211_registered_device *rdev, struct net_device *dev, u8 *peer, u8 action_code, u8 dialog_token, - u16 status_code, const u8 *buf, size_t len) + u16 status_code, u32 peer_capability, + const u8 *buf, size_t len) { int ret; trace_rdev_tdls_mgmt(&rdev->wiphy, dev, peer, action_code, - dialog_token, status_code, buf, len); + dialog_token, status_code, peer_capability, + buf, len); ret = rdev->ops->tdls_mgmt(&rdev->wiphy, dev, peer, action_code, - dialog_token, status_code, buf, len); + dialog_token, status_code, peer_capability, + buf, len); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index f0541370e68e..f59aaac586f8 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -91,10 +91,6 @@ static struct regulatory_request __rcu *last_request = /* To trigger userspace events */ static struct platform_device *reg_pdev; -static struct device_type reg_device_type = { - .uevent = reg_device_uevent, -}; - /* * Central wireless core regulatory domains, we only need two, * the current one and a world regulatory domain in case we have no @@ -244,19 +240,21 @@ static char user_alpha2[2]; module_param(ieee80211_regdom, charp, 0444); MODULE_PARM_DESC(ieee80211_regdom, "IEEE 802.11 regulatory domain code"); -static void reg_kfree_last_request(void) +static void reg_free_request(struct regulatory_request *lr) { - struct regulatory_request *lr; - - lr = get_last_request(); - if (lr != &core_request_world && lr) kfree_rcu(lr, rcu_head); } static void reg_update_last_request(struct regulatory_request *request) { - reg_kfree_last_request(); + struct regulatory_request *lr; + + lr = get_last_request(); + if (lr == request) + return; + + reg_free_request(lr); rcu_assign_pointer(last_request, request); } @@ -487,11 +485,16 @@ static inline void reg_regdb_query(const char *alpha2) {} /* * This lets us keep regulatory code which is updated on a regulatory - * basis in userspace. Country information is filled in by - * reg_device_uevent + * basis in userspace. */ static int call_crda(const char *alpha2) { + char country[12]; + char *env[] = { country, NULL }; + + snprintf(country, sizeof(country), "COUNTRY=%c%c", + alpha2[0], alpha2[1]); + if (!is_world_regdom((char *) alpha2)) pr_info("Calling CRDA for country: %c%c\n", alpha2[0], alpha2[1]); @@ -501,7 +504,7 @@ static int call_crda(const char *alpha2) /* query internal regulatory database (if it exists) */ reg_regdb_query(alpha2); - return kobject_uevent(®_pdev->dev.kobj, KOBJ_CHANGE); + return kobject_uevent_env(®_pdev->dev.kobj, KOBJ_CHANGE, env); } static enum reg_request_treatment @@ -522,6 +525,71 @@ bool reg_is_valid_request(const char *alpha2) return alpha2_equal(lr->alpha2, alpha2); } +static const struct ieee80211_regdomain *reg_get_regdomain(struct wiphy *wiphy) +{ + struct regulatory_request *lr = get_last_request(); + + /* + * Follow the driver's regulatory domain, if present, unless a country + * IE has been processed or a user wants to help complaince further + */ + if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && + lr->initiator != NL80211_REGDOM_SET_BY_USER && + wiphy->regd) + return get_wiphy_regdom(wiphy); + + return get_cfg80211_regdom(); +} + +unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd, + const struct ieee80211_reg_rule *rule) +{ + const struct ieee80211_freq_range *freq_range = &rule->freq_range; + const struct ieee80211_freq_range *freq_range_tmp; + const struct ieee80211_reg_rule *tmp; + u32 start_freq, end_freq, idx, no; + + for (idx = 0; idx < rd->n_reg_rules; idx++) + if (rule == &rd->reg_rules[idx]) + break; + + if (idx == rd->n_reg_rules) + return 0; + + /* get start_freq */ + no = idx; + + while (no) { + tmp = &rd->reg_rules[--no]; + freq_range_tmp = &tmp->freq_range; + + if (freq_range_tmp->end_freq_khz < freq_range->start_freq_khz) + break; + + freq_range = freq_range_tmp; + } + + start_freq = freq_range->start_freq_khz; + + /* get end_freq */ + freq_range = &rule->freq_range; + no = idx; + + while (no < rd->n_reg_rules - 1) { + tmp = &rd->reg_rules[++no]; + freq_range_tmp = &tmp->freq_range; + + if (freq_range_tmp->start_freq_khz > freq_range->end_freq_khz) + break; + + freq_range = freq_range_tmp; + } + + end_freq = freq_range->end_freq_khz; + + return end_freq - start_freq; +} + /* Sanity check on a regulatory rule */ static bool is_valid_reg_rule(const struct ieee80211_reg_rule *rule) { @@ -630,7 +698,9 @@ reg_intersect_dfs_region(const enum nl80211_dfs_regions dfs_region1, * Helper for regdom_intersect(), this does the real * mathematical intersection fun */ -static int reg_rules_intersect(const struct ieee80211_reg_rule *rule1, +static int reg_rules_intersect(const struct ieee80211_regdomain *rd1, + const struct ieee80211_regdomain *rd2, + const struct ieee80211_reg_rule *rule1, const struct ieee80211_reg_rule *rule2, struct ieee80211_reg_rule *intersected_rule) { @@ -638,7 +708,7 @@ static int reg_rules_intersect(const struct ieee80211_reg_rule *rule1, struct ieee80211_freq_range *freq_range; const struct ieee80211_power_rule *power_rule1, *power_rule2; struct ieee80211_power_rule *power_rule; - u32 freq_diff; + u32 freq_diff, max_bandwidth1, max_bandwidth2; freq_range1 = &rule1->freq_range; freq_range2 = &rule2->freq_range; @@ -652,8 +722,32 @@ static int reg_rules_intersect(const struct ieee80211_reg_rule *rule1, freq_range2->start_freq_khz); freq_range->end_freq_khz = min(freq_range1->end_freq_khz, freq_range2->end_freq_khz); - freq_range->max_bandwidth_khz = min(freq_range1->max_bandwidth_khz, - freq_range2->max_bandwidth_khz); + + max_bandwidth1 = freq_range1->max_bandwidth_khz; + max_bandwidth2 = freq_range2->max_bandwidth_khz; + + if (rule1->flags & NL80211_RRF_AUTO_BW) + max_bandwidth1 = reg_get_max_bandwidth(rd1, rule1); + if (rule2->flags & NL80211_RRF_AUTO_BW) + max_bandwidth2 = reg_get_max_bandwidth(rd2, rule2); + + freq_range->max_bandwidth_khz = min(max_bandwidth1, max_bandwidth2); + + intersected_rule->flags = rule1->flags | rule2->flags; + + /* + * In case NL80211_RRF_AUTO_BW requested for both rules + * set AUTO_BW in intersected rule also. Next we will + * calculate BW correctly in handle_channel function. + * In other case remove AUTO_BW flag while we calculate + * maximum bandwidth correctly and auto calculation is + * not required. + */ + if ((rule1->flags & NL80211_RRF_AUTO_BW) && + (rule2->flags & NL80211_RRF_AUTO_BW)) + intersected_rule->flags |= NL80211_RRF_AUTO_BW; + else + intersected_rule->flags &= ~NL80211_RRF_AUTO_BW; freq_diff = freq_range->end_freq_khz - freq_range->start_freq_khz; if (freq_range->max_bandwidth_khz > freq_diff) @@ -664,7 +758,8 @@ static int reg_rules_intersect(const struct ieee80211_reg_rule *rule1, power_rule->max_antenna_gain = min(power_rule1->max_antenna_gain, power_rule2->max_antenna_gain); - intersected_rule->flags = rule1->flags | rule2->flags; + intersected_rule->dfs_cac_ms = max(rule1->dfs_cac_ms, + rule2->dfs_cac_ms); if (!is_valid_reg_rule(intersected_rule)) return -EINVAL; @@ -713,7 +808,8 @@ regdom_intersect(const struct ieee80211_regdomain *rd1, rule1 = &rd1->reg_rules[x]; for (y = 0; y < rd2->n_reg_rules; y++) { rule2 = &rd2->reg_rules[y]; - if (!reg_rules_intersect(rule1, rule2, &dummy_rule)) + if (!reg_rules_intersect(rd1, rd2, rule1, rule2, + &dummy_rule)) num_rules++; } } @@ -738,7 +834,8 @@ regdom_intersect(const struct ieee80211_regdomain *rd1, * a memcpy() */ intersected_rule = &rd->reg_rules[rule_idx]; - r = reg_rules_intersect(rule1, rule2, intersected_rule); + r = reg_rules_intersect(rd1, rd2, rule1, rule2, + intersected_rule); /* * No need to memset here the intersected rule here as * we're not using the stack anymore @@ -821,18 +918,8 @@ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, u32 center_freq) { const struct ieee80211_regdomain *regd; - struct regulatory_request *lr = get_last_request(); - /* - * Follow the driver's regulatory domain, if present, unless a country - * IE has been processed or a user wants to help complaince further - */ - if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && - lr->initiator != NL80211_REGDOM_SET_BY_USER && - wiphy->regd) - regd = get_wiphy_regdom(wiphy); - else - regd = get_cfg80211_regdom(); + regd = reg_get_regdomain(wiphy); return freq_reg_info_regd(wiphy, center_freq, regd); } @@ -857,31 +944,42 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator) EXPORT_SYMBOL(reg_initiator_name); #ifdef CONFIG_CFG80211_REG_DEBUG -static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan, +static void chan_reg_rule_print_dbg(const struct ieee80211_regdomain *regd, + struct ieee80211_channel *chan, const struct ieee80211_reg_rule *reg_rule) { const struct ieee80211_power_rule *power_rule; const struct ieee80211_freq_range *freq_range; - char max_antenna_gain[32]; + char max_antenna_gain[32], bw[32]; power_rule = ®_rule->power_rule; freq_range = ®_rule->freq_range; if (!power_rule->max_antenna_gain) - snprintf(max_antenna_gain, 32, "N/A"); + snprintf(max_antenna_gain, sizeof(max_antenna_gain), "N/A"); else - snprintf(max_antenna_gain, 32, "%d", power_rule->max_antenna_gain); + snprintf(max_antenna_gain, sizeof(max_antenna_gain), "%d", + power_rule->max_antenna_gain); + + if (reg_rule->flags & NL80211_RRF_AUTO_BW) + snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO", + freq_range->max_bandwidth_khz, + reg_get_max_bandwidth(regd, reg_rule)); + else + snprintf(bw, sizeof(bw), "%d KHz", + freq_range->max_bandwidth_khz); REG_DBG_PRINT("Updating information on frequency %d MHz with regulatory rule:\n", chan->center_freq); - REG_DBG_PRINT("%d KHz - %d KHz @ %d KHz), (%s mBi, %d mBm)\n", + REG_DBG_PRINT("%d KHz - %d KHz @ %s), (%s mBi, %d mBm)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, - freq_range->max_bandwidth_khz, max_antenna_gain, + bw, max_antenna_gain, power_rule->max_eirp); } #else -static void chan_reg_rule_print_dbg(struct ieee80211_channel *chan, +static void chan_reg_rule_print_dbg(const struct ieee80211_regdomain *regd, + struct ieee80211_channel *chan, const struct ieee80211_reg_rule *reg_rule) { return; @@ -903,6 +1001,8 @@ static void handle_channel(struct wiphy *wiphy, const struct ieee80211_freq_range *freq_range = NULL; struct wiphy *request_wiphy = NULL; struct regulatory_request *lr = get_last_request(); + const struct ieee80211_regdomain *regd; + u32 max_bandwidth_khz; request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); @@ -939,16 +1039,22 @@ static void handle_channel(struct wiphy *wiphy, return; } - chan_reg_rule_print_dbg(chan, reg_rule); + regd = reg_get_regdomain(wiphy); + chan_reg_rule_print_dbg(regd, chan, reg_rule); power_rule = ®_rule->power_rule; freq_range = ®_rule->freq_range; - if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(40)) + max_bandwidth_khz = freq_range->max_bandwidth_khz; + /* Check if auto calculation requested */ + if (reg_rule->flags & NL80211_RRF_AUTO_BW) + max_bandwidth_khz = reg_get_max_bandwidth(regd, reg_rule); + + if (max_bandwidth_khz < MHZ_TO_KHZ(40)) bw_flags = IEEE80211_CHAN_NO_HT40; - if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(80)) + if (max_bandwidth_khz < MHZ_TO_KHZ(80)) bw_flags |= IEEE80211_CHAN_NO_80MHZ; - if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(160)) + if (max_bandwidth_khz < MHZ_TO_KHZ(160)) bw_flags |= IEEE80211_CHAN_NO_160MHZ; if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && @@ -977,6 +1083,14 @@ static void handle_channel(struct wiphy *wiphy, min_t(int, chan->orig_mag, MBI_TO_DBI(power_rule->max_antenna_gain)); chan->max_reg_power = (int) MBM_TO_DBM(power_rule->max_eirp); + + if (chan->flags & IEEE80211_CHAN_RADAR) { + if (reg_rule->dfs_cac_ms) + chan->dfs_cac_ms = reg_rule->dfs_cac_ms; + else + chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; + } + if (chan->orig_mpwr) { /* * Devices that use REGULATORY_COUNTRY_IE_FOLLOW_POWER @@ -1334,6 +1448,7 @@ static void handle_channel_custom(struct wiphy *wiphy, const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_power_rule *power_rule = NULL; const struct ieee80211_freq_range *freq_range = NULL; + u32 max_bandwidth_khz; reg_rule = freq_reg_info_regd(wiphy, MHZ_TO_KHZ(chan->center_freq), regd); @@ -1346,16 +1461,21 @@ static void handle_channel_custom(struct wiphy *wiphy, return; } - chan_reg_rule_print_dbg(chan, reg_rule); + chan_reg_rule_print_dbg(regd, chan, reg_rule); power_rule = ®_rule->power_rule; freq_range = ®_rule->freq_range; - if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(40)) + max_bandwidth_khz = freq_range->max_bandwidth_khz; + /* Check if auto calculation requested */ + if (reg_rule->flags & NL80211_RRF_AUTO_BW) + max_bandwidth_khz = reg_get_max_bandwidth(regd, reg_rule); + + if (max_bandwidth_khz < MHZ_TO_KHZ(40)) bw_flags = IEEE80211_CHAN_NO_HT40; - if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(80)) + if (max_bandwidth_khz < MHZ_TO_KHZ(80)) bw_flags |= IEEE80211_CHAN_NO_80MHZ; - if (freq_range->max_bandwidth_khz < MHZ_TO_KHZ(160)) + if (max_bandwidth_khz < MHZ_TO_KHZ(160)) bw_flags |= IEEE80211_CHAN_NO_160MHZ; chan->flags |= map_regdom_flags(reg_rule->flags) | bw_flags; @@ -1683,17 +1803,9 @@ static void reg_process_hint(struct regulatory_request *reg_request) struct wiphy *wiphy = NULL; enum reg_request_treatment treatment; - if (WARN_ON(!reg_request->alpha2)) - return; - if (reg_request->wiphy_idx != WIPHY_IDX_INVALID) wiphy = wiphy_idx_to_wiphy(reg_request->wiphy_idx); - if (reg_request->initiator == NL80211_REGDOM_SET_BY_DRIVER && !wiphy) { - kfree(reg_request); - return; - } - switch (reg_request->initiator) { case NL80211_REGDOM_SET_BY_CORE: reg_process_hint_core(reg_request); @@ -1703,23 +1815,33 @@ static void reg_process_hint(struct regulatory_request *reg_request) if (treatment == REG_REQ_IGNORE || treatment == REG_REQ_ALREADY_SET) return; - schedule_delayed_work(®_timeout, msecs_to_jiffies(3142)); + queue_delayed_work(system_power_efficient_wq, + ®_timeout, msecs_to_jiffies(3142)); return; case NL80211_REGDOM_SET_BY_DRIVER: + if (!wiphy) + goto out_free; treatment = reg_process_hint_driver(wiphy, reg_request); break; case NL80211_REGDOM_SET_BY_COUNTRY_IE: + if (!wiphy) + goto out_free; treatment = reg_process_hint_country_ie(wiphy, reg_request); break; default: WARN(1, "invalid initiator %d\n", reg_request->initiator); - return; + goto out_free; } /* This is required so that the orig_* parameters are saved */ if (treatment == REG_REQ_ALREADY_SET && wiphy && wiphy->regulatory_flags & REGULATORY_STRICT_REG) wiphy_update_regulatory(wiphy, reg_request->initiator); + + return; + +out_free: + kfree(reg_request); } /* @@ -2147,31 +2269,49 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_freq_range *freq_range = NULL; const struct ieee80211_power_rule *power_rule = NULL; + char bw[32], cac_time[32]; - pr_info(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp)\n"); + pr_info(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n"); for (i = 0; i < rd->n_reg_rules; i++) { reg_rule = &rd->reg_rules[i]; freq_range = ®_rule->freq_range; power_rule = ®_rule->power_rule; + if (reg_rule->flags & NL80211_RRF_AUTO_BW) + snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO", + freq_range->max_bandwidth_khz, + reg_get_max_bandwidth(rd, reg_rule)); + else + snprintf(bw, sizeof(bw), "%d KHz", + freq_range->max_bandwidth_khz); + + if (reg_rule->flags & NL80211_RRF_DFS) + scnprintf(cac_time, sizeof(cac_time), "%u s", + reg_rule->dfs_cac_ms/1000); + else + scnprintf(cac_time, sizeof(cac_time), "N/A"); + + /* * There may not be documentation for max antenna gain * in certain regions */ if (power_rule->max_antenna_gain) - pr_info(" (%d KHz - %d KHz @ %d KHz), (%d mBi, %d mBm)\n", + pr_info(" (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, - freq_range->max_bandwidth_khz, + bw, power_rule->max_antenna_gain, - power_rule->max_eirp); + power_rule->max_eirp, + cac_time); else - pr_info(" (%d KHz - %d KHz @ %d KHz), (N/A, %d mBm)\n", + pr_info(" (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, - freq_range->max_bandwidth_khz, - power_rule->max_eirp); + bw, + power_rule->max_eirp, + cac_time); } } @@ -2244,9 +2384,6 @@ static int reg_set_rd_user(const struct ieee80211_regdomain *rd, { const struct ieee80211_regdomain *intersected_rd = NULL; - if (is_world_regdom(rd->alpha2)) - return -EINVAL; - if (!regdom_changes(rd->alpha2)) return -EALREADY; @@ -2294,7 +2431,8 @@ static int reg_set_rd_driver(const struct ieee80211_regdomain *rd, request_wiphy = wiphy_idx_to_wiphy(driver_request->wiphy_idx); if (!request_wiphy) { - schedule_delayed_work(®_timeout, 0); + queue_delayed_work(system_power_efficient_wq, + ®_timeout, 0); return -ENODEV; } @@ -2354,7 +2492,8 @@ static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd, request_wiphy = wiphy_idx_to_wiphy(country_ie_request->wiphy_idx); if (!request_wiphy) { - schedule_delayed_work(®_timeout, 0); + queue_delayed_work(system_power_efficient_wq, + ®_timeout, 0); return -ENODEV; } @@ -2433,26 +2572,6 @@ int set_regdom(const struct ieee80211_regdomain *rd) return 0; } -int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env) -{ - struct regulatory_request *lr; - u8 alpha2[2]; - bool add = false; - - rcu_read_lock(); - lr = get_last_request(); - if (lr && !lr->processed) { - memcpy(alpha2, lr->alpha2, 2); - add = true; - } - rcu_read_unlock(); - - if (add) - return add_uevent_var(env, "COUNTRY=%c%c", - alpha2[0], alpha2[1]); - return 0; -} - void wiphy_regulatory_register(struct wiphy *wiphy) { struct regulatory_request *lr; @@ -2503,8 +2622,6 @@ int __init regulatory_init(void) if (IS_ERR(reg_pdev)) return PTR_ERR(reg_pdev); - reg_pdev->dev.type = ®_device_type; - spin_lock_init(®_requests_lock); spin_lock_init(®_pending_beacons_lock); diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 02bd8f4b0921..37c180df34b7 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -26,7 +26,6 @@ enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy); int regulatory_hint_user(const char *alpha2, enum nl80211_user_reg_hint_type user_reg_hint_type); -int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env); void wiphy_regulatory_register(struct wiphy *wiphy); void wiphy_regulatory_deregister(struct wiphy *wiphy); @@ -34,6 +33,8 @@ int __init regulatory_init(void); void regulatory_exit(void); int set_regdom(const struct ieee80211_regdomain *rd); +unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd, + const struct ieee80211_reg_rule *rule); bool reg_last_request_cell_base(void); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index d1ed4aebbbb7..7d09a712cb1f 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -659,9 +659,6 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *dev, continue; if (ssidlen && ie[1] != ssidlen) continue; - /* that would be odd ... */ - if (bss->pub.beacon_ies) - continue; if (WARN_ON_ONCE(bss->pub.hidden_beacon_bss)) continue; if (WARN_ON_ONCE(!list_empty(&bss->hidden_list))) @@ -680,7 +677,8 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *dev, /* Returned bss is reference counted and must be cleaned up appropriately. */ static struct cfg80211_internal_bss * cfg80211_bss_update(struct cfg80211_registered_device *dev, - struct cfg80211_internal_bss *tmp) + struct cfg80211_internal_bss *tmp, + bool signal_valid) { struct cfg80211_internal_bss *found = NULL; @@ -765,7 +763,12 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, } found->pub.beacon_interval = tmp->pub.beacon_interval; - found->pub.signal = tmp->pub.signal; + /* + * don't update the signal if beacon was heard on + * adjacent channel. + */ + if (signal_valid) + found->pub.signal = tmp->pub.signal; found->pub.capability = tmp->pub.capability; found->ts = tmp->ts; } else { @@ -869,13 +872,14 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, /* Returned bss is reference counted and must be cleaned up appropriately. */ struct cfg80211_bss* cfg80211_inform_bss_width(struct wiphy *wiphy, - struct ieee80211_channel *channel, + struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, const u8 *bssid, u64 tsf, u16 capability, u16 beacon_interval, const u8 *ie, size_t ielen, s32 signal, gfp_t gfp) { struct cfg80211_bss_ies *ies; + struct ieee80211_channel *channel; struct cfg80211_internal_bss tmp = {}, *res; if (WARN_ON(!wiphy)) @@ -885,7 +889,7 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, (signal < 0 || signal > 100))) return NULL; - channel = cfg80211_get_bss_channel(wiphy, ie, ielen, channel); + channel = cfg80211_get_bss_channel(wiphy, ie, ielen, rx_channel); if (!channel) return NULL; @@ -913,7 +917,8 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, rcu_assign_pointer(tmp.pub.beacon_ies, ies); rcu_assign_pointer(tmp.pub.ies, ies); - res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp); + res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp, + rx_channel == channel); if (!res) return NULL; @@ -929,20 +934,21 @@ EXPORT_SYMBOL(cfg80211_inform_bss_width); /* Returned bss is reference counted and must be cleaned up appropriately. */ struct cfg80211_bss * cfg80211_inform_bss_width_frame(struct wiphy *wiphy, - struct ieee80211_channel *channel, + struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, struct ieee80211_mgmt *mgmt, size_t len, s32 signal, gfp_t gfp) { struct cfg80211_internal_bss tmp = {}, *res; struct cfg80211_bss_ies *ies; + struct ieee80211_channel *channel; size_t ielen = len - offsetof(struct ieee80211_mgmt, u.probe_resp.variable); BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) != offsetof(struct ieee80211_mgmt, u.beacon.variable)); - trace_cfg80211_inform_bss_width_frame(wiphy, channel, scan_width, mgmt, + trace_cfg80211_inform_bss_width_frame(wiphy, rx_channel, scan_width, mgmt, len, signal); if (WARN_ON(!mgmt)) @@ -959,7 +965,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, return NULL; channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable, - ielen, channel); + ielen, rx_channel); if (!channel) return NULL; @@ -983,7 +989,8 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int); tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); - res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp); + res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp, + rx_channel == channel); if (!res) return NULL; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f04d4c32e96e..acdcb4a81817 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -64,7 +64,6 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) int n_channels, err; ASSERT_RTNL(); - ASSERT_RDEV_LOCK(rdev); ASSERT_WDEV_LOCK(wdev); if (rdev->scan_req || rdev->scan_msg) diff --git a/net/wireless/trace.h b/net/wireless/trace.h index fbcc23edee54..aabccf13e07b 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1468,9 +1468,10 @@ TRACE_EVENT(rdev_sched_scan_start, TRACE_EVENT(rdev_tdls_mgmt, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *peer, u8 action_code, u8 dialog_token, - u16 status_code, const u8 *buf, size_t len), + u16 status_code, u32 peer_capability, + const u8 *buf, size_t len), TP_ARGS(wiphy, netdev, peer, action_code, dialog_token, status_code, - buf, len), + peer_capability, buf, len), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY @@ -1478,6 +1479,7 @@ TRACE_EVENT(rdev_tdls_mgmt, __field(u8, action_code) __field(u8, dialog_token) __field(u16, status_code) + __field(u32, peer_capability) __dynamic_array(u8, buf, len) ), TP_fast_assign( @@ -1487,13 +1489,15 @@ TRACE_EVENT(rdev_tdls_mgmt, __entry->action_code = action_code; __entry->dialog_token = dialog_token; __entry->status_code = status_code; + __entry->peer_capability = peer_capability; memcpy(__get_dynamic_array(buf), buf, len); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT ", action_code: %u, " - "dialog_token: %u, status_code: %u, buf: %#.2x ", + "dialog_token: %u, status_code: %u, peer_capability: %u buf: %#.2x ", WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->action_code, __entry->dialog_token, - __entry->status_code, ((u8 *)__get_dynamic_array(buf))[0]) + __entry->status_code, __entry->peer_capability, + ((u8 *)__get_dynamic_array(buf))[0]) ); TRACE_EVENT(rdev_dump_survey, @@ -2278,11 +2282,6 @@ DECLARE_EVENT_CLASS(cfg80211_rx_evt, TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT, NETDEV_PR_ARG, MAC_PR_ARG(addr)) ); -DEFINE_EVENT(cfg80211_rx_evt, cfg80211_ibss_joined, - TP_PROTO(struct net_device *netdev, const u8 *addr), - TP_ARGS(netdev, addr) -); - DEFINE_EVENT(cfg80211_rx_evt, cfg80211_rx_spurious_frame, TP_PROTO(struct net_device *netdev, const u8 *addr), TP_ARGS(netdev, addr) @@ -2293,6 +2292,24 @@ DEFINE_EVENT(cfg80211_rx_evt, cfg80211_rx_unexpected_4addr_frame, TP_ARGS(netdev, addr) ); +TRACE_EVENT(cfg80211_ibss_joined, + TP_PROTO(struct net_device *netdev, const u8 *bssid, + struct ieee80211_channel *channel), + TP_ARGS(netdev, bssid, channel), + TP_STRUCT__entry( + NETDEV_ENTRY + MAC_ENTRY(bssid) + CHAN_ENTRY + ), + TP_fast_assign( + NETDEV_ASSIGN; + MAC_ASSIGN(bssid, bssid); + CHAN_ASSIGN(channel); + ), + TP_printk(NETDEV_PR_FMT ", bssid: " MAC_PR_FMT ", " CHAN_PR_FMT, + NETDEV_PR_ARG, MAC_PR_ARG(bssid), CHAN_PR_ARG) +); + TRACE_EVENT(cfg80211_probe_status, TP_PROTO(struct net_device *netdev, const u8 *addr, u64 cookie, bool acked), diff --git a/net/wireless/util.c b/net/wireless/util.c index d39c37104ae2..e5872ff2c27c 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -11,6 +11,7 @@ #include <net/ip.h> #include <net/dsfield.h> #include <linux/if_vlan.h> +#include <linux/mpls.h> #include "core.h" #include "rdev-ops.h" @@ -717,6 +718,21 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, case htons(ETH_P_IPV6): dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & 0xfc; break; + case htons(ETH_P_MPLS_UC): + case htons(ETH_P_MPLS_MC): { + struct mpls_label mpls_tmp, *mpls; + + mpls = skb_header_pointer(skb, sizeof(struct ethhdr), + sizeof(*mpls), &mpls_tmp); + if (!mpls) + return 0; + + return (ntohl(mpls->entry) & MPLS_LS_TC_MASK) + >> MPLS_LS_TC_SHIFT; + } + case htons(ETH_P_80221): + /* 802.21 is always network control traffic */ + return 7; default: return 0; } @@ -820,7 +836,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) ev->dc.reason, true); break; case EVENT_IBSS_JOINED: - __cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid); + __cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid, + ev->ij.channel); break; } wdev_unlock(wdev); @@ -837,7 +854,6 @@ void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev) struct wireless_dev *wdev; ASSERT_RTNL(); - ASSERT_RDEV_LOCK(rdev); list_for_each_entry(wdev, &rdev->wdev_list, list) cfg80211_process_wdev_events(wdev); @@ -850,7 +866,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, int err; enum nl80211_iftype otype = dev->ieee80211_ptr->iftype; - ASSERT_RDEV_LOCK(rdev); + ASSERT_RTNL(); /* don't support changing VLANs, you just re-create them */ if (otype == NL80211_IFTYPE_AP_VLAN) @@ -885,7 +901,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, switch (otype) { case NL80211_IFTYPE_AP: - cfg80211_stop_ap(rdev, dev); + cfg80211_stop_ap(rdev, dev, true); break; case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, dev, false); @@ -1268,7 +1284,6 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, enum cfg80211_chan_mode chmode; int num_different_channels = 0; int total = 1; - bool radar_required = false; int i, j; ASSERT_RTNL(); @@ -1276,35 +1291,7 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, if (WARN_ON(hweight32(radar_detect) > 1)) return -EINVAL; - switch (iftype) { - case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_MESH_POINT: - case NL80211_IFTYPE_P2P_GO: - case NL80211_IFTYPE_WDS: - /* if the interface could potentially choose a DFS channel, - * then mark DFS as required. - */ - if (!chan) { - if (chanmode != CHAN_MODE_UNDEFINED && radar_detect) - radar_required = true; - break; - } - radar_required = !!(chan->flags & IEEE80211_CHAN_RADAR); - break; - case NL80211_IFTYPE_P2P_CLIENT: - case NL80211_IFTYPE_STATION: - case NL80211_IFTYPE_P2P_DEVICE: - case NL80211_IFTYPE_MONITOR: - break; - case NUM_NL80211_IFTYPES: - case NL80211_IFTYPE_UNSPECIFIED: - default: - return -EINVAL; - } - - if (radar_required && !radar_detect) + if (WARN_ON(iftype >= NUM_NL80211_IFTYPES)) return -EINVAL; /* Always allow software iftypes */ @@ -1356,7 +1343,7 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev, */ mutex_lock_nested(&wdev_iter->mtx, 1); __acquire(wdev_iter->mtx); - cfg80211_get_chan_state(wdev_iter, &ch, &chmode); + cfg80211_get_chan_state(wdev_iter, &ch, &chmode, &radar_detect); wdev_unlock(wdev_iter); switch (chmode) { diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 14c9a2583ba0..86c331a65664 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -21,7 +21,7 @@ int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, const u8 *prev_bssid = NULL; int err, i; - ASSERT_RDEV_LOCK(rdev); + ASSERT_RTNL(); ASSERT_WDEV_LOCK(wdev); if (!netif_running(wdev->netdev)) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 6c7ac016ce3a..85d1d4764612 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -16,6 +16,81 @@ static struct kmem_cache *secpath_cachep __read_mostly; +static DEFINE_SPINLOCK(xfrm_input_afinfo_lock); +static struct xfrm_input_afinfo __rcu *xfrm_input_afinfo[NPROTO]; + +int xfrm_input_register_afinfo(struct xfrm_input_afinfo *afinfo) +{ + int err = 0; + + if (unlikely(afinfo == NULL)) + return -EINVAL; + if (unlikely(afinfo->family >= NPROTO)) + return -EAFNOSUPPORT; + spin_lock_bh(&xfrm_input_afinfo_lock); + if (unlikely(xfrm_input_afinfo[afinfo->family] != NULL)) + err = -ENOBUFS; + else + rcu_assign_pointer(xfrm_input_afinfo[afinfo->family], afinfo); + spin_unlock_bh(&xfrm_input_afinfo_lock); + return err; +} +EXPORT_SYMBOL(xfrm_input_register_afinfo); + +int xfrm_input_unregister_afinfo(struct xfrm_input_afinfo *afinfo) +{ + int err = 0; + + if (unlikely(afinfo == NULL)) + return -EINVAL; + if (unlikely(afinfo->family >= NPROTO)) + return -EAFNOSUPPORT; + spin_lock_bh(&xfrm_input_afinfo_lock); + if (likely(xfrm_input_afinfo[afinfo->family] != NULL)) { + if (unlikely(xfrm_input_afinfo[afinfo->family] != afinfo)) + err = -EINVAL; + else + RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->family], NULL); + } + spin_unlock_bh(&xfrm_input_afinfo_lock); + synchronize_rcu(); + return err; +} +EXPORT_SYMBOL(xfrm_input_unregister_afinfo); + +static struct xfrm_input_afinfo *xfrm_input_get_afinfo(unsigned int family) +{ + struct xfrm_input_afinfo *afinfo; + + if (unlikely(family >= NPROTO)) + return NULL; + rcu_read_lock(); + afinfo = rcu_dereference(xfrm_input_afinfo[family]); + if (unlikely(!afinfo)) + rcu_read_unlock(); + return afinfo; +} + +static void xfrm_input_put_afinfo(struct xfrm_input_afinfo *afinfo) +{ + rcu_read_unlock(); +} + +static int xfrm_rcv_cb(struct sk_buff *skb, unsigned int family, u8 protocol, + int err) +{ + int ret; + struct xfrm_input_afinfo *afinfo = xfrm_input_get_afinfo(family); + + if (!afinfo) + return -EAFNOSUPPORT; + + ret = afinfo->callback(skb, protocol, err); + xfrm_input_put_afinfo(afinfo); + + return ret; +} + void __secpath_destroy(struct sec_path *sp) { int i; @@ -108,7 +183,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) int err; __be32 seq; __be32 seq_hi; - struct xfrm_state *x; + struct xfrm_state *x = NULL; xfrm_address_t *daddr; struct xfrm_mode *inner_mode; unsigned int family; @@ -120,9 +195,14 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) async = 1; x = xfrm_input_state(skb); seq = XFRM_SKB_CB(skb)->seq.input.low; + family = x->outer_mode->afinfo->family; goto resume; } + daddr = (xfrm_address_t *)(skb_network_header(skb) + + XFRM_SPI_SKB_CB(skb)->daddroff); + family = XFRM_SPI_SKB_CB(skb)->family; + /* Allocate new secpath or COW existing one. */ if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) { struct sec_path *sp; @@ -137,10 +217,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp = sp; } - daddr = (xfrm_address_t *)(skb_network_header(skb) + - XFRM_SPI_SKB_CB(skb)->daddroff); - family = XFRM_SPI_SKB_CB(skb)->family; - seq = 0; if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); @@ -162,6 +238,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp->xvec[skb->sp->len++] = x; + if (xfrm_tunnel_check(skb, x, family)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); + goto drop; + } + spin_lock(&x->lock); if (unlikely(x->km.state == XFRM_STATE_ACQ)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); @@ -201,7 +282,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) if (nexthdr == -EINPROGRESS) return 0; - resume: spin_lock(&x->lock); if (nexthdr <= 0) { @@ -263,6 +343,10 @@ resume: } } while (!err); + err = xfrm_rcv_cb(skb, family, x->type->proto, 0); + if (err) + goto drop; + nf_reset(skb); if (decaps) { @@ -276,6 +360,7 @@ resume: drop_unlock: spin_unlock(&x->lock); drop: + xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1); kfree_skb(skb); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 1d5c7bf29938..f02f511b7107 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -39,8 +39,6 @@ #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) #define XFRM_MAX_QUEUE_LEN 100 -static struct dst_entry *xfrm_policy_sk_bundles; - static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO] __read_mostly; @@ -661,7 +659,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) hlist_add_head(&policy->bydst, chain); xfrm_pol_hold(policy); net->xfrm.policy_count[dir]++; - atomic_inc(&flow_cache_genid); + atomic_inc(&net->xfrm.flow_cache_genid); /* After previous checking, family can either be AF_INET or AF_INET6 */ if (policy->family == AF_INET) @@ -2109,13 +2107,6 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, goto no_transform; } - dst_hold(&xdst->u.dst); - - spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - xdst->u.dst.next = xfrm_policy_sk_bundles; - xfrm_policy_sk_bundles = &xdst->u.dst; - spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - route = xdst->route; } } @@ -2549,33 +2540,15 @@ static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) return dst; } -static void __xfrm_garbage_collect(struct net *net) -{ - struct dst_entry *head, *next; - - spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - head = xfrm_policy_sk_bundles; - xfrm_policy_sk_bundles = NULL; - spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - - while (head) { - next = head->next; - dst_free(head); - head = next; - } -} - void xfrm_garbage_collect(struct net *net) { - flow_cache_flush(); - __xfrm_garbage_collect(net); + flow_cache_flush(net); } EXPORT_SYMBOL(xfrm_garbage_collect); static void xfrm_garbage_collect_deferred(struct net *net) { - flow_cache_flush_deferred(); - __xfrm_garbage_collect(net); + flow_cache_flush_deferred(net); } static void xfrm_init_pmtu(struct dst_entry *dst) @@ -2940,15 +2913,19 @@ static int __net_init xfrm_net_init(struct net *net) rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; + rv = flow_cache_init(net); + if (rv < 0) + goto out; /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); rwlock_init(&net->xfrm.xfrm_policy_lock); - spin_lock_init(&net->xfrm.xfrm_policy_sk_bundle_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); return 0; +out: + xfrm_sysctl_fini(net); out_sysctl: xfrm_policy_fini(net); out_policy: @@ -2961,6 +2938,7 @@ out_statistics: static void __net_exit xfrm_net_exit(struct net *net) { + flow_cache_fini(net); xfrm_sysctl_fini(net); xfrm_policy_fini(net); xfrm_state_fini(net); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 40f1b3e92e78..8e9c781a6bba 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -161,6 +161,7 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); +bool km_is_alive(const struct km_event *c); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); static DEFINE_SPINLOCK(xfrm_type_lock); @@ -788,6 +789,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; unsigned short encap_family = tmpl->encap_family; + struct km_event c; to_put = NULL; @@ -832,6 +834,17 @@ found: error = -EEXIST; goto out; } + + c.net = net; + /* If the KMs have no listeners (yet...), avoid allocating an SA + * for each and every packet - garbage collection might not + * handle the flood. + */ + if (!km_is_alive(&c)) { + error = -ESRCH; + goto out; + } + x = xfrm_state_alloc(net); if (x == NULL) { error = -ENOMEM; @@ -1135,10 +1148,9 @@ out: EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE -static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) +static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig) { struct net *net = xs_net(orig); - int err = -ENOMEM; struct xfrm_state *x = xfrm_state_alloc(net); if (!x) goto out; @@ -1192,15 +1204,13 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) } if (orig->replay_esn) { - err = xfrm_replay_clone(x, orig); - if (err) + if (xfrm_replay_clone(x, orig)) goto error; } memcpy(&x->mark, &orig->mark, sizeof(x->mark)); - err = xfrm_init_state(x); - if (err) + if (xfrm_init_state(x) < 0) goto error; x->props.flags = orig->props.flags; @@ -1218,8 +1228,6 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) error: xfrm_state_put(x); out: - if (errp) - *errp = err; return NULL; } @@ -1274,9 +1282,8 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m) { struct xfrm_state *xc; - int err; - xc = xfrm_state_clone(x, &err); + xc = xfrm_state_clone(x); if (!xc) return NULL; @@ -1289,7 +1296,7 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, state is to be updated as it is a part of triplet */ xfrm_state_insert(xc); } else { - if ((err = xfrm_state_add(xc)) < 0) + if (xfrm_state_add(xc) < 0) goto error; } @@ -1601,6 +1608,23 @@ unlock: } EXPORT_SYMBOL(xfrm_alloc_spi); +static bool __xfrm_state_filter_match(struct xfrm_state *x, + struct xfrm_address_filter *filter) +{ + if (filter) { + if ((filter->family == AF_INET || + filter->family == AF_INET6) && + x->props.family != filter->family) + return false; + + return addr_match(&x->props.saddr, &filter->saddr, + filter->splen) && + addr_match(&x->id.daddr, &filter->daddr, + filter->dplen); + } + return true; +} + int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *data) @@ -1623,6 +1647,8 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, state = container_of(x, struct xfrm_state, km); if (!xfrm_id_proto_match(state->id.proto, walk->proto)) continue; + if (!__xfrm_state_filter_match(state, walk->filter)) + continue; err = func(state, walk->seq, data); if (err) { list_move_tail(&walk->all, &x->all); @@ -1641,17 +1667,21 @@ out: } EXPORT_SYMBOL(xfrm_state_walk); -void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto) +void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, + struct xfrm_address_filter *filter) { INIT_LIST_HEAD(&walk->all); walk->proto = proto; walk->state = XFRM_STATE_DEAD; walk->seq = 0; + walk->filter = filter; } EXPORT_SYMBOL(xfrm_state_walk_init); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net) { + kfree(walk->filter); + if (list_empty(&walk->all)) return; @@ -1804,6 +1834,24 @@ int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address } EXPORT_SYMBOL(km_report); +bool km_is_alive(const struct km_event *c) +{ + struct xfrm_mgr *km; + bool is_alive = false; + + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { + if (km->is_alive && km->is_alive(c)) { + is_alive = true; + break; + } + } + rcu_read_unlock(); + + return is_alive; +} +EXPORT_SYMBOL(km_is_alive); + int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen) { int err; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 2f7ddc3a59b4..8f131c10a6f3 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -137,7 +137,8 @@ static inline int verify_replay(struct xfrm_usersa_info *p, if (!rt) return 0; - if (p->id.proto != IPPROTO_ESP) + /* As only ESP and AH support ESN feature. */ + if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH)) return -EINVAL; if (p->replay_window != 0) @@ -881,6 +882,7 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb) return 0; } +static const struct nla_policy xfrma_policy[XFRMA_MAX+1]; static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -896,8 +898,31 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) info.nlmsg_flags = NLM_F_MULTI; if (!cb->args[0]) { + struct nlattr *attrs[XFRMA_MAX+1]; + struct xfrm_address_filter *filter = NULL; + u8 proto = 0; + int err; + cb->args[0] = 1; - xfrm_state_walk_init(walk, 0); + + err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX, + xfrma_policy); + if (err < 0) + return err; + + if (attrs[XFRMA_ADDRESS_FILTER]) { + filter = kmalloc(sizeof(*filter), GFP_KERNEL); + if (filter == NULL) + return -ENOMEM; + + memcpy(filter, nla_data(attrs[XFRMA_ADDRESS_FILTER]), + sizeof(*filter)); + } + + if (attrs[XFRMA_PROTO]) + proto = nla_get_u8(attrs[XFRMA_PROTO]); + + xfrm_state_walk_init(walk, proto, filter); } (void) xfrm_state_walk(net, walk, dump_one_state, &info); @@ -2303,6 +2328,8 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_TFCPAD] = { .type = NLA_U32 }, [XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) }, [XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 }, + [XFRMA_PROTO] = { .type = NLA_U8 }, + [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, }; static const struct xfrm_link { @@ -2976,6 +3003,11 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MAPPING, GFP_ATOMIC); } +static bool xfrm_is_alive(const struct km_event *c) +{ + return (bool)xfrm_acquire_is_on(c->net); +} + static struct xfrm_mgr netlink_mgr = { .id = "netlink", .notify = xfrm_send_state_notify, @@ -2985,6 +3017,7 @@ static struct xfrm_mgr netlink_mgr = { .report = xfrm_send_report, .migrate = xfrm_send_migrate, .new_mapping = xfrm_send_mapping, + .is_alive = xfrm_is_alive, }; static int __net_init xfrm_user_net_init(struct net *net) |