diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-06 18:39:49 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-06 18:39:49 -0700 |
| commit | 1c8c5a9d38f607c0b6fd12c91cbe1a4418762a21 (patch) | |
| tree | dcc97181d4d187252e0cc8fdf29d9b365fa3ffd0 /net | |
| parent | 285767604576148fc1be7fcd112e4a90eb0d6ad2 (diff) | |
| parent | 7170e6045a6a8b33f4fa5753589dc77b16198e2d (diff) | |
| download | linux-0-day-1c8c5a9d38f607c0b6fd12c91cbe1a4418762a21.tar.gz linux-0-day-1c8c5a9d38f607c0b6fd12c91cbe1a4418762a21.tar.xz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Add Maglev hashing scheduler to IPVS, from Inju Song.
2) Lots of new TC subsystem tests from Roman Mashak.
3) Add TCP zero copy receive and fix delayed acks and autotuning with
SO_RCVLOWAT, from Eric Dumazet.
4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
Brouer.
5) Add ttl inherit support to vxlan, from Hangbin Liu.
6) Properly separate ipv6 routes into their logically independant
components. fib6_info for the routing table, and fib6_nh for sets of
nexthops, which thus can be shared. From David Ahern.
7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
messages from XDP programs. From Nikita V. Shirokov.
8) Lots of long overdue cleanups to the r8169 driver, from Heiner
Kallweit.
9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.
10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.
11) Plumb extack down into fib_rules, from Roopa Prabhu.
12) Add Flower classifier offload support to igb, from Vinicius Costa
Gomes.
13) Add UDP GSO support, from Willem de Bruijn.
14) Add documentation for eBPF helpers, from Quentin Monnet.
15) Add TLS tx offload to mlx5, from Ilya Lesokhin.
16) Allow applications to be given the number of bytes available to read
on a socket via a control message returned from recvmsg(), from
Soheil Hassas Yeganeh.
17) Add x86_32 eBPF JIT compiler, from Wang YanQing.
18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
From Björn Töpel.
19) Remove indirect load support from all of the BPF JITs and handle
these operations in the verifier by translating them into native BPF
instead. From Daniel Borkmann.
20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.
21) Allow XDP programs to do lookups in the main kernel routing tables
for forwarding. From David Ahern.
22) Allow drivers to store hardware state into an ELF section of kernel
dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.
23) Various RACK and loss detection improvements in TCP, from Yuchung
Cheng.
24) Add TCP SACK compression, from Eric Dumazet.
25) Add User Mode Helper support and basic bpfilter infrastructure, from
Alexei Starovoitov.
26) Support ports and protocol values in RTM_GETROUTE, from Roopa
Prabhu.
27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
Brouer.
28) Add lots of forwarding selftests, from Petr Machata.
29) Add generic network device failover driver, from Sridhar Samudrala.
* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
strparser: Add __strp_unpause and use it in ktls.
rxrpc: Fix terminal retransmission connection ID to include the channel
net: hns3: Optimize PF CMDQ interrupt switching process
net: hns3: Fix for VF mailbox receiving unknown message
net: hns3: Fix for VF mailbox cannot receiving PF response
bnx2x: use the right constant
Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
enic: fix UDP rss bits
netdev-FAQ: clarify DaveM's position for stable backports
rtnetlink: validate attributes in do_setlink()
mlxsw: Add extack messages for port_{un, }split failures
netdevsim: Add extack error message for devlink reload
devlink: Add extack to reload and port_{un, }split operations
net: metrics: add proper netlink validation
ipmr: fix error path when ipmr_new_table fails
ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
net: hns3: remove unused hclgevf_cfg_func_mta_filter
netfilter: provide udp*_lib_lookup for nf_tproxy
qed*: Utilize FW 8.37.2.0
...
Diffstat (limited to 'net')
332 files changed, 20336 insertions, 8128 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 5505ee6ebdbe6..73a65789271ba 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -118,17 +118,21 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) } int vlan_check_real_dev(struct net_device *real_dev, - __be16 protocol, u16 vlan_id) + __be16 protocol, u16 vlan_id, + struct netlink_ext_ack *extack) { const char *name = real_dev->name; if (real_dev->features & NETIF_F_VLAN_CHALLENGED) { pr_info("VLANs not supported on %s\n", name); + NL_SET_ERR_MSG_MOD(extack, "VLANs not supported on device"); return -EOPNOTSUPP; } - if (vlan_find_dev(real_dev, protocol, vlan_id) != NULL) + if (vlan_find_dev(real_dev, protocol, vlan_id) != NULL) { + NL_SET_ERR_MSG_MOD(extack, "VLAN device already exists"); return -EEXIST; + } return 0; } @@ -215,7 +219,8 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) if (vlan_id >= VLAN_VID_MASK) return -ERANGE; - err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id); + err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id, + NULL); if (err < 0) return err; diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index e23aac3e4d377..44df1c3df02d3 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -109,7 +109,8 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask); void vlan_dev_get_realdev_name(const struct net_device *dev, char *result); int vlan_check_real_dev(struct net_device *real_dev, - __be16 protocol, u16 vlan_id); + __be16 protocol, u16 vlan_id, + struct netlink_ext_ack *extack); void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 236452ebbd9ea..546af0e73ac34 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -215,7 +215,9 @@ int vlan_dev_set_egress_priority(const struct net_device *dev, return 0; } -/* Flags are defined in the vlan_flags enum in include/linux/if_vlan.h file. */ +/* Flags are defined in the vlan_flags enum in + * include/uapi/linux/if_vlan.h file. + */ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 6689c0b272a7d..9b60c1e399e27 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -47,14 +47,20 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[], int err; if (tb[IFLA_ADDRESS]) { - if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) + if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { + NL_SET_ERR_MSG_MOD(extack, "Invalid link address"); return -EINVAL; - if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) + } + if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { + NL_SET_ERR_MSG_MOD(extack, "Invalid link address"); return -EADDRNOTAVAIL; + } } - if (!data) + if (!data) { + NL_SET_ERR_MSG_MOD(extack, "VLAN properties not specified"); return -EINVAL; + } if (data[IFLA_VLAN_PROTOCOL]) { switch (nla_get_be16(data[IFLA_VLAN_PROTOCOL])) { @@ -62,29 +68,38 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[], case htons(ETH_P_8021AD): break; default: + NL_SET_ERR_MSG_MOD(extack, "Invalid VLAN protocol"); return -EPROTONOSUPPORT; } } if (data[IFLA_VLAN_ID]) { id = nla_get_u16(data[IFLA_VLAN_ID]); - if (id >= VLAN_VID_MASK) + if (id >= VLAN_VID_MASK) { + NL_SET_ERR_MSG_MOD(extack, "Invalid VLAN id"); return -ERANGE; + } } if (data[IFLA_VLAN_FLAGS]) { flags = nla_data(data[IFLA_VLAN_FLAGS]); if ((flags->flags & flags->mask) & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | - VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP)) + VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid VLAN flags"); return -EINVAL; + } } err = vlan_validate_qos_map(data[IFLA_VLAN_INGRESS_QOS]); - if (err < 0) + if (err < 0) { + NL_SET_ERR_MSG_MOD(extack, "Invalid ingress QOS map"); return err; + } err = vlan_validate_qos_map(data[IFLA_VLAN_EGRESS_QOS]); - if (err < 0) + if (err < 0) { + NL_SET_ERR_MSG_MOD(extack, "Invalid egress QOS map"); return err; + } return 0; } @@ -126,14 +141,21 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, __be16 proto; int err; - if (!data[IFLA_VLAN_ID]) + if (!data[IFLA_VLAN_ID]) { + NL_SET_ERR_MSG_MOD(extack, "VLAN id not specified"); return -EINVAL; + } - if (!tb[IFLA_LINK]) + if (!tb[IFLA_LINK]) { + NL_SET_ERR_MSG_MOD(extack, "link not specified"); return -EINVAL; + } + real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); - if (!real_dev) + if (!real_dev) { + NL_SET_ERR_MSG_MOD(extack, "link does not exist"); return -ENODEV; + } if (data[IFLA_VLAN_PROTOCOL]) proto = nla_get_be16(data[IFLA_VLAN_PROTOCOL]); @@ -146,7 +168,8 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, dev->priv_flags |= (real_dev->priv_flags & IFF_XMIT_DST_RELEASE); vlan->flags = VLAN_FLAG_REORDER_HDR; - err = vlan_check_real_dev(real_dev, vlan->vlan_proto, vlan->vlan_id); + err = vlan_check_real_dev(real_dev, vlan->vlan_proto, vlan->vlan_id, + extack); if (err < 0) return err; diff --git a/net/9p/mod.c b/net/9p/mod.c index 6ab36aea77275..eb9777f057556 100644 --- a/net/9p/mod.c +++ b/net/9p/mod.c @@ -104,7 +104,7 @@ EXPORT_SYMBOL(v9fs_unregister_trans); /** * v9fs_get_trans_by_name - get transport with the matching name - * @name: string identifying transport + * @s: string identifying transport * */ struct p9_trans_module *v9fs_get_trans_by_name(char *s) diff --git a/net/Kconfig b/net/Kconfig index 0428f12c25c2f..f738a6f276655 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -59,6 +59,7 @@ source "net/tls/Kconfig" source "net/xfrm/Kconfig" source "net/iucv/Kconfig" source "net/smc/Kconfig" +source "net/xdp/Kconfig" config INET bool "TCP/IP networking" @@ -201,6 +202,8 @@ source "net/bridge/netfilter/Kconfig" endif +source "net/bpfilter/Kconfig" + source "net/dccp/Kconfig" source "net/sctp/Kconfig" source "net/rds/Kconfig" @@ -407,6 +410,9 @@ config GRO_CELLS bool default n +config SOCK_VALIDATE_XMIT + bool + config NET_DEVLINK tristate "Network physical/parent device Netlink interface" help @@ -423,6 +429,22 @@ config MAY_USE_DEVLINK on MAY_USE_DEVLINK to ensure they do not cause link errors when devlink is a loadable module and the driver using it is built-in. +config PAGE_POOL + bool + +config FAILOVER + tristate "Generic failover module" + help + The failover module provides a generic interface for paravirtual + drivers to register a netdev and a set of ops with a failover + instance. The ops are used as event handlers that get called to + handle netdev register/unregister/link change/name change events + on slave pci ethernet devices with the same mac address as the + failover netdev. This enables paravirtual drivers to use a + VF as an accelerated low latency datapath. It also allows live + migration of VMs with direct attached VFs by failing over to the + paravirtual datapath when the VF is unplugged. + endif # if NET # Used by archs to tell that they support BPF JIT compiler plus which flavour. diff --git a/net/Makefile b/net/Makefile index a6147c61b1740..13ec0d5415c74 100644 --- a/net/Makefile +++ b/net/Makefile @@ -20,6 +20,11 @@ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ obj-$(CONFIG_UNIX) += unix/ obj-$(CONFIG_NET) += ipv6/ +ifneq ($(CC_CAN_LINK),y) +$(warning CC cannot link executables. Skipping bpfilter.) +else +obj-$(CONFIG_BPFILTER) += bpfilter/ +endif obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ @@ -85,3 +90,4 @@ obj-y += l3mdev/ endif obj-$(CONFIG_QRTR) += qrtr/ obj-$(CONFIG_NET_NCSI) += ncsi/ +obj-$(CONFIG_XDP_SOCKETS) += xdp/ diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index e4e2e02b73800..de8034d806235 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -35,7 +35,7 @@ config BATMAN_ADV config BATMAN_ADV_BATMAN_V bool "B.A.T.M.A.N. V protocol (experimental)" depends on BATMAN_ADV && !(CFG80211=m && BATMAN_ADV=y) - default n + default y help This option enables the B.A.T.M.A.N. V protocol, the successor of the currently used B.A.T.M.A.N. IV protocol. The main @@ -94,13 +94,13 @@ config BATMAN_ADV_DEBUGFS bool "batman-adv debugfs entries" depends on BATMAN_ADV depends on DEBUG_FS - default y + default n help Enable this to export routing related debug tables via debugfs. The information for each soft-interface and used hard-interface can be found under batman_adv/ - If unsure, say Y. + If unsure, say N. config BATMAN_ADV_DEBUG bool "B.A.T.M.A.N. debugging" diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 28687493599f5..71c20c1d40028 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -127,7 +127,20 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) rtnl_lock(); ret = __ethtool_get_link_ksettings(hard_iface->net_dev, &link_settings); rtnl_unlock(); - if (ret == 0) { + + /* Virtual interface drivers such as tun / tap interfaces, VLAN, etc + * tend to initialize the interface throughput with some value for the + * sake of having a throughput number to export via ethtool. This + * exported throughput leaves batman-adv to conclude the interface + * throughput is genuine (reflecting reality), thus no measurements + * are necessary. + * + * Based on the observation that those interface types also tend to set + * the link auto-negotiation to 'off', batman-adv shall check this + * setting to differentiate between genuine link throughput information + * and placeholders installed by virtual interfaces. + */ + if (ret == 0 && link_settings.base.autoneg == AUTONEG_ENABLE) { /* link characteristics might change over time */ if (link_settings.base.duplex == DUPLEX_FULL) hard_iface->bat_v.flags |= BATADV_FULL_DUPLEX; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 057a28a9fe880..8da3c93361118 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -25,7 +25,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2018.1" +#define BATADV_SOURCE_VERSION "2018.2" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index a35f597e8c8bf..86725d792e155 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -815,9 +815,6 @@ static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv, 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, @@ -1183,33 +1180,23 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv, { bool orig_mcast_enabled = !(flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND); u8 mcast_flags = BATADV_NO_FLAGS; - bool orig_initialized; if (orig_mcast_enabled && tvlv_value && tvlv_value_len >= sizeof(mcast_flags)) mcast_flags = *(u8 *)tvlv_value; + if (!orig_mcast_enabled) { + mcast_flags |= BATADV_MCAST_WANT_ALL_IPV4; + mcast_flags |= BATADV_MCAST_WANT_ALL_IPV6; + } + spin_lock_bh(&orig->mcast_handler_lock); - orig_initialized = test_bit(BATADV_ORIG_CAPA_HAS_MCAST, - &orig->capa_initialized); - /* 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 && !test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities)) { - if (orig_initialized) - atomic_dec(&bat_priv->mcast.num_disabled); set_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities); - /* If mcast support is being switched off or if this is an initial - * OGM without mcast support then increase the disabled mcast - * node counter. - */ } else if (!orig_mcast_enabled && - (test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities) || - !orig_initialized)) { - atomic_inc(&bat_priv->mcast.num_disabled); + test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities)) { clear_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities); } @@ -1595,10 +1582,6 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig) spin_lock_bh(&orig->mcast_handler_lock); - if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities) && - test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capa_initialized)) - 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/soft-interface.c b/net/batman-adv/soft-interface.c index edeffcb9f3a24..1485263a348bb 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -188,8 +188,8 @@ static void batadv_interface_set_rx_mode(struct net_device *dev) { } -static int batadv_interface_tx(struct sk_buff *skb, - struct net_device *soft_iface) +static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, + struct net_device *soft_iface) { struct ethhdr *ethhdr; struct batadv_priv *bat_priv = netdev_priv(soft_iface); @@ -796,7 +796,6 @@ static int batadv_softif_init_late(struct net_device *dev) bat_priv->mcast.querier_ipv6.shadowing = false; 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); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 476b052ad9824..360357f83f203 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -215,10 +215,12 @@ struct batadv_hard_iface { struct batadv_hard_iface_bat_v bat_v; #endif +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * @debug_dir: dentry for nc subdir in batman-adv directory in debugfs */ struct dentry *debug_dir; +#endif /** * @neigh_list: list of unique single hop neighbors via this interface @@ -1160,13 +1162,13 @@ struct batadv_priv_dat { */ struct batadv_mcast_querier_state { /** @exists: whether a querier exists in the mesh */ - bool exists; + unsigned char exists:1; /** * @shadowing: if a querier exists, whether it is potentially shadowing * multicast listeners (i.e. querier is behind our own bridge segment) */ - bool shadowing; + unsigned char shadowing:1; }; /** @@ -1207,13 +1209,10 @@ struct batadv_priv_mcast { u8 flags; /** @enabled: whether the multicast tvlv is currently enabled */ - bool enabled; + unsigned char enabled:1; /** @bridged: whether the soft interface has a bridge on top */ - bool bridged; - - /** @num_disabled: number of nodes that have no mcast tvlv */ - atomic_t num_disabled; + unsigned char bridged:1; /** * @num_want_all_unsnoopables: number of nodes wanting unsnoopable IP @@ -1245,10 +1244,12 @@ struct batadv_priv_nc { /** @work: work queue callback item for cleanup */ struct delayed_work work; +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** * @debug_dir: dentry for nc subdir in batman-adv directory in debugfs */ struct dentry *debug_dir; +#endif /** * @min_tq: only consider neighbors for encoding if neigh_tq > min_tq @@ -1392,7 +1393,7 @@ struct batadv_tp_vars { atomic_t dup_acks; /** @fast_recovery: true if in Fast Recovery mode */ - bool fast_recovery; + unsigned char fast_recovery:1; /** @recover: last sent seqno when entering Fast Recovery */ u32 recover; @@ -1601,8 +1602,10 @@ struct batadv_priv { /** @mesh_obj: kobject for sysfs mesh subdirectory */ struct kobject *mesh_obj; +#ifdef CONFIG_BATMAN_ADV_DEBUGFS /** @debug_dir: dentry for debugfs batman-adv subdirectory */ struct dentry *debug_dir; +#endif /** @forw_bat_list: list of aggregated OGMs that will be forwarded */ struct hlist_head forw_bat_list; @@ -2049,10 +2052,10 @@ struct batadv_skb_cb { * @decoded: Marks a skb as decoded, which is checked when searching for * coding opportunities in network-coding.c */ - bool decoded; + unsigned char decoded:1; /** @num_bcasts: Counter for broadcast packet retransmissions */ - unsigned int num_bcasts; + unsigned char num_bcasts; }; /** diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 40d260f2bea5e..1dec337901988 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -76,19 +76,15 @@ static ssize_t dut_mode_write(struct file *file, const char __user *user_buf, { struct hci_dev *hdev = file->private_data; struct sk_buff *skb; - char buf[32]; - size_t buf_size = min(count, (sizeof(buf)-1)); bool enable; + int err; if (!test_bit(HCI_UP, &hdev->flags)) return -ENETDOWN; - if (copy_from_user(buf, user_buf, buf_size)) - return -EFAULT; - - buf[buf_size] = '\0'; - if (strtobool(buf, &enable)) - return -EINVAL; + err = kstrtobool_from_user(user_buf, count, &enable); + if (err) + return err; if (enable == hci_dev_test_flag(hdev, HCI_DUT_MODE)) return -EALREADY; @@ -135,17 +131,12 @@ static ssize_t vendor_diag_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; int err; - if (copy_from_user(buf, user_buf, buf_size)) - return -EFAULT; - - buf[buf_size] = '\0'; - if (strtobool(buf, &enable)) - return -EINVAL; + err = kstrtobool_from_user(user_buf, count, &enable); + if (err) + return err; /* When the diagnostic flags are not persistent and the transport * is not active or in user channel operation, then there is no need @@ -3422,6 +3413,37 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, return 0; } +int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param) +{ + struct sk_buff *skb; + + if (hci_opcode_ogf(opcode) != 0x3f) { + /* A controller receiving a command shall respond with either + * a Command Status Event or a Command Complete Event. + * Therefore, all standard HCI commands must be sent via the + * standard API, using hci_send_cmd or hci_cmd_sync helpers. + * Some vendors do not comply with this rule for vendor-specific + * commands and do not return any event. We want to support + * unresponded commands for such cases only. + */ + bt_dev_err(hdev, "unresponded command not supported"); + return -EINVAL; + } + + skb = hci_prepare_cmd(hdev, opcode, plen, param); + if (!skb) { + bt_dev_err(hdev, "no memory for command (opcode 0x%4.4x)", + opcode); + return -ENOMEM; + } + + hci_send_frame(hdev, skb); + + return 0; +} +EXPORT_SYMBOL(__hci_cmd_send); + /* Get data from the previously sent command */ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) { diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 418b76e557b0a..0d8ab5b3c177d 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -47,19 +47,15 @@ static ssize_t __name ## _write(struct file *file, \ 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; \ + int err; \ \ 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; \ + err = kstrtobool_from_user(user_buf, count, &enable); \ + if (err) \ + return err; \ \ if (enable == test_bit(__quirk, &hdev->quirks)) \ return -EALREADY; \ @@ -658,19 +654,15 @@ static ssize_t force_static_address_write(struct file *file, 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; + int err; 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; + err = kstrtobool_from_user(user_buf, count, &enable); + if (err) + return err; if (enable == hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR)) return -EALREADY; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 139707cd9d352..235b5aaab23de 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -4942,10 +4942,14 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) struct hci_ev_le_advertising_info *ev = ptr; s8 rssi; - rssi = ev->data[ev->length]; - process_adv_report(hdev, ev->evt_type, &ev->bdaddr, - ev->bdaddr_type, NULL, 0, rssi, - ev->data, ev->length); + if (ev->length <= HCI_MAX_AD_LENGTH) { + rssi = ev->data[ev->length]; + process_adv_report(hdev, ev->evt_type, &ev->bdaddr, + ev->bdaddr_type, NULL, 0, rssi, + ev->data, ev->length); + } else { + bt_dev_err(hdev, "Dropping invalid advertising data"); + } ptr += sizeof(*ev) + ev->length + 1; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 66c0781773dff..e44d34734834a 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -122,7 +122,6 @@ void hci_req_sync_cancel(struct hci_dev *hdev, int err) struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param, u8 event, u32 timeout) { - DECLARE_WAITQUEUE(wait, current); struct hci_request req; struct sk_buff *skb; int err = 0; @@ -135,21 +134,14 @@ struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, hdev->req_status = HCI_REQ_PEND; - add_wait_queue(&hdev->req_wait_q, &wait); - set_current_state(TASK_INTERRUPTIBLE); - err = hci_req_run_skb(&req, hci_req_sync_complete); - if (err < 0) { - remove_wait_queue(&hdev->req_wait_q, &wait); - set_current_state(TASK_RUNNING); + if (err < 0) return ERR_PTR(err); - } - schedule_timeout(timeout); + err = wait_event_interruptible_timeout(hdev->req_wait_q, + hdev->req_status != HCI_REQ_PEND, timeout); - remove_wait_queue(&hdev->req_wait_q, &wait); - - if (signal_pending(current)) + if (err == -ERESTARTSYS) return ERR_PTR(-EINTR); switch (hdev->req_status) { @@ -197,7 +189,6 @@ int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req, unsigned long opt, u32 timeout, u8 *hci_status) { struct hci_request req; - DECLARE_WAITQUEUE(wait, current); int err = 0; BT_DBG("%s start", hdev->name); @@ -213,16 +204,10 @@ int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req, return err; } - add_wait_queue(&hdev->req_wait_q, &wait); - set_current_state(TASK_INTERRUPTIBLE); - err = hci_req_run_skb(&req, hci_req_sync_complete); if (err < 0) { hdev->req_status = 0; - remove_wait_queue(&hdev->req_wait_q, &wait); - set_current_state(TASK_RUNNING); - /* ENODATA means the HCI request command queue is empty. * This can happen when a request with conditionals doesn't * trigger any commands to be sent. This is normal behavior @@ -240,11 +225,10 @@ int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req, return err; } - schedule_timeout(timeout); - - remove_wait_queue(&hdev->req_wait_q, &wait); + err = wait_event_interruptible_timeout(hdev->req_wait_q, + hdev->req_status != HCI_REQ_PEND, timeout); - if (signal_pending(current)) + if (err == -ERESTARTSYS) return -EINTR; switch (hdev->req_status) { diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index a2ddae2f37d7a..ae91e2d40056b 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -3315,16 +3315,12 @@ static ssize_t force_bredr_smp_write(struct file *file, 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; + int err; - if (copy_from_user(buf, user_buf, buf_size)) - return -EFAULT; - - buf[buf_size] = '\0'; - if (strtobool(buf, &enable)) - return -EINVAL; + err = kstrtobool_from_user(user_buf, count, &enable); + if (err) + return err; if (enable == hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP)) return -EALREADY; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 2ced48662c1fa..68c3578343b4b 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -170,7 +170,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, xdp.rxq = &rxqueue->xdp_rxq; retval = bpf_test_run(prog, &xdp, repeat, &duration); - if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN) + if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN || + xdp.data_end != xdp.data + size) size = xdp.data_end - xdp.data; ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration); kfree(data); diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig new file mode 100644 index 0000000000000..a948b072c28f3 --- /dev/null +++ b/net/bpfilter/Kconfig @@ -0,0 +1,16 @@ +menuconfig BPFILTER + bool "BPF based packet filtering framework (BPFILTER)" + default n + depends on NET && BPF && INET + help + This builds experimental bpfilter framework that is aiming to + provide netfilter compatible functionality via BPF + +if BPFILTER +config BPFILTER_UMH + tristate "bpfilter kernel module with user mode helper" + default m + help + This builds bpfilter kernel module with embedded user mode helper +endif + diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile new file mode 100644 index 0000000000000..aafa72001fcd7 --- /dev/null +++ b/net/bpfilter/Makefile @@ -0,0 +1,32 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the Linux BPFILTER layer. +# + +hostprogs-y := bpfilter_umh +bpfilter_umh-objs := main.o +HOSTCFLAGS += -I. -Itools/include/ -Itools/include/uapi +HOSTCC := $(CC) + +ifeq ($(CONFIG_BPFILTER_UMH), y) +# builtin bpfilter_umh should be compiled with -static +# since rootfs isn't mounted at the time of __init +# function is called and do_execv won't find elf interpreter +HOSTLDFLAGS += -static +endif + +# a bit of elf magic to convert bpfilter_umh binary into a binary blob +# inside bpfilter_umh.o elf file referenced by +# _binary_net_bpfilter_bpfilter_umh_start symbol +# which bpfilter_kern.c passes further into umh blob loader at run-time +quiet_cmd_copy_umh = GEN $@ + cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \ + $(OBJCOPY) -I binary -O $(CONFIG_OUTPUT_FORMAT) \ + -B `$(OBJDUMP) -f $<|grep architecture|cut -d, -f1|cut -d' ' -f2` \ + --rename-section .data=.init.rodata $< $@ + +$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh + $(call cmd,copy_umh) + +obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o +bpfilter-objs += bpfilter_kern.o bpfilter_umh.o diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c new file mode 100644 index 0000000000000..b13d058f8c340 --- /dev/null +++ b/net/bpfilter/bpfilter_kern.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/init.h> +#include <linux/module.h> +#include <linux/umh.h> +#include <linux/bpfilter.h> +#include <linux/sched.h> +#include <linux/sched/signal.h> +#include <linux/fs.h> +#include <linux/file.h> +#include "msgfmt.h" + +#define UMH_start _binary_net_bpfilter_bpfilter_umh_start +#define UMH_end _binary_net_bpfilter_bpfilter_umh_end + +extern char UMH_start; +extern char UMH_end; + +static struct umh_info info; +/* since ip_getsockopt() can run in parallel, serialize access to umh */ +static DEFINE_MUTEX(bpfilter_lock); + +static void shutdown_umh(struct umh_info *info) +{ + struct task_struct *tsk; + + tsk = pid_task(find_vpid(info->pid), PIDTYPE_PID); + if (tsk) + force_sig(SIGKILL, tsk); + fput(info->pipe_to_umh); + fput(info->pipe_from_umh); +} + +static void __stop_umh(void) +{ + if (IS_ENABLED(CONFIG_INET) && + bpfilter_process_sockopt) { + bpfilter_process_sockopt = NULL; + shutdown_umh(&info); + } +} + +static void stop_umh(void) +{ + mutex_lock(&bpfilter_lock); + __stop_umh(); + mutex_unlock(&bpfilter_lock); +} + +static int __bpfilter_process_sockopt(struct sock *sk, int optname, + char __user *optval, + unsigned int optlen, bool is_set) +{ + struct mbox_request req; + struct mbox_reply reply; + loff_t pos; + ssize_t n; + int ret; + + req.is_set = is_set; + req.pid = current->pid; + req.cmd = optname; + req.addr = (long)optval; + req.len = optlen; + mutex_lock(&bpfilter_lock); + n = __kernel_write(info.pipe_to_umh, &req, sizeof(req), &pos); + if (n != sizeof(req)) { + pr_err("write fail %zd\n", n); + __stop_umh(); + ret = -EFAULT; + goto out; + } + pos = 0; + n = kernel_read(info.pipe_from_umh, &reply, sizeof(reply), &pos); + if (n != sizeof(reply)) { + pr_err("read fail %zd\n", n); + __stop_umh(); + ret = -EFAULT; + goto out; + } + ret = reply.status; +out: + mutex_unlock(&bpfilter_lock); + return ret; +} + +static int __init load_umh(void) +{ + int err; + + /* fork usermode process */ + err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info); + if (err) + return err; + pr_info("Loaded bpfilter_umh pid %d\n", info.pid); + + /* health check that usermode process started correctly */ + if (__bpfilter_process_sockopt(NULL, 0, 0, 0, 0) != 0) { + stop_umh(); + return -EFAULT; + } + if (IS_ENABLED(CONFIG_INET)) + bpfilter_process_sockopt = &__bpfilter_process_sockopt; + + return 0; +} + +static void __exit fini_umh(void) +{ + stop_umh(); +} +module_init(load_umh); +module_exit(fini_umh); +MODULE_LICENSE("GPL"); diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c new file mode 100644 index 0000000000000..1317f108df8ae --- /dev/null +++ b/net/bpfilter/main.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <sys/uio.h> +#include <errno.h> +#include <stdio.h> +#include <sys/socket.h> +#include <fcntl.h> +#include <unistd.h> +#include "include/uapi/linux/bpf.h" +#include <asm/unistd.h> +#include "msgfmt.h" + +int debug_fd; + +static int handle_get_cmd(struct mbox_request *cmd) +{ + switch (cmd->cmd) { + case 0: + return 0; + default: + break; + } + return -ENOPROTOOPT; +} + +static int handle_set_cmd(struct mbox_request *cmd) +{ + return -ENOPROTOOPT; +} + +static void loop(void) +{ + while (1) { + struct mbox_request req; + struct mbox_reply reply; + int n; + + n = read(0, &req, sizeof(req)); + if (n != sizeof(req)) { + dprintf(debug_fd, "invalid request %d\n", n); + return; + } + + reply.status = req.is_set ? + handle_set_cmd(&req) : + handle_get_cmd(&req); + + n = write(1, &reply, sizeof(reply)); + if (n != sizeof(reply)) { + dprintf(debug_fd, "reply failed %d\n", n); + return; + } + } +} + +int main(void) +{ + debug_fd = open("/dev/console", 00000002); + dprintf(debug_fd, "Started bpfilter\n"); + loop(); + close(debug_fd); + return 0; +} diff --git a/net/bpfilter/msgfmt.h b/net/bpfilter/msgfmt.h new file mode 100644 index 0000000000000..98d121c629450 --- /dev/null +++ b/net/bpfilter/msgfmt.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NET_BPFILTER_MSGFMT_H +#define _NET_BPFILTER_MSGFMT_H + +struct mbox_request { + __u64 addr; + __u32 len; + __u32 is_set; + __u32 cmd; + __u32 pid; +}; + +struct mbox_reply { + __u32 status; +}; + +#endif diff --git a/net/bridge/br.c b/net/bridge/br.c index 671d13c10f6f4..b0a0b82e2d910 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -34,6 +34,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; + bool notified = false; bool changed_addr; int err; @@ -67,7 +68,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v break; case NETDEV_CHANGE: - br_port_carrier_check(p); + br_port_carrier_check(p, ¬ified); break; case NETDEV_FEAT_CHANGE: @@ -76,8 +77,10 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v case NETDEV_DOWN: spin_lock_bh(&br->lock); - if (br->dev->flags & IFF_UP) + if (br->dev->flags & IFF_UP) { br_stp_disable_port(p); + notified = true; + } spin_unlock_bh(&br->lock); break; @@ -85,6 +88,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v if (netif_running(br->dev) && netif_oper_up(dev)) { spin_lock_bh(&br->lock); br_stp_enable_port(p); + notified = true; spin_unlock_bh(&br->lock); } break; @@ -110,8 +114,8 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v } /* Events that may cause spanning tree to refresh */ - if (event == NETDEV_CHANGEADDR || event == NETDEV_UP || - event == NETDEV_CHANGE || event == NETDEV_DOWN) + if (!notified && (event == NETDEV_CHANGEADDR || event == NETDEV_UP || + event == NETDEV_CHANGE || event == NETDEV_DOWN)) br_ifinfo_notify(RTM_NEWLINK, NULL, p); return NOTIFY_DONE; @@ -141,7 +145,7 @@ static int br_switchdev_event(struct notifier_block *unused, case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, - fdb_info->vid); + fdb_info->vid, false); if (err) { err = notifier_from_errno(err); break; @@ -152,7 +156,7 @@ static int br_switchdev_event(struct notifier_block *unused, case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_del(br, p, fdb_info->addr, - fdb_info->vid); + fdb_info->vid, false); if (err) err = notifier_from_errno(err); break; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index d9e69e4514beb..b19e3104afd6b 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -40,7 +40,7 @@ static struct kmem_cache *br_fdb_cache __read_mostly; static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid); static void fdb_notify(struct net_bridge *br, - const struct net_bridge_fdb_entry *, int); + const struct net_bridge_fdb_entry *, int, bool); int __init br_fdb_init(void) { @@ -121,6 +121,28 @@ static struct net_bridge_fdb_entry *br_fdb_find(struct net_bridge *br, return fdb; } +struct net_device *br_fdb_find_port(const struct net_device *br_dev, + const unsigned char *addr, + __u16 vid) +{ + struct net_bridge_fdb_entry *f; + struct net_device *dev = NULL; + struct net_bridge *br; + + ASSERT_RTNL(); + + if (!netif_is_bridge_master(br_dev)) + return NULL; + + br = netdev_priv(br_dev); + f = br_fdb_find(br, addr, vid); + if (f && f->dst) + dev = f->dst->dev; + + return dev; +} +EXPORT_SYMBOL_GPL(br_fdb_find_port); + struct net_bridge_fdb_entry *br_fdb_find_rcu(struct net_bridge *br, const unsigned char *addr, __u16 vid) @@ -173,7 +195,8 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr) } } -static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) +static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f, + bool swdev_notify) { trace_fdb_delete(br, f); @@ -183,7 +206,7 @@ static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) hlist_del_init_rcu(&f->fdb_node); rhashtable_remove_fast(&br->fdb_hash_tbl, &f->rhnode, br_fdb_rht_params); - fdb_notify(br, f, RTM_DELNEIGH); + fdb_notify(br, f, RTM_DELNEIGH, swdev_notify); call_rcu(&f->rcu, fdb_rcu_free); } @@ -219,7 +242,7 @@ static void fdb_delete_local(struct net_bridge *br, return; } - fdb_delete(br, f); + fdb_delete(br, f, true); } void br_fdb_find_delete_local(struct net_bridge *br, @@ -334,7 +357,7 @@ void br_fdb_cleanup(struct work_struct *work) } else { spin_lock_bh(&br->hash_lock); if (!hlist_unhashed(&f->fdb_node)) - fdb_delete(br, f); + fdb_delete(br, f, true); spin_unlock_bh(&br->hash_lock); } } @@ -354,7 +377,7 @@ void br_fdb_flush(struct net_bridge *br) spin_lock_bh(&br->hash_lock); hlist_for_each_entry_safe(f, tmp, &br->fdb_list, fdb_node) { if (!f->is_static) - fdb_delete(br, f); + fdb_delete(br, f, true); } spin_unlock_bh(&br->hash_lock); } @@ -383,7 +406,7 @@ void br_fdb_delete_by_port(struct net_bridge *br, if (f->is_local) fdb_delete_local(br, p, f); else - fdb_delete(br, f); + fdb_delete(br, f, true); } spin_unlock_bh(&br->hash_lock); } @@ -509,7 +532,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, return 0; br_warn(br, "adding interface %s with same address as a received packet (addr:%pM, vlan:%u)\n", source ? source->dev->name : br->dev->name, addr, vid); - fdb_delete(br, fdb); + fdb_delete(br, fdb, true); } fdb = fdb_create(br, source, addr, vid, 1, 1); @@ -517,7 +540,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, return -ENOMEM; fdb_add_hw_addr(br, addr); - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, true); return 0; } @@ -572,7 +595,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, fdb->added_by_user = 1; if (unlikely(fdb_modified)) { trace_br_fdb_update(br, source, addr, vid, added_by_user); - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, true); } } } else { @@ -583,7 +606,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, fdb->added_by_user = 1; trace_br_fdb_update(br, source, addr, vid, added_by_user); - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, true); } /* else we lose race and someone else inserts * it first, don't bother updating @@ -665,13 +688,15 @@ static inline size_t fdb_nlmsg_size(void) } static void fdb_notify(struct net_bridge *br, - const struct net_bridge_fdb_entry *fdb, int type) + const struct net_bridge_fdb_entry *fdb, int type, + bool swdev_notify) { struct net *net = dev_net(br->dev); struct sk_buff *skb; int err = -ENOBUFS; - br_switchdev_fdb_notify(fdb, type); + if (swdev_notify) + br_switchdev_fdb_notify(fdb, type); skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) @@ -810,7 +835,7 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, fdb->used = jiffies; if (modified) { fdb->updated = jiffies; - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, true); } return 0; @@ -834,7 +859,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, rcu_read_unlock(); local_bh_enable(); } else if (ndm->ndm_flags & NTF_EXT_LEARNED) { - err = br_fdb_external_learn_add(br, p, addr, vid); + err = br_fdb_external_learn_add(br, p, addr, vid, true); } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm->ndm_state, @@ -923,7 +948,7 @@ static int fdb_delete_by_addr_and_port(struct net_bridge *br, if (!fdb || fdb->dst != p) return -ENOENT; - fdb_delete(br, fdb); + fdb_delete(br, fdb, true); return 0; } @@ -1043,7 +1068,8 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) } int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid) + const unsigned char *addr, u16 vid, + bool swdev_notify) { struct net_bridge_fdb_entry *fdb; bool modified = false; @@ -1061,7 +1087,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, goto err_unlock; } fdb->added_by_external_learn = 1; - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } else { fdb->updated = jiffies; @@ -1080,7 +1106,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, } if (modified) - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } err_unlock: @@ -1090,7 +1116,8 @@ err_unlock: } int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid) + const unsigned char *addr, u16 vid, + bool swdev_notify) { struct net_bridge_fdb_entry *fdb; int err = 0; @@ -1099,7 +1126,7 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, fdb = br_fdb_find(br, addr, vid); if (fdb && fdb->added_by_external_learn) - fdb_delete(br, fdb); + fdb_delete(br, fdb, swdev_notify); else err = -ENOENT; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index b4eed113d2ec8..9019f326fe81e 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -30,7 +30,8 @@ static inline int should_deliver(const struct net_bridge_port *p, vg = nbp_vlan_group_rcu(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING && - nbp_switchdev_allowed_egress(p, skb); + nbp_switchdev_allowed_egress(p, skb) && + !br_skb_isolated(p, skb); } int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -274,8 +275,7 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, struct net_bridge_port *port, *lport, *rport; lport = p ? p->port : NULL; - rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) : - NULL; + rport = hlist_entry_safe(rp, struct net_bridge_port, rlist); if ((unsigned long)lport > (unsigned long)rport) { port = lport; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 5bb6681fa91e6..05e42d86882d6 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -64,7 +64,7 @@ static int port_cost(struct net_device *dev) /* Check for port carrier transitions. */ -void br_port_carrier_check(struct net_bridge_port *p) +void br_port_carrier_check(struct net_bridge_port *p, bool *notified) { struct net_device *dev = p->dev; struct net_bridge *br = p->br; @@ -73,16 +73,21 @@ void br_port_carrier_check(struct net_bridge_port *p) netif_running(dev) && netif_oper_up(dev)) p->path_cost = port_cost(dev); + *notified = false; if (!netif_running(br->dev)) return; spin_lock_bh(&br->lock); if (netif_running(dev) && netif_oper_up(dev)) { - if (p->state == BR_STATE_DISABLED) + if (p->state == BR_STATE_DISABLED) { br_stp_enable_port(p); + *notified = true; + } } else { - if (p->state != BR_STATE_DISABLED) + if (p->state != BR_STATE_DISABLED) { br_stp_disable_port(p); + *notified = true; + } } spin_unlock_bh(&br->lock); } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 7f98a7d25866d..72074276c0889 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -114,6 +114,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb goto drop; BR_INPUT_SKB_CB(skb)->brdev = br->dev; + BR_INPUT_SKB_CB(skb)->src_port_isolated = !!(p->flags & BR_ISOLATED); if (IS_ENABLED(CONFIG_INET) && (skb->protocol == htons(ETH_P_ARP) || diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 015f465c514b2..9f5eb05b03737 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -139,6 +139,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -213,7 +214,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, BR_VLAN_TUNNEL)) || nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, - !!(p->flags & BR_NEIGH_SUPPRESS))) + !!(p->flags & BR_NEIGH_SUPPRESS)) || + nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -660,6 +662,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_VLAN_TUNNEL] = { .type = NLA_U8 }, [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, + [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, }; /* Change the state of the port and notify spanning tree */ @@ -810,6 +813,10 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) if (err) return err; + err = br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); + if (err) + return err; + br_port_flags_change(p, old_flags ^ p->flags); return 0; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index a7cb3ece50310..5216a524b5370 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -423,6 +423,7 @@ struct br_input_skb_cb { #endif bool proxyarp_replied; + bool src_port_isolated; #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool vlan_filtered; @@ -553,9 +554,11 @@ int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid); + const unsigned char *addr, u16 vid, + bool swdev_notify); int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid); + const unsigned char *addr, u16 vid, + bool swdev_notify); void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid); @@ -572,8 +575,16 @@ int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb); void br_flood(struct net_bridge *br, struct sk_buff *skb, enum br_pkt_type pkt_type, bool local_rcv, bool local_orig); +/* return true if both source port and dest port are isolated */ +static inline bool br_skb_isolated(const struct net_bridge_port *to, + const struct sk_buff *skb) +{ + return BR_INPUT_SKB_CB(skb)->src_port_isolated && + (to->flags & BR_ISOLATED); +} + /* br_if.c */ -void br_port_carrier_check(struct net_bridge_port *p); +void br_port_carrier_check(struct net_bridge_port *p, bool *notified); int br_add_bridge(struct net *net, const char *name); int br_del_bridge(struct net *net, const char *name); int br_add_if(struct net_bridge *br, struct net_device *dev, @@ -594,11 +605,22 @@ static inline bool br_rx_handler_check_rcu(const struct net_device *dev) return rcu_dereference(dev->rx_handler) == br_handle_frame; } +static inline bool br_rx_handler_check_rtnl(const struct net_device *dev) +{ + return rcu_dereference_rtnl(dev->rx_handler) == br_handle_frame; +} + static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev) { return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL; } +static inline struct net_bridge_port * +br_port_get_check_rtnl(const struct net_device *dev) +{ + return br_rx_handler_check_rtnl(dev) ? br_port_get_rtnl_rcu(dev) : NULL; +} + /* br_ioctl.c */ int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, @@ -1117,6 +1139,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, unsigned long mask); void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type); +int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags); +int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid); static inline void br_switchdev_frame_unmark(struct sk_buff *skb) { @@ -1146,6 +1170,17 @@ static inline int br_switchdev_set_port_flag(struct net_bridge_port *p, return 0; } +static inline int br_switchdev_port_vlan_add(struct net_device *dev, + u16 vid, u16 flags) +{ + return -EOPNOTSUPP; +} + +static inline int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid) +{ + return -EOPNOTSUPP; +} + static inline void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) { diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index ee775f4ff76c2..d77f807420c48 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -102,13 +102,15 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, static void br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac, - u16 vid, struct net_device *dev) + u16 vid, struct net_device *dev, + bool added_by_user) { struct switchdev_notifier_fdb_info info; unsigned long notifier_type; info.addr = mac; info.vid = vid; + info.added_by_user = added_by_user; notifier_type = adding ? SWITCHDEV_FDB_ADD_TO_DEVICE : SWITCHDEV_FDB_DEL_TO_DEVICE; call_switchdev_notifiers(notifier_type, dev, &info.info); } @@ -116,19 +118,46 @@ br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac, void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) { - if (!fdb->added_by_user || !fdb->dst) + if (!fdb->dst) return; switch (type) { case RTM_DELNEIGH: br_switchdev_fdb_call_notifiers(false, fdb->key.addr.addr, fdb->key.vlan_id, - fdb->dst->dev); + fdb->dst->dev, + fdb->added_by_user); break; case RTM_NEWNEIGH: br_switchdev_fdb_call_notifiers(true, fdb->key.addr.addr, fdb->key.vlan_id, - fdb->dst->dev); + fdb->dst->dev, + fdb->added_by_user); break; } } + +int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags) +{ + struct switchdev_obj_port_vlan v = { + .obj.orig_dev = dev, + .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, + .flags = flags, + .vid_begin = vid, + .vid_end = vid, + }; + + return switchdev_port_obj_add(dev, &v.obj); +} + +int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid) +{ + struct switchdev_obj_port_vlan v = { + .obj.orig_dev = dev, + .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, + .vid_begin = vid, + .vid_end = vid, + }; + + return switchdev_port_obj_del(dev, &v.obj); +} diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index fd31ad83ec7b6..f99c5bf5c9062 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -192,6 +192,7 @@ BRPORT_ATTR_FLAG(proxyarp_wifi, BR_PROXYARP_WIFI); BRPORT_ATTR_FLAG(multicast_flood, BR_MCAST_FLOOD); BRPORT_ATTR_FLAG(broadcast_flood, BR_BCAST_FLOOD); BRPORT_ATTR_FLAG(neigh_suppress, BR_NEIGH_SUPPRESS); +BRPORT_ATTR_FLAG(isolated, BR_ISOLATED); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) @@ -243,6 +244,7 @@ static const struct brport_attribute *brport_attrs[] = { &brport_attr_broadcast_flood, &brport_attr_group_fwd_mask, &brport_attr_neigh_suppress, + &brport_attr_isolated, NULL }; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 9896f4975353d..7df269092103c 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -82,19 +82,12 @@ static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, u16 vid, u16 flags) { - struct switchdev_obj_port_vlan v = { - .obj.orig_dev = dev, - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .flags = flags, - .vid_begin = vid, - .vid_end = vid, - }; int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q add. */ - err = switchdev_port_obj_add(dev, &v.obj); + err = br_switchdev_port_vlan_add(dev, vid, flags); if (err == -EOPNOTSUPP) return vlan_vid_add(dev, br->vlan_proto, vid); return err; @@ -130,18 +123,12 @@ static void __vlan_del_list(struct net_bridge_vlan *v) static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, u16 vid) { - struct switchdev_obj_port_vlan v = { - .obj.orig_dev = dev, - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .vid_begin = vid, - .vid_end = vid, - }; int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q del. */ - err = switchdev_port_obj_del(dev, &v.obj); + err = br_switchdev_port_vlan_del(dev, vid); if (err == -EOPNOTSUPP) { vlan_vid_del(dev, br->vlan_proto, vid); return 0; @@ -259,6 +246,10 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags) goto out_filt; v->brvlan = masterv; v->stats = masterv->stats; + } else { + err = br_switchdev_port_vlan_add(dev, v->vid, flags); + if (err && err != -EOPNOTSUPP) + goto out; } /* Add the dev mac and count the vlan only if it's usable */ @@ -294,6 +285,8 @@ out_filt: br_vlan_put_master(masterv); v->brvlan = NULL; } + } else { + br_switchdev_port_vlan_del(dev, v->vid); } goto out; @@ -319,6 +312,11 @@ static int __vlan_del(struct net_bridge_vlan *v) err = __vlan_vid_del(p->dev, p->br, v->vid); if (err) goto out; + } else { + err = br_switchdev_port_vlan_del(v->br->dev, v->vid); + if (err && err != -EOPNOTSUPP) + goto out; + err = 0; } if (br_vlan_should_use(v)) { @@ -564,6 +562,48 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) return false; } +static int br_vlan_add_existing(struct net_bridge *br, + struct net_bridge_vlan_group *vg, + struct net_bridge_vlan *vlan, + u16 flags, bool *changed) +{ + int err; + + err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags); + if (err && err != -EOPNOTSUPP) + return err; + + if (!br_vlan_is_brentry(vlan)) { + /* Trying to change flags of non-existent bridge vlan */ + if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) { + err = -EINVAL; + goto err_flags; + } + /* It was only kept for port vlans, now make it real */ + err = br_fdb_insert(br, NULL, br->dev->dev_addr, + vlan->vid); + if (err) { + br_err(br, "failed to insert local address into bridge forwarding table\n"); + goto err_fdb_insert; + } + + refcount_inc(&vlan->refcnt); + vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; + vg->num_vlans++; + *changed = true; + } + + if (__vlan_add_flags(vlan, flags)) + *changed = true; + + return 0; + +err_fdb_insert: +err_flags: + br_switchdev_port_vlan_del(br->dev, vlan->vid); + return err; +} + /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated @@ -579,28 +619,8 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed) *changed = false; vg = br_vlan_group(br); vlan = br_vlan_find(vg, vid); - if (vlan) { - if (!br_vlan_is_brentry(vlan)) { - /* Trying to change flags of non-existent bridge vlan */ - if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) - return -EINVAL; - /* It was only kept for port vlans, now make it real */ - ret = br_fdb_insert(br, NULL, br->dev->dev_addr, - vlan->vid); - if (ret) { - br_err(br, "failed insert local address into bridge forwarding table\n"); - return ret; - } - refcount_inc(&vlan->refcnt); - vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; - vg->num_vlans++; - *changed = true; - } - if (__vlan_add_flags(vlan, flags)) - *changed = true; - - return 0; - } + if (vlan) + return br_vlan_add_existing(br, vg, vlan, flags, changed); vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); if (!vlan) @@ -1053,13 +1073,6 @@ err_vlan_enabled: int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, bool *changed) { - struct switchdev_obj_port_vlan v = { - .obj.orig_dev = port->dev, - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .flags = flags, - .vid_begin = vid, - .vid_end = vid, - }; struct net_bridge_vlan *vlan; int ret; @@ -1069,7 +1082,7 @@ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, vlan = br_vlan_find(nbp_vlan_group(port), vid); if (vlan) { /* Pass the flags to the hardware bridge */ - ret = switchdev_port_obj_add(port->dev, &v.obj); + ret = br_switchdev_port_vlan_add(port->dev, vid, flags); if (ret && ret != -EOPNOTSUPP) return ret; *changed = __vlan_add_flags(vlan, flags); @@ -1149,3 +1162,44 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, stats->tx_packets += txpackets; } } + +int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) +{ + struct net_bridge_vlan_group *vg; + + ASSERT_RTNL(); + if (netif_is_bridge_master(dev)) + vg = br_vlan_group(netdev_priv(dev)); + else + return -EINVAL; + + *p_pvid = br_get_pvid(vg); + return 0; +} +EXPORT_SYMBOL_GPL(br_vlan_get_pvid); + +int br_vlan_get_info(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + struct net_bridge_port *p; + + ASSERT_RTNL(); + p = br_port_get_check_rtnl(dev); + if (p) + vg = nbp_vlan_group(p); + else if (netif_is_bridge_master(dev)) + vg = br_vlan_group(netdev_priv(dev)); + else + return -EINVAL; + + v = br_vlan_find(vg, vid); + if (!v) + return -ENOENT; + + p_vinfo->vid = vid; + p_vinfo->flags = v->flags; + return 0; +} +EXPORT_SYMBOL_GPL(br_vlan_get_info); diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index f212447794bd5..9a0159aebe1ac 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -8,13 +8,6 @@ menuconfig NF_TABLES_BRIDGE bool "Ethernet Bridge nf_tables support" if NF_TABLES_BRIDGE - -config NFT_BRIDGE_META - tristate "Netfilter nf_table bridge meta support" - depends on NFT_META - help - Add support for bridge dedicated meta key. - config NFT_BRIDGE_REJECT tristate "Netfilter nf_tables bridge reject support" depends on NFT_REJECT && NFT_REJECT_IPV4 && NFT_REJECT_IPV6 diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile index 4bc758dd4a8c1..9b868861f21ad 100644 --- a/net/bridge/netfilter/Makefile +++ b/net/bridge/netfilter/Makefile @@ -3,7 +3,6 @@ # Makefile for the netfilter modules for Link Layer filtering on a bridge. # -obj-$(CONFIG_NFT_BRIDGE_META) += nft_meta_bridge.o obj-$(CONFIG_NFT_BRIDGE_REJECT) += nft_reject_bridge.o # packet logging diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 0e27c51331fb7..28f68a2ec911d 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -101,7 +101,7 @@ ebt_do_match(struct ebt_entry_match *m, const struct sk_buff *skb, { par->match = m->u.match; par->matchinfo = m->data; - return m->u.match->match(skb, par) ? EBT_MATCH : EBT_NOMATCH; + return !m->u.match->match(skb, par); } static inline int @@ -177,6 +177,12 @@ struct ebt_entry *ebt_next_entry(const struct ebt_entry *entry) return (void *)entry + entry->next_offset; } +static inline const struct ebt_entry_target * +ebt_get_target_c(const struct ebt_entry *e) +{ + return ebt_get_target((struct ebt_entry *)e); +} + /* Do some firewalling */ unsigned int ebt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, @@ -230,8 +236,7 @@ unsigned int ebt_do_table(struct sk_buff *skb, */ EBT_WATCHER_ITERATE(point, ebt_do_watcher, skb, &acpar); - t = (struct ebt_entry_target *) - (((char *)point) + point->target_offset); + t = ebt_get_target_c(point); /* standard target */ if (!t->u.target->target) verdict = ((struct ebt_standard_target *)t)->verdict; @@ -343,6 +348,16 @@ find_table_lock(struct net *net, const char *name, int *error, "ebtable_", error, mutex); } +static inline void ebt_free_table_info(struct ebt_table_info *info) +{ + int i; + + if (info->chainstack) { + for_each_possible_cpu(i) + vfree(info->chainstack[i]); + vfree(info->chainstack); + } +} static inline int ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par, unsigned int *cnt) @@ -627,7 +642,7 @@ ebt_cleanup_entry(struct ebt_entry *e, struct net *net, unsigned int *cnt) return 1; EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, net, NULL); EBT_MATCH_ITERATE(e, ebt_cleanup_match, net, NULL); - t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); + t = ebt_get_target(e); par.net = net; par.target = t->u.target; @@ -706,7 +721,7 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, ret = EBT_WATCHER_ITERATE(e, ebt_check_watcher, &tgpar, &j); if (ret != 0) goto cleanup_watchers; - t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); + t = ebt_get_target(e); gap = e->next_offset - e->target_offset; target = xt_request_find_target(NFPROTO_BRIDGE, t->u.name, 0); @@ -779,8 +794,7 @@ static int check_chainloops(const struct ebt_entries *chain, struct ebt_cl_stack if (pos == nentries) continue; } - t = (struct ebt_entry_target *) - (((char *)e) + e->target_offset); + t = ebt_get_target_c(e); if (strcmp(t->u.name, EBT_STANDARD_TARGET)) goto letscontinue; if (e->target_offset + sizeof(struct ebt_standard_target) > @@ -975,7 +989,7 @@ static void get_counters(const struct ebt_counter *oldcounters, static int do_replace_finish(struct net *net, struct ebt_replace *repl, struct ebt_table_info *newinfo) { - int ret, i; + int ret; struct ebt_counter *counterstmp = NULL; /* used to be able to unlock earlier */ struct ebt_table_info *table; @@ -1051,13 +1065,8 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, ebt_cleanup_entry, net, NULL); vfree(table->entries); - if (table->chainstack) { - for_each_possible_cpu(i) - vfree(table->chainstack[i]); - vfree(table->chainstack); - } + ebt_free_table_info(table); vfree(table); - vfree(counterstmp); #ifdef CONFIG_AUDIT @@ -1078,11 +1087,7 @@ free_iterate: free_counterstmp: vfree(counterstmp); /* can be initialized in translate_table() */ - if (newinfo->chainstack) { - for_each_possible_cpu(i) - vfree(newinfo->chainstack[i]); - vfree(newinfo->chainstack); - } + ebt_free_table_info(newinfo); return ret; } @@ -1147,8 +1152,6 @@ free_newinfo: static void __ebt_unregister_table(struct net *net, struct ebt_table *table) { - int i; - mutex_lock(&ebt_mutex); list_del(&table->list); mutex_unlock(&ebt_mutex); @@ -1157,11 +1160,7 @@ static void __ebt_unregister_table(struct net *net, struct ebt_table *table) if (table->private->nentries) module_put(table->me); vfree(table->private->entries); - if (table->private->chainstack) { - for_each_possible_cpu(i) - vfree(table->private->chainstack[i]); - vfree(table->private->chainstack); - } + ebt_free_table_info(table->private); vfree(table->private); kfree(table); } @@ -1263,11 +1262,7 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, free_unlock: mutex_unlock(&ebt_mutex); free_chainstack: - if (newinfo->chainstack) { - for_each_possible_cpu(i) - vfree(newinfo->chainstack[i]); - vfree(newinfo->chainstack); - } + ebt_free_table_info(newinfo); vfree(newinfo->entries); free_newinfo: vfree(newinfo); @@ -1405,7 +1400,7 @@ static inline int ebt_entry_to_user(struct ebt_entry *e, const char *base, return -EFAULT; hlp = ubase + (((char *)e + e->target_offset) - base); - t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); + t = ebt_get_target_c(e); ret = EBT_MATCH_ITERATE(e, ebt_match_to_user, base, ubase); if (ret != 0) @@ -1746,7 +1741,7 @@ static int compat_copy_entry_to_user(struct ebt_entry *e, void __user **dstptr, return ret; target_offset = e->target_offset - (origsize - *size); - t = (struct ebt_entry_target *) ((char *) e + e->target_offset); + t = ebt_get_target(e); ret = compat_target_to_user(t, dstptr, size); if (ret) @@ -1794,7 +1789,7 @@ static int compat_calc_entry(const struct ebt_entry *e, EBT_MATCH_ITERATE(e, compat_calc_match, &off); EBT_WATCHER_ITERATE(e, compat_calc_watcher, &off); - t = (const struct ebt_entry_target *) ((char *) e + e->target_offset); + t = ebt_get_target_c(e); off += xt_compat_target_offset(t->u.target); off += ebt_compat_entry_padsize(); diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c deleted file mode 100644 index bb63c9aed55d2..0000000000000 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ /dev/null @@ -1,135 +0,0 @@ -/* - * Copyright (c) 2014 Intel Corporation - * - * 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. - * - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/netlink.h> -#include <linux/netfilter.h> -#include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables.h> -#include <net/netfilter/nft_meta.h> - -#include "../br_private.h" - -static void nft_meta_bridge_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - const struct nft_meta *priv = nft_expr_priv(expr); - const struct net_device *in = nft_in(pkt), *out = nft_out(pkt); - u32 *dest = ®s->data[priv->dreg]; - const struct net_bridge_port *p; - - switch (priv->key) { - case NFT_META_BRI_IIFNAME: - if (in == NULL || (p = br_port_get_rcu(in)) == NULL) - goto err; - break; - case NFT_META_BRI_OIFNAME: - if (out == NULL || (p = br_port_get_rcu(out)) == NULL) - goto err; - break; - default: - goto out; - } - - strncpy((char *)dest, p->br->dev->name, IFNAMSIZ); - return; -out: - return nft_meta_get_eval(expr, regs, pkt); -err: - regs->verdict.code = NFT_BREAK; -} - -static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_meta *priv = nft_expr_priv(expr); - unsigned int len; - - priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); - switch (priv->key) { - case NFT_META_BRI_IIFNAME: - case NFT_META_BRI_OIFNAME: - len = IFNAMSIZ; - break; - default: - return nft_meta_get_init(ctx, expr, tb); - } - - priv->dreg = nft_parse_register(tb[NFTA_META_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); -} - -static struct nft_expr_type nft_meta_bridge_type; -static const struct nft_expr_ops nft_meta_bridge_get_ops = { - .type = &nft_meta_bridge_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), - .eval = nft_meta_bridge_get_eval, - .init = nft_meta_bridge_get_init, - .dump = nft_meta_get_dump, -}; - -static const struct nft_expr_ops nft_meta_bridge_set_ops = { - .type = &nft_meta_bridge_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), - .eval = nft_meta_set_eval, - .init = nft_meta_set_init, - .destroy = nft_meta_set_destroy, - .dump = nft_meta_set_dump, - .validate = nft_meta_set_validate, -}; - -static const struct nft_expr_ops * -nft_meta_bridge_select_ops(const struct nft_ctx *ctx, - const struct nlattr * const tb[]) -{ - if (tb[NFTA_META_KEY] == NULL) - return ERR_PTR(-EINVAL); - - if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) - return ERR_PTR(-EINVAL); - - if (tb[NFTA_META_DREG]) - return &nft_meta_bridge_get_ops; - - if (tb[NFTA_META_SREG]) - return &nft_meta_bridge_set_ops; - - return ERR_PTR(-EINVAL); -} - -static struct nft_expr_type nft_meta_bridge_type __read_mostly = { - .family = NFPROTO_BRIDGE, - .name = "meta", - .select_ops = nft_meta_bridge_select_ops, - .policy = nft_meta_policy, - .maxattr = NFTA_META_MAX, - .owner = THIS_MODULE, -}; - -static int __init nft_meta_bridge_module_init(void) -{ - return nft_register_expr(&nft_meta_bridge_type); -} - -static void __exit nft_meta_bridge_module_exit(void) -{ - nft_unregister_expr(&nft_meta_bridge_type); -} - -module_init(nft_meta_bridge_module_init); -module_exit(nft_meta_bridge_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>"); -MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta"); diff --git a/net/core/Makefile b/net/core/Makefile index 6dbbba8c57ae7..80175e6a2eb87 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -14,6 +14,7 @@ obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ fib_notifier.o xdp.o obj-y += net-sysfs.o +obj-$(CONFIG_PAGE_POOL) += page_pool.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_NETPOLL) += netpoll.o @@ -30,3 +31,4 @@ obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o +obj-$(CONFIG_FAILOVER) += failover.o diff --git a/net/core/dev.c b/net/core/dev.c index 9c149238a4cea..6e18242a1caec 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1285,6 +1285,7 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) return len; } +EXPORT_SYMBOL(dev_set_alias); /** * dev_get_alias - get ifalias of a device @@ -1586,7 +1587,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) - }; + } #undef N return "UNKNOWN_NETDEV_EVENT"; } @@ -1754,38 +1755,38 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) EXPORT_SYMBOL(call_netdevice_notifiers); #ifdef CONFIG_NET_INGRESS -static struct static_key ingress_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(ingress_needed_key); void net_inc_ingress_queue(void) { - static_key_slow_inc(&ingress_needed); + static_branch_inc(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_ingress_queue); void net_dec_ingress_queue(void) { - static_key_slow_dec(&ingress_needed); + static_branch_dec(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_ingress_queue); #endif #ifdef CONFIG_NET_EGRESS -static struct static_key egress_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(egress_needed_key); void net_inc_egress_queue(void) { - static_key_slow_inc(&egress_needed); + static_branch_inc(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_egress_queue); void net_dec_egress_queue(void) { - static_key_slow_dec(&egress_needed); + static_branch_dec(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif -static struct static_key netstamp_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); #ifdef HAVE_JUMP_LABEL static atomic_t netstamp_needed_deferred; static atomic_t netstamp_wanted; @@ -1796,9 +1797,9 @@ static void netstamp_clear(struct work_struct *work) wanted = atomic_add_return(deferred, &netstamp_wanted); if (wanted > 0) - static_key_enable(&netstamp_needed); + static_branch_enable(&netstamp_needed_key); else - static_key_disable(&netstamp_needed); + static_branch_disable(&netstamp_needed_key); } static DECLARE_WORK(netstamp_work, netstamp_clear); #endif @@ -1818,7 +1819,7 @@ void net_enable_timestamp(void) atomic_inc(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else - static_key_slow_inc(&netstamp_needed); + static_branch_inc(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_enable_timestamp); @@ -1838,7 +1839,7 @@ void net_disable_timestamp(void) atomic_dec(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else - static_key_slow_dec(&netstamp_needed); + static_branch_dec(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_disable_timestamp); @@ -1846,15 +1847,15 @@ EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; - if (static_key_false(&netstamp_needed)) + if (static_branch_unlikely(&netstamp_needed_key)) __net_timestamp(skb); } -#define net_timestamp_check(COND, SKB) \ - if (static_key_false(&netstamp_needed)) { \ - if ((COND) && !(SKB)->tstamp) \ - __net_timestamp(SKB); \ - } \ +#define net_timestamp_check(COND, SKB) \ + if (static_branch_unlikely(&netstamp_needed_key)) { \ + if ((COND) && !(SKB)->tstamp) \ + __net_timestamp(SKB); \ + } \ bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) { @@ -2614,17 +2615,16 @@ EXPORT_SYMBOL(netif_device_attach); * Returns a Tx hash based on the given packet descriptor a Tx queues' number * to be used as a distribution range. */ -u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, - unsigned int num_tx_queues) +static u16 skb_tx_hash(const struct net_device *dev, struct sk_buff *skb) { u32 hash; u16 qoffset = 0; - u16 qcount = num_tx_queues; + u16 qcount = dev->real_num_tx_queues; if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); - while (unlikely(hash >= num_tx_queues)) - hash -= num_tx_queues; + while (unlikely(hash >= qcount)) + hash -= qcount; return hash; } @@ -2637,7 +2637,6 @@ u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; } -EXPORT_SYMBOL(__skb_tx_hash); static void skb_warn_bad_offload(const struct sk_buff *skb) { @@ -3095,6 +3094,10 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device if (unlikely(!skb)) goto out_null; + skb = sk_validate_xmit_skb(skb, dev); + if (unlikely(!skb)) + goto out_null; + if (netif_needs_gso(skb, features)) { struct sk_buff *segs; @@ -3223,7 +3226,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, rc = NET_XMIT_DROP; } else { rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - __qdisc_run(q); + qdisc_run(q); } if (unlikely(to_free)) @@ -3511,7 +3514,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) #ifdef CONFIG_NET_CLS_ACT skb->tc_at_ingress = 0; # ifdef CONFIG_NET_EGRESS - if (static_key_false(&egress_needed)) { + if (static_branch_unlikely(&egress_needed_key)) { skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; @@ -3606,6 +3609,44 @@ int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) } EXPORT_SYMBOL(dev_queue_xmit_accel); +int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +{ + struct net_device *dev = skb->dev; + struct sk_buff *orig_skb = skb; + struct netdev_queue *txq; + int ret = NETDEV_TX_BUSY; + bool again = false; + + if (unlikely(!netif_running(dev) || + !netif_carrier_ok(dev))) + goto drop; + + skb = validate_xmit_skb_list(skb, dev, &again); + if (skb != orig_skb) + goto drop; + + skb_set_queue_mapping(skb, queue_id); + txq = skb_get_tx_queue(dev, skb); + + local_bh_disable(); + + HARD_TX_LOCK(dev, txq, smp_processor_id()); + if (!netif_xmit_frozen_or_drv_stopped(txq)) + ret = netdev_start_xmit(skb, dev, txq, false); + HARD_TX_UNLOCK(dev, txq); + + local_bh_enable(); + + if (!dev_xmit_complete(ret)) + kfree_skb(skb); + + return ret; +drop: + atomic_long_inc(&dev->tx_dropped); + kfree_skb_list(skb); + return NET_XMIT_DROP; +} +EXPORT_SYMBOL(dev_direct_xmit); /************************************************************************* * Receiver routines @@ -3975,12 +4016,12 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) } static u32 netif_receive_generic_xdp(struct sk_buff *skb, + struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct netdev_rx_queue *rxqueue; + void *orig_data, *orig_data_end; u32 metalen, act = XDP_DROP; - struct xdp_buff xdp; - void *orig_data; int hlen, off; u32 mac_len; @@ -4015,31 +4056,42 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, */ mac_len = skb->data - skb_mac_header(skb); hlen = skb_headlen(skb) + mac_len; - xdp.data = skb->data - mac_len; - xdp.data_meta = xdp.data; - xdp.data_end = xdp.data + hlen; - xdp.data_hard_start = skb->data - skb_headroom(skb); - orig_data = xdp.data; + xdp->data = skb->data - mac_len; + xdp->data_meta = xdp->data; + xdp->data_end = xdp->data + hlen; + xdp->data_hard_start = skb->data - skb_headroom(skb); + orig_data_end = xdp->data_end; + orig_data = xdp->data; rxqueue = netif_get_rxqueue(skb); - xdp.rxq = &rxqueue->xdp_rxq; + xdp->rxq = &rxqueue->xdp_rxq; - act = bpf_prog_run_xdp(xdp_prog, &xdp); + act = bpf_prog_run_xdp(xdp_prog, xdp); - off = xdp.data - orig_data; + off = xdp->data - orig_data; if (off > 0) __skb_pull(skb, off); else if (off < 0) __skb_push(skb, -off); skb->mac_header += off; + /* check if bpf_xdp_adjust_tail was used. it can only "shrink" + * pckt. + */ + off = orig_data_end - xdp->data_end; + if (off != 0) { + skb_set_tail_pointer(skb, xdp->data_end - xdp->data); + skb->len -= off; + + } + switch (act) { case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); break; case XDP_PASS: - metalen = xdp.data - xdp.data_meta; + metalen = xdp->data - xdp->data_meta; if (metalen) skb_metadata_set(skb, metalen); break; @@ -4084,22 +4136,24 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) } EXPORT_SYMBOL_GPL(generic_xdp_tx); -static struct static_key generic_xdp_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb) { if (xdp_prog) { - u32 act = netif_receive_generic_xdp(skb, xdp_prog); + struct xdp_buff xdp; + u32 act; int err; + act = netif_receive_generic_xdp(skb, &xdp, xdp_prog); if (act != XDP_PASS) { switch (act) { case XDP_REDIRECT: err = xdp_do_generic_redirect(skb->dev, skb, - xdp_prog); + &xdp, xdp_prog); if (err) goto out_redir; - /* fallthru to submit skb */ + break; case XDP_TX: generic_xdp_tx(skb, xdp_prog); break; @@ -4122,7 +4176,7 @@ static int netif_rx_internal(struct sk_buff *skb) trace_netif_rx(skb); - if (static_key_false(&generic_xdp_needed)) { + if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret; preempt_disable(); @@ -4494,7 +4548,7 @@ another_round: skip_taps: #ifdef CONFIG_NET_INGRESS - if (static_key_false(&ingress_needed)) { + if (static_branch_unlikely(&ingress_needed_key)) { skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev); if (!skb) goto out; @@ -4654,9 +4708,9 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) bpf_prog_put(old); if (old && !new) { - static_key_slow_dec(&generic_xdp_needed); + static_branch_dec(&generic_xdp_needed_key); } else if (new && !old) { - static_key_slow_inc(&generic_xdp_needed); + static_branch_inc(&generic_xdp_needed_key); dev_disable_lro(dev); dev_disable_gro_hw(dev); } @@ -4684,7 +4738,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; - if (static_key_false(&generic_xdp_needed)) { + if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret; preempt_disable(); @@ -7852,6 +7906,8 @@ int register_netdevice(struct net_device *dev) int ret; struct net *net = dev_net(dev); + BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE < + NETDEV_FEATURE_COUNT); BUG_ON(dev_boot_phase); ASSERT_RTNL(); diff --git a/net/core/devlink.c b/net/core/devlink.c index ad1317376798c..22099705cc410 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -453,6 +453,27 @@ static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } +static int devlink_nl_port_attrs_put(struct sk_buff *msg, + struct devlink_port *devlink_port) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + + if (!attrs->set) + return 0; + if (nla_put_u16(msg, DEVLINK_ATTR_PORT_FLAVOUR, attrs->flavour)) + return -EMSGSIZE; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->port_number)) + return -EMSGSIZE; + if (!attrs->split) + return 0; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, attrs->port_number)) + return -EMSGSIZE; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER, + attrs->split_subport_number)) + return -EMSGSIZE; + return 0; +} + static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_port *devlink_port, enum devlink_command cmd, u32 portid, @@ -492,9 +513,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, ibdev->name)) goto nla_put_failure; } - if (devlink_port->split && - nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, - devlink_port->split_group)) + if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -683,12 +702,13 @@ static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, return 0; } -static int devlink_port_split(struct devlink *devlink, - u32 port_index, u32 count) +static int devlink_port_split(struct devlink *devlink, u32 port_index, + u32 count, struct netlink_ext_ack *extack) { if (devlink->ops && devlink->ops->port_split) - return devlink->ops->port_split(devlink, port_index, count); + return devlink->ops->port_split(devlink, port_index, count, + extack); return -EOPNOTSUPP; } @@ -705,14 +725,15 @@ static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); - return devlink_port_split(devlink, port_index, count); + return devlink_port_split(devlink, port_index, count, info->extack); } -static int devlink_port_unsplit(struct devlink *devlink, u32 port_index) +static int devlink_port_unsplit(struct devlink *devlink, u32 port_index, + struct netlink_ext_ack *extack) { if (devlink->ops && devlink->ops->port_unsplit) - return devlink->ops->port_unsplit(devlink, port_index); + return devlink->ops->port_unsplit(devlink, port_index, extack); return -EOPNOTSUPP; } @@ -726,7 +747,7 @@ static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, return -EINVAL; port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); - return devlink_port_unsplit(devlink, port_index); + return devlink_port_unsplit(devlink, port_index, info->extack); } static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, @@ -1807,7 +1828,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: - genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; } @@ -2013,7 +2033,6 @@ int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx) return 0; nla_put_failure: - genlmsg_cancel(dump_ctx->skb, dump_ctx->hdr); nlmsg_free(dump_ctx->skb); return -EMSGSIZE; } @@ -2230,7 +2249,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: - genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; } @@ -2532,7 +2550,6 @@ nla_put_failure: err = -EMSGSIZE; err_resource_put: err_skb_send_alloc: - genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; } @@ -2584,7 +2601,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); return err; } - return devlink->ops->reload(devlink); + return devlink->ops->reload(devlink, info->extack); } static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { @@ -2737,7 +2754,8 @@ static const struct genl_ops devlink_nl_ops[] = { .doit = devlink_nl_cmd_eswitch_set_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + DEVLINK_NL_FLAG_NO_LOCK, }, { .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, @@ -2971,19 +2989,64 @@ void devlink_port_type_clear(struct devlink_port *devlink_port) EXPORT_SYMBOL_GPL(devlink_port_type_clear); /** - * devlink_port_split_set - Set port is split + * devlink_port_attrs_set - Set port attributes * * @devlink_port: devlink port - * @split_group: split group - identifies group split port is part of + * @flavour: flavour of the port + * @port_number: number of the port that is facing user, for example + * the front panel port number + * @split: indicates if this is split port + * @split_subport_number: if the port is split, this is the number + * of subport. */ -void devlink_port_split_set(struct devlink_port *devlink_port, - u32 split_group) -{ - devlink_port->split = true; - devlink_port->split_group = split_group; +void devlink_port_attrs_set(struct devlink_port *devlink_port, + enum devlink_port_flavour flavour, + u32 port_number, bool split, + u32 split_subport_number) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + + attrs->set = true; + attrs->flavour = flavour; + attrs->port_number = port_number; + attrs->split = split; + attrs->split_subport_number = split_subport_number; devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } -EXPORT_SYMBOL_GPL(devlink_port_split_set); +EXPORT_SYMBOL_GPL(devlink_port_attrs_set); + +int devlink_port_get_phys_port_name(struct devlink_port *devlink_port, + char *name, size_t len) +{ + struct devlink_port_attrs *attrs = &devlink_port->attrs; + int n = 0; + + if (!attrs->set) + return -EOPNOTSUPP; + + switch (attrs->flavour) { + case DEVLINK_PORT_FLAVOUR_PHYSICAL: + if (!attrs->split) + n = snprintf(name, len, "p%u", attrs->port_number); + else + n = snprintf(name, len, "p%us%u", attrs->port_number, + attrs->split_subport_number); + break; + case DEVLINK_PORT_FLAVOUR_CPU: + case DEVLINK_PORT_FLAVOUR_DSA: + /* As CPU and DSA ports do not have a netdevice associated + * case should not ever happen. + */ + WARN_ON(1); + return -EINVAL; + } + + if (n >= len) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_port_get_phys_port_name); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, diff --git a/net/core/dst.c b/net/core/dst.c index 007aa0b082915..2d9b37f8944a9 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -58,6 +58,7 @@ const struct dst_metrics dst_default_metrics = { */ .refcnt = REFCOUNT_INIT(1), }; +EXPORT_SYMBOL(dst_default_metrics); void dst_init(struct dst_entry *dst, struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, diff --git a/net/core/ethtool.c b/net/core/ethtool.c index ba02f0dfe85cd..c15075dc7572c 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -92,6 +92,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", [NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation", + [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", @@ -109,6 +110,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_HW_ESP_TX_CSUM_BIT] = "esp-tx-csum-hw-offload", [NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload", [NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record", + [NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload", }; static const char @@ -210,23 +212,6 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) return ret; } -static int phy_get_sset_count(struct phy_device *phydev) -{ - int ret; - - if (phydev->drv->get_sset_count && - phydev->drv->get_strings && - phydev->drv->get_stats) { - mutex_lock(&phydev->lock); - ret = phydev->drv->get_sset_count(phydev); - mutex_unlock(&phydev->lock); - - return ret; - } - - return -EOPNOTSUPP; -} - static int __ethtool_get_sset_count(struct net_device *dev, int sset) { const struct ethtool_ops *ops = dev->ethtool_ops; @@ -243,12 +228,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) if (sset == ETH_SS_PHY_TUNABLES) return ARRAY_SIZE(phy_tunable_strings); - if (sset == ETH_SS_PHY_STATS) { - if (dev->phydev) - return phy_get_sset_count(dev->phydev); - else - return -EOPNOTSUPP; - } + if (sset == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) + return phy_ethtool_get_sset_count(dev->phydev); if (ops->get_sset_count && ops->get_strings) return ops->get_sset_count(dev, sset); @@ -271,17 +253,10 @@ static void __ethtool_get_strings(struct net_device *dev, memcpy(data, tunable_strings, sizeof(tunable_strings)); else if (stringset == ETH_SS_PHY_TUNABLES) memcpy(data, phy_tunable_strings, sizeof(phy_tunable_strings)); - else if (stringset == ETH_SS_PHY_STATS) { - struct phy_device *phydev = dev->phydev; - - if (phydev) { - mutex_lock(&phydev->lock); - phydev->drv->get_strings(phydev, data); - mutex_unlock(&phydev->lock); - } else { - return; - } - } else + else if (stringset == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) + phy_ethtool_get_strings(dev->phydev, data); + else /* ops->get_strings is valid because checked earlier */ ops->get_strings(dev, stringset, data); } @@ -1998,15 +1973,19 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) { - struct ethtool_stats stats; + const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; + struct ethtool_stats stats; u64 *data; int ret, n_stats; - if (!phydev) + if (!phydev && (!ops->get_ethtool_phy_stats || !ops->get_sset_count)) return -EOPNOTSUPP; - n_stats = phy_get_sset_count(phydev); + if (dev->phydev && !ops->get_ethtool_phy_stats) + n_stats = phy_ethtool_get_sset_count(dev->phydev); + else + n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS); if (n_stats < 0) return n_stats; if (n_stats > S32_MAX / sizeof(u64)) @@ -2021,9 +2000,13 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) if (n_stats && !data) return -ENOMEM; - mutex_lock(&phydev->lock); - phydev->drv->get_stats(phydev, &stats, data); - mutex_unlock(&phydev->lock); + if (dev->phydev && !ops->get_ethtool_phy_stats) { + ret = phy_ethtool_get_stats(dev->phydev, &stats, data); + if (ret < 0) + return ret; + } else { + ops->get_ethtool_phy_stats(dev, &stats, data); + } ret = -EFAULT; if (copy_to_user(useraddr, &stats, sizeof(stats))) diff --git a/net/core/failover.c b/net/core/failover.c new file mode 100644 index 0000000000000..4a92a98ccce9a --- /dev/null +++ b/net/core/failover.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +/* A common module to handle registrations and notifications for paravirtual + * drivers to enable accelerated datapath and support VF live migration. + * + * The notifier and event handling code is based on netvsc driver. + */ + +#include <linux/module.h> +#include <linux/etherdevice.h> +#include <uapi/linux/if_arp.h> +#include <linux/rtnetlink.h> +#include <linux/if_vlan.h> +#include <net/failover.h> + +static LIST_HEAD(failover_list); +static DEFINE_SPINLOCK(failover_lock); + +static struct net_device *failover_get_bymac(u8 *mac, struct failover_ops **ops) +{ + struct net_device *failover_dev; + struct failover *failover; + + spin_lock(&failover_lock); + list_for_each_entry(failover, &failover_list, list) { + failover_dev = rtnl_dereference(failover->failover_dev); + if (ether_addr_equal(failover_dev->perm_addr, mac)) { + *ops = rtnl_dereference(failover->ops); + spin_unlock(&failover_lock); + return failover_dev; + } + } + spin_unlock(&failover_lock); + return NULL; +} + +/** + * failover_slave_register - Register a slave netdev + * + * @slave_dev: slave netdev that is being registered + * + * Registers a slave device to a failover instance. Only ethernet devices + * are supported. + */ +static int failover_slave_register(struct net_device *slave_dev) +{ + struct netdev_lag_upper_info lag_upper_info; + struct net_device *failover_dev; + struct failover_ops *fops; + int err; + + if (slave_dev->type != ARPHRD_ETHER) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (fops && fops->slave_pre_register && + fops->slave_pre_register(slave_dev, failover_dev)) + goto done; + + err = netdev_rx_handler_register(slave_dev, fops->slave_handle_frame, + failover_dev); + if (err) { + netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n", + err); + goto done; + } + + lag_upper_info.tx_type = NETDEV_LAG_TX_TYPE_ACTIVEBACKUP; + err = netdev_master_upper_dev_link(slave_dev, failover_dev, NULL, + &lag_upper_info, NULL); + if (err) { + netdev_err(slave_dev, "can not set failover device %s (err = %d)\n", + failover_dev->name, err); + goto err_upper_link; + } + + slave_dev->priv_flags |= IFF_FAILOVER_SLAVE; + + if (fops && fops->slave_register && + !fops->slave_register(slave_dev, failover_dev)) + return NOTIFY_OK; + + netdev_upper_dev_unlink(slave_dev, failover_dev); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; +err_upper_link: + netdev_rx_handler_unregister(slave_dev); +done: + return NOTIFY_DONE; +} + +/** + * failover_slave_unregister - Unregister a slave netdev + * + * @slave_dev: slave netdev that is being unregistered + * + * Unregisters a slave device from a failover instance. + */ +int failover_slave_unregister(struct net_device *slave_dev) +{ + struct net_device *failover_dev; + struct failover_ops *fops; + + if (!netif_is_failover_slave(slave_dev)) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (fops && fops->slave_pre_unregister && + fops->slave_pre_unregister(slave_dev, failover_dev)) + goto done; + + netdev_rx_handler_unregister(slave_dev); + netdev_upper_dev_unlink(slave_dev, failover_dev); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + + if (fops && fops->slave_unregister && + !fops->slave_unregister(slave_dev, failover_dev)) + return NOTIFY_OK; + +done: + return NOTIFY_DONE; +} +EXPORT_SYMBOL_GPL(failover_slave_unregister); + +static int failover_slave_link_change(struct net_device *slave_dev) +{ + struct net_device *failover_dev; + struct failover_ops *fops; + + if (!netif_is_failover_slave(slave_dev)) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (!netif_running(failover_dev)) + goto done; + + if (fops && fops->slave_link_change && + !fops->slave_link_change(slave_dev, failover_dev)) + return NOTIFY_OK; + +done: + return NOTIFY_DONE; +} + +static int failover_slave_name_change(struct net_device *slave_dev) +{ + struct net_device *failover_dev; + struct failover_ops *fops; + + if (!netif_is_failover_slave(slave_dev)) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (!netif_running(failover_dev)) + goto done; + + if (fops && fops->slave_name_change && + !fops->slave_name_change(slave_dev, failover_dev)) + return NOTIFY_OK; + +done: + return NOTIFY_DONE; +} + +static int +failover_event(struct notifier_block *this, unsigned long event, void *ptr) +{ + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + + /* Skip parent events */ + if (netif_is_failover(event_dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_REGISTER: + return failover_slave_register(event_dev); + case NETDEV_UNREGISTER: + return failover_slave_unregister(event_dev); + case NETDEV_UP: + case NETDEV_DOWN: + case NETDEV_CHANGE: + return failover_slave_link_change(event_dev); + case NETDEV_CHANGENAME: + return failover_slave_name_change(event_dev); + default: + return NOTIFY_DONE; + } +} + +static struct notifier_block failover_notifier = { + .notifier_call = failover_event, +}; + +static void +failover_existing_slave_register(struct net_device *failover_dev) +{ + struct net *net = dev_net(failover_dev); + struct net_device *dev; + + rtnl_lock(); + for_each_netdev(net, dev) { + if (netif_is_failover(dev)) + continue; + if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr)) + failover_slave_register(dev); + } + rtnl_unlock(); +} + +/** + * failover_register - Register a failover instance + * + * @dev: failover netdev + * @ops: failover ops + * + * Allocate and register a failover instance for a failover netdev. ops + * provides handlers for slave device register/unregister/link change/ + * name change events. + * + * Return: pointer to failover instance + */ +struct failover *failover_register(struct net_device *dev, + struct failover_ops *ops) +{ + struct failover *failover; + + if (dev->type != ARPHRD_ETHER) + return ERR_PTR(-EINVAL); + + failover = kzalloc(sizeof(*failover), GFP_KERNEL); + if (!failover) + return ERR_PTR(-ENOMEM); + + rcu_assign_pointer(failover->ops, ops); + dev_hold(dev); + dev->priv_flags |= IFF_FAILOVER; + rcu_assign_pointer(failover->failover_dev, dev); + + spin_lock(&failover_lock); + list_add_tail(&failover->list, &failover_list); + spin_unlock(&failover_lock); + + netdev_info(dev, "failover master:%s registered\n", dev->name); + + failover_existing_slave_register(dev); + + return failover; +} +EXPORT_SYMBOL_GPL(failover_register); + +/** + * failover_unregister - Unregister a failover instance + * + * @failover: pointer to failover instance + * + * Unregisters and frees a failover instance. + */ +void failover_unregister(struct failover *failover) +{ + struct net_device *failover_dev; + + failover_dev = rcu_dereference(failover->failover_dev); + + netdev_info(failover_dev, "failover master:%s unregistered\n", + failover_dev->name); + + failover_dev->priv_flags &= ~IFF_FAILOVER; + dev_put(failover_dev); + + spin_lock(&failover_lock); + list_del(&failover->list); + spin_unlock(&failover_lock); + + kfree(failover); +} +EXPORT_SYMBOL_GPL(failover_unregister); + +static __init int +failover_init(void) +{ + register_netdevice_notifier(&failover_notifier); + + return 0; +} +module_init(failover_init); + +static __exit +void failover_exit(void) +{ + unregister_netdevice_notifier(&failover_notifier); +} +module_exit(failover_exit); + +MODULE_DESCRIPTION("Generic failover infrastructure/interface"); +MODULE_LICENSE("GPL v2"); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 33958f84c1736..126ffc5bc630c 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -387,247 +387,304 @@ unsigned int fib_rules_seq_read(struct net *net, int family) } EXPORT_SYMBOL_GPL(fib_rules_seq_read); -static int validate_rulemsg(struct fib_rule_hdr *frh, struct nlattr **tb, - struct fib_rules_ops *ops) -{ - int err = -EINVAL; - - if (frh->src_len) - if (tb[FRA_SRC] == NULL || - frh->src_len > (ops->addr_size * 8) || - nla_len(tb[FRA_SRC]) != ops->addr_size) - goto errout; - - if (frh->dst_len) - if (tb[FRA_DST] == NULL || - frh->dst_len > (ops->addr_size * 8) || - nla_len(tb[FRA_DST]) != ops->addr_size) - goto errout; - - err = 0; -errout: - return err; -} - -static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, - struct nlattr **tb, struct fib_rule *rule) +static struct fib_rule *rule_find(struct fib_rules_ops *ops, + struct fib_rule_hdr *frh, + struct nlattr **tb, + struct fib_rule *rule, + bool user_priority) { struct fib_rule *r; list_for_each_entry(r, &ops->rules_list, list) { - if (r->action != rule->action) + if (rule->action && r->action != rule->action) continue; - if (r->table != rule->table) + if (rule->table && r->table != rule->table) continue; - if (r->pref != rule->pref) + if (user_priority && r->pref != rule->pref) continue; - if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) + if (rule->iifname[0] && + memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue; - if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) + if (rule->oifname[0] && + memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue; - if (r->mark != rule->mark) + if (rule->mark && r->mark != rule->mark) continue; - if (r->mark_mask != rule->mark_mask) + if (rule->mark_mask && r->mark_mask != rule->mark_mask) continue; - if (r->tun_id != rule->tun_id) + if (rule->tun_id && r->tun_id != rule->tun_id) continue; if (r->fr_net != rule->fr_net) continue; - if (r->l3mdev != rule->l3mdev) + if (rule->l3mdev && r->l3mdev != rule->l3mdev) continue; - if (!uid_eq(r->uid_range.start, rule->uid_range.start) || - !uid_eq(r->uid_range.end, rule->uid_range.end)) + if (uid_range_set(&rule->uid_range) && + (!uid_eq(r->uid_range.start, rule->uid_range.start) || + !uid_eq(r->uid_range.end, rule->uid_range.end))) continue; - if (r->ip_proto != rule->ip_proto) + if (rule->ip_proto && r->ip_proto != rule->ip_proto) continue; - if (!fib_rule_port_range_compare(&r->sport_range, + if (fib_rule_port_range_set(&rule->sport_range) && + !fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue; - if (!fib_rule_port_range_compare(&r->dport_range, + if (fib_rule_port_range_set(&rule->dport_range) && + !fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; if (!ops->compare(r, frh, tb)) continue; - return 1; + return r; + } + + return NULL; +} + +#ifdef CONFIG_NET_L3_MASTER_DEV +static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, + struct netlink_ext_ack *extack) +{ + nlrule->l3mdev = nla_get_u8(nla); + if (nlrule->l3mdev != 1) { + NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute"); + return -1; } + return 0; } +#else +static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel"); + return -1; +} +#endif -int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) +static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack, + struct fib_rules_ops *ops, + struct nlattr *tb[], + struct fib_rule **rule, + bool *user_priority) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); - struct fib_rules_ops *ops = NULL; - struct fib_rule *rule, *r, *last = NULL; - struct nlattr *tb[FRA_MAX+1]; - int err = -EINVAL, unresolved = 0; - - if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) - goto errout; + struct fib_rule *nlrule = NULL; + int err = -EINVAL; - ops = lookup_rules_ops(net, frh->family); - if (ops == NULL) { - err = -EAFNOSUPPORT; - goto errout; + if (frh->src_len) + if (!tb[FRA_SRC] || + frh->src_len > (ops->addr_size * 8) || + nla_len(tb[FRA_SRC]) != ops->addr_size) { + NL_SET_ERR_MSG(extack, "Invalid source address"); + goto errout; } - err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack); - if (err < 0) - goto errout; - - err = validate_rulemsg(frh, tb, ops); - if (err < 0) - goto errout; + if (frh->dst_len) + if (!tb[FRA_DST] || + frh->dst_len > (ops->addr_size * 8) || + nla_len(tb[FRA_DST]) != ops->addr_size) { + NL_SET_ERR_MSG(extack, "Invalid dst address"); + goto errout; + } - rule = kzalloc(ops->rule_size, GFP_KERNEL); - if (rule == NULL) { + nlrule = kzalloc(ops->rule_size, GFP_KERNEL); + if (!nlrule) { err = -ENOMEM; goto errout; } - refcount_set(&rule->refcnt, 1); - rule->fr_net = net; + refcount_set(&nlrule->refcnt, 1); + nlrule->fr_net = net; - rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY]) - : fib_default_rule_pref(ops); + if (tb[FRA_PRIORITY]) { + nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]); + *user_priority = true; + } else { + nlrule->pref = fib_default_rule_pref(ops); + } - rule->proto = tb[FRA_PROTOCOL] ? + nlrule->proto = tb[FRA_PROTOCOL] ? nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC; if (tb[FRA_IIFNAME]) { struct net_device *dev; - rule->iifindex = -1; - nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); - dev = __dev_get_by_name(net, rule->iifname); + nlrule->iifindex = -1; + nla_strlcpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, nlrule->iifname); if (dev) - rule->iifindex = dev->ifindex; + nlrule->iifindex = dev->ifindex; } if (tb[FRA_OIFNAME]) { struct net_device *dev; - rule->oifindex = -1; - nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); - dev = __dev_get_by_name(net, rule->oifname); + nlrule->oifindex = -1; + nla_strlcpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, nlrule->oifname); if (dev) - rule->oifindex = dev->ifindex; + nlrule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { - rule->mark = nla_get_u32(tb[FRA_FWMARK]); - if (rule->mark) + nlrule->mark = nla_get_u32(tb[FRA_FWMARK]); + if (nlrule->mark) /* compatibility: if the mark value is non-zero all bits * are compared unless a mask is explicitly specified. */ - rule->mark_mask = 0xFFFFFFFF; + nlrule->mark_mask = 0xFFFFFFFF; } if (tb[FRA_FWMASK]) - rule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); + nlrule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); if (tb[FRA_TUN_ID]) - rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); + nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); err = -EINVAL; - if (tb[FRA_L3MDEV]) { -#ifdef CONFIG_NET_L3_MASTER_DEV - rule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]); - if (rule->l3mdev != 1) -#endif - goto errout_free; - } + if (tb[FRA_L3MDEV] && + fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0) + goto errout_free; - rule->action = frh->action; - rule->flags = frh->flags; - rule->table = frh_get_table(frh, tb); + nlrule->action = frh->action; + nlrule->flags = frh->flags; + nlrule->table = frh_get_table(frh, tb); if (tb[FRA_SUPPRESS_PREFIXLEN]) - rule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); + nlrule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); else - rule->suppress_prefixlen = -1; + nlrule->suppress_prefixlen = -1; if (tb[FRA_SUPPRESS_IFGROUP]) - rule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); + nlrule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); else - rule->suppress_ifgroup = -1; + nlrule->suppress_ifgroup = -1; if (tb[FRA_GOTO]) { - if (rule->action != FR_ACT_GOTO) + if (nlrule->action != FR_ACT_GOTO) { + NL_SET_ERR_MSG(extack, "Unexpected goto"); goto errout_free; + } - rule->target = nla_get_u32(tb[FRA_GOTO]); + nlrule->target = nla_get_u32(tb[FRA_GOTO]); /* Backward jumps are prohibited to avoid endless loops */ - if (rule->target <= rule->pref) + if (nlrule->target <= nlrule->pref) { + NL_SET_ERR_MSG(extack, "Backward goto not supported"); goto errout_free; - - list_for_each_entry(r, &ops->rules_list, list) { - if (r->pref == rule->target) { - RCU_INIT_POINTER(rule->ctarget, r); - break; - } } - - if (rcu_dereference_protected(rule->ctarget, 1) == NULL) - unresolved = 1; - } else if (rule->action == FR_ACT_GOTO) + } else if (nlrule->action == FR_ACT_GOTO) { + NL_SET_ERR_MSG(extack, "Missing goto target for action goto"); goto errout_free; + } - if (rule->l3mdev && rule->table) + if (nlrule->l3mdev && nlrule->table) { + NL_SET_ERR_MSG(extack, "l3mdev and table are mutually exclusive"); goto errout_free; + } if (tb[FRA_UID_RANGE]) { if (current_user_ns() != net->user_ns) { err = -EPERM; + NL_SET_ERR_MSG(extack, "No permission to set uid"); goto errout_free; } - rule->uid_range = nla_get_kuid_range(tb); + nlrule->uid_range = nla_get_kuid_range(tb); - if (!uid_range_set(&rule->uid_range) || - !uid_lte(rule->uid_range.start, rule->uid_range.end)) + if (!uid_range_set(&nlrule->uid_range) || + !uid_lte(nlrule->uid_range.start, nlrule->uid_range.end)) { + NL_SET_ERR_MSG(extack, "Invalid uid range"); goto errout_free; + } } else { - rule->uid_range = fib_kuid_range_unset; + nlrule->uid_range = fib_kuid_range_unset; } if (tb[FRA_IP_PROTO]) - rule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]); + nlrule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]); if (tb[FRA_SPORT_RANGE]) { err = nla_get_port_range(tb[FRA_SPORT_RANGE], - &rule->sport_range); - if (err) + &nlrule->sport_range); + if (err) { + NL_SET_ERR_MSG(extack, "Invalid sport range"); goto errout_free; + } } if (tb[FRA_DPORT_RANGE]) { err = nla_get_port_range(tb[FRA_DPORT_RANGE], - &rule->dport_range); - if (err) + &nlrule->dport_range); + if (err) { + NL_SET_ERR_MSG(extack, "Invalid dport range"); goto errout_free; + } } + *rule = nlrule; + + return 0; + +errout_free: + kfree(nlrule); +errout: + return err; +} + +int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rules_ops *ops = NULL; + struct fib_rule *rule = NULL, *r, *last = NULL; + struct nlattr *tb[FRA_MAX + 1]; + int err = -EINVAL, unresolved = 0; + bool user_priority = false; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { + NL_SET_ERR_MSG(extack, "Invalid msg length"); + goto errout; + } + + ops = lookup_rules_ops(net, frh->family); + if (!ops) { + err = -EAFNOSUPPORT; + NL_SET_ERR_MSG(extack, "Rule family not supported"); + goto errout; + } + + err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Error parsing msg"); + goto errout; + } + + err = fib_nl2rule(skb, nlh, extack, ops, tb, &rule, &user_priority); + if (err) + goto errout; + if ((nlh->nlmsg_flags & NLM_F_EXCL) && - rule_exists(ops, frh, tb, rule)) { + rule_find(ops, frh, tb, rule, user_priority)) { err = -EEXIST; goto errout_free; } - err = ops->configure(rule, skb, frh, tb); + err = ops->configure(rule, skb, frh, tb, extack); if (err < 0) goto errout_free; @@ -637,6 +694,16 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout_free; list_for_each_entry(r, &ops->rules_list, list) { + if (r->pref == rule->target) { + RCU_INIT_POINTER(rule->ctarget, r); + break; + } + } + + if (rcu_dereference_protected(rule->ctarget, 1) == NULL) + unresolved = 1; + + list_for_each_entry(r, &ops->rules_list, list) { if (r->pref > rule->pref) break; last = r; @@ -690,171 +757,97 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); - struct fib_rule_port_range sprange = {0, 0}; - struct fib_rule_port_range dprange = {0, 0}; struct fib_rules_ops *ops = NULL; - struct fib_rule *rule, *r; + struct fib_rule *rule = NULL, *r, *nlrule = NULL; struct nlattr *tb[FRA_MAX+1]; - struct fib_kuid_range range; int err = -EINVAL; + bool user_priority = false; - if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { + NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; + } ops = lookup_rules_ops(net, frh->family); if (ops == NULL) { err = -EAFNOSUPPORT; + NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; } err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack); - if (err < 0) + if (err < 0) { + NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; + } - err = validate_rulemsg(frh, tb, ops); - if (err < 0) + err = fib_nl2rule(skb, nlh, extack, ops, tb, &nlrule, &user_priority); + if (err) goto errout; - if (tb[FRA_UID_RANGE]) { - range = nla_get_kuid_range(tb); - if (!uid_range_set(&range)) { - err = -EINVAL; - goto errout; - } - } else { - range = fib_kuid_range_unset; + rule = rule_find(ops, frh, tb, nlrule, user_priority); + if (!rule) { + err = -ENOENT; + goto errout; } - if (tb[FRA_SPORT_RANGE]) { - err = nla_get_port_range(tb[FRA_SPORT_RANGE], - &sprange); - if (err) - goto errout; + if (rule->flags & FIB_RULE_PERMANENT) { + err = -EPERM; + goto errout; } - if (tb[FRA_DPORT_RANGE]) { - err = nla_get_port_range(tb[FRA_DPORT_RANGE], - &dprange); + if (ops->delete) { + err = ops->delete(rule); if (err) goto errout; } - list_for_each_entry(rule, &ops->rules_list, list) { - if (tb[FRA_PROTOCOL] && - (rule->proto != nla_get_u8(tb[FRA_PROTOCOL]))) - continue; - - if (frh->action && (frh->action != rule->action)) - continue; - - if (frh_get_table(frh, tb) && - (frh_get_table(frh, tb) != rule->table)) - continue; - - if (tb[FRA_PRIORITY] && - (rule->pref != nla_get_u32(tb[FRA_PRIORITY]))) - continue; - - if (tb[FRA_IIFNAME] && - nla_strcmp(tb[FRA_IIFNAME], rule->iifname)) - continue; - - if (tb[FRA_OIFNAME] && - nla_strcmp(tb[FRA_OIFNAME], rule->oifname)) - continue; - - if (tb[FRA_FWMARK] && - (rule->mark != nla_get_u32(tb[FRA_FWMARK]))) - continue; - - if (tb[FRA_FWMASK] && - (rule->mark_mask != nla_get_u32(tb[FRA_FWMASK]))) - continue; - - if (tb[FRA_TUN_ID] && - (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID]))) - continue; - - if (tb[FRA_L3MDEV] && - (rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV]))) - continue; - - if (uid_range_set(&range) && - (!uid_eq(rule->uid_range.start, range.start) || - !uid_eq(rule->uid_range.end, range.end))) - continue; - - if (tb[FRA_IP_PROTO] && - (rule->ip_proto != nla_get_u8(tb[FRA_IP_PROTO]))) - continue; - - if (fib_rule_port_range_set(&sprange) && - !fib_rule_port_range_compare(&rule->sport_range, &sprange)) - continue; - - if (fib_rule_port_range_set(&dprange) && - !fib_rule_port_range_compare(&rule->dport_range, &dprange)) - continue; - - if (!ops->compare(rule, frh, tb)) - continue; - - if (rule->flags & FIB_RULE_PERMANENT) { - err = -EPERM; - goto errout; - } - - if (ops->delete) { - err = ops->delete(rule); - if (err) - goto errout; - } + if (rule->tun_id) + ip_tunnel_unneed_metadata(); - if (rule->tun_id) - ip_tunnel_unneed_metadata(); + list_del_rcu(&rule->list); - list_del_rcu(&rule->list); - - if (rule->action == FR_ACT_GOTO) { - ops->nr_goto_rules--; - if (rtnl_dereference(rule->ctarget) == NULL) - ops->unresolved_rules--; - } + if (rule->action == FR_ACT_GOTO) { + ops->nr_goto_rules--; + if (rtnl_dereference(rule->ctarget) == NULL) + ops->unresolved_rules--; + } - /* - * Check if this rule is a target to any of them. If so, - * adjust to the next one with the same preference or - * disable them. As this operation is eventually very - * expensive, it is only performed if goto rules, except - * current if it is goto rule, have actually been added. - */ - if (ops->nr_goto_rules > 0) { - struct fib_rule *n; - - n = list_next_entry(rule, list); - if (&n->list == &ops->rules_list || n->pref != rule->pref) - n = NULL; - list_for_each_entry(r, &ops->rules_list, list) { - if (rtnl_dereference(r->ctarget) != rule) - continue; - rcu_assign_pointer(r->ctarget, n); - if (!n) - ops->unresolved_rules++; - } + /* + * Check if this rule is a target to any of them. If so, + * adjust to the next one with the same preference or + * disable them. As this operation is eventually very + * expensive, it is only performed if goto rules, except + * current if it is goto rule, have actually been added. + */ + if (ops->nr_goto_rules > 0) { + struct fib_rule *n; + + n = list_next_entry(rule, list); + if (&n->list == &ops->rules_list || n->pref != rule->pref) + n = NULL; + list_for_each_entry(r, &ops->rules_list, list) { + if (rtnl_dereference(r->ctarget) != rule) + continue; + rcu_assign_pointer(r->ctarget, n); + if (!n) + ops->unresolved_rules++; } - - call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, - NULL); - notify_rule_change(RTM_DELRULE, rule, ops, nlh, - NETLINK_CB(skb).portid); - fib_rule_put(rule); - flush_route_cache(ops); - rules_ops_put(ops); - return 0; } - err = -ENOENT; + call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, + NULL); + notify_rule_change(RTM_DELRULE, rule, ops, nlh, + NETLINK_CB(skb).portid); + fib_rule_put(rule); + flush_route_cache(ops); + rules_ops_put(ops); + kfree(nlrule); + return 0; + errout: + if (nlrule) + kfree(nlrule); rules_ops_put(ops); return err; } diff --git a/net/core/filter.c b/net/core/filter.c index 201ff36b17a8c..3d9ba7e5965ad 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -57,7 +57,17 @@ #include <net/sock_reuseport.h> #include <net/busy_poll.h> #include <net/tcp.h> +#include <net/xfrm.h> #include <linux/bpf_trace.h> +#include <net/xdp_sock.h> +#include <linux/inetdevice.h> +#include <net/ip_fib.h> +#include <net/flow.h> +#include <net/arp.h> +#include <net/ipv6.h> +#include <linux/seg6_local.h> +#include <net/seg6.h> +#include <net/seg6_local.h> /** * sk_filter_trim_cap - run a packet through a socket filter @@ -111,12 +121,12 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) } EXPORT_SYMBOL(sk_filter_trim_cap); -BPF_CALL_1(__skb_get_pay_offset, struct sk_buff *, skb) +BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb) { return skb_get_poff(skb); } -BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) +BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; @@ -136,7 +146,7 @@ BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) return 0; } -BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) +BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; @@ -160,13 +170,94 @@ BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) return 0; } -BPF_CALL_0(__get_raw_cpu_id) +BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *, + data, int, headlen, int, offset) +{ + u8 tmp, *ptr; + const int len = sizeof(tmp); + + if (offset >= 0) { + if (headlen - offset >= len) + return *(u8 *)(data + offset); + if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) + return tmp; + } else { + ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len); + if (likely(ptr)) + return *(u8 *)ptr; + } + + return -EFAULT; +} + +BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb, + int, offset) +{ + return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len, + offset); +} + +BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *, + data, int, headlen, int, offset) +{ + u16 tmp, *ptr; + const int len = sizeof(tmp); + + if (offset >= 0) { + if (headlen - offset >= len) + return get_unaligned_be16(data + offset); + if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) + return be16_to_cpu(tmp); + } else { + ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len); + if (likely(ptr)) + return get_unaligned_be16(ptr); + } + + return -EFAULT; +} + +BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb, + int, offset) +{ + return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len, + offset); +} + +BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *, + data, int, headlen, int, offset) +{ + u32 tmp, *ptr; + const int len = sizeof(tmp); + + if (likely(offset >= 0)) { + if (headlen - offset >= len) + return get_unaligned_be32(data + offset); + if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) + return be32_to_cpu(tmp); + } else { + ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len); + if (likely(ptr)) + return get_unaligned_be32(ptr); + } + + return -EFAULT; +} + +BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb, + int, offset) +{ + return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len, + offset); +} + +BPF_CALL_0(bpf_get_raw_cpu_id) { return raw_smp_processor_id(); } static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = { - .func = __get_raw_cpu_id, + .func = bpf_get_raw_cpu_id, .gpl_only = false, .ret_type = RET_INTEGER, }; @@ -316,16 +407,16 @@ static bool convert_bpf_extensions(struct sock_filter *fp, /* Emit call(arg1=CTX, arg2=A, arg3=X) */ switch (fp->k) { case SKF_AD_OFF + SKF_AD_PAY_OFFSET: - *insn = BPF_EMIT_CALL(__skb_get_pay_offset); + *insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset); break; case SKF_AD_OFF + SKF_AD_NLATTR: - *insn = BPF_EMIT_CALL(__skb_get_nlattr); + *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr); break; case SKF_AD_OFF + SKF_AD_NLATTR_NEST: - *insn = BPF_EMIT_CALL(__skb_get_nlattr_nest); + *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest); break; case SKF_AD_OFF + SKF_AD_CPU: - *insn = BPF_EMIT_CALL(__get_raw_cpu_id); + *insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: *insn = BPF_EMIT_CALL(bpf_user_rnd_u32); @@ -352,26 +443,87 @@ static bool convert_bpf_extensions(struct sock_filter *fp, return true; } +static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) +{ + const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS); + int size = bpf_size_to_bytes(BPF_SIZE(fp->code)); + bool endian = BPF_SIZE(fp->code) == BPF_H || + BPF_SIZE(fp->code) == BPF_W; + bool indirect = BPF_MODE(fp->code) == BPF_IND; + const int ip_align = NET_IP_ALIGN; + struct bpf_insn *insn = *insnp; + int offset = fp->k; + + if (!indirect && + ((unaligned_ok && offset >= 0) || + (!unaligned_ok && offset >= 0 && + offset + ip_align >= 0 && + offset + ip_align % size == 0))) { + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); + *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset); + *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian); + *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D, + offset); + if (endian) + *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8); + *insn++ = BPF_JMP_A(8); + } + + *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); + *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D); + *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H); + if (!indirect) { + *insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset); + } else { + *insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X); + if (fp->k) + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset); + } + + switch (BPF_SIZE(fp->code)) { + case BPF_B: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8); + break; + case BPF_H: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16); + break; + case BPF_W: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32); + break; + default: + return false; + } + + *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2); + *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); + *insn = BPF_EXIT_INSN(); + + *insnp = insn; + return true; +} + /** * bpf_convert_filter - convert filter program * @prog: the user passed filter program * @len: the length of the user passed filter program * @new_prog: allocated 'struct bpf_prog' or NULL * @new_len: pointer to store length of converted program + * @seen_ld_abs: bool whether we've seen ld_abs/ind * * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn' * style extended BPF (eBPF). * Conversion workflow: * * 1) First pass for calculating the new program length: - * bpf_convert_filter(old_prog, old_len, NULL, &new_len) + * bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs) * * 2) 2nd pass to remap in two passes: 1st pass finds new * jump offsets, 2nd pass remapping: - * bpf_convert_filter(old_prog, old_len, new_prog, &new_len); + * bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs) */ static int bpf_convert_filter(struct sock_filter *prog, int len, - struct bpf_prog *new_prog, int *new_len) + struct bpf_prog *new_prog, int *new_len, + bool *seen_ld_abs) { int new_flen = 0, pass = 0, target, i, stack_off; struct bpf_insn *new_insn, *first_insn = NULL; @@ -410,12 +562,27 @@ do_pass: * do this ourself. Initial CTX is present in BPF_REG_ARG1. */ *new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); + if (*seen_ld_abs) { + /* For packet access in classic BPF, cache skb->data + * in callee-saved BPF R8 and skb->len - skb->data_len + * (headlen) in BPF R9. Since classic BPF is read-only + * on CTX, we only need to cache it once. + */ + *new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), + BPF_REG_D, BPF_REG_CTX, + offsetof(struct sk_buff, data)); + *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX, + offsetof(struct sk_buff, len)); + *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX, + offsetof(struct sk_buff, data_len)); + *new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP); + } } else { new_insn += 3; } for (i = 0; i < len; fp++, i++) { - struct bpf_insn tmp_insns[6] = { }; + struct bpf_insn tmp_insns[32] = { }; struct bpf_insn *insn = tmp_insns; if (addrs) @@ -458,6 +625,11 @@ do_pass: BPF_MODE(fp->code) == BPF_ABS && convert_bpf_extensions(fp, &insn)) break; + if (BPF_CLASS(fp->code) == BPF_LD && + convert_bpf_ld_abs(fp, &insn)) { + *seen_ld_abs = true; + break; + } if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) || fp->code == (BPF_ALU | BPF_MOD | BPF_X)) { @@ -567,21 +739,31 @@ jmp_rest: break; /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ - case BPF_LDX | BPF_MSH | BPF_B: - /* tmp = A */ - *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A); + case BPF_LDX | BPF_MSH | BPF_B: { + struct sock_filter tmp = { + .code = BPF_LD | BPF_ABS | BPF_B, + .k = fp->k, + }; + + *seen_ld_abs = true; + + /* X = A */ + *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = BPF_R0 = *(u8 *) (skb->data + K) */ - *insn++ = BPF_LD_ABS(BPF_B, fp->k); + convert_bpf_ld_abs(&tmp, &insn); + insn++; /* A &= 0xf */ *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); /* A <<= 2 */ *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); + /* tmp = X */ + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X); /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = tmp */ *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break; - + } /* RET_K is remaped into 2 insns. RET_A case doesn't need an * extra mov as BPF_REG_0 is already mapped into BPF_REG_A. */ @@ -663,6 +845,8 @@ jmp_rest: if (!new_prog) { /* Only calculating new length. */ *new_len = new_insn - first_insn; + if (*seen_ld_abs) + *new_len += 4; /* Prologue bits. */ return 0; } @@ -1024,6 +1208,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) struct sock_filter *old_prog; struct bpf_prog *old_fp; int err, new_len, old_len = fp->len; + bool seen_ld_abs = false; /* We are free to overwrite insns et al right here as it * won't be used at this point in time anymore internally @@ -1045,7 +1230,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) } /* 1st pass: calculate the new program length. */ - err = bpf_convert_filter(old_prog, old_len, NULL, &new_len); + err = bpf_convert_filter(old_prog, old_len, NULL, &new_len, + &seen_ld_abs); if (err) goto out_err_free; @@ -1064,7 +1250,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) fp->len = new_len; /* 2nd pass: remap sock_filter insns into bpf_insn insns. */ - err = bpf_convert_filter(old_prog, old_len, fp, &new_len); + err = bpf_convert_filter(old_prog, old_len, fp, &new_len, + &seen_ld_abs); if (err) /* 2nd bpf_convert_filter() can fail only if it fails * to allocate memory, remapping must succeed. Note, @@ -1512,6 +1699,47 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .arg4_type = ARG_CONST_SIZE, }; +BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, + u32, offset, void *, to, u32, len, u32, start_header) +{ + u8 *ptr; + + if (unlikely(offset > 0xffff || len > skb_headlen(skb))) + goto err_clear; + + switch (start_header) { + case BPF_HDR_START_MAC: + ptr = skb_mac_header(skb) + offset; + break; + case BPF_HDR_START_NET: + ptr = skb_network_header(skb) + offset; + break; + default: + goto err_clear; + } + + if (likely(ptr >= skb_mac_header(skb) && + ptr + len <= skb_tail_pointer(skb))) { + memcpy(to, ptr, len); + return 0; + } + +err_clear: + memset(to, 0, len); + return -EFAULT; +} + +static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = { + .func = bpf_skb_load_bytes_relative, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, + .arg5_type = ARG_ANYTHING, +}; + BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write @@ -1857,6 +2085,33 @@ static const struct bpf_func_proto bpf_redirect_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, + struct bpf_map *, map, void *, key, u64, flags) +{ + struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + + /* If user passes invalid input drop the packet. */ + if (unlikely(flags & ~(BPF_F_INGRESS))) + return SK_DROP; + + tcb->bpf.flags = flags; + tcb->bpf.sk_redir = __sock_hash_lookup_elem(map, key); + if (!tcb->bpf.sk_redir) + return SK_DROP; + + return SK_PASS; +} + +static const struct bpf_func_proto bpf_sk_redirect_hash_proto = { + .func = bpf_sk_redirect_hash, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, +}; + BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, struct bpf_map *, map, u32, key, u64, flags) { @@ -1866,9 +2121,10 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; - tcb->bpf.key = key; tcb->bpf.flags = flags; - tcb->bpf.map = map; + tcb->bpf.sk_redir = __sock_map_lookup_elem(map, key); + if (!tcb->bpf.sk_redir) + return SK_DROP; return SK_PASS; } @@ -1876,16 +2132,8 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, struct sock *do_sk_redirect_map(struct sk_buff *skb) { struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); - struct sock *sk = NULL; - - if (tcb->bpf.map) { - sk = __sock_map_lookup_elem(tcb->bpf.map, tcb->bpf.key); - tcb->bpf.key = 0; - tcb->bpf.map = NULL; - } - - return sk; + return tcb->bpf.sk_redir; } static const struct bpf_func_proto bpf_sk_redirect_map_proto = { @@ -1898,32 +2146,49 @@ static const struct bpf_func_proto bpf_sk_redirect_map_proto = { .arg4_type = ARG_ANYTHING, }; -BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg, - struct bpf_map *, map, u32, key, u64, flags) +BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg_buff *, msg, + struct bpf_map *, map, void *, key, u64, flags) { /* If user passes invalid input drop the packet. */ if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; - msg->key = key; msg->flags = flags; - msg->map = map; + msg->sk_redir = __sock_hash_lookup_elem(map, key); + if (!msg->sk_redir) + return SK_DROP; return SK_PASS; } -struct sock *do_msg_redirect_map(struct sk_msg_buff *msg) +static const struct bpf_func_proto bpf_msg_redirect_hash_proto = { + .func = bpf_msg_redirect_hash, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_PTR_TO_MAP_KEY, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg, + struct bpf_map *, map, u32, key, u64, flags) { - struct sock *sk = NULL; + /* If user passes invalid input drop the packet. */ + if (unlikely(flags & ~(BPF_F_INGRESS))) + return SK_DROP; - if (msg->map) { - sk = __sock_map_lookup_elem(msg->map, msg->key); + msg->flags = flags; + msg->sk_redir = __sock_map_lookup_elem(map, key); + if (!msg->sk_redir) + return SK_DROP; - msg->key = 0; - msg->map = NULL; - } + return SK_PASS; +} - return sk; +struct sock *do_msg_redirect_map(struct sk_msg_buff *msg) +{ + return msg->sk_redir; } static const struct bpf_func_proto bpf_msg_redirect_map_proto = { @@ -2186,7 +2451,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, return ret; } -const struct bpf_func_proto bpf_skb_vlan_push_proto = { +static const struct bpf_func_proto bpf_skb_vlan_push_proto = { .func = bpf_skb_vlan_push, .gpl_only = false, .ret_type = RET_INTEGER, @@ -2194,7 +2459,6 @@ const struct bpf_func_proto bpf_skb_vlan_push_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; -EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto); BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) { @@ -2208,13 +2472,12 @@ BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) return ret; } -const struct bpf_func_proto bpf_skb_vlan_pop_proto = { +static const struct bpf_func_proto bpf_skb_vlan_pop_proto = { .func = bpf_skb_vlan_pop, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; -EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto); static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) { @@ -2699,8 +2962,9 @@ static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { + void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); unsigned long metalen = xdp_get_metalen(xdp); - void *data_start = xdp->data_hard_start + metalen; + void *data_start = xdp_frame_end + metalen; void *data = xdp->data + offset; if (unlikely(data < data_start || @@ -2724,14 +2988,39 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) +{ + void *data_end = xdp->data_end + offset; + + /* only shrinking is allowed for now. */ + if (unlikely(offset >= 0)) + return -EINVAL; + + if (unlikely(data_end < xdp->data + ETH_HLEN)) + return -EINVAL; + + xdp->data_end = data_end; + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_adjust_tail_proto = { + .func = bpf_xdp_adjust_tail, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) { + void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); void *meta = xdp->data_meta + offset; unsigned long metalen = xdp->data - meta; if (xdp_data_meta_unsupported(xdp)) return -ENOTSUPP; - if (unlikely(meta < xdp->data_hard_start || + if (unlikely(meta < xdp_frame_end || meta > xdp->data)) return -EINVAL; if (unlikely((metalen & (sizeof(__u32) - 1)) || @@ -2756,16 +3045,20 @@ static int __bpf_tx_xdp(struct net_device *dev, struct xdp_buff *xdp, u32 index) { - int err; + struct xdp_frame *xdpf; + int sent; if (!dev->netdev_ops->ndo_xdp_xmit) { return -EOPNOTSUPP; } - err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp); - if (err) - return err; - dev->netdev_ops->ndo_xdp_flush(dev); + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) + return -EOVERFLOW; + + sent = dev->netdev_ops->ndo_xdp_xmit(dev, 1, &xdpf, XDP_XMIT_FLUSH); + if (sent <= 0) + return sent; return 0; } @@ -2776,24 +3069,33 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, { int err; - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { - struct net_device *dev = fwd; - - if (!dev->netdev_ops->ndo_xdp_xmit) - return -EOPNOTSUPP; + switch (map->map_type) { + case BPF_MAP_TYPE_DEVMAP: { + struct bpf_dtab_netdev *dst = fwd; - err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp); + err = dev_map_enqueue(dst, xdp, dev_rx); if (err) return err; __dev_map_insert_ctx(map, index); - - } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + break; + } + case BPF_MAP_TYPE_CPUMAP: { struct bpf_cpu_map_entry *rcpu = fwd; err = cpu_map_enqueue(rcpu, xdp, dev_rx); if (err) return err; __cpu_map_insert_ctx(map, index); + break; + } + case BPF_MAP_TYPE_XSKMAP: { + struct xdp_sock *xs = fwd; + + err = __xsk_map_redirect(map, xdp, xs); + return err; + } + default: + break; } return 0; } @@ -2812,6 +3114,9 @@ void xdp_do_flush_map(void) case BPF_MAP_TYPE_CPUMAP: __cpu_map_flush(map); break; + case BPF_MAP_TYPE_XSKMAP: + __xsk_map_flush(map); + break; default: break; } @@ -2826,6 +3131,8 @@ static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) return __dev_map_lookup_elem(map, index); case BPF_MAP_TYPE_CPUMAP: return __cpu_map_lookup_elem(map, index); + case BPF_MAP_TYPE_XSKMAP: + return __xsk_map_lookup_elem(map, index); default: return NULL; } @@ -2923,13 +3230,14 @@ static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd) static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, + struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; - struct net_device *fwd = NULL; u32 index = ri->ifindex; + void *fwd = NULL; int err = 0; ri->ifindex = 0; @@ -2951,6 +3259,14 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) goto err; skb->dev = fwd; + generic_xdp_tx(skb, xdp_prog); + } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { + struct xdp_sock *xs = fwd; + + err = xsk_generic_rcv(xs, xdp); + if (err) + goto err; + consume_skb(skb); } else { /* TODO: Handle BPF_MAP_TYPE_CPUMAP */ err = -EBADRQC; @@ -2965,7 +3281,7 @@ err: } int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog) + struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); u32 index = ri->ifindex; @@ -2973,7 +3289,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, int err = 0; if (ri->map) - return xdp_do_generic_redirect_map(dev, skb, xdp_prog); + return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog); ri->ifindex = 0; fwd = dev_get_by_index_rcu(dev_net(dev), index); @@ -2987,6 +3303,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, skb->dev = fwd; _trace_xdp_redirect(dev, xdp_prog, index); + generic_xdp_tx(skb, xdp_prog); return 0; err: _trace_xdp_redirect_err(dev, xdp_prog, index, err); @@ -3045,27 +3362,6 @@ static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { .arg3_type = ARG_ANYTHING, }; -bool bpf_helper_changes_pkt_data(void *func) -{ - if (func == bpf_skb_vlan_push || - func == bpf_skb_vlan_pop || - func == bpf_skb_store_bytes || - func == bpf_skb_change_proto || - func == bpf_skb_change_head || - func == bpf_skb_change_tail || - func == bpf_skb_adjust_room || - func == bpf_skb_pull_data || - func == bpf_clone_redirect || - func == bpf_l3_csum_replace || - func == bpf_l4_csum_replace || - func == bpf_xdp_adjust_head || - func == bpf_xdp_adjust_meta || - func == bpf_msg_pull_data) - return true; - - return false; -} - static unsigned long bpf_skb_copy(void *dst_buff, const void *skb, unsigned long off, unsigned long len) { @@ -3148,6 +3444,7 @@ set_compat: to->tunnel_id = be64_to_cpu(info->key.tun_id); to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; + to->tunnel_ext = 0; if (flags & BPF_F_TUNINFO_IPV6) { memcpy(to->remote_ipv6, &info->key.u.ipv6.src, @@ -3155,6 +3452,8 @@ set_compat: to->tunnel_label = be32_to_cpu(info->key.label); } else { to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); + memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); + to->tunnel_label = 0; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) @@ -3364,6 +3663,27 @@ static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { .arg3_type = ARG_ANYTHING, }; +#ifdef CONFIG_SOCK_CGROUP_DATA +BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) +{ + struct sock *sk = skb_to_full_sk(skb); + struct cgroup *cgrp; + + if (!sk || !sk_fullsock(sk)) + return 0; + + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + return cgrp->kn->id.id; +} + +static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { + .func = bpf_skb_cgroup_id, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; +#endif + static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, unsigned long off, unsigned long len) { @@ -3711,6 +4031,603 @@ static const struct bpf_func_proto bpf_bind_proto = { .arg3_type = ARG_CONST_SIZE, }; +#ifdef CONFIG_XFRM +BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index, + struct bpf_xfrm_state *, to, u32, size, u64, flags) +{ + const struct sec_path *sp = skb_sec_path(skb); + const struct xfrm_state *x; + + if (!sp || unlikely(index >= sp->len || flags)) + goto err_clear; + + x = sp->xvec[index]; + + if (unlikely(size != sizeof(struct bpf_xfrm_state))) + goto err_clear; + + to->reqid = x->props.reqid; + to->spi = x->id.spi; + to->family = x->props.family; + to->ext = 0; + + if (to->family == AF_INET6) { + memcpy(to->remote_ipv6, x->props.saddr.a6, + sizeof(to->remote_ipv6)); + } else { + to->remote_ipv4 = x->props.saddr.a4; + memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); + } + + return 0; +err_clear: + memset(to, 0, size); + return -EINVAL; +} + +static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { + .func = bpf_skb_get_xfrm_state, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, + .arg5_type = ARG_ANYTHING, +}; +#endif + +#if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) +static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, + const struct neighbour *neigh, + const struct net_device *dev) +{ + memcpy(params->dmac, neigh->ha, ETH_ALEN); + memcpy(params->smac, dev->dev_addr, ETH_ALEN); + params->h_vlan_TCI = 0; + params->h_vlan_proto = 0; + + return dev->ifindex; +} +#endif + +#if IS_ENABLED(CONFIG_INET) +static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, + u32 flags, bool check_mtu) +{ + struct in_device *in_dev; + struct neighbour *neigh; + struct net_device *dev; + struct fib_result res; + struct fib_nh *nh; + struct flowi4 fl4; + int err; + u32 mtu; + + dev = dev_get_by_index_rcu(net, params->ifindex); + if (unlikely(!dev)) + return -ENODEV; + + /* verify forwarding is enabled on this interface */ + in_dev = __in_dev_get_rcu(dev); + if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev))) + return 0; + + if (flags & BPF_FIB_LOOKUP_OUTPUT) { + fl4.flowi4_iif = 1; + fl4.flowi4_oif = params->ifindex; + } else { + fl4.flowi4_iif = params->ifindex; + fl4.flowi4_oif = 0; + } + fl4.flowi4_tos = params->tos & IPTOS_RT_MASK; + fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_flags = 0; + + fl4.flowi4_proto = params->l4_protocol; + fl4.daddr = params->ipv4_dst; + fl4.saddr = params->ipv4_src; + fl4.fl4_sport = params->sport; + fl4.fl4_dport = params->dport; + + if (flags & BPF_FIB_LOOKUP_DIRECT) { + u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; + struct fib_table *tb; + + tb = fib_get_table(net, tbid); + if (unlikely(!tb)) + return 0; + + err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); + } else { + fl4.flowi4_mark = 0; + fl4.flowi4_secid = 0; + fl4.flowi4_tun_key.tun_id = 0; + fl4.flowi4_uid = sock_net_uid(net, NULL); + + err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF); + } + + if (err || res.type != RTN_UNICAST) + return 0; + + if (res.fi->fib_nhs > 1) + fib_select_path(net, &res, &fl4, NULL); + + if (check_mtu) { + mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); + if (params->tot_len > mtu) + return 0; + } + + nh = &res.fi->fib_nh[res.nh_sel]; + + /* do not handle lwt encaps right now */ + if (nh->nh_lwtstate) + return 0; + + dev = nh->nh_dev; + if (unlikely(!dev)) + return 0; + + if (nh->nh_gw) + params->ipv4_dst = nh->nh_gw; + + params->rt_metric = res.fi->fib_priority; + + /* xdp and cls_bpf programs are run in RCU-bh so + * rcu_read_lock_bh is not needed here + */ + neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst); + if (neigh) + return bpf_fib_set_fwd_params(params, neigh, dev); + + return 0; +} +#endif + +#if IS_ENABLED(CONFIG_IPV6) +static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, + u32 flags, bool check_mtu) +{ + struct in6_addr *src = (struct in6_addr *) params->ipv6_src; + struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst; + struct neighbour *neigh; + struct net_device *dev; + struct inet6_dev *idev; + struct fib6_info *f6i; + struct flowi6 fl6; + int strict = 0; + int oif; + u32 mtu; + + /* link local addresses are never forwarded */ + if (rt6_need_strict(dst) || rt6_need_strict(src)) + return 0; + + dev = dev_get_by_index_rcu(net, params->ifindex); + if (unlikely(!dev)) + return -ENODEV; + + idev = __in6_dev_get_safely(dev); + if (unlikely(!idev || !net->ipv6.devconf_all->forwarding)) + return 0; + + if (flags & BPF_FIB_LOOKUP_OUTPUT) { + fl6.flowi6_iif = 1; + oif = fl6.flowi6_oif = params->ifindex; + } else { + oif = fl6.flowi6_iif = params->ifindex; + fl6.flowi6_oif = 0; + strict = RT6_LOOKUP_F_HAS_SADDR; + } + fl6.flowlabel = params->flowinfo; + fl6.flowi6_scope = 0; + fl6.flowi6_flags = 0; + fl6.mp_hash = 0; + + fl6.flowi6_proto = params->l4_protocol; + fl6.daddr = *dst; + fl6.saddr = *src; + fl6.fl6_sport = params->sport; + fl6.fl6_dport = params->dport; + + if (flags & BPF_FIB_LOOKUP_DIRECT) { + u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; + struct fib6_table *tb; + + tb = ipv6_stub->fib6_get_table(net, tbid); + if (unlikely(!tb)) + return 0; + + f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict); + } else { + fl6.flowi6_mark = 0; + fl6.flowi6_secid = 0; + fl6.flowi6_tun_key.tun_id = 0; + fl6.flowi6_uid = sock_net_uid(net, NULL); + + f6i = ipv6_stub->fib6_lookup(net, oif, &fl6, strict); + } + + if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry)) + return 0; + + if (unlikely(f6i->fib6_flags & RTF_REJECT || + f6i->fib6_type != RTN_UNICAST)) + return 0; + + if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0) + f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6, + fl6.flowi6_oif, NULL, + strict); + + if (check_mtu) { + mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src); + if (params->tot_len > mtu) + return 0; + } + + if (f6i->fib6_nh.nh_lwtstate) + return 0; + + if (f6i->fib6_flags & RTF_GATEWAY) + *dst = f6i->fib6_nh.nh_gw; + + dev = f6i->fib6_nh.nh_dev; + params->rt_metric = f6i->fib6_metric; + + /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is + * not needed here. Can not use __ipv6_neigh_lookup_noref here + * because we need to get nd_tbl via the stub + */ + neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128, + ndisc_hashfn, dst, dev); + if (neigh) + return bpf_fib_set_fwd_params(params, neigh, dev); + + return 0; +} +#endif + +BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, + struct bpf_fib_lookup *, params, int, plen, u32, flags) +{ + if (plen < sizeof(*params)) + return -EINVAL; + + if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT)) + return -EINVAL; + + switch (params->family) { +#if IS_ENABLED(CONFIG_INET) + case AF_INET: + return bpf_ipv4_fib_lookup(dev_net(ctx->rxq->dev), params, + flags, true); +#endif +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + return bpf_ipv6_fib_lookup(dev_net(ctx->rxq->dev), params, + flags, true); +#endif + } + return -EAFNOSUPPORT; +} + +static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = { + .func = bpf_xdp_fib_lookup, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, + struct bpf_fib_lookup *, params, int, plen, u32, flags) +{ + struct net *net = dev_net(skb->dev); + int index = -EAFNOSUPPORT; + + if (plen < sizeof(*params)) + return -EINVAL; + + if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT)) + return -EINVAL; + + switch (params->family) { +#if IS_ENABLED(CONFIG_INET) + case AF_INET: + index = bpf_ipv4_fib_lookup(net, params, flags, false); + break; +#endif +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + index = bpf_ipv6_fib_lookup(net, params, flags, false); + break; +#endif + } + + if (index > 0) { + struct net_device *dev; + + dev = dev_get_by_index_rcu(net, index); + if (!is_skb_forwardable(dev, skb)) + index = 0; + } + + return index; +} + +static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { + .func = bpf_skb_fib_lookup, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) +static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) +{ + int err; + struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)hdr; + + if (!seg6_validate_srh(srh, len)) + return -EINVAL; + + switch (type) { + case BPF_LWT_ENCAP_SEG6_INLINE: + if (skb->protocol != htons(ETH_P_IPV6)) + return -EBADMSG; + + err = seg6_do_srh_inline(skb, srh); + break; + case BPF_LWT_ENCAP_SEG6: + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + err = seg6_do_srh_encap(skb, srh, IPPROTO_IPV6); + break; + default: + return -EINVAL; + } + + bpf_compute_data_pointers(skb); + if (err) + return err; + + ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + + return seg6_lookup_nexthop(skb, NULL, 0); +} +#endif /* CONFIG_IPV6_SEG6_BPF */ + +BPF_CALL_4(bpf_lwt_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, + u32, len) +{ + switch (type) { +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) + case BPF_LWT_ENCAP_SEG6: + case BPF_LWT_ENCAP_SEG6_INLINE: + return bpf_push_seg6_encap(skb, type, hdr, len); +#endif + default: + return -EINVAL; + } +} + +static const struct bpf_func_proto bpf_lwt_push_encap_proto = { + .func = bpf_lwt_push_encap, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_CONST_SIZE +}; + +BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, + const void *, from, u32, len) +{ +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) + struct seg6_bpf_srh_state *srh_state = + this_cpu_ptr(&seg6_bpf_srh_states); + void *srh_tlvs, *srh_end, *ptr; + struct ipv6_sr_hdr *srh; + int srhoff = 0; + + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + return -EINVAL; + + srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); + srh_tlvs = (void *)((char *)srh + ((srh->first_segment + 1) << 4)); + srh_end = (void *)((char *)srh + sizeof(*srh) + srh_state->hdrlen); + + ptr = skb->data + offset; + if (ptr >= srh_tlvs && ptr + len <= srh_end) + srh_state->valid = 0; + else if (ptr < (void *)&srh->flags || + ptr + len > (void *)&srh->segments) + return -EFAULT; + + if (unlikely(bpf_try_make_writable(skb, offset + len))) + return -EFAULT; + + memcpy(skb->data + offset, from, len); + return 0; +#else /* CONFIG_IPV6_SEG6_BPF */ + return -EOPNOTSUPP; +#endif +} + +static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { + .func = bpf_lwt_seg6_store_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_CONST_SIZE +}; + +BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, + u32, action, void *, param, u32, param_len) +{ +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) + struct seg6_bpf_srh_state *srh_state = + this_cpu_ptr(&seg6_bpf_srh_states); + struct ipv6_sr_hdr *srh; + int srhoff = 0; + int err; + + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + return -EINVAL; + srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); + + if (!srh_state->valid) { + if (unlikely((srh_state->hdrlen & 7) != 0)) + return -EBADMSG; + + srh->hdrlen = (u8)(srh_state->hdrlen >> 3); + if (unlikely(!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3))) + return -EBADMSG; + + srh_state->valid = 1; + } + + switch (action) { + case SEG6_LOCAL_ACTION_END_X: + if (param_len != sizeof(struct in6_addr)) + return -EINVAL; + return seg6_lookup_nexthop(skb, (struct in6_addr *)param, 0); + case SEG6_LOCAL_ACTION_END_T: + if (param_len != sizeof(int)) + return -EINVAL; + return seg6_lookup_nexthop(skb, NULL, *(int *)param); + case SEG6_LOCAL_ACTION_END_B6: + err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6_INLINE, + param, param_len); + if (!err) + srh_state->hdrlen = + ((struct ipv6_sr_hdr *)param)->hdrlen << 3; + return err; + case SEG6_LOCAL_ACTION_END_B6_ENCAP: + err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6, + param, param_len); + if (!err) + srh_state->hdrlen = + ((struct ipv6_sr_hdr *)param)->hdrlen << 3; + return err; + default: + return -EINVAL; + } +#else /* CONFIG_IPV6_SEG6_BPF */ + return -EOPNOTSUPP; +#endif +} + +static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { + .func = bpf_lwt_seg6_action, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_CONST_SIZE +}; + +BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, + s32, len) +{ +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) + struct seg6_bpf_srh_state *srh_state = + this_cpu_ptr(&seg6_bpf_srh_states); + void *srh_end, *srh_tlvs, *ptr; + struct ipv6_sr_hdr *srh; + struct ipv6hdr *hdr; + int srhoff = 0; + int ret; + + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + return -EINVAL; + srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); + + srh_tlvs = (void *)((unsigned char *)srh + sizeof(*srh) + + ((srh->first_segment + 1) << 4)); + srh_end = (void *)((unsigned char *)srh + sizeof(*srh) + + srh_state->hdrlen); + ptr = skb->data + offset; + + if (unlikely(ptr < srh_tlvs || ptr > srh_end)) + return -EFAULT; + if (unlikely(len < 0 && (void *)((char *)ptr - len) > srh_end)) + return -EFAULT; + + if (len > 0) { + ret = skb_cow_head(skb, len); + if (unlikely(ret < 0)) + return ret; + + ret = bpf_skb_net_hdr_push(skb, offset, len); + } else { + ret = bpf_skb_net_hdr_pop(skb, offset, -1 * len); + } + + bpf_compute_data_pointers(skb); + if (unlikely(ret < 0)) + return ret; + + hdr = (struct ipv6hdr *)skb->data; + hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + + srh_state->hdrlen += len; + srh_state->valid = 0; + return 0; +#else /* CONFIG_IPV6_SEG6_BPF */ + return -EOPNOTSUPP; +#endif +} + +static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { + .func = bpf_lwt_seg6_adjust_srh, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + +bool bpf_helper_changes_pkt_data(void *func) +{ + if (func == bpf_skb_vlan_push || + func == bpf_skb_vlan_pop || + func == bpf_skb_store_bytes || + func == bpf_skb_change_proto || + func == bpf_skb_change_head || + func == bpf_skb_change_tail || + func == bpf_skb_adjust_room || + func == bpf_skb_pull_data || + func == bpf_clone_redirect || + func == bpf_l3_csum_replace || + func == bpf_l4_csum_replace || + func == bpf_xdp_adjust_head || + func == bpf_xdp_adjust_meta || + func == bpf_msg_pull_data || + func == bpf_xdp_adjust_tail || + func == bpf_lwt_push_encap || + func == bpf_lwt_seg6_store_bytes || + func == bpf_lwt_seg6_adjust_srh || + func == bpf_lwt_seg6_action + ) + return true; + + return false; +} + static const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { @@ -3781,6 +4698,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_load_bytes_relative: + return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: @@ -3798,6 +4717,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_load_bytes_relative: + return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: @@ -3852,6 +4773,16 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; + case BPF_FUNC_fib_lookup: + return &bpf_skb_fib_lookup_proto; +#ifdef CONFIG_XFRM + case BPF_FUNC_skb_get_xfrm_state: + return &bpf_skb_get_xfrm_state_proto; +#endif +#ifdef CONFIG_SOCK_CGROUP_DATA + case BPF_FUNC_skb_cgroup_id: + return &bpf_skb_cgroup_id_proto; +#endif default: return bpf_base_func_proto(func_id); } @@ -3875,33 +4806,10 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: return &bpf_xdp_redirect_map_proto; - default: - return bpf_base_func_proto(func_id); - } -} - -static const struct bpf_func_proto * -lwt_inout_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) -{ - switch (func_id) { - case BPF_FUNC_skb_load_bytes: - return &bpf_skb_load_bytes_proto; - case BPF_FUNC_skb_pull_data: - return &bpf_skb_pull_data_proto; - case BPF_FUNC_csum_diff: - return &bpf_csum_diff_proto; - case BPF_FUNC_get_cgroup_classid: - return &bpf_get_cgroup_classid_proto; - case BPF_FUNC_get_route_realm: - return &bpf_get_route_realm_proto; - case BPF_FUNC_get_hash_recalc: - return &bpf_get_hash_recalc_proto; - case BPF_FUNC_perf_event_output: - return &bpf_skb_event_output_proto; - case BPF_FUNC_get_smp_processor_id: - return &bpf_get_smp_processor_id_proto; - case BPF_FUNC_skb_under_cgroup: - return &bpf_skb_under_cgroup_proto; + case BPF_FUNC_xdp_adjust_tail: + return &bpf_xdp_adjust_tail_proto; + case BPF_FUNC_fib_lookup: + return &bpf_xdp_fib_lookup_proto; default: return bpf_base_func_proto(func_id); } @@ -3919,6 +4827,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sock_ops_cb_flags_set_proto; case BPF_FUNC_sock_map_update: return &bpf_sock_map_update_proto; + case BPF_FUNC_sock_hash_update: + return &bpf_sock_hash_update_proto; default: return bpf_base_func_proto(func_id); } @@ -3930,6 +4840,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) switch (func_id) { case BPF_FUNC_msg_redirect_map: return &bpf_msg_redirect_map_proto; + case BPF_FUNC_msg_redirect_hash: + return &bpf_msg_redirect_hash_proto; case BPF_FUNC_msg_apply_bytes: return &bpf_msg_apply_bytes_proto; case BPF_FUNC_msg_cork_bytes: @@ -3961,12 +4873,52 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_uid_proto; case BPF_FUNC_sk_redirect_map: return &bpf_sk_redirect_map_proto; + case BPF_FUNC_sk_redirect_hash: + return &bpf_sk_redirect_hash_proto; default: return bpf_base_func_proto(func_id); } } static const struct bpf_func_proto * +lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_skb_load_bytes: + return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_pull_data: + return &bpf_skb_pull_data_proto; + case BPF_FUNC_csum_diff: + return &bpf_csum_diff_proto; + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_proto; + case BPF_FUNC_get_route_realm: + return &bpf_get_route_realm_proto; + case BPF_FUNC_get_hash_recalc: + return &bpf_get_hash_recalc_proto; + case BPF_FUNC_perf_event_output: + return &bpf_skb_event_output_proto; + case BPF_FUNC_get_smp_processor_id: + return &bpf_get_smp_processor_id_proto; + case BPF_FUNC_skb_under_cgroup: + return &bpf_skb_under_cgroup_proto; + default: + return bpf_base_func_proto(func_id); + } +} + +static const struct bpf_func_proto * +lwt_in_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_lwt_push_encap: + return &bpf_lwt_push_encap_proto; + default: + return lwt_out_func_proto(func_id, prog); + } +} + +static const struct bpf_func_proto * lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { @@ -3997,7 +4949,22 @@ lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; default: - return lwt_inout_func_proto(func_id, prog); + return lwt_out_func_proto(func_id, prog); + } +} + +static const struct bpf_func_proto * +lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_lwt_seg6_store_bytes: + return &bpf_lwt_seg6_store_bytes_proto; + case BPF_FUNC_lwt_seg6_action: + return &bpf_lwt_seg6_action_proto; + case BPF_FUNC_lwt_seg6_adjust_srh: + return &bpf_lwt_seg6_adjust_srh_proto; + default: + return lwt_out_func_proto(func_id, prog); } } @@ -4105,7 +5072,6 @@ static bool lwt_is_valid_access(int off, int size, return bpf_skb_is_valid_access(off, size, type, prog, info); } - /* Attach type specific accesses */ static bool __sock_filter_check_attach_type(int off, enum bpf_access_type access_type, @@ -4221,6 +5187,41 @@ static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, return insn - insn_buf; } +static int bpf_gen_ld_abs(const struct bpf_insn *orig, + struct bpf_insn *insn_buf) +{ + bool indirect = BPF_MODE(orig->code) == BPF_IND; + struct bpf_insn *insn = insn_buf; + + /* We're guaranteed here that CTX is in R6. */ + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); + if (!indirect) { + *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); + } else { + *insn++ = BPF_MOV64_REG(BPF_REG_2, orig->src_reg); + if (orig->imm) + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); + } + + switch (BPF_SIZE(orig->code)) { + case BPF_B: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8_no_cache); + break; + case BPF_H: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16_no_cache); + break; + case BPF_W: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32_no_cache); + break; + } + + *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 2); + *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); + *insn++ = BPF_EXIT_INSN(); + + return insn - insn_buf; +} + static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { @@ -4279,8 +5280,15 @@ static bool xdp_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (type == BPF_WRITE) + if (type == BPF_WRITE) { + if (bpf_prog_is_dev_bound(prog->aux)) { + switch (off) { + case offsetof(struct xdp_md, rx_queue_index): + return __is_valid_xdp_access(off, size); + } + } return false; + } switch (off) { case offsetof(struct xdp_md, data): @@ -4327,6 +5335,7 @@ static bool sock_addr_is_valid_access(int off, int size, switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: break; default: return false; @@ -4336,6 +5345,24 @@ static bool sock_addr_is_valid_access(int off, int size, switch (prog->expected_attach_type) { case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP6_SENDMSG: + break; + default: + return false; + } + break; + case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): + switch (prog->expected_attach_type) { + case BPF_CGROUP_UDP4_SENDMSG: + break; + default: + return false; + } + break; + case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], + msg_src_ip6[3]): + switch (prog->expected_attach_type) { + case BPF_CGROUP_UDP6_SENDMSG: break; default: return false; @@ -4346,6 +5373,9 @@ static bool sock_addr_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): + case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): + case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], + msg_src_ip6[3]): /* Only narrow read access allowed for now. */ if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); @@ -4465,18 +5495,23 @@ static bool sk_msg_is_valid_access(int off, int size, switch (off) { case offsetof(struct sk_msg_md, data): info->reg_type = PTR_TO_PACKET; + if (size != sizeof(__u64)) + return false; break; case offsetof(struct sk_msg_md, data_end): info->reg_type = PTR_TO_PACKET_END; + if (size != sizeof(__u64)) + return false; break; + default: + if (size != sizeof(__u32)) + return false; } if (off < 0 || off >= sizeof(struct sk_msg_md)) return false; if (off % size != 0) return false; - if (size != sizeof(__u64)) - return false; return true; } @@ -5095,6 +6130,23 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT); break; + + case offsetof(struct bpf_sock_addr, msg_src_ip4): + /* Treat t_ctx as struct in_addr for msg_src_ip4. */ + SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( + struct bpf_sock_addr_kern, struct in_addr, t_ctx, + s_addr, BPF_SIZE(si->code), 0, tmp_reg); + break; + + case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], + msg_src_ip6[3]): + off = si->off; + off -= offsetof(struct bpf_sock_addr, msg_src_ip6[0]); + /* Treat t_ctx as struct in6_addr for msg_src_ip6. */ + SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( + struct bpf_sock_addr_kern, struct in6_addr, t_ctx, + s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); + break; } return insn - insn_buf; @@ -5152,7 +6204,8 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_ops, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_rcv_saddr) != 4); + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@ -5469,6 +6522,9 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; +#if IS_ENABLED(CONFIG_IPV6) + int off; +#endif switch (si->off) { case offsetof(struct sk_msg_md, data): @@ -5481,6 +6537,107 @@ static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, offsetof(struct sk_msg_buff, data_end)); break; + case offsetof(struct sk_msg_md, family): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct sk_msg_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_msg_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_family)); + break; + + case offsetof(struct sk_msg_md, remote_ip4): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct sk_msg_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_msg_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_daddr)); + break; + + case offsetof(struct sk_msg_md, local_ip4): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_rcv_saddr) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct sk_msg_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_msg_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_rcv_saddr)); + break; + + case offsetof(struct sk_msg_md, remote_ip6[0]) ... + offsetof(struct sk_msg_md, remote_ip6[3]): +#if IS_ENABLED(CONFIG_IPV6) + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_v6_daddr.s6_addr32[0]) != 4); + + off = si->off; + off -= offsetof(struct sk_msg_md, remote_ip6[0]); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct sk_msg_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_msg_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_v6_daddr.s6_addr32[0]) + + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + + case offsetof(struct sk_msg_md, local_ip6[0]) ... + offsetof(struct sk_msg_md, local_ip6[3]): +#if IS_ENABLED(CONFIG_IPV6) + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_v6_rcv_saddr.s6_addr32[0]) != 4); + + off = si->off; + off -= offsetof(struct sk_msg_md, local_ip6[0]); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct sk_msg_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_msg_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_v6_rcv_saddr.s6_addr32[0]) + + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + + case offsetof(struct sk_msg_md, remote_port): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct sk_msg_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_msg_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_dport)); +#ifndef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); +#endif + break; + + case offsetof(struct sk_msg_md, local_port): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct sk_msg_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_msg_buff, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_num)); + break; } return insn - insn_buf; @@ -5490,6 +6647,7 @@ const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, + .gen_ld_abs = bpf_gen_ld_abs, }; const struct bpf_prog_ops sk_filter_prog_ops = { @@ -5501,6 +6659,7 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, + .gen_ld_abs = bpf_gen_ld_abs, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { @@ -5527,13 +6686,23 @@ const struct bpf_prog_ops cg_skb_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops lwt_inout_verifier_ops = { - .get_func_proto = lwt_inout_func_proto, +const struct bpf_verifier_ops lwt_in_verifier_ops = { + .get_func_proto = lwt_in_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; -const struct bpf_prog_ops lwt_inout_prog_ops = { +const struct bpf_prog_ops lwt_in_prog_ops = { + .test_run = bpf_prog_test_run_skb, +}; + +const struct bpf_verifier_ops lwt_out_verifier_ops = { + .get_func_proto = lwt_out_func_proto, + .is_valid_access = lwt_is_valid_access, + .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops lwt_out_prog_ops = { .test_run = bpf_prog_test_run_skb, }; @@ -5548,6 +6717,16 @@ const struct bpf_prog_ops lwt_xmit_prog_ops = { .test_run = bpf_prog_test_run_skb, }; +const struct bpf_verifier_ops lwt_seg6local_verifier_ops = { + .get_func_proto = lwt_seg6local_func_proto, + .is_valid_access = lwt_is_valid_access, + .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops lwt_seg6local_prog_ops = { + .test_run = bpf_prog_test_run_skb, +}; + const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d29f09bc5ff90..53f96e4f7bf59 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1253,7 +1253,7 @@ __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb) EXPORT_SYMBOL(skb_get_hash_perturb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, - const struct flow_keys *keys, int hlen) + const struct flow_keys_basic *keys, int hlen) { u32 poff = keys->control.thoff; @@ -1314,9 +1314,9 @@ u32 __skb_get_poff(const struct sk_buff *skb, void *data, */ u32 skb_get_poff(const struct sk_buff *skb) { - struct flow_keys keys; + struct flow_keys_basic keys; - if (!skb_flow_dissect_flow_keys(skb, &keys, 0)) + if (!skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); @@ -1334,7 +1334,7 @@ __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys) keys->ports.src = fl6->fl6_sport; keys->ports.dst = fl6->fl6_dport; keys->keyid.keyid = fl6->fl6_gre_key; - keys->tags.flow_label = (__force u32)fl6->flowlabel; + keys->tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); keys->basic.ip_proto = fl6->flowi6_proto; return flow_hash_from_keys(keys); @@ -1403,7 +1403,7 @@ static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { }, }; -static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { +static const struct flow_dissector_key flow_keys_basic_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), @@ -1417,7 +1417,8 @@ static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { struct flow_dissector flow_keys_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_dissector); -struct flow_dissector flow_keys_buf_dissector __read_mostly; +struct flow_dissector flow_keys_basic_dissector __read_mostly; +EXPORT_SYMBOL(flow_keys_basic_dissector); static int __init init_default_flow_dissectors(void) { @@ -1427,9 +1428,9 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_dissector_symmetric, flow_keys_dissector_symmetric_keys, ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); - skb_flow_dissector_init(&flow_keys_buf_dissector, - flow_keys_buf_dissector_keys, - ARRAY_SIZE(flow_keys_buf_dissector_keys)); + skb_flow_dissector_init(&flow_keys_basic_dissector, + flow_keys_basic_dissector_keys, + ARRAY_SIZE(flow_keys_basic_dissector_keys)); return 0; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 1fb43bff417d7..a7a9c3d738ba8 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -820,7 +820,8 @@ static void neigh_periodic_work(struct work_struct *work) write_lock(&n->lock); state = n->nud_state; - if (state & (NUD_PERMANENT | NUD_IN_TIMER)) { + if ((state & (NUD_PERMANENT | NUD_IN_TIMER)) || + (n->flags & NTF_EXT_LEARNED)) { write_unlock(&n->lock); goto next_elt; } @@ -1136,6 +1137,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, if (neigh->dead) goto out; + neigh_update_ext_learned(neigh, flags, ¬ify); + if (!(new & NUD_VALID)) { neigh_del_timer(neigh); if (old & NUD_CONNECTED) @@ -1781,6 +1784,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, flags &= ~NEIGH_UPDATE_F_OVERRIDE; } + if (ndm->ndm_flags & NTF_EXT_LEARNED) + flags |= NEIGH_UPDATE_F_EXT_LEARNED; + if (ndm->ndm_flags & NTF_USE) { neigh_event_send(neigh, NULL); err = 0; diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 380934580fa14..419af6dfe29f4 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -35,10 +35,6 @@ #include <trace/events/tcp.h> #include <trace/events/fib.h> #include <trace/events/qdisc.h> -#if IS_ENABLED(CONFIG_IPV6) -#include <trace/events/fib6.h> -EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup); -#endif #if IS_ENABLED(CONFIG_BRIDGE) #include <trace/events/bridge.h> EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_add); diff --git a/net/core/page_pool.c b/net/core/page_pool.c new file mode 100644 index 0000000000000..68bf072067442 --- /dev/null +++ b/net/core/page_pool.c @@ -0,0 +1,317 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * page_pool.c + * Author: Jesper Dangaard Brouer <netoptimizer@brouer.com> + * Copyright (C) 2016 Red Hat, Inc. + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/slab.h> + +#include <net/page_pool.h> +#include <linux/dma-direction.h> +#include <linux/dma-mapping.h> +#include <linux/page-flags.h> +#include <linux/mm.h> /* for __put_page() */ + +static int page_pool_init(struct page_pool *pool, + const struct page_pool_params *params) +{ + unsigned int ring_qsize = 1024; /* Default */ + + memcpy(&pool->p, params, sizeof(pool->p)); + + /* Validate only known flags were used */ + if (pool->p.flags & ~(PP_FLAG_ALL)) + return -EINVAL; + + if (pool->p.pool_size) + ring_qsize = pool->p.pool_size; + + /* Sanity limit mem that can be pinned down */ + if (ring_qsize > 32768) + return -E2BIG; + + /* DMA direction is either DMA_FROM_DEVICE or DMA_BIDIRECTIONAL. + * DMA_BIDIRECTIONAL is for allowing page used for DMA sending, + * which is the XDP_TX use-case. + */ + if ((pool->p.dma_dir != DMA_FROM_DEVICE) && + (pool->p.dma_dir != DMA_BIDIRECTIONAL)) + return -EINVAL; + + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) + return -ENOMEM; + + return 0; +} + +struct page_pool *page_pool_create(const struct page_pool_params *params) +{ + struct page_pool *pool; + int err = 0; + + pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, params->nid); + if (!pool) + return ERR_PTR(-ENOMEM); + + err = page_pool_init(pool, params); + if (err < 0) { + pr_warn("%s() gave up with errno %d\n", __func__, err); + kfree(pool); + return ERR_PTR(err); + } + return pool; +} +EXPORT_SYMBOL(page_pool_create); + +/* fast path */ +static struct page *__page_pool_get_cached(struct page_pool *pool) +{ + struct ptr_ring *r = &pool->ring; + struct page *page; + + /* Quicker fallback, avoid locks when ring is empty */ + if (__ptr_ring_empty(r)) + return NULL; + + /* Test for safe-context, caller should provide this guarantee */ + if (likely(in_serving_softirq())) { + if (likely(pool->alloc.count)) { + /* Fast-path */ + page = pool->alloc.cache[--pool->alloc.count]; + return page; + } + /* Slower-path: Alloc array empty, time to refill + * + * Open-coded bulk ptr_ring consumer. + * + * Discussion: the ring consumer lock is not really + * needed due to the softirq/NAPI protection, but + * later need the ability to reclaim pages on the + * ring. Thus, keeping the locks. + */ + spin_lock(&r->consumer_lock); + while ((page = __ptr_ring_consume(r))) { + if (pool->alloc.count == PP_ALLOC_CACHE_REFILL) + break; + pool->alloc.cache[pool->alloc.count++] = page; + } + spin_unlock(&r->consumer_lock); + return page; + } + + /* Slow-path: Get page from locked ring queue */ + page = ptr_ring_consume(&pool->ring); + return page; +} + +/* slow path */ +noinline +static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, + gfp_t _gfp) +{ + struct page *page; + gfp_t gfp = _gfp; + dma_addr_t dma; + + /* We could always set __GFP_COMP, and avoid this branch, as + * prep_new_page() can handle order-0 with __GFP_COMP. + */ + if (pool->p.order) + gfp |= __GFP_COMP; + + /* FUTURE development: + * + * Current slow-path essentially falls back to single page + * allocations, which doesn't improve performance. This code + * need bulk allocation support from the page allocator code. + */ + + /* Cache was empty, do real allocation */ + page = alloc_pages_node(pool->p.nid, gfp, pool->p.order); + if (!page) + return NULL; + + if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + goto skip_dma_map; + + /* Setup DMA mapping: use page->private for DMA-addr + * This mapping is kept for lifetime of page, until leaving pool. + */ + dma = dma_map_page(pool->p.dev, page, 0, + (PAGE_SIZE << pool->p.order), + pool->p.dma_dir); + if (dma_mapping_error(pool->p.dev, dma)) { + put_page(page); + return NULL; + } + set_page_private(page, dma); /* page->private = dma; */ + +skip_dma_map: + /* When page just alloc'ed is should/must have refcnt 1. */ + return page; +} + +/* For using page_pool replace: alloc_pages() API calls, but provide + * synchronization guarantee for allocation side. + */ +struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) +{ + struct page *page; + + /* Fast-path: Get a page from cache */ + page = __page_pool_get_cached(pool); + if (page) + return page; + + /* Slow-path: cache empty, do real allocation */ + page = __page_pool_alloc_pages_slow(pool, gfp); + return page; +} +EXPORT_SYMBOL(page_pool_alloc_pages); + +/* Cleanup page_pool state from page */ +static void __page_pool_clean_page(struct page_pool *pool, + struct page *page) +{ + if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + return; + + /* DMA unmap */ + dma_unmap_page(pool->p.dev, page_private(page), + PAGE_SIZE << pool->p.order, pool->p.dma_dir); + set_page_private(page, 0); +} + +/* Return a page to the page allocator, cleaning up our state */ +static void __page_pool_return_page(struct page_pool *pool, struct page *page) +{ + __page_pool_clean_page(pool, page); + put_page(page); + /* An optimization would be to call __free_pages(page, pool->p.order) + * knowing page is not part of page-cache (thus avoiding a + * __page_cache_release() call). + */ +} + +static bool __page_pool_recycle_into_ring(struct page_pool *pool, + struct page *page) +{ + int ret; + /* BH protection not needed if current is serving softirq */ + if (in_serving_softirq()) + ret = ptr_ring_produce(&pool->ring, page); + else + ret = ptr_ring_produce_bh(&pool->ring, page); + + return (ret == 0) ? true : false; +} + +/* Only allow direct recycling in special circumstances, into the + * alloc side cache. E.g. during RX-NAPI processing for XDP_DROP use-case. + * + * Caller must provide appropriate safe context. + */ +static bool __page_pool_recycle_direct(struct page *page, + struct page_pool *pool) +{ + if (unlikely(pool->alloc.count == PP_ALLOC_CACHE_SIZE)) + return false; + + /* Caller MUST have verified/know (page_ref_count(page) == 1) */ + pool->alloc.cache[pool->alloc.count++] = page; + return true; +} + +void __page_pool_put_page(struct page_pool *pool, + struct page *page, bool allow_direct) +{ + /* This allocator is optimized for the XDP mode that uses + * one-frame-per-page, but have fallbacks that act like the + * regular page allocator APIs. + * + * refcnt == 1 means page_pool owns page, and can recycle it. + */ + if (likely(page_ref_count(page) == 1)) { + /* Read barrier done in page_ref_count / READ_ONCE */ + + if (allow_direct && in_serving_softirq()) + if (__page_pool_recycle_direct(page, pool)) + return; + + if (!__page_pool_recycle_into_ring(pool, page)) { + /* Cache full, fallback to free pages */ + __page_pool_return_page(pool, page); + } + return; + } + /* Fallback/non-XDP mode: API user have elevated refcnt. + * + * Many drivers split up the page into fragments, and some + * want to keep doing this to save memory and do refcnt based + * recycling. Support this use case too, to ease drivers + * switching between XDP/non-XDP. + * + * In-case page_pool maintains the DMA mapping, API user must + * call page_pool_put_page once. In this elevated refcnt + * case, the DMA is unmapped/released, as driver is likely + * doing refcnt based recycle tricks, meaning another process + * will be invoking put_page. + */ + __page_pool_clean_page(pool, page); + put_page(page); +} +EXPORT_SYMBOL(__page_pool_put_page); + +static void __page_pool_empty_ring(struct page_pool *pool) +{ + struct page *page; + + /* Empty recycle ring */ + while ((page = ptr_ring_consume(&pool->ring))) { + /* Verify the refcnt invariant of cached pages */ + if (!(page_ref_count(page) == 1)) + pr_crit("%s() page_pool refcnt %d violation\n", + __func__, page_ref_count(page)); + + __page_pool_return_page(pool, page); + } +} + +static void __page_pool_destroy_rcu(struct rcu_head *rcu) +{ + struct page_pool *pool; + + pool = container_of(rcu, struct page_pool, rcu); + + WARN(pool->alloc.count, "API usage violation"); + + __page_pool_empty_ring(pool); + ptr_ring_cleanup(&pool->ring, NULL); + kfree(pool); +} + +/* Cleanup and release resources */ +void page_pool_destroy(struct page_pool *pool) +{ + struct page *page; + + /* Empty alloc cache, assume caller made sure this is + * no-longer in use, and page_pool_alloc_pages() cannot be + * call concurrently. + */ + while (pool->alloc.count) { + page = pool->alloc.cache[--pool->alloc.count]; + __page_pool_return_page(pool, page); + } + + /* No more consumers should exist, but producers could still + * be in-flight. + */ + __page_pool_empty_ring(pool); + + /* An xdp_mem_allocator can still ref page_pool pointer */ + call_rcu(&pool->rcu, __page_pool_destroy_rcu); +} +EXPORT_SYMBOL(page_pool_destroy); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 45936922d7e23..5ef61222fdef1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -59,6 +59,9 @@ #include <net/rtnetlink.h> #include <net/net_namespace.h> +#define RTNL_MAX_TYPE 48 +#define RTNL_SLAVE_MAX_TYPE 36 + struct rtnl_link { rtnl_doit_func doit; rtnl_dumpit_func dumpit; @@ -389,6 +392,11 @@ int rtnl_link_register(struct rtnl_link_ops *ops) { int err; + /* Sanity-check max sizes to avoid stack buffer overflow. */ + if (WARN_ON(ops->maxtype > RTNL_MAX_TYPE || + ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE)) + return -EINVAL; + rtnl_lock(); err = __rtnl_link_register(ops); rtnl_unlock(); @@ -785,13 +793,15 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error) { struct rta_cacheinfo ci = { - .rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse), - .rta_used = dst->__use, - .rta_clntref = atomic_read(&(dst->__refcnt)), .rta_error = error, .rta_id = id, }; + if (dst) { + ci.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse); + ci.rta_used = dst->__use; + ci.rta_clntref = atomic_read(&dst->__refcnt); + } if (expires) { unsigned long clock; @@ -2256,6 +2266,10 @@ static int do_setlink(const struct sk_buff *skb, const struct net_device_ops *ops = dev->netdev_ops; int err; + err = validate_linkmsg(dev, tb); + if (err < 0) + return err; + if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_IF_NETNSID]) { struct net *net = rtnl_link_get_net_capable(skb, dev_net(dev), tb, CAP_NET_ADMIN); @@ -2619,10 +2633,6 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - err = validate_linkmsg(dev, tb); - if (err < 0) - goto errout; - err = do_setlink(skb, dev, ifm, extack, tb, ifname, 0); errout: return err; @@ -2900,13 +2910,16 @@ replay: } if (1) { - struct nlattr *attr[ops ? ops->maxtype + 1 : 1]; - struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 1]; + struct nlattr *attr[RTNL_MAX_TYPE + 1]; + struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1]; struct nlattr **data = NULL; struct nlattr **slave_data = NULL; struct net *dest_net, *link_net = NULL; if (ops) { + if (ops->maxtype > RTNL_MAX_TYPE) + return -EINVAL; + if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) { err = nla_parse_nested(attr, ops->maxtype, linkinfo[IFLA_INFO_DATA], @@ -2923,6 +2936,9 @@ replay: } if (m_ops) { + if (m_ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE) + return -EINVAL; + if (m_ops->slave_maxtype && linkinfo[IFLA_INFO_SLAVE_DATA]) { err = nla_parse_nested(slave_attr, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 345b51837ca80..c642304f178ce 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1305,7 +1305,7 @@ static void skb_headers_offset_update(struct sk_buff *skb, int off) skb->inner_mac_header += off; } -static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) +void skb_copy_header(struct sk_buff *new, const struct sk_buff *old) { __copy_skb_header(new, old); @@ -1313,6 +1313,7 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } +EXPORT_SYMBOL(skb_copy_header); static inline int skb_alloc_rx_flag(const struct sk_buff *skb) { @@ -1355,7 +1356,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); - copy_skb_header(n, skb); + skb_copy_header(n, skb); return n; } EXPORT_SYMBOL(skb_copy); @@ -1419,7 +1420,7 @@ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, skb_clone_fraglist(n); } - copy_skb_header(n, skb); + skb_copy_header(n, skb); out: return n; } @@ -1599,7 +1600,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, skb->len + head_copy_len)); - copy_skb_header(n, skb); + skb_copy_header(n, skb); skb_headers_offset_update(n, newheadroom - oldheadroom); @@ -1839,6 +1840,20 @@ done: } EXPORT_SYMBOL(___pskb_trim); +/* Note : use pskb_trim_rcsum() instead of calling this directly + */ +int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) { + int delta = skb->len - len; + + skb->csum = csum_sub(skb->csum, + skb_checksum(skb, len, delta, 0)); + } + return __pskb_trim(skb, len); +} +EXPORT_SYMBOL(pskb_trim_rcsum_slow); + /** * __pskb_pull_tail - advance tail of skb header * @skb: buffer to reallocate @@ -4926,6 +4941,8 @@ static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) thlen = tcp_hdrlen(skb); } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); + } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { + thlen = sizeof(struct udphdr); } /* UFO sets gso_size to the size of the fragmentation * payload, i.e. the size of the L4 (UDP) header is already diff --git a/net/core/sock.c b/net/core/sock.c index 2aed99a541d5d..f333d75ef1a9c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -226,7 +226,8 @@ static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ - x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX" + x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ + x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { _sock_locks("sk_lock-") @@ -262,7 +263,8 @@ static const char *const af_family_rlock_key_strings[AF_MAX+1] = { "rlock-AF_RXRPC" , "rlock-AF_ISDN" , "rlock-AF_PHONET" , "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG" , "rlock-AF_NFC" , "rlock-AF_VSOCK" , "rlock-AF_KCM" , - "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_MAX" + "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_XDP" , + "rlock-AF_MAX" }; static const char *const af_family_wlock_key_strings[AF_MAX+1] = { "wlock-AF_UNSPEC", "wlock-AF_UNIX" , "wlock-AF_INET" , @@ -279,7 +281,8 @@ static const char *const af_family_wlock_key_strings[AF_MAX+1] = { "wlock-AF_RXRPC" , "wlock-AF_ISDN" , "wlock-AF_PHONET" , "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG" , "wlock-AF_NFC" , "wlock-AF_VSOCK" , "wlock-AF_KCM" , - "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_MAX" + "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_XDP" , + "wlock-AF_MAX" }; static const char *const af_family_elock_key_strings[AF_MAX+1] = { "elock-AF_UNSPEC", "elock-AF_UNIX" , "elock-AF_INET" , @@ -296,7 +299,8 @@ static const char *const af_family_elock_key_strings[AF_MAX+1] = { "elock-AF_RXRPC" , "elock-AF_ISDN" , "elock-AF_PHONET" , "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG" , "elock-AF_NFC" , "elock-AF_VSOCK" , "elock-AF_KCM" , - "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_MAX" + "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_XDP" , + "elock-AF_MAX" }; /* @@ -323,8 +327,8 @@ EXPORT_SYMBOL(sysctl_optmem_max); int sysctl_tstamp_allow_data __read_mostly = 1; -struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE; -EXPORT_SYMBOL_GPL(memalloc_socks); +DEFINE_STATIC_KEY_FALSE(memalloc_socks_key); +EXPORT_SYMBOL_GPL(memalloc_socks_key); /** * sk_set_memalloc - sets %SOCK_MEMALLOC @@ -338,7 +342,7 @@ void sk_set_memalloc(struct sock *sk) { sock_set_flag(sk, SOCK_MEMALLOC); sk->sk_allocation |= __GFP_MEMALLOC; - static_key_slow_inc(&memalloc_socks); + static_branch_inc(&memalloc_socks_key); } EXPORT_SYMBOL_GPL(sk_set_memalloc); @@ -346,7 +350,7 @@ void sk_clear_memalloc(struct sock *sk) { sock_reset_flag(sk, SOCK_MEMALLOC); sk->sk_allocation &= ~__GFP_MEMALLOC; - static_key_slow_dec(&memalloc_socks); + static_branch_dec(&memalloc_socks_key); /* * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward @@ -724,9 +728,22 @@ int sock_setsockopt(struct socket *sock, int level, int optname, sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: - sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); + val = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); + if ((sk->sk_family == PF_INET || sk->sk_family == PF_INET6) && + inet_sk(sk)->inet_num && + (sk->sk_reuse != val)) { + ret = (sk->sk_state == TCP_ESTABLISHED) ? -EISCONN : -EUCLEAN; + break; + } + sk->sk_reuse = val; break; case SO_REUSEPORT: + if ((sk->sk_family == PF_INET || sk->sk_family == PF_INET6) && + inet_sk(sk)->inet_num && + (sk->sk_reuseport != valbool)) { + ret = (sk->sk_state == TCP_ESTABLISHED) ? -EISCONN : -EUCLEAN; + break; + } sk->sk_reuseport = valbool; break; case SO_TYPE: @@ -905,7 +922,10 @@ set_rcvbuf: case SO_RCVLOWAT: if (val < 0) val = INT_MAX; - sk->sk_rcvlowat = val ? : 1; + if (sock->ops->set_rcvlowat) + ret = sock->ops->set_rcvlowat(sk, val); + else + sk->sk_rcvlowat = val ? : 1; break; case SO_RCVTIMEO: diff --git a/net/core/xdp.c b/net/core/xdp.c index 097a0f74e0048..9d1f22072d5d5 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -5,6 +5,10 @@ */ #include <linux/types.h> #include <linux/mm.h> +#include <linux/slab.h> +#include <linux/idr.h> +#include <linux/rhashtable.h> +#include <net/page_pool.h> #include <net/xdp.h> @@ -13,6 +17,105 @@ #define REG_STATE_UNREGISTERED 0x2 #define REG_STATE_UNUSED 0x3 +static DEFINE_IDA(mem_id_pool); +static DEFINE_MUTEX(mem_id_lock); +#define MEM_ID_MAX 0xFFFE +#define MEM_ID_MIN 1 +static int mem_id_next = MEM_ID_MIN; + +static bool mem_id_init; /* false */ +static struct rhashtable *mem_id_ht; + +struct xdp_mem_allocator { + struct xdp_mem_info mem; + union { + void *allocator; + struct page_pool *page_pool; + struct zero_copy_allocator *zc_alloc; + }; + struct rhash_head node; + struct rcu_head rcu; +}; + +static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) +{ + const u32 *k = data; + const u32 key = *k; + + BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id) + != sizeof(u32)); + + /* Use cyclic increasing ID as direct hash key, see rht_bucket_index */ + return key << RHT_HASH_RESERVED_SPACE; +} + +static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct xdp_mem_allocator *xa = ptr; + u32 mem_id = *(u32 *)arg->key; + + return xa->mem.id != mem_id; +} + +static const struct rhashtable_params mem_id_rht_params = { + .nelem_hint = 64, + .head_offset = offsetof(struct xdp_mem_allocator, node), + .key_offset = offsetof(struct xdp_mem_allocator, mem.id), + .key_len = FIELD_SIZEOF(struct xdp_mem_allocator, mem.id), + .max_size = MEM_ID_MAX, + .min_size = 8, + .automatic_shrinking = true, + .hashfn = xdp_mem_id_hashfn, + .obj_cmpfn = xdp_mem_id_cmp, +}; + +static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) +{ + struct xdp_mem_allocator *xa; + + xa = container_of(rcu, struct xdp_mem_allocator, rcu); + + /* Allow this ID to be reused */ + ida_simple_remove(&mem_id_pool, xa->mem.id); + + /* Notice, driver is expected to free the *allocator, + * e.g. page_pool, and MUST also use RCU free. + */ + + /* Poison memory */ + xa->mem.id = 0xFFFF; + xa->mem.type = 0xF0F0; + xa->allocator = (void *)0xDEAD9001; + + kfree(xa); +} + +static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) +{ + struct xdp_mem_allocator *xa; + int id = xdp_rxq->mem.id; + int err; + + if (id == 0) + return; + + mutex_lock(&mem_id_lock); + + xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); + if (!xa) { + mutex_unlock(&mem_id_lock); + return; + } + + err = rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params); + WARN_ON(err); + + call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); + + mutex_unlock(&mem_id_lock); +} + void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { /* Simplify driver cleanup code paths, allow unreg "unused" */ @@ -21,8 +124,14 @@ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG"); + __xdp_rxq_info_unreg_mem_model(xdp_rxq); + xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; + + /* Reset mem info to defaults */ + xdp_rxq->mem.id = 0; + xdp_rxq->mem.type = 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg); @@ -71,3 +180,193 @@ bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq) return (xdp_rxq->reg_state == REG_STATE_REGISTERED); } EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg); + +static int __mem_id_init_hash_table(void) +{ + struct rhashtable *rht; + int ret; + + if (unlikely(mem_id_init)) + return 0; + + rht = kzalloc(sizeof(*rht), GFP_KERNEL); + if (!rht) + return -ENOMEM; + + ret = rhashtable_init(rht, &mem_id_rht_params); + if (ret < 0) { + kfree(rht); + return ret; + } + mem_id_ht = rht; + smp_mb(); /* mutex lock should provide enough pairing */ + mem_id_init = true; + + return 0; +} + +/* Allocate a cyclic ID that maps to allocator pointer. + * See: https://www.kernel.org/doc/html/latest/core-api/idr.html + * + * Caller must lock mem_id_lock. + */ +static int __mem_id_cyclic_get(gfp_t gfp) +{ + int retries = 1; + int id; + +again: + id = ida_simple_get(&mem_id_pool, mem_id_next, MEM_ID_MAX, gfp); + if (id < 0) { + if (id == -ENOSPC) { + /* Cyclic allocator, reset next id */ + if (retries--) { + mem_id_next = MEM_ID_MIN; + goto again; + } + } + return id; /* errno */ + } + mem_id_next = id + 1; + + return id; +} + +static bool __is_supported_mem_type(enum xdp_mem_type type) +{ + if (type == MEM_TYPE_PAGE_POOL) + return is_page_pool_compiled_in(); + + if (type >= MEM_TYPE_MAX) + return false; + + return true; +} + +int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, + enum xdp_mem_type type, void *allocator) +{ + struct xdp_mem_allocator *xdp_alloc; + gfp_t gfp = GFP_KERNEL; + int id, errno, ret; + void *ptr; + + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { + WARN(1, "Missing register, driver bug"); + return -EFAULT; + } + + if (!__is_supported_mem_type(type)) + return -EOPNOTSUPP; + + xdp_rxq->mem.type = type; + + if (!allocator) { + if (type == MEM_TYPE_PAGE_POOL || type == MEM_TYPE_ZERO_COPY) + return -EINVAL; /* Setup time check page_pool req */ + return 0; + } + + /* Delay init of rhashtable to save memory if feature isn't used */ + if (!mem_id_init) { + mutex_lock(&mem_id_lock); + ret = __mem_id_init_hash_table(); + mutex_unlock(&mem_id_lock); + if (ret < 0) { + WARN_ON(1); + return ret; + } + } + + xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); + if (!xdp_alloc) + return -ENOMEM; + + mutex_lock(&mem_id_lock); + id = __mem_id_cyclic_get(gfp); + if (id < 0) { + errno = id; + goto err; + } + xdp_rxq->mem.id = id; + xdp_alloc->mem = xdp_rxq->mem; + xdp_alloc->allocator = allocator; + + /* Insert allocator into ID lookup table */ + ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); + if (IS_ERR(ptr)) { + errno = PTR_ERR(ptr); + goto err; + } + + mutex_unlock(&mem_id_lock); + + return 0; +err: + mutex_unlock(&mem_id_lock); + kfree(xdp_alloc); + return errno; +} +EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); + +/* XDP RX runs under NAPI protection, and in different delivery error + * scenarios (e.g. queue full), it is possible to return the xdp_frame + * while still leveraging this protection. The @napi_direct boolian + * is used for those calls sites. Thus, allowing for faster recycling + * of xdp_frames/pages in those cases. + */ +static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + unsigned long handle) +{ + struct xdp_mem_allocator *xa; + struct page *page; + + switch (mem->type) { + case MEM_TYPE_PAGE_POOL: + rcu_read_lock(); + /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ + xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); + page = virt_to_head_page(data); + if (xa) + page_pool_put_page(xa->page_pool, page, napi_direct); + else + put_page(page); + rcu_read_unlock(); + break; + case MEM_TYPE_PAGE_SHARED: + page_frag_free(data); + break; + case MEM_TYPE_PAGE_ORDER0: + page = virt_to_page(data); /* Assumes order0 page*/ + put_page(page); + break; + case MEM_TYPE_ZERO_COPY: + /* NB! Only valid from an xdp_buff! */ + rcu_read_lock(); + /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ + xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); + xa->zc_alloc->free(xa->zc_alloc, handle); + rcu_read_unlock(); + default: + /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ + break; + } +} + +void xdp_return_frame(struct xdp_frame *xdpf) +{ + __xdp_return(xdpf->data, &xdpf->mem, false, 0); +} +EXPORT_SYMBOL_GPL(xdp_return_frame); + +void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) +{ + __xdp_return(xdpf->data, &xdpf->mem, true, 0); +} +EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); + +void xdp_return_buff(struct xdp_buff *xdp) +{ + __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp->handle); +} +EXPORT_SYMBOL_GPL(xdp_return_buff); diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index bae7d78aa0689..d2f4e0c1faafa 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -176,6 +176,7 @@ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { [DCB_ATTR_IEEE_MAXRATE] = {.len = sizeof(struct ieee_maxrate)}, [DCB_ATTR_IEEE_QCN] = {.len = sizeof(struct ieee_qcn)}, [DCB_ATTR_IEEE_QCN_STATS] = {.len = sizeof(struct ieee_qcn_stats)}, + [DCB_ATTR_DCB_BUFFER] = {.len = sizeof(struct dcbnl_buffer)}, }; /* DCB number of traffic classes nested attributes. */ @@ -1094,6 +1095,16 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) return -EMSGSIZE; } + if (ops->dcbnl_getbuffer) { + struct dcbnl_buffer buffer; + + memset(&buffer, 0, sizeof(buffer)); + err = ops->dcbnl_getbuffer(netdev, &buffer); + if (!err && + nla_put(skb, DCB_ATTR_DCB_BUFFER, sizeof(buffer), &buffer)) + return -EMSGSIZE; + } + app = nla_nest_start(skb, DCB_ATTR_IEEE_APP_TABLE); if (!app) return -EMSGSIZE; @@ -1453,6 +1464,15 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, goto err; } + if (ieee[DCB_ATTR_DCB_BUFFER] && ops->dcbnl_setbuffer) { + struct dcbnl_buffer *buffer = + nla_data(ieee[DCB_ATTR_DCB_BUFFER]); + + err = ops->dcbnl_setbuffer(netdev, buffer); + if (err) + goto err; + } + if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { struct nlattr *attr; int rem; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 37ccbe62eb1af..ba6fc3c1186b9 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -53,7 +53,6 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) if (timeo < rto) timeo = rto; - tw->tw_timeout = DCCP_TIMEWAIT_LEN; if (state == DCCP_TIME_WAIT) timeo = DCCP_TIMEWAIT_LEN; diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index c795c3f509c94..72236695db3db 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -121,13 +121,16 @@ static int dn_fib_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) static int dn_fib_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, - struct nlattr **tb) + struct nlattr **tb, + struct netlink_ext_ack *extack) { int err = -EINVAL; struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - if (frh->tos) + if (frh->tos) { + NL_SET_ERR_MSG(extack, "Invalid tos value"); goto errout; + } if (rule->table == RT_TABLE_UNSPEC) { if (rule->action == FR_ACT_TO_TBL) { diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index bbf2c82cf7b29..4183e4ba27a50 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -9,7 +9,7 @@ config NET_DSA depends on HAVE_NET_DSA && MAY_USE_DEVLINK depends on BRIDGE || BRIDGE=n select NET_SWITCHDEV - select PHYLIB + select PHYLINK ---help--- Say Y if you want to enable support for the hardware switches supported by the Distributed Switch Architecture. diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 47725250b4cad..dc5d9af3dc80d 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -272,7 +272,28 @@ static int dsa_port_setup(struct dsa_port *dp) case DSA_PORT_TYPE_UNUSED: break; case DSA_PORT_TYPE_CPU: + /* dp->index is used now as port_number. However + * CPU ports should have separate numbering + * independent from front panel port numbers. + */ + devlink_port_attrs_set(&dp->devlink_port, + DEVLINK_PORT_FLAVOUR_CPU, + dp->index, false, 0); + err = dsa_port_link_register_of(dp); + if (err) { + dev_err(ds->dev, "failed to setup link for port %d.%d\n", + ds->index, dp->index); + return err; + } + break; case DSA_PORT_TYPE_DSA: + /* dp->index is used now as port_number. However + * DSA ports should have separate numbering + * independent from front panel port numbers. + */ + devlink_port_attrs_set(&dp->devlink_port, + DEVLINK_PORT_FLAVOUR_DSA, + dp->index, false, 0); err = dsa_port_link_register_of(dp); if (err) { dev_err(ds->dev, "failed to setup link for port %d.%d\n", @@ -281,6 +302,9 @@ static int dsa_port_setup(struct dsa_port *dp) } break; case DSA_PORT_TYPE_USER: + devlink_port_attrs_set(&dp->devlink_port, + DEVLINK_PORT_FLAVOUR_PHYSICAL, + dp->index, false, 0); err = dsa_slave_create(dp); if (err) dev_err(ds->dev, "failed to create slave for port %d.%d\n", diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 053731473c993..3964c6f7a7c0d 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -75,15 +75,6 @@ struct dsa_slave_priv { /* DSA port data, such as switch, port index, etc. */ struct dsa_port *dp; - /* - * The phylib phy_device pointer for the PHY connected - * to this port. - */ - phy_interface_t phy_interface; - int old_link; - int old_pause; - int old_duplex; - #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif diff --git a/net/dsa/master.c b/net/dsa/master.c index 90e6df0351eb2..c90ee3227deab 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -22,7 +22,7 @@ static void dsa_master_get_ethtool_stats(struct net_device *dev, int port = cpu_dp->index; int count = 0; - if (ops && ops->get_sset_count && ops->get_ethtool_stats) { + if (ops->get_sset_count && ops->get_ethtool_stats) { count = ops->get_sset_count(dev, ETH_SS_STATS); ops->get_ethtool_stats(dev, stats, data); } @@ -31,6 +31,32 @@ static void dsa_master_get_ethtool_stats(struct net_device *dev, ds->ops->get_ethtool_stats(ds, port, data + count); } +static void dsa_master_get_ethtool_phy_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; + int count = 0; + + if (dev->phydev && !ops->get_ethtool_phy_stats) { + count = phy_ethtool_get_sset_count(dev->phydev); + if (count >= 0) + phy_ethtool_get_stats(dev->phydev, stats, data); + } else if (ops->get_sset_count && ops->get_ethtool_phy_stats) { + count = ops->get_sset_count(dev, ETH_SS_PHY_STATS); + ops->get_ethtool_phy_stats(dev, stats, data); + } + + if (count < 0) + count = 0; + + if (ds->ops->get_ethtool_phy_stats) + ds->ops->get_ethtool_phy_stats(ds, port, data + count); +} + static int dsa_master_get_sset_count(struct net_device *dev, int sset) { struct dsa_port *cpu_dp = dev->dsa_ptr; @@ -38,11 +64,17 @@ static int dsa_master_get_sset_count(struct net_device *dev, int sset) struct dsa_switch *ds = cpu_dp->ds; int count = 0; - if (ops && ops->get_sset_count) - count += ops->get_sset_count(dev, sset); + if (sset == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) + count = phy_ethtool_get_sset_count(dev->phydev); + else if (ops->get_sset_count) + count = ops->get_sset_count(dev, sset); + + if (count < 0) + count = 0; - if (sset == ETH_SS_STATS && ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, cpu_dp->index); + if (ds->ops->get_sset_count) + count += ds->ops->get_sset_count(ds, cpu_dp->index, sset); return count; } @@ -64,19 +96,28 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, /* We do not want to be NULL-terminated, since this is a prefix */ pfx[sizeof(pfx) - 1] = '_'; - if (ops && ops->get_sset_count && ops->get_strings) { - mcount = ops->get_sset_count(dev, ETH_SS_STATS); + if (stringset == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) { + mcount = phy_ethtool_get_sset_count(dev->phydev); + if (mcount < 0) + mcount = 0; + else + phy_ethtool_get_strings(dev->phydev, data); + } else if (ops->get_sset_count && ops->get_strings) { + mcount = ops->get_sset_count(dev, stringset); + if (mcount < 0) + mcount = 0; ops->get_strings(dev, stringset, data); } - if (stringset == ETH_SS_STATS && ds->ops->get_strings) { + if (ds->ops->get_strings) { ndata = data + mcount * len; /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle * the output after to prepend our CPU port prefix we * constructed earlier */ - ds->ops->get_strings(ds, port, ndata); - count = ds->ops->get_sset_count(ds, port); + ds->ops->get_strings(ds, port, stringset, ndata); + count = ds->ops->get_sset_count(ds, port, stringset); for (i = 0; i < count; i++) { memmove(ndata + (i * len + sizeof(pfx)), ndata + i * len, len - sizeof(pfx)); @@ -102,6 +143,7 @@ static int dsa_master_ethtool_setup(struct net_device *dev) ops->get_sset_count = dsa_master_get_sset_count; ops->get_ethtool_stats = dsa_master_get_ethtool_stats; ops->get_strings = dsa_master_get_strings; + ops->get_ethtool_phy_stats = dsa_master_get_ethtool_phy_stats; dev->ethtool_ops = ops; diff --git a/net/dsa/port.c b/net/dsa/port.c index 7acc1169d75e1..ed0595459df13 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -252,6 +252,9 @@ int dsa_port_vlan_add(struct dsa_port *dp, .vlan = vlan, }; + if (netif_is_bridge_master(vlan->obj.orig_dev)) + return -EOPNOTSUPP; + if (br_vlan_enabled(dp->bridge_dev)) return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info); @@ -267,31 +270,47 @@ int dsa_port_vlan_del(struct dsa_port *dp, .vlan = vlan, }; + if (netif_is_bridge_master(vlan->obj.orig_dev)) + return -EOPNOTSUPP; + if (br_vlan_enabled(dp->bridge_dev)) return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info); return 0; } -static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable) +static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) { - struct device_node *port_dn = dp->dn; struct device_node *phy_dn; - struct dsa_switch *ds = dp->ds; struct phy_device *phydev; - int port = dp->index; - int err = 0; - phy_dn = of_parse_phandle(port_dn, "phy-handle", 0); + phy_dn = of_parse_phandle(dp->dn, "phy-handle", 0); if (!phy_dn) - return 0; + return NULL; phydev = of_phy_find_device(phy_dn); if (!phydev) { - err = -EPROBE_DEFER; - goto err_put_of; + of_node_put(phy_dn); + return ERR_PTR(-EPROBE_DEFER); } + return phydev; +} + +static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable) +{ + struct dsa_switch *ds = dp->ds; + struct phy_device *phydev; + int port = dp->index; + int err = 0; + + phydev = dsa_port_get_phy_device(dp); + if (!phydev) + return 0; + + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + if (enable) { err = genphy_config_init(phydev); if (err < 0) @@ -317,8 +336,6 @@ static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable) err_put_dev: put_device(&phydev->mdio.dev); -err_put_of: - of_node_put(phy_dn); return err; } @@ -372,3 +389,60 @@ void dsa_port_link_unregister_of(struct dsa_port *dp) else dsa_port_setup_phy_of(dp, false); } + +int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data) +{ + struct phy_device *phydev; + int ret = -EOPNOTSUPP; + + if (of_phy_is_fixed_link(dp->dn)) + return ret; + + phydev = dsa_port_get_phy_device(dp); + if (IS_ERR_OR_NULL(phydev)) + return ret; + + ret = phy_ethtool_get_strings(phydev, data); + put_device(&phydev->mdio.dev); + + return ret; +} +EXPORT_SYMBOL_GPL(dsa_port_get_phy_strings); + +int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data) +{ + struct phy_device *phydev; + int ret = -EOPNOTSUPP; + + if (of_phy_is_fixed_link(dp->dn)) + return ret; + + phydev = dsa_port_get_phy_device(dp); + if (IS_ERR_OR_NULL(phydev)) + return ret; + + ret = phy_ethtool_get_stats(phydev, NULL, data); + put_device(&phydev->mdio.dev); + + return ret; +} +EXPORT_SYMBOL_GPL(dsa_port_get_ethtool_phy_stats); + +int dsa_port_get_phy_sset_count(struct dsa_port *dp) +{ + struct phy_device *phydev; + int ret = -EOPNOTSUPP; + + if (of_phy_is_fixed_link(dp->dn)) + return ret; + + phydev = dsa_port_get_phy_device(dp); + if (IS_ERR_OR_NULL(phydev)) + return ret; + + ret = phy_ethtool_get_sset_count(phydev); + put_device(&phydev->mdio.dev); + + return ret; +} +EXPORT_SYMBOL_GPL(dsa_port_get_phy_sset_count); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 18561af7a8f1d..1e3b6a6d8a40d 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -13,6 +13,7 @@ #include <linux/netdevice.h> #include <linux/phy.h> #include <linux/phy_fixed.h> +#include <linux/phylink.h> #include <linux/of_net.h> #include <linux/of_mdio.h> #include <linux/mdio.h> @@ -97,8 +98,7 @@ static int dsa_slave_open(struct net_device *dev) if (err) goto clear_promisc; - if (dev->phydev) - phy_start(dev->phydev); + phylink_start(dp->pl); return 0; @@ -120,8 +120,7 @@ static int dsa_slave_close(struct net_device *dev) struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); - if (dev->phydev) - phy_stop(dev->phydev); + phylink_stop(dp->pl); dsa_port_disable(dp, dev->phydev); @@ -272,10 +271,7 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; } - if (!dev->phydev) - return -ENODEV; - - return phy_mii_ioctl(dev->phydev, ifr, cmd); + return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } static int dsa_slave_port_attr_set(struct net_device *dev, @@ -498,14 +494,11 @@ dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) ds->ops->get_regs(ds, dp->index, regs, _p); } -static u32 dsa_slave_get_link(struct net_device *dev) +static int dsa_slave_nway_reset(struct net_device *dev) { - if (!dev->phydev) - return -ENODEV; - - genphy_update_link(dev->phydev); + struct dsa_port *dp = dsa_slave_to_port(dev); - return dev->phydev->link; + return phylink_ethtool_nway_reset(dp->pl); } static int dsa_slave_get_eeprom_len(struct net_device *dev) @@ -560,7 +553,8 @@ static void dsa_slave_get_strings(struct net_device *dev, strncpy(data + 2 * len, "rx_packets", len); strncpy(data + 3 * len, "rx_bytes", len); if (ds->ops->get_strings) - ds->ops->get_strings(ds, dp->index, data + 4 * len); + ds->ops->get_strings(ds, dp->index, stringset, + data + 4 * len); } } @@ -605,7 +599,7 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) count = 4; if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, dp->index); + count += ds->ops->get_sset_count(ds, dp->index, sset); return count; } @@ -618,6 +612,8 @@ static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_switch *ds = dp->ds; + phylink_ethtool_get_wol(dp->pl, w); + if (ds->ops->get_wol) ds->ops->get_wol(ds, dp->index, w); } @@ -628,6 +624,8 @@ static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; + phylink_ethtool_set_wol(dp->pl, w); + if (ds->ops->set_wol) ret = ds->ops->set_wol(ds, dp->index, w); @@ -651,13 +649,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) if (ret) return ret; - if (e->eee_enabled) { - ret = phy_init_eee(dev->phydev, 0); - if (ret) - return ret; - } - - return phy_ethtool_set_eee(dev->phydev, e); + return phylink_ethtool_set_eee(dp->pl, e); } static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) @@ -677,7 +669,23 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) if (ret) return ret; - return phy_ethtool_get_eee(dev->phydev, e); + return phylink_ethtool_get_eee(dp->pl, e); +} + +static int dsa_slave_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + + return phylink_ethtool_ksettings_get(dp->pl, cmd); +} + +static int dsa_slave_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + + return phylink_ethtool_ksettings_set(dp->pl, cmd); } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -980,8 +988,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_drvinfo = dsa_slave_get_drvinfo, .get_regs_len = dsa_slave_get_regs_len, .get_regs = dsa_slave_get_regs, - .nway_reset = phy_ethtool_nway_reset, - .get_link = dsa_slave_get_link, + .nway_reset = dsa_slave_nway_reset, + .get_link = ethtool_op_get_link, .get_eeprom_len = dsa_slave_get_eeprom_len, .get_eeprom = dsa_slave_get_eeprom, .set_eeprom = dsa_slave_set_eeprom, @@ -992,8 +1000,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_wol = dsa_slave_get_wol, .set_eee = dsa_slave_set_eee, .get_eee = dsa_slave_get_eee, - .get_link_ksettings = phy_ethtool_get_link_ksettings, - .set_link_ksettings = phy_ethtool_set_link_ksettings, + .get_link_ksettings = dsa_slave_get_link_ksettings, + .set_link_ksettings = dsa_slave_set_link_ksettings, .get_rxnfc = dsa_slave_get_rxnfc, .set_rxnfc = dsa_slave_set_rxnfc, .get_ts_info = dsa_slave_get_ts_info, @@ -1052,56 +1060,122 @@ static struct device_type dsa_type = { .name = "dsa", }; -static void dsa_slave_adjust_link(struct net_device *dev) +static void dsa_slave_phylink_validate(struct net_device *dev, + unsigned long *supported, + struct phylink_link_state *state) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = dp->ds; - unsigned int status_changed = 0; - if (p->old_link != dev->phydev->link) { - status_changed = 1; - p->old_link = dev->phydev->link; - } + if (!ds->ops->phylink_validate) + return; - if (p->old_duplex != dev->phydev->duplex) { - status_changed = 1; - p->old_duplex = dev->phydev->duplex; - } + ds->ops->phylink_validate(ds, dp->index, supported, state); +} - if (p->old_pause != dev->phydev->pause) { - status_changed = 1; - p->old_pause = dev->phydev->pause; - } +static int dsa_slave_phylink_mac_link_state(struct net_device *dev, + struct phylink_link_state *state) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + /* Only called for SGMII and 802.3z */ + if (!ds->ops->phylink_mac_link_state) + return -EOPNOTSUPP; + + return ds->ops->phylink_mac_link_state(ds, dp->index, state); +} + +static void dsa_slave_phylink_mac_config(struct net_device *dev, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->phylink_mac_config) + return; + + ds->ops->phylink_mac_config(ds, dp->index, mode, state); +} - if (ds->ops->adjust_link && status_changed) - ds->ops->adjust_link(ds, dp->index, dev->phydev); +static void dsa_slave_phylink_mac_an_restart(struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; - if (status_changed) - phy_print_status(dev->phydev); + if (!ds->ops->phylink_mac_an_restart) + return; + + ds->ops->phylink_mac_an_restart(ds, dp->index); } -static int dsa_slave_fixed_link_update(struct net_device *dev, - struct fixed_phy_status *status) +static void dsa_slave_phylink_mac_link_down(struct net_device *dev, + unsigned int mode, + phy_interface_t interface) { - struct dsa_switch *ds; - struct dsa_port *dp; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; - if (dev) { - dp = dsa_slave_to_port(dev); - ds = dp->ds; - if (ds->ops->fixed_link_update) - ds->ops->fixed_link_update(ds, dp->index, status); + if (!ds->ops->phylink_mac_link_down) { + if (ds->ops->adjust_link && dev->phydev) + ds->ops->adjust_link(ds, dp->index, dev->phydev); + return; } - return 0; + ds->ops->phylink_mac_link_down(ds, dp->index, mode, interface); +} + +static void dsa_slave_phylink_mac_link_up(struct net_device *dev, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->phylink_mac_link_up) { + if (ds->ops->adjust_link && dev->phydev) + ds->ops->adjust_link(ds, dp->index, dev->phydev); + return; + } + + ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev); +} + +static const struct phylink_mac_ops dsa_slave_phylink_mac_ops = { + .validate = dsa_slave_phylink_validate, + .mac_link_state = dsa_slave_phylink_mac_link_state, + .mac_config = dsa_slave_phylink_mac_config, + .mac_an_restart = dsa_slave_phylink_mac_an_restart, + .mac_link_down = dsa_slave_phylink_mac_link_down, + .mac_link_up = dsa_slave_phylink_mac_link_up, +}; + +void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) +{ + const struct dsa_port *dp = dsa_to_port(ds, port); + + phylink_mac_change(dp->pl, up); +} +EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); + +static void dsa_slave_phylink_fixed_state(struct net_device *dev, + struct phylink_link_state *state) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + /* No need to check that this operation is valid, the callback would + * not be called if it was not. + */ + ds->ops->phylink_fixed_state(ds, dp->index, state); } /* slave device setup *******************************************************/ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); - struct dsa_slave_priv *p = netdev_priv(slave_dev); struct dsa_switch *ds = dp->ds; slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr); @@ -1110,75 +1184,54 @@ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) return -ENODEV; } - /* Use already configured phy mode */ - if (p->phy_interface == PHY_INTERFACE_MODE_NA) - p->phy_interface = slave_dev->phydev->interface; - - return phy_connect_direct(slave_dev, slave_dev->phydev, - dsa_slave_adjust_link, p->phy_interface); + return phylink_connect_phy(dp->pl, slave_dev->phydev); } static int dsa_slave_phy_setup(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); - struct dsa_slave_priv *p = netdev_priv(slave_dev); struct device_node *port_dn = dp->dn; struct dsa_switch *ds = dp->ds; - struct device_node *phy_dn; - bool phy_is_fixed = false; u32 phy_flags = 0; int mode, ret; mode = of_get_phy_mode(port_dn); if (mode < 0) mode = PHY_INTERFACE_MODE_NA; - p->phy_interface = mode; - phy_dn = of_parse_phandle(port_dn, "phy-handle", 0); - if (!phy_dn && of_phy_is_fixed_link(port_dn)) { - /* In the case of a fixed PHY, the DT node associated - * to the fixed PHY is the Port DT node - */ - ret = of_phy_register_fixed_link(port_dn); - if (ret) { - netdev_err(slave_dev, "failed to register fixed PHY: %d\n", ret); - return ret; - } - phy_is_fixed = true; - phy_dn = of_node_get(port_dn); + dp->pl = phylink_create(slave_dev, of_fwnode_handle(port_dn), mode, + &dsa_slave_phylink_mac_ops); + if (IS_ERR(dp->pl)) { + netdev_err(slave_dev, + "error creating PHYLINK: %ld\n", PTR_ERR(dp->pl)); + return PTR_ERR(dp->pl); } + /* Register only if the switch provides such a callback, since this + * callback takes precedence over polling the link GPIO in PHYLINK + * (see phylink_get_fixed_state). + */ + if (ds->ops->phylink_fixed_state) + phylink_fixed_state_cb(dp->pl, dsa_slave_phylink_fixed_state); + if (ds->ops->get_phy_flags) phy_flags = ds->ops->get_phy_flags(ds, dp->index); - if (phy_dn) { - slave_dev->phydev = of_phy_connect(slave_dev, phy_dn, - dsa_slave_adjust_link, - phy_flags, - p->phy_interface); - of_node_put(phy_dn); - } - - if (slave_dev->phydev && phy_is_fixed) - fixed_phy_set_link_update(slave_dev->phydev, - dsa_slave_fixed_link_update); - - /* We could not connect to a designated PHY, so use the switch internal - * MDIO bus instead - */ - if (!slave_dev->phydev) { + ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags); + if (ret == -ENODEV) { + /* We could not connect to a designated PHY or SFP, so use the + * switch internal MDIO bus instead + */ ret = dsa_slave_phy_connect(slave_dev, dp->index); if (ret) { - netdev_err(slave_dev, "failed to connect to port %d: %d\n", + netdev_err(slave_dev, + "failed to connect to port %d: %d\n", dp->index, ret); - if (phy_is_fixed) - of_phy_deregister_fixed_link(port_dn); + phylink_destroy(dp->pl); return ret; } } - phy_attached_info(slave_dev->phydev); - return 0; } @@ -1193,29 +1246,26 @@ static void dsa_slave_set_lockdep_class_one(struct net_device *dev, int dsa_slave_suspend(struct net_device *slave_dev) { - struct dsa_slave_priv *p = netdev_priv(slave_dev); + struct dsa_port *dp = dsa_slave_to_port(slave_dev); netif_device_detach(slave_dev); - if (slave_dev->phydev) { - phy_stop(slave_dev->phydev); - p->old_pause = -1; - p->old_link = -1; - p->old_duplex = -1; - phy_suspend(slave_dev->phydev); - } + rtnl_lock(); + phylink_stop(dp->pl); + rtnl_unlock(); return 0; } int dsa_slave_resume(struct net_device *slave_dev) { + struct dsa_port *dp = dsa_slave_to_port(slave_dev); + netif_device_attach(slave_dev); - if (slave_dev->phydev) { - phy_resume(slave_dev->phydev); - phy_start(slave_dev->phydev); - } + rtnl_lock(); + phylink_start(dp->pl); + rtnl_unlock(); return 0; } @@ -1280,11 +1330,6 @@ int dsa_slave_create(struct dsa_port *port) p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); p->xmit = cpu_dp->tag_ops->xmit; - - p->old_pause = -1; - p->old_link = -1; - p->old_duplex = -1; - port->slave = slave_dev; netif_carrier_off(slave_dev); @@ -1307,9 +1352,10 @@ int dsa_slave_create(struct dsa_port *port) return 0; out_phy: - phy_disconnect(slave_dev->phydev); - if (of_phy_is_fixed_link(port->dn)) - of_phy_deregister_fixed_link(port->dn); + rtnl_lock(); + phylink_disconnect_phy(p->dp->pl); + rtnl_unlock(); + phylink_destroy(p->dp->pl); out_free: free_percpu(p->stats64); free_netdev(slave_dev); @@ -1321,17 +1367,15 @@ void dsa_slave_destroy(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); - struct device_node *port_dn = dp->dn; netif_carrier_off(slave_dev); - if (slave_dev->phydev) { - phy_disconnect(slave_dev->phydev); + rtnl_lock(); + phylink_disconnect_phy(dp->pl); + rtnl_unlock(); - if (of_phy_is_fixed_link(port_dn)) - of_phy_deregister_fixed_link(port_dn); - } dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); unregister_netdev(slave_dev); + phylink_destroy(dp->pl); free_percpu(p->stats64); free_netdev(slave_dev); } @@ -1394,6 +1438,9 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; + if (!fdb_info->added_by_user) + break; + err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid); if (err) { netdev_dbg(dev, "fdb add failed err=%d\n", err); @@ -1405,6 +1452,9 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; + if (!fdb_info->added_by_user) + break; + err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid); if (err) { netdev_dbg(dev, "fdb del failed err=%d\n", err); @@ -1457,8 +1507,7 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, switch (event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */ case SWITCHDEV_FDB_DEL_TO_DEVICE: - if (dsa_slave_switchdev_fdb_work_init(switchdev_work, - ptr)) + if (dsa_slave_switchdev_fdb_work_init(switchdev_work, ptr)) goto err_fdb_work_init; dev_hold(dev); break; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index eaeba9b99a737..ee28440f57c58 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -128,15 +128,15 @@ u32 eth_get_headlen(void *data, unsigned int len) { const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG; const struct ethhdr *eth = (const struct ethhdr *)data; - struct flow_keys keys; + struct flow_keys_basic keys; /* this should never happen, but better safe than sorry */ if (unlikely(len < sizeof(*eth))) return len; /* parse any remaining L2/L3 headers, check for L4 */ - if (!skb_flow_dissect_flow_keys_buf(&keys, data, eth->h_proto, - sizeof(*eth), len, flags)) + if (!skb_flow_dissect_flow_keys_basic(NULL, &keys, data, eth->h_proto, + sizeof(*eth), len, flags)) return max_t(u32, keys.control.thoff, sizeof(*eth)); /* parse for any L4 headers */ diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index a07b7dd06defb..eec9569ffa5cb 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -13,7 +13,10 @@ obj-y := route.o inetpeer.o protocol.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ - inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o + inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \ + metrics.o netlink.o + +obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8a59428e63ab3..15e125558c76e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -994,7 +994,9 @@ const struct proto_ops inet_stream_ops = { .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, - .mmap = sock_no_mmap, +#ifdef CONFIG_MMU + .mmap = tcp_mmap, +#endif .sendpage = inet_sendpage, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, @@ -1006,6 +1008,7 @@ const struct proto_ops inet_stream_ops = { .compat_getsockopt = compat_sock_common_getsockopt, .compat_ioctl = inet_compat_ioctl, #endif + .set_rcvlowat = tcp_set_rcvlowat, }; EXPORT_SYMBOL(inet_stream_ops); diff --git a/net/ipv4/bpfilter/Makefile b/net/ipv4/bpfilter/Makefile new file mode 100644 index 0000000000000..ce262d76cc488 --- /dev/null +++ b/net/ipv4/bpfilter/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_BPFILTER) += sockopt.o + diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c new file mode 100644 index 0000000000000..5e04ed25bc0e9 --- /dev/null +++ b/net/ipv4/bpfilter/sockopt.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/uaccess.h> +#include <linux/bpfilter.h> +#include <uapi/linux/bpf.h> +#include <linux/wait.h> +#include <linux/kmod.h> + +int (*bpfilter_process_sockopt)(struct sock *sk, int optname, + char __user *optval, + unsigned int optlen, bool is_set); +EXPORT_SYMBOL_GPL(bpfilter_process_sockopt); + +static int bpfilter_mbox_request(struct sock *sk, int optname, + char __user *optval, + unsigned int optlen, bool is_set) +{ + if (!bpfilter_process_sockopt) { + int err = request_module("bpfilter"); + + if (err) + return err; + if (!bpfilter_process_sockopt) + return -ECHILD; + } + return bpfilter_process_sockopt(sk, optname, optval, optlen, is_set); +} + +int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, + unsigned int optlen) +{ + return bpfilter_mbox_request(sk, optname, optval, optlen, true); +} + +int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, + int __user *optlen) +{ + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + return bpfilter_mbox_request(sk, optname, optval, len, false); +} diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 40f001782c1b3..d7585ab1a77a0 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -99,6 +99,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .type = NLA_U32 }, + [IFA_RT_PRIORITY] = { .type = NLA_U32 }, }; #define IN4_ADDR_HSIZE_SHIFT 8 @@ -835,6 +836,9 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); + if (tb[IFA_RT_PRIORITY]) + ifa->ifa_rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); + if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; @@ -906,12 +910,20 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid, extack); } else { + u32 new_metric = ifa->ifa_rt_priority; + inet_free_ifa(ifa); if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) return -EEXIST; ifa = ifa_existing; + + if (ifa->ifa_rt_priority != new_metric) { + fib_modify_prefix_metric(ifa, new_metric); + ifa->ifa_rt_priority = new_metric; + } + set_ifa_lifetime(ifa, valid_lft, prefered_lft); cancel_delayed_work(&check_lifetime_work); queue_delayed_work(system_power_efficient_wq, @@ -1549,6 +1561,7 @@ static size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_BROADCAST */ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + nla_total_size(4) /* IFA_FLAGS */ + + nla_total_size(4) /* IFA_RT_PRIORITY */ + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } @@ -1618,6 +1631,8 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) || + (ifa->ifa_rt_priority && + nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) || put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, preferred, valid)) goto nla_put_failure; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e66172aaf2418..63aa39b3af03c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -354,8 +354,6 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.fl4_dport = 0; } - trace_fib_validate_source(dev, &fl4); - if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; if (res.type != RTN_UNICAST && @@ -650,6 +648,9 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, + [RTA_IP_PROTO] = { .type = NLA_U8 }, + [RTA_SPORT] = { .type = NLA_U16 }, + [RTA_DPORT] = { .type = NLA_U16 }, }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, @@ -846,7 +847,8 @@ out_err: * to fib engine. It is legal, because all events occur * only when netlink is already locked. */ -static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) +static void fib_magic(int cmd, int type, __be32 dst, int dst_len, + struct in_ifaddr *ifa, u32 rt_priority) { struct net *net = dev_net(ifa->ifa_dev->dev); u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev); @@ -856,6 +858,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad .fc_type = type, .fc_dst = dst, .fc_dst_len = dst_len, + .fc_priority = rt_priority, .fc_prefsrc = ifa->ifa_local, .fc_oif = ifa->ifa_dev->dev->ifindex, .fc_nlflags = NLM_F_CREATE | NLM_F_APPEND, @@ -901,31 +904,57 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) } } - fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim); + fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim, 0); if (!(dev->flags & IFF_UP)) return; /* Add broadcast address, if it is explicitly assigned. */ if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) - fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); + fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, + prim, 0); if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) && (prefix != addr || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, - prefix, ifa->ifa_prefixlen, prim); + prefix, ifa->ifa_prefixlen, prim, + ifa->ifa_rt_priority); /* Add network specific broadcasts, when it takes a sense */ if (ifa->ifa_prefixlen < 31) { - fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, prim); + fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, + prim, 0); fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, - 32, prim); + 32, prim, 0); } } } +void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric) +{ + __be32 prefix = ifa->ifa_address & ifa->ifa_mask; + struct in_device *in_dev = ifa->ifa_dev; + struct net_device *dev = in_dev->dev; + + if (!(dev->flags & IFF_UP) || + ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) || + ipv4_is_zeronet(prefix) || + prefix == ifa->ifa_local || ifa->ifa_prefixlen == 32) + return; + + /* add the new */ + fib_magic(RTM_NEWROUTE, + dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, + prefix, ifa->ifa_prefixlen, ifa, new_metric); + + /* delete the old */ + fib_magic(RTM_DELROUTE, + dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, + prefix, ifa->ifa_prefixlen, ifa, ifa->ifa_rt_priority); +} + /* Delete primary or secondary address. * Optionally, on secondary address promotion consider the addresses * from subnet iprim as deleted, even if they are in device list. @@ -967,7 +996,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, - any, ifa->ifa_prefixlen, prim); + any, ifa->ifa_prefixlen, prim, 0); subnet = 1; } @@ -1051,17 +1080,20 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) no_promotions: if (!(ok & BRD_OK)) - fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); + fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, + prim, 0); if (subnet && ifa->ifa_prefixlen < 31) { if (!(ok & BRD1_OK)) - fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim); + fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, + prim, 0); if (!(ok & BRD0_OK)) - fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim); + fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, + prim, 0); } if (!(ok & LOCAL_OK)) { unsigned int addr_type; - fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim); + fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim, 0); /* Check, that this local address finally disappeared. */ addr_type = inet_addr_type_dev_table(dev_net(dev), dev, diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 737d11bc8838b..f8eb78d042a48 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -213,14 +213,17 @@ static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, - struct nlattr **tb) + struct nlattr **tb, + struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); int err = -EINVAL; struct fib4_rule *rule4 = (struct fib4_rule *) rule; - if (frh->tos & ~IPTOS_TOS_MASK) + if (frh->tos & ~IPTOS_TOS_MASK) { + NL_SET_ERR_MSG(extack, "Invalid tos"); goto errout; + } /* split local/main if they are not already split */ err = fib_unmerge(net); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index c27122f01b874..f3c89ccf14c5b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -717,6 +717,8 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) nla_strlcpy(tmp, nla, sizeof(tmp)); val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca); } else { + if (nla_len(nla) != sizeof(u32)) + return false; val = nla_get_u32(nla); } @@ -1019,47 +1021,8 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc) static int fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) { - bool ecn_ca = false; - struct nlattr *nla; - int remaining; - - if (!cfg->fc_mx) - return 0; - - nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { - int type = nla_type(nla); - u32 val; - - if (!type) - continue; - if (type > RTAX_MAX) - return -EINVAL; - - if (type == RTAX_CC_ALGO) { - char tmp[TCP_CA_NAME_MAX]; - - nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca); - if (val == TCP_CA_UNSPEC) - return -EINVAL; - } else { - val = nla_get_u32(nla); - } - if (type == RTAX_ADVMSS && val > 65535 - 40) - val = 65535 - 40; - if (type == RTAX_MTU && val > 65535 - 15) - val = 65535 - 15; - if (type == RTAX_HOPLIMIT && val > 255) - val = 255; - if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) - return -EINVAL; - fi->fib_metrics->metrics[type - 1] = val; - } - - if (ecn_ca) - fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; - - return 0; + return ip_metrics_convert(fi->fib_net, cfg->fc_mx, cfg->fc_mx_len, + fi->fib_metrics->metrics); } struct fib_info *fib_create_info(struct fib_config *cfg, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 99c23a0cb8ca2..5bc0c89e81e4c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1326,14 +1326,14 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, unsigned long index; t_key cindex; - trace_fib_table_lookup(tb->tb_id, flp); - pn = t->kv; cindex = 0; n = get_child_rcu(pn, cindex); - if (!n) + if (!n) { + trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; + } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->gets); @@ -1416,8 +1416,11 @@ backtrace: * nothing for us to do as we do not have any * further nodes to parse. */ - if (IS_TRIE(pn)) + if (IS_TRIE(pn)) { + trace_fib_table_lookup(tb->tb_id, flp, + NULL, -EAGAIN); return -EAGAIN; + } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->backtrack); #endif @@ -1459,6 +1462,7 @@ found: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif + trace_fib_table_lookup(tb->tb_id, flp, NULL, err); return err; } if (fi->fib_flags & RTNH_F_DEAD) @@ -1494,7 +1498,7 @@ found: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif - trace_fib_table_lookup_nh(nh); + trace_fib_table_lookup(tb->tb_id, flp, nh, err); return err; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 881ac6d046f2d..33a88e045efd9 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -27,11 +27,6 @@ #include <net/sock_reuseport.h> #include <net/addrconf.h> -#ifdef INET_CSK_DEBUG -const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; -EXPORT_SYMBOL(inet_csk_timer_bug_msg); -#endif - #if IS_ENABLED(CONFIG_IPV6) /* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6 * only, and any IPv4 addresses if not IPv6 only diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f200b304f76cb..2d8efeecf6197 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -578,6 +578,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, int tunnel_hlen; int version; __be16 df; + int nhoff; + int thoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -605,6 +607,16 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, truncate = true; } + nhoff = skb_network_header(skb) - skb_mac_header(skb); + if (skb->protocol == htons(ETH_P_IP) && + (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) + truncate = true; + + thoff = skb_transport_header(skb) - skb_mac_header(skb); + if (skb->protocol == htons(ETH_P_IPV6) && + (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)) + truncate = true; + if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index d54abc0978006..af5a830ff6ad3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -878,11 +878,14 @@ static int __ip_append_data(struct sock *sk, struct rtable *rt = (struct rtable *)cork->dst; unsigned int wmem_alloc_delta = 0; u32 tskey = 0; + bool paged; skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; - mtu = cork->fragsize; + mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; + paged = !!cork->gso_size; + if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) tskey = sk->sk_tskey++; @@ -906,8 +909,8 @@ static int __ip_append_data(struct sock *sk, if (transhdrlen && length + fragheaderlen <= mtu && rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && - !(flags & MSG_MORE) && - !exthdrlen) + (!(flags & MSG_MORE) || cork->gso_size) && + (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; cork->length += length; @@ -933,6 +936,7 @@ static int __ip_append_data(struct sock *sk, unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; + unsigned int pagedlen = 0; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; @@ -953,8 +957,12 @@ alloc_new_skb: if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; - else + else if (!paged) alloclen = fraglen; + else { + alloclen = min_t(int, fraglen, MAX_HEADER); + pagedlen = fraglen - alloclen; + } alloclen += exthdrlen; @@ -998,7 +1006,7 @@ alloc_new_skb: /* * Find where to start putting bytes. */ - data = skb_put(skb, fraglen + exthdrlen); + data = skb_put(skb, fraglen + exthdrlen - pagedlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); @@ -1014,7 +1022,7 @@ alloc_new_skb: pskb_trim_unique(skb_prev, maxfraglen); } - copy = datalen - transhdrlen - fraggap; + copy = datalen - transhdrlen - fraggap - pagedlen; if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); @@ -1022,7 +1030,7 @@ alloc_new_skb: } offset += copy; - length -= datalen - fraggap; + length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; csummode = CHECKSUM_NONE; @@ -1136,6 +1144,8 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, *rtp = NULL; cork->fragsize = ip_sk_use_pmtu(sk) ? dst_mtu(&rt->dst) : rt->dst.dev->mtu; + + cork->gso_size = sk->sk_type == SOCK_DGRAM ? ipc->gso_size : 0; cork->dst = &rt->dst; cork->length = 0; cork->ttl = ipc->ttl; @@ -1215,7 +1225,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, return -EOPNOTSUPP; hh_len = LL_RESERVED_SPACE(rt->dst.dev); - mtu = cork->fragsize; + mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; @@ -1471,9 +1481,8 @@ struct sk_buff *ip_make_skb(struct sock *sk, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, - unsigned int flags) + struct inet_cork *cork, unsigned int flags) { - struct inet_cork cork; struct sk_buff_head queue; int err; @@ -1482,22 +1491,22 @@ struct sk_buff *ip_make_skb(struct sock *sk, __skb_queue_head_init(&queue); - cork.flags = 0; - cork.addr = 0; - cork.opt = NULL; - err = ip_setup_cork(sk, &cork, ipc, rtp); + cork->flags = 0; + cork->addr = 0; + cork->opt = NULL; + err = ip_setup_cork(sk, cork, ipc, rtp); if (err) return ERR_PTR(err); - err = __ip_append_data(sk, fl4, &queue, &cork, + err = __ip_append_data(sk, fl4, &queue, cork, ¤t->task_frag, getfrag, from, length, transhdrlen, flags); if (err) { - __ip_flush_pending_frames(sk, &queue, &cork); + __ip_flush_pending_frames(sk, &queue, cork); return ERR_PTR(err); } - return __ip_make_skb(sk, fl4, &queue, &cork); + return __ip_make_skb(sk, fl4, &queue, cork); } /* @@ -1553,7 +1562,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, oif = skb->skb_iif; flowi4_init_output(&fl4, oif, - IP4_REPLY_MARK(net, skb->mark), + IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark, RT_TOS(arg->tos), RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 57bbb060faaf8..fc32fdbeefa61 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -47,6 +47,8 @@ #include <linux/errqueue.h> #include <linux/uaccess.h> +#include <linux/bpfilter.h> + /* * SOL_IP control messages. */ @@ -1242,6 +1244,11 @@ int ip_setsockopt(struct sock *sk, int level, return -ENOPROTOOPT; err = do_ip_setsockopt(sk, level, optname, optval, optlen); +#ifdef CONFIG_BPFILTER + if (optname >= BPFILTER_IPT_SO_SET_REPLACE && + optname < BPFILTER_IPT_SET_MAX) + err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen); +#endif #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_HDRINCL && @@ -1550,6 +1557,11 @@ int ip_getsockopt(struct sock *sk, int level, int err; err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0); +#ifdef CONFIG_BPFILTER + if (optname >= BPFILTER_IPT_SO_GET_INFO && + optname < BPFILTER_IPT_GET_MAX) + err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); +#endif #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS && @@ -1582,6 +1594,11 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, err = do_ip_getsockopt(sk, level, optname, optval, optlen, MSG_CMSG_COMPAT); +#ifdef CONFIG_BPFILTER + if (optname >= BPFILTER_IPT_SO_GET_INFO && + optname < BPFILTER_IPT_GET_MAX) + err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); +#endif #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS && diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 2f39479be92f4..dde671e978298 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -423,17 +423,17 @@ void __init ip_tunnel_core_init(void) lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6); } -struct static_key ip_tunnel_metadata_cnt = STATIC_KEY_INIT_FALSE; +DEFINE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt); EXPORT_SYMBOL(ip_tunnel_metadata_cnt); void ip_tunnel_need_metadata(void) { - static_key_slow_inc(&ip_tunnel_metadata_cnt); + static_branch_inc(&ip_tunnel_metadata_cnt); } EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata); void ip_tunnel_unneed_metadata(void) { - static_key_slow_dec(&ip_tunnel_metadata_cnt); + static_branch_dec(&ip_tunnel_metadata_cnt); } EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index bbcbcc113d197..88212615bf4ce 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -28,6 +28,9 @@ * * Multiple Nameservers in /proc/net/pnp * -- Josef Siemes <jsiemes@web.de>, Aug 2002 + * + * NTP servers in /proc/net/ipconfig/ntp_servers + * -- Chris Novakovic <chris@chrisn.me.uk>, April 2018 */ #include <linux/types.h> @@ -93,6 +96,7 @@ #define CONF_TIMEOUT_MAX (HZ*30) /* Maximum allowed timeout */ #define CONF_NAMESERVERS_MAX 3 /* Maximum number of nameservers - '3' from resolv.h */ +#define CONF_NTP_SERVERS_MAX 3 /* Maximum number of NTP servers */ #define NONE cpu_to_be32(INADDR_NONE) #define ANY cpu_to_be32(INADDR_ANY) @@ -152,6 +156,7 @@ static int ic_proto_used; /* Protocol used, if any */ #define ic_proto_used 0 #endif static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */ +static __be32 ic_ntp_servers[CONF_NTP_SERVERS_MAX]; /* NTP server IP addresses */ static u8 ic_domain[64]; /* DNS (not NIS) domain name */ /* @@ -576,6 +581,15 @@ static inline void __init ic_nameservers_predef(void) ic_nameservers[i] = NONE; } +/* Predefine NTP servers */ +static inline void __init ic_ntp_servers_predef(void) +{ + int i; + + for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) + ic_ntp_servers[i] = NONE; +} + /* * DHCP/BOOTP support. */ @@ -671,6 +685,7 @@ ic_dhcp_init_options(u8 *options, struct ic_device *d) 17, /* Boot path */ 26, /* MTU */ 40, /* NIS domain name */ + 42, /* NTP servers */ }; *e++ = 55; /* Parameter request list */ @@ -721,9 +736,11 @@ static void __init ic_bootp_init_ext(u8 *e) *e++ = 3; /* Default gateway request */ *e++ = 4; e += 4; - *e++ = 5; /* Name server request */ - *e++ = 8; - e += 8; +#if CONF_NAMESERVERS_MAX > 0 + *e++ = 6; /* (DNS) name server request */ + *e++ = 4 * CONF_NAMESERVERS_MAX; + e += 4 * CONF_NAMESERVERS_MAX; +#endif *e++ = 12; /* Host name request */ *e++ = 32; e += 32; @@ -748,7 +765,13 @@ static void __init ic_bootp_init_ext(u8 *e) */ static inline void __init ic_bootp_init(void) { + /* Re-initialise all name servers and NTP servers to NONE, in case any + * were set via the "ip=" or "nfsaddrs=" kernel command line parameters: + * any IP addresses specified there will already have been decoded but + * are no longer needed + */ ic_nameservers_predef(); + ic_ntp_servers_predef(); dev_add_pack(&bootp_packet_type); } @@ -912,6 +935,15 @@ static void __init ic_do_bootp_ext(u8 *ext) ic_bootp_string(utsname()->domainname, ext+1, *ext, __NEW_UTS_LEN); break; + case 42: /* NTP servers */ + servers = *ext / 4; + if (servers > CONF_NTP_SERVERS_MAX) + servers = CONF_NTP_SERVERS_MAX; + for (i = 0; i < servers; i++) { + if (ic_ntp_servers[i] == NONE) + memcpy(&ic_ntp_servers[i], ext+1+4*i, 4); + } + break; } } @@ -1257,7 +1289,10 @@ static int __init ic_dynamic(void) #endif /* IPCONFIG_DYNAMIC */ #ifdef CONFIG_PROC_FS +/* proc_dir_entry for /proc/net/ipconfig */ +static struct proc_dir_entry *ipconfig_dir; +/* Name servers: */ static int pnp_seq_show(struct seq_file *seq, void *v) { int i; @@ -1282,6 +1317,62 @@ static int pnp_seq_show(struct seq_file *seq, void *v) &ic_servaddr); return 0; } + +/* Create the /proc/net/ipconfig directory */ +static int __init ipconfig_proc_net_init(void) +{ + ipconfig_dir = proc_net_mkdir(&init_net, "ipconfig", init_net.proc_net); + if (!ipconfig_dir) + return -ENOMEM; + + return 0; +} + +/* Create a new file under /proc/net/ipconfig */ +static int ipconfig_proc_net_create(const char *name, + const struct file_operations *fops) +{ + char *pname; + struct proc_dir_entry *p; + + if (!ipconfig_dir) + return -ENOMEM; + + pname = kasprintf(GFP_KERNEL, "%s%s", "ipconfig/", name); + if (!pname) + return -ENOMEM; + + p = proc_create(pname, 0444, init_net.proc_net, fops); + kfree(pname); + if (!p) + return -ENOMEM; + + return 0; +} + +/* Write NTP server IP addresses to /proc/net/ipconfig/ntp_servers */ +static int ntp_servers_seq_show(struct seq_file *seq, void *v) +{ + int i; + + for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) { + if (ic_ntp_servers[i] != NONE) + seq_printf(seq, "%pI4\n", &ic_ntp_servers[i]); + } + return 0; +} + +static int ntp_servers_seq_open(struct inode *inode, struct file *file) +{ + return single_open(file, ntp_servers_seq_show, NULL); +} + +static const struct file_operations ntp_servers_seq_fops = { + .open = ntp_servers_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif /* CONFIG_PROC_FS */ /* @@ -1356,8 +1447,20 @@ static int __init ip_auto_config(void) int err; unsigned int i; + /* Initialise all name servers and NTP servers to NONE (but only if the + * "ip=" or "nfsaddrs=" kernel command line parameters weren't decoded, + * otherwise we'll overwrite the IP addresses specified there) + */ + if (ic_set_manually == 0) { + ic_nameservers_predef(); + ic_ntp_servers_predef(); + } + #ifdef CONFIG_PROC_FS proc_create_single("pnp", 0444, init_net.proc_net, pnp_seq_show); + + if (ipconfig_proc_net_init() == 0) + ipconfig_proc_net_create("ntp_servers", &ntp_servers_seq_fops); #endif /* CONFIG_PROC_FS */ if (!ic_enable) @@ -1469,16 +1572,32 @@ static int __init ip_auto_config(void) &ic_servaddr, &root_server_addr, root_server_path); if (ic_dev_mtu) pr_cont(", mtu=%d", ic_dev_mtu); - for (i = 0; i < CONF_NAMESERVERS_MAX; i++) + /* Name servers (if any): */ + for (i = 0; i < CONF_NAMESERVERS_MAX; i++) { if (ic_nameservers[i] != NONE) { - pr_cont(" nameserver%u=%pI4", - i, &ic_nameservers[i]); - break; + if (i == 0) + pr_info(" nameserver%u=%pI4", + i, &ic_nameservers[i]); + else + pr_cont(", nameserver%u=%pI4", + i, &ic_nameservers[i]); } - for (i++; i < CONF_NAMESERVERS_MAX; i++) - if (ic_nameservers[i] != NONE) - pr_cont(", nameserver%u=%pI4", i, &ic_nameservers[i]); - pr_cont("\n"); + if (i + 1 == CONF_NAMESERVERS_MAX) + pr_cont("\n"); + } + /* NTP servers (if any): */ + for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) { + if (ic_ntp_servers[i] != NONE) { + if (i == 0) + pr_info(" ntpserver%u=%pI4", + i, &ic_ntp_servers[i]); + else + pr_cont(", ntpserver%u=%pI4", + i, &ic_ntp_servers[i]); + } + if (i + 1 == CONF_NTP_SERVERS_MAX) + pr_cont("\n"); + } #endif /* !SILENT */ /* @@ -1576,7 +1695,9 @@ static int __init ip_auto_config_setup(char *addrs) return 1; } + /* Initialise all name servers and NTP servers to NONE */ ic_nameservers_predef(); + ic_ntp_servers_predef(); /* Parse string for static IP assignment. */ ip = addrs; @@ -1635,6 +1756,13 @@ static int __init ip_auto_config_setup(char *addrs) ic_nameservers[1] = NONE; } break; + case 9: + if (CONF_NTP_SERVERS_MAX >= 1) { + ic_ntp_servers[0] = in_aton(ip); + if (ic_ntp_servers[0] == ANY) + ic_ntp_servers[0] = NONE; + } + break; } } ip = cp; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 37c4f885ff7b6..9f79b9803a161 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -201,7 +201,8 @@ static const struct nla_policy ipmr_rule_policy[FRA_MAX + 1] = { }; static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, - struct fib_rule_hdr *frh, struct nlattr **tb) + struct fib_rule_hdr *frh, struct nlattr **tb, + struct netlink_ext_ack *extack) { return 0; } diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 30221701614c5..cafb0506c8c99 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -35,17 +35,19 @@ mr_table_alloc(struct net *net, u32 id, struct net *net)) { struct mr_table *mrt; + int err; mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); if (!mrt) - return NULL; + return ERR_PTR(-ENOMEM); mrt->id = id; write_pnet(&mrt->net, net); mrt->ops = *ops; - if (rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params)) { + err = rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params); + if (err) { kfree(mrt); - return NULL; + return ERR_PTR(err); } INIT_LIST_HEAD(&mrt->mfc_cache_list); INIT_LIST_HEAD(&mrt->mfc_unres_queue); diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c new file mode 100644 index 0000000000000..04311f7067e2e --- /dev/null +++ b/net/ipv4/metrics.c @@ -0,0 +1,55 @@ +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <linux/types.h> +#include <net/ip.h> +#include <net/net_namespace.h> +#include <net/tcp.h> + +int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len, + u32 *metrics) +{ + bool ecn_ca = false; + struct nlattr *nla; + int remaining; + + if (!fc_mx) + return 0; + + nla_for_each_attr(nla, fc_mx, fc_mx_len, remaining) { + int type = nla_type(nla); + u32 val; + + if (!type) + continue; + if (type > RTAX_MAX) + return -EINVAL; + + if (type == RTAX_CC_ALGO) { + char tmp[TCP_CA_NAME_MAX]; + + nla_strlcpy(tmp, nla, sizeof(tmp)); + val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca); + if (val == TCP_CA_UNSPEC) + return -EINVAL; + } else { + if (nla_len(nla) != sizeof(u32)) + return -EINVAL; + val = nla_get_u32(nla); + } + if (type == RTAX_ADVMSS && val > 65535 - 40) + val = 65535 - 40; + if (type == RTAX_MTU && val > 65535 - 15) + val = 65535 - 15; + if (type == RTAX_HOPLIMIT && val > 255) + val = 255; + if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) + return -EINVAL; + metrics[type - 1] = val; + } + + if (ecn_ca) + metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; + + return 0; +} +EXPORT_SYMBOL_GPL(ip_metrics_convert); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 280048e1e3958..bbfc356cb1b52 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -29,7 +29,10 @@ config NF_SOCKET_IPV4 tristate "IPv4 socket lookup support" help This option enables the IPv4 socket lookup infrastructure. This is - is required by the iptables socket match. + is required by the {ip,nf}tables socket match. + +config NF_TPROXY_IPV4 + tristate "IPv4 tproxy support" if NF_TABLES @@ -129,10 +132,7 @@ config NFT_CHAIN_NAT_IPV4 source and destination ports. config NF_NAT_MASQUERADE_IPV4 - tristate "IPv4 masquerade support" - help - This is the kernel functionality to provide NAT in the masquerade - flavour (automatic source address selection). + bool config NFT_MASQ_IPV4 tristate "IPv4 masquerading support for nf_tables" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 0e5edd0c79267..8394c17c269f2 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -10,12 +10,14 @@ nf_conntrack_ipv4-y := nf_conntrack_l3proto_ipv4.o nf_conntrack_proto_icmp.o obj-$(CONFIG_NF_CONNTRACK_IPV4) += nf_conntrack_ipv4.o nf_nat_ipv4-y := nf_nat_l3proto_ipv4.o nf_nat_proto_icmp.o +nf_nat_ipv4-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o # defrag obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o obj-$(CONFIG_NF_SOCKET_IPV4) += nf_socket_ipv4.o +obj-$(CONFIG_NF_TPROXY_IPV4) += nf_tproxy_ipv4.o # logging obj-$(CONFIG_NF_LOG_ARP) += nf_log_arp.o @@ -32,9 +34,6 @@ nf_nat_snmp_basic-y := nf_nat_snmp_basic.asn1.o nf_nat_snmp_basic_main.o $(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o -obj-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o - - # NAT protocols (nf_nat) obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index e85f35b89c49a..38ab97b0a2ece 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -301,7 +301,7 @@ ipt_do_table(struct sk_buff *skb, counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, skb->len, 1); - t = ipt_get_target(e); + t = ipt_get_target_c(e); WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) @@ -1783,6 +1783,8 @@ int ipt_register_table(struct net *net, const struct xt_table *table, /* set res now, will see skbs right after nf_register_net_hooks */ WRITE_ONCE(*res, new_table); + if (!ops) + return 0; ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); if (ret != 0) { @@ -1800,7 +1802,8 @@ out_free: void ipt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { - nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + if (ops) + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); __ipt_unregister_table(net, table); } diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index a03e4e7ef5f90..ce1512b02cb20 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -47,7 +47,7 @@ static int masquerade_tg_check(const struct xt_tgchk_param *par) static unsigned int masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) { - struct nf_nat_range range; + struct nf_nat_range2 range; const struct nf_nat_ipv4_multi_range_compat *mr; mr = par->targinfo; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 0f7255cc65ee1..a317445448bfb 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -33,75 +33,63 @@ static const struct xt_table nf_nat_ipv4_table = { static unsigned int iptable_nat_do_chain(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct) -{ - return ipt_do_table(skb, state, state->net->ipv4.nat_table); -} - -static unsigned int iptable_nat_ipv4_fn(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv4_fn(priv, skb, state, iptable_nat_do_chain); -} - -static unsigned int iptable_nat_ipv4_in(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv4_in(priv, skb, state, iptable_nat_do_chain); -} - -static unsigned int iptable_nat_ipv4_out(void *priv, - struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_out(priv, skb, state, iptable_nat_do_chain); -} - -static unsigned int iptable_nat_ipv4_local_fn(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv4_local_fn(priv, skb, state, iptable_nat_do_chain); + return ipt_do_table(skb, state, state->net->ipv4.nat_table); } static const struct nf_hook_ops nf_nat_ipv4_ops[] = { - /* Before packet filtering, change destination */ { - .hook = iptable_nat_ipv4_in, + .hook = iptable_nat_do_chain, .pf = NFPROTO_IPV4, - .nat_hook = true, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, }, - /* After packet filtering, change source */ { - .hook = iptable_nat_ipv4_out, + .hook = iptable_nat_do_chain, .pf = NFPROTO_IPV4, - .nat_hook = true, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, }, - /* Before packet filtering, change destination */ { - .hook = iptable_nat_ipv4_local_fn, + .hook = iptable_nat_do_chain, .pf = NFPROTO_IPV4, - .nat_hook = true, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, }, - /* After packet filtering, change source */ { - .hook = iptable_nat_ipv4_fn, + .hook = iptable_nat_do_chain, .pf = NFPROTO_IPV4, - .nat_hook = true, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, }, }; +static int ipt_nat_register_lookups(struct net *net) +{ + int i, ret; + + for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++) { + ret = nf_nat_l3proto_ipv4_register_fn(net, &nf_nat_ipv4_ops[i]); + if (ret) { + while (i) + nf_nat_l3proto_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[--i]); + + return ret; + } + } + + return 0; +} + +static void ipt_nat_unregister_lookups(struct net *net) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++) + nf_nat_l3proto_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[i]); +} + static int __net_init iptable_nat_table_init(struct net *net) { struct ipt_replace *repl; @@ -114,7 +102,18 @@ static int __net_init iptable_nat_table_init(struct net *net) if (repl == NULL) return -ENOMEM; ret = ipt_register_table(net, &nf_nat_ipv4_table, repl, - nf_nat_ipv4_ops, &net->ipv4.nat_table); + NULL, &net->ipv4.nat_table); + if (ret < 0) { + kfree(repl); + return ret; + } + + ret = ipt_nat_register_lookups(net); + if (ret < 0) { + ipt_unregister_table(net, net->ipv4.nat_table, NULL); + net->ipv4.nat_table = NULL; + } + kfree(repl); return ret; } @@ -123,7 +122,8 @@ static void __net_exit iptable_nat_net_exit(struct net *net) { if (!net->ipv4.nat_table) return; - ipt_unregister_table(net, net->ipv4.nat_table, nf_nat_ipv4_ops); + ipt_nat_unregister_lookups(net); + ipt_unregister_table(net, net->ipv4.nat_table, NULL); net->ipv4.nat_table = NULL; } diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index 0cd46bffa4691..e1e56d7123d2c 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -2,265 +2,12 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> -#include <linux/rhashtable.h> -#include <linux/ip.h> -#include <linux/netdevice.h> -#include <net/ip.h> -#include <net/neighbour.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_tables.h> -/* For layer 4 checksum field offset. */ -#include <linux/tcp.h> -#include <linux/udp.h> - -static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff, - __be32 addr, __be32 new_addr) -{ - struct tcphdr *tcph; - - if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || - skb_try_make_writable(skb, thoff + sizeof(*tcph))) - return -1; - - tcph = (void *)(skb_network_header(skb) + thoff); - inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true); - - return 0; -} - -static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, - __be32 addr, __be32 new_addr) -{ - struct udphdr *udph; - - if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || - skb_try_make_writable(skb, thoff + sizeof(*udph))) - return -1; - - udph = (void *)(skb_network_header(skb) + thoff); - if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { - inet_proto_csum_replace4(&udph->check, skb, addr, - new_addr, true); - if (!udph->check) - udph->check = CSUM_MANGLED_0; - } - - return 0; -} - -static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph, - unsigned int thoff, __be32 addr, - __be32 new_addr) -{ - switch (iph->protocol) { - case IPPROTO_TCP: - if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; - break; - case IPPROTO_UDP: - if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; - break; - } - - return 0; -} - -static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb, - struct iphdr *iph, unsigned int thoff, - enum flow_offload_tuple_dir dir) -{ - __be32 addr, new_addr; - - switch (dir) { - case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = iph->saddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr; - iph->saddr = new_addr; - break; - case FLOW_OFFLOAD_DIR_REPLY: - addr = iph->daddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr; - iph->daddr = new_addr; - break; - default: - return -1; - } - csum_replace4(&iph->check, addr, new_addr); - - return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); -} - -static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, - struct iphdr *iph, unsigned int thoff, - enum flow_offload_tuple_dir dir) -{ - __be32 addr, new_addr; - - switch (dir) { - case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = iph->daddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr; - iph->daddr = new_addr; - break; - case FLOW_OFFLOAD_DIR_REPLY: - addr = iph->saddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr; - iph->saddr = new_addr; - break; - default: - return -1; - } - csum_replace4(&iph->check, addr, new_addr); - - return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); -} - -static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, - enum flow_offload_tuple_dir dir) -{ - struct iphdr *iph = ip_hdr(skb); - unsigned int thoff = iph->ihl * 4; - - if (flow->flags & FLOW_OFFLOAD_SNAT && - (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 || - nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0)) - return -1; - if (flow->flags & FLOW_OFFLOAD_DNAT && - (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 || - nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0)) - return -1; - - return 0; -} - -static bool ip_has_options(unsigned int thoff) -{ - return thoff != sizeof(struct iphdr); -} - -static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, - struct flow_offload_tuple *tuple) -{ - struct flow_ports *ports; - unsigned int thoff; - struct iphdr *iph; - - if (!pskb_may_pull(skb, sizeof(*iph))) - return -1; - - iph = ip_hdr(skb); - thoff = iph->ihl * 4; - - if (ip_is_fragment(iph) || - unlikely(ip_has_options(thoff))) - return -1; - - if (iph->protocol != IPPROTO_TCP && - iph->protocol != IPPROTO_UDP) - return -1; - - thoff = iph->ihl * 4; - if (!pskb_may_pull(skb, thoff + sizeof(*ports))) - return -1; - - ports = (struct flow_ports *)(skb_network_header(skb) + thoff); - - tuple->src_v4.s_addr = iph->saddr; - tuple->dst_v4.s_addr = iph->daddr; - tuple->src_port = ports->source; - tuple->dst_port = ports->dest; - tuple->l3proto = AF_INET; - tuple->l4proto = iph->protocol; - tuple->iifidx = dev->ifindex; - - return 0; -} - -/* Based on ip_exceeds_mtu(). */ -static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) -{ - if (skb->len <= mtu) - return false; - - if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) - return false; - - if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) - return false; - - return true; -} - -static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rtable *rt) -{ - u32 mtu; - - mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); - if (__nf_flow_exceeds_mtu(skb, mtu)) - return true; - - return false; -} - -unsigned int -nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct flow_offload_tuple_rhash *tuplehash; - struct nf_flowtable *flow_table = priv; - struct flow_offload_tuple tuple = {}; - enum flow_offload_tuple_dir dir; - struct flow_offload *flow; - struct net_device *outdev; - const struct rtable *rt; - struct iphdr *iph; - __be32 nexthop; - - if (skb->protocol != htons(ETH_P_IP)) - return NF_ACCEPT; - - if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0) - return NF_ACCEPT; - - tuplehash = flow_offload_lookup(flow_table, &tuple); - if (tuplehash == NULL) - return NF_ACCEPT; - - outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx); - if (!outdev) - return NF_ACCEPT; - - dir = tuplehash->tuple.dir; - flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - - rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache; - if (unlikely(nf_flow_exceeds_mtu(skb, rt))) - return NF_ACCEPT; - - if (skb_try_make_writable(skb, sizeof(*iph))) - return NF_DROP; - - if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) && - nf_flow_nat_ip(flow, skb, dir) < 0) - return NF_DROP; - - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; - iph = ip_hdr(skb); - ip_decrease_ttl(iph); - - skb->dev = outdev; - nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); - neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb); - - return NF_STOLEN; -} -EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook); static struct nf_flowtable_type flowtable_ipv4 = { .family = NFPROTO_IPV4, - .params = &nf_flow_offload_rhash_params, - .gc = nf_flow_offload_work_gc, + .init = nf_flow_table_init, .free = nf_flow_table_free, .hook = nf_flow_offload_ip_hook, .owner = THIS_MODULE, diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index ac8342dcb55eb..4e6b53ab6c337 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -395,7 +395,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, static void ip_nat_q931_expect(struct nf_conn *new, struct nf_conntrack_expect *this) { - struct nf_nat_range range; + struct nf_nat_range2 range; if (this->tuple.src.u3.ip != 0) { /* Only accept calls from GK */ nf_nat_follow_master(new, this); @@ -497,7 +497,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, static void ip_nat_callforwarding_expect(struct nf_conn *new, struct nf_conntrack_expect *this) { - struct nf_nat_range range; + struct nf_nat_range2 range; /* This must be a fresh one. */ BUG_ON(new->status & IPS_NAT_DONE_MASK); diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index f7ff6a364d7bc..6115bf1ff6f0a 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -63,7 +63,7 @@ static void nf_nat_ipv4_decode_session(struct sk_buff *skb, #endif /* CONFIG_XFRM */ static bool nf_nat_ipv4_in_range(const struct nf_conntrack_tuple *t, - const struct nf_nat_range *range) + const struct nf_nat_range2 *range) { return ntohl(t->src.u3.ip) >= ntohl(range->min_addr.ip) && ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip); @@ -143,7 +143,7 @@ static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range *range) + struct nf_nat_range2 *range) { if (tb[CTA_NAT_V4_MINIP]) { range->min_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MINIP]); @@ -241,34 +241,18 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); -unsigned int +static unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - unsigned int (*do_chain)(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; - struct nf_conn_nat *nat; - /* maniptype == SRC for postrouting. */ - enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook); ct = nf_ct_get(skb, &ctinfo); - /* Can't track? It's not due to stress, or conntrack would - * have dropped it. Hence it's the user's responsibilty to - * packet filter it out, or implement conntrack/NAT for that - * protocol. 8) --RR - */ if (!ct) return NF_ACCEPT; - nat = nfct_nat(ct); - - switch (ctinfo) { - case IP_CT_RELATED: - case IP_CT_RELATED_REPLY: + if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, state->hook)) @@ -276,78 +260,30 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, else return NF_ACCEPT; } - /* Only ICMPs can be IP_CT_IS_REPLY: */ - /* fall through */ - case IP_CT_NEW: - /* Seen it before? This can happen for loopback, retrans, - * or local packets. - */ - if (!nf_nat_initialized(ct, maniptype)) { - unsigned int ret; - - ret = do_chain(priv, skb, state, ct); - if (ret != NF_ACCEPT) - return ret; - - if (nf_nat_initialized(ct, HOOK2MANIP(state->hook))) - break; - - ret = nf_nat_alloc_null_binding(ct, state->hook); - if (ret != NF_ACCEPT) - return ret; - } else { - pr_debug("Already setup manip %s for ct %p\n", - maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", - ct); - if (nf_nat_oif_changed(state->hook, ctinfo, nat, - state->out)) - goto oif_changed; - } - break; - - default: - /* ESTABLISHED */ - WARN_ON(ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) - goto oif_changed; } - return nf_nat_packet(ct, ctinfo, state->hook, skb); - -oif_changed: - nf_ct_kill_acct(ct, ctinfo, skb); - return NF_DROP; + return nf_nat_inet_fn(priv, skb, state); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn); -unsigned int +static unsigned int nf_nat_ipv4_in(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - unsigned int (*do_chain)(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state) { unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; - ret = nf_nat_ipv4_fn(priv, skb, state, do_chain); + ret = nf_nat_ipv4_fn(priv, skb, state); if (ret != NF_DROP && ret != NF_STOLEN && daddr != ip_hdr(skb)->daddr) skb_dst_drop(skb); return ret; } -EXPORT_SYMBOL_GPL(nf_nat_ipv4_in); -unsigned int +static unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - unsigned int (*do_chain)(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; @@ -356,7 +292,7 @@ nf_nat_ipv4_out(void *priv, struct sk_buff *skb, #endif unsigned int ret; - ret = nf_nat_ipv4_fn(priv, skb, state, do_chain); + ret = nf_nat_ipv4_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && @@ -376,22 +312,17 @@ nf_nat_ipv4_out(void *priv, struct sk_buff *skb, #endif return ret; } -EXPORT_SYMBOL_GPL(nf_nat_ipv4_out); -unsigned int +static unsigned int nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - unsigned int (*do_chain)(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; - ret = nf_nat_ipv4_fn(priv, skb, state, do_chain); + ret = nf_nat_ipv4_fn(priv, skb, state); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -415,7 +346,49 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, } return ret; } -EXPORT_SYMBOL_GPL(nf_nat_ipv4_local_fn); + +static const struct nf_hook_ops nf_nat_ipv4_ops[] = { + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv4_in, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv4_out, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_NAT_SRC, + }, + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv4_local_fn, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv4_fn, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_NAT_SRC, + }, +}; + +int nf_nat_l3proto_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops) +{ + return nf_nat_register_fn(net, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); +} +EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_register_fn); + +void nf_nat_l3proto_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops) +{ + nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); +} +EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_unregister_fn); static int __init nf_nat_l3proto_ipv4_init(void) { diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index 0c366aad89cb4..ad3aeff152ede 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -7,7 +7,6 @@ */ #include <linux/types.h> -#include <linux/module.h> #include <linux/atomic.h> #include <linux/inetdevice.h> #include <linux/ip.h> @@ -24,13 +23,13 @@ unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, const struct net_device *out) { struct nf_conn *ct; struct nf_conn_nat *nat; enum ip_conntrack_info ctinfo; - struct nf_nat_range newrange; + struct nf_nat_range2 newrange; const struct rtable *rt; __be32 newsrc, nh; @@ -157,6 +156,3 @@ void nf_nat_masquerade_ipv4_unregister_notifier(void) unregister_inetaddr_notifier(&masq_inet_notifier); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>"); diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 8a69363b48846..5d259a12e25fa 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -48,7 +48,7 @@ static void pptp_nat_expected(struct nf_conn *ct, struct nf_conntrack_tuple t = {}; const struct nf_ct_pptp_master *ct_pptp_info; const struct nf_nat_pptp *nat_pptp_info; - struct nf_nat_range range; + struct nf_nat_range2 range; struct nf_conn_nat *nat; nat = nf_ct_nat_ext_add(ct); diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c index edf05002d674e..00fda6331ce5a 100644 --- a/net/ipv4/netfilter/nf_nat_proto_gre.c +++ b/net/ipv4/netfilter/nf_nat_proto_gre.c @@ -41,7 +41,7 @@ MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE"); static void gre_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c index 7b98baa13edeb..6d7cf1d79baf3 100644 --- a/net/ipv4/netfilter/nf_nat_proto_icmp.c +++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c @@ -30,7 +30,7 @@ icmp_in_range(const struct nf_conntrack_tuple *tuple, static void icmp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c new file mode 100644 index 0000000000000..805e83ec3ad93 --- /dev/null +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -0,0 +1,147 @@ +/* + * Copyright (C) 2007-2008 BalaBit IT Ltd. + * Author: Krisztian Kovacs + * + * 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. + * + */ + +#include <net/netfilter/nf_tproxy.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <net/sock.h> +#include <net/inet_sock.h> +#include <linux/ip.h> +#include <net/checksum.h> +#include <net/udp.h> +#include <net/tcp.h> +#include <linux/inetdevice.h> + +struct sock * +nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, + __be32 laddr, __be16 lport, struct sock *sk) +{ + const struct iphdr *iph = ip_hdr(skb); + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); + if (hp == NULL) { + inet_twsk_put(inet_twsk(sk)); + return NULL; + } + + if (hp->syn && !hp->rst && !hp->ack && !hp->fin) { + /* SYN to a TIME_WAIT socket, we'd rather redirect it + * to a listener socket if there's one */ + struct sock *sk2; + + sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, + iph->saddr, laddr ? laddr : iph->daddr, + hp->source, lport ? lport : hp->dest, + skb->dev, NF_TPROXY_LOOKUP_LISTENER); + if (sk2) { + inet_twsk_deschedule_put(inet_twsk(sk)); + sk = sk2; + } + } + + return sk; +} +EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait4); + +__be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) +{ + struct in_device *indev; + __be32 laddr; + + if (user_laddr) + return user_laddr; + + laddr = 0; + indev = __in_dev_get_rcu(skb->dev); + for_primary_ifa(indev) { + laddr = ifa->ifa_local; + break; + } endfor_ifa(indev); + + return laddr ? laddr : daddr; +} +EXPORT_SYMBOL_GPL(nf_tproxy_laddr4); + +struct sock * +nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, + const u8 protocol, + const __be32 saddr, const __be32 daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in, + const enum nf_tproxy_lookup_t lookup_type) +{ + struct sock *sk; + struct tcphdr *tcph; + + switch (protocol) { + case IPPROTO_TCP: + switch (lookup_type) { + case NF_TPROXY_LOOKUP_LISTENER: + tcph = hp; + sk = inet_lookup_listener(net, &tcp_hashinfo, skb, + ip_hdrlen(skb) + + __tcp_hdrlen(tcph), + saddr, sport, + daddr, dport, + in->ifindex, 0); + + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + break; + case NF_TPROXY_LOOKUP_ESTABLISHED: + sk = inet_lookup_established(net, &tcp_hashinfo, + saddr, sport, daddr, dport, + in->ifindex); + break; + default: + BUG(); + } + break; + case IPPROTO_UDP: + sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + if (sk) { + int connected = (sk->sk_state == TCP_ESTABLISHED); + int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + if ((lookup_type == NF_TPROXY_LOOKUP_ESTABLISHED && + (!connected || wildcard)) || + (lookup_type == NF_TPROXY_LOOKUP_LISTENER && connected)) { + sock_put(sk); + sk = NULL; + } + } + break; + default: + WARN_ON(1); + sk = NULL; + } + + pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n", + protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk); + + return sk; +} +EXPORT_SYMBOL_GPL(nf_tproxy_get_sock_v4); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs"); +MODULE_DESCRIPTION("Netfilter IPv4 transparent proxy support"); diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c index b5464a3f253ba..a3c4ea303e3ec 100644 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c @@ -27,9 +27,8 @@ #include <net/ip.h> static unsigned int nft_nat_do_chain(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct) + struct sk_buff *skb, + const struct nf_hook_state *state) { struct nft_pktinfo pkt; @@ -39,42 +38,14 @@ static unsigned int nft_nat_do_chain(void *priv, return nft_do_chain(&pkt, priv); } -static unsigned int nft_nat_ipv4_fn(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv4_fn(priv, skb, state, nft_nat_do_chain); -} - -static unsigned int nft_nat_ipv4_in(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv4_in(priv, skb, state, nft_nat_do_chain); -} - -static unsigned int nft_nat_ipv4_out(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv4_out(priv, skb, state, nft_nat_do_chain); -} - -static unsigned int nft_nat_ipv4_local_fn(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv4_local_fn(priv, skb, state, nft_nat_do_chain); -} - -static int nft_nat_ipv4_init(struct nft_ctx *ctx) +static int nft_nat_ipv4_reg(struct net *net, const struct nf_hook_ops *ops) { - return nf_ct_netns_get(ctx->net, ctx->family); + return nf_nat_l3proto_ipv4_register_fn(net, ops); } -static void nft_nat_ipv4_free(struct nft_ctx *ctx) +static void nft_nat_ipv4_unreg(struct net *net, const struct nf_hook_ops *ops) { - nf_ct_netns_put(ctx->net, ctx->family); + nf_nat_l3proto_ipv4_unregister_fn(net, ops); } static const struct nft_chain_type nft_chain_nat_ipv4 = { @@ -87,13 +58,13 @@ static const struct nft_chain_type nft_chain_nat_ipv4 = { (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .hooks = { - [NF_INET_PRE_ROUTING] = nft_nat_ipv4_in, - [NF_INET_POST_ROUTING] = nft_nat_ipv4_out, - [NF_INET_LOCAL_OUT] = nft_nat_ipv4_local_fn, - [NF_INET_LOCAL_IN] = nft_nat_ipv4_fn, + [NF_INET_PRE_ROUTING] = nft_nat_do_chain, + [NF_INET_POST_ROUTING] = nft_nat_do_chain, + [NF_INET_LOCAL_OUT] = nft_nat_do_chain, + [NF_INET_LOCAL_IN] = nft_nat_do_chain, }, - .init = nft_nat_ipv4_init, - .free = nft_nat_ipv4_free, + .ops_register = nft_nat_ipv4_reg, + .ops_unregister = nft_nat_ipv4_unreg, }; static int __init nft_chain_nat_init(void) diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index f186772771193..f1193e1e928aa 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -21,7 +21,7 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_masq *priv = nft_expr_priv(expr); - struct nf_nat_range range; + struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); range.flags = priv->flags; diff --git a/net/ipv4/netlink.c b/net/ipv4/netlink.c new file mode 100644 index 0000000000000..f86bb4f066095 --- /dev/null +++ b/net/ipv4/netlink.c @@ -0,0 +1,23 @@ +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <linux/types.h> +#include <net/net_namespace.h> +#include <net/netlink.h> +#include <net/ip.h> + +int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, + struct netlink_ext_ack *extack) +{ + *ip_proto = nla_get_u8(attr); + + switch (*ip_proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_ICMP: + return 0; + default: + NL_SET_ERR_MSG(extack, "Unsupported ip proto"); + return -EOPNOTSUPP; + } +} +EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 573e43c8ed874..77350c1256ce9 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -284,6 +284,9 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE), SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL), SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS), + SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED), + SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE), + SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 75fb8864be67f..bf4e4adc2d000 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1341,6 +1341,37 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) return NULL; } +/* MTU selection: + * 1. mtu on route is locked - use it + * 2. mtu from nexthop exception + * 3. mtu from egress device + */ + +u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) +{ + struct fib_info *fi = res->fi; + struct fib_nh *nh = &fi->fib_nh[res->nh_sel]; + struct net_device *dev = nh->nh_dev; + u32 mtu = 0; + + if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu || + fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU)) + mtu = fi->fib_mtu; + + if (likely(!mtu)) { + struct fib_nh_exception *fnhe; + + fnhe = find_exception(nh, daddr); + if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires)) + mtu = fnhe->fnhe_pmtu; + } + + if (likely(!mtu)) + mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU); + + return mtu - lwtunnel_headroom(nh->nh_lwtstate, mtu); +} + static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, __be32 daddr, const bool do_cache) { @@ -2563,11 +2594,10 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ -static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, - struct flowi4 *fl4, struct sk_buff *skb, u32 portid, - u32 seq) +static int rt_fill_info(struct net *net, __be32 dst, __be32 src, + struct rtable *rt, u32 table_id, struct flowi4 *fl4, + struct sk_buff *skb, u32 portid, u32 seq) { - struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; unsigned long expires = 0; @@ -2663,7 +2693,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, } } else #endif - if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex)) + if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif)) goto nla_put_failure; } @@ -2678,43 +2708,93 @@ nla_put_failure: return -EMSGSIZE; } +static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, + u8 ip_proto, __be16 sport, + __be16 dport) +{ + struct sk_buff *skb; + struct iphdr *iph; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return NULL; + + /* Reserve room for dummy headers, this skb can pass + * through good chunk of routing engine. + */ + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb->protocol = htons(ETH_P_IP); + iph = skb_put(skb, sizeof(struct iphdr)); + iph->protocol = ip_proto; + iph->saddr = src; + iph->daddr = dst; + iph->version = 0x4; + iph->frag_off = 0; + iph->ihl = 0x5; + skb_set_transport_header(skb, skb->len); + + switch (iph->protocol) { + case IPPROTO_UDP: { + struct udphdr *udph; + + udph = skb_put_zero(skb, sizeof(struct udphdr)); + udph->source = sport; + udph->dest = dport; + udph->len = sizeof(struct udphdr); + udph->check = 0; + break; + } + case IPPROTO_TCP: { + struct tcphdr *tcph; + + tcph = skb_put_zero(skb, sizeof(struct tcphdr)); + tcph->source = sport; + tcph->dest = dport; + tcph->doff = sizeof(struct tcphdr) / 4; + tcph->rst = 1; + tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), + src, dst, 0); + break; + } + case IPPROTO_ICMP: { + struct icmphdr *icmph; + + icmph = skb_put_zero(skb, sizeof(struct icmphdr)); + icmph->type = ICMP_ECHO; + icmph->code = 0; + } + } + + return skb; +} + static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); - struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; + u32 table_id = RT_TABLE_MAIN; + __be16 sport = 0, dport = 0; struct fib_result res = {}; + u8 ip_proto = IPPROTO_UDP; struct rtable *rt = NULL; + struct sk_buff *skb; + struct rtmsg *rtm; struct flowi4 fl4; __be32 dst = 0; __be32 src = 0; + kuid_t uid; u32 iif; int err; int mark; - struct sk_buff *skb; - u32 table_id = RT_TABLE_MAIN; - kuid_t uid; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) - goto errout; + return err; rtm = nlmsg_data(nlh); - - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) { - err = -ENOBUFS; - goto errout; - } - - /* Reserve room for dummy headers, this skb can pass - through good chunk of routing engine. - */ - skb_reset_mac_header(skb); - skb_reset_network_header(skb); - src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; @@ -2724,14 +2804,22 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, else uid = (iif ? INVALID_UID : current_uid()); - /* Bugfix: need to give ip_route_input enough of an IP header to - * not gag. - */ - ip_hdr(skb)->protocol = IPPROTO_UDP; - ip_hdr(skb)->saddr = src; - ip_hdr(skb)->daddr = dst; + if (tb[RTA_IP_PROTO]) { + err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], + &ip_proto, extack); + if (err) + return err; + } - skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr)); + if (tb[RTA_SPORT]) + sport = nla_get_be16(tb[RTA_SPORT]); + + if (tb[RTA_DPORT]) + dport = nla_get_be16(tb[RTA_DPORT]); + + skb = inet_rtm_getroute_build_skb(src, dst, ip_proto, sport, dport); + if (!skb) + return -ENOBUFS; memset(&fl4, 0, sizeof(fl4)); fl4.daddr = dst; @@ -2740,6 +2828,11 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; + if (sport) + fl4.fl4_sport = sport; + if (dport) + fl4.fl4_dport = dport; + fl4.flowi4_proto = ip_proto; rcu_read_lock(); @@ -2749,10 +2842,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, dev = dev_get_by_index_rcu(net, iif); if (!dev) { err = -ENODEV; - goto errout_free; + goto errout_rcu; } - skb->protocol = htons(ETH_P_IP); + fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos, @@ -2772,7 +2865,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, } if (err) - goto errout_free; + goto errout_rcu; if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; @@ -2780,34 +2873,40 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) table_id = res.table ? res.table->tb_id : 0; + /* reset skb for netlink reply msg */ + skb_trim(skb, 0); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + skb_reset_mac_header(skb); + if (rtm->rtm_flags & RTM_F_FIB_MATCH) { if (!res.fi) { err = fib_props[res.type].error; if (!err) err = -EHOSTUNREACH; - goto errout_free; + goto errout_rcu; } err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, table_id, rt->rt_type, res.prefix, res.prefixlen, fl4.flowi4_tos, res.fi, 0); } else { - err = rt_fill_info(net, dst, src, table_id, &fl4, skb, + err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq); } if (err < 0) - goto errout_free; + goto errout_rcu; rcu_read_unlock(); err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); -errout: - return err; errout_free: + return err; +errout_rcu: rcu_read_unlock(); kfree_skb(skb); - goto errout; + goto errout_free; } void ip_rt_multicast_event(struct in_device *in_dev) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4b195bac8ac0e..d06247ba08b26 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -30,6 +30,7 @@ static int zero; static int one = 1; +static int two = 2; static int four = 4; static int thousand = 1000; static int gso_max_segs = GSO_MAX_SEGS; @@ -46,6 +47,7 @@ static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; +static int comp_sack_nr_max = 255; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -844,7 +846,9 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_tcp_tw_reuse, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, }, { .procname = "tcp_max_tw_buckets", @@ -1152,6 +1156,22 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = &one, }, { + .procname = "tcp_comp_sack_delay_ns", + .data = &init_net.ipv4.sysctl_tcp_comp_sack_delay_ns, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "tcp_comp_sack_nr", + .data = &init_net.ipv4.sysctl_tcp_comp_sack_nr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &comp_sack_nr_max, + }, + { .procname = "udp_rmem_min", .data = &init_net.ipv4.sysctl_udp_rmem_min, .maxlen = sizeof(init_net.ipv4.sysctl_udp_rmem_min), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index dec47e6789e75..2741953adaba2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1691,6 +1691,139 @@ int tcp_peek_len(struct socket *sock) } EXPORT_SYMBOL(tcp_peek_len); +/* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ +int tcp_set_rcvlowat(struct sock *sk, int val) +{ + sk->sk_rcvlowat = val ? : 1; + + /* Check if we need to signal EPOLLIN right now */ + tcp_data_ready(sk); + + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + return 0; + + /* val comes from user space and might be close to INT_MAX */ + val <<= 1; + if (val < 0) + val = INT_MAX; + + val = min(val, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); + if (val > sk->sk_rcvbuf) { + sk->sk_rcvbuf = val; + tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); + } + return 0; +} +EXPORT_SYMBOL(tcp_set_rcvlowat); + +#ifdef CONFIG_MMU +static const struct vm_operations_struct tcp_vm_ops = { +}; + +int tcp_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma) +{ + if (vma->vm_flags & (VM_WRITE | VM_EXEC)) + return -EPERM; + vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC); + + /* Instruct vm_insert_page() to not down_read(mmap_sem) */ + vma->vm_flags |= VM_MIXEDMAP; + + vma->vm_ops = &tcp_vm_ops; + return 0; +} +EXPORT_SYMBOL(tcp_mmap); + +static int tcp_zerocopy_receive(struct sock *sk, + struct tcp_zerocopy_receive *zc) +{ + unsigned long address = (unsigned long)zc->address; + const skb_frag_t *frags = NULL; + u32 length = 0, seq, offset; + struct vm_area_struct *vma; + struct sk_buff *skb = NULL; + struct tcp_sock *tp; + int ret; + + if (address & (PAGE_SIZE - 1) || address != zc->address) + return -EINVAL; + + if (sk->sk_state == TCP_LISTEN) + return -ENOTCONN; + + sock_rps_record_flow(sk); + + down_read(¤t->mm->mmap_sem); + + ret = -EINVAL; + vma = find_vma(current->mm, address); + if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) + goto out; + zc->length = min_t(unsigned long, zc->length, vma->vm_end - address); + + tp = tcp_sk(sk); + seq = tp->copied_seq; + zc->length = min_t(u32, zc->length, tcp_inq(sk)); + zc->length &= ~(PAGE_SIZE - 1); + + zap_page_range(vma, address, zc->length); + + zc->recv_skip_hint = 0; + ret = 0; + while (length + PAGE_SIZE <= zc->length) { + if (zc->recv_skip_hint < PAGE_SIZE) { + if (skb) { + skb = skb->next; + offset = seq - TCP_SKB_CB(skb)->seq; + } else { + skb = tcp_recv_skb(sk, seq, &offset); + } + + zc->recv_skip_hint = skb->len - offset; + offset -= skb_headlen(skb); + if ((int)offset < 0 || skb_has_frag_list(skb)) + break; + frags = skb_shinfo(skb)->frags; + while (offset) { + if (frags->size > offset) + goto out; + offset -= frags->size; + frags++; + } + } + if (frags->size != PAGE_SIZE || frags->page_offset) + break; + ret = vm_insert_page(vma, address + length, + skb_frag_page(frags)); + if (ret) + break; + length += PAGE_SIZE; + seq += PAGE_SIZE; + zc->recv_skip_hint -= PAGE_SIZE; + frags++; + } +out: + up_read(¤t->mm->mmap_sem); + if (length) { + tp->copied_seq = seq; + tcp_rcv_space_adjust(sk); + + /* Clean up data we have read: This will do ACK frames. */ + tcp_recv_skb(sk, seq, &offset); + tcp_cleanup_rbuf(sk, length); + ret = 0; + if (length == zc->length) + zc->recv_skip_hint = 0; + } else { + if (!zc->recv_skip_hint && sock_flag(sk, SOCK_DONE)) + ret = -EIO; + } + zc->length = length; + return ret; +} +#endif + static void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping *tss) { @@ -1746,6 +1879,22 @@ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, } } +static int tcp_inq_hint(struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + u32 copied_seq = READ_ONCE(tp->copied_seq); + u32 rcv_nxt = READ_ONCE(tp->rcv_nxt); + int inq; + + inq = rcv_nxt - copied_seq; + if (unlikely(inq < 0 || copied_seq != READ_ONCE(tp->copied_seq))) { + lock_sock(sk); + inq = tp->rcv_nxt - tp->copied_seq; + release_sock(sk); + } + return inq; +} + /* * This routine copies from a sock struct into the user buffer. * @@ -1762,13 +1911,14 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, u32 peek_seq; u32 *seq; unsigned long used; - int err; + int err, inq; int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; u32 urg_hole = 0; struct scm_timestamping tss; bool has_tss = false; + bool has_cmsg; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -1783,6 +1933,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (sk->sk_state == TCP_LISTEN) goto out; + has_cmsg = tp->recvmsg_inq; timeo = sock_rcvtimeo(sk, nonblock); /* Urgent data needs to be handled specially. */ @@ -1969,6 +2120,7 @@ skip_copy: if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, &tss); has_tss = true; + has_cmsg = true; } if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; @@ -1988,13 +2140,20 @@ skip_copy: * on connected socket. I was just happy when found this 8) --ANK */ - if (has_tss) - tcp_recv_timestamp(msg, sk, &tss); - /* Clean up data we have read: This will do ACK frames. */ tcp_cleanup_rbuf(sk, copied); release_sock(sk); + + if (has_cmsg) { + if (has_tss) + tcp_recv_timestamp(msg, sk, &tss); + if (tp->recvmsg_inq) { + inq = tcp_inq_hint(sk); + put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); + } + } + return copied; out: @@ -2411,6 +2570,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; + tp->delivered_ce = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); @@ -2424,6 +2584,7 @@ int tcp_disconnect(struct sock *sk, int flags) dst_release(sk->sk_rx_dst); sk->sk_rx_dst = NULL; tcp_saved_syn_free(tp); + tp->compressed_ack = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); @@ -2862,6 +3023,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level, tp->notsent_lowat = val; sk->sk_write_space(sk); break; + case TCP_INQ: + if (val > 1 || val < 0) + err = -EINVAL; + else + tp->recvmsg_inq = val; + break; default: err = -ENOPROTOOPT; break; @@ -3020,6 +3187,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) rate64 = tcp_compute_delivery_rate(tp); if (rate64) info->tcpi_delivery_rate = rate64; + info->tcpi_delivered = tp->delivered; + info->tcpi_delivered_ce = tp->delivered_ce; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -3033,7 +3202,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) u32 rate; stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) + - 5 * nla_total_size(sizeof(u32)) + + 7 * nla_total_size(sizeof(u32)) + 3 * nla_total_size(sizeof(u8)), GFP_ATOMIC); if (!stats) return NULL; @@ -3064,9 +3233,12 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); + nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); + nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce); nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); + return stats; } @@ -3282,6 +3454,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; break; + case TCP_INQ: + val = tp->recvmsg_inq; + break; case TCP_SAVE_SYN: val = tp->save_syn; break; @@ -3318,6 +3493,25 @@ static int do_tcp_getsockopt(struct sock *sk, int level, } return 0; } +#ifdef CONFIG_MMU + case TCP_ZEROCOPY_RECEIVE: { + struct tcp_zerocopy_receive zc; + int err; + + if (get_user(len, optlen)) + return -EFAULT; + if (len != sizeof(zc)) + return -EINVAL; + if (copy_from_user(&zc, optval, len)) + return -EFAULT; + lock_sock(sk); + err = tcp_zerocopy_receive(sk, &zc); + release_sock(sk); + if (!err && copy_to_user(optval, &zc, len)) + err = -EFAULT; + return err; + } +#endif default: return -ENOPROTOOPT; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e51c644484dc5..355d3dffd021c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -111,6 +111,25 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE; #define REXMIT_LOST 1 /* retransmit packets marked lost */ #define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */ +#if IS_ENABLED(CONFIG_TLS_DEVICE) +static DEFINE_STATIC_KEY_FALSE(clean_acked_data_enabled); + +void clean_acked_data_enable(struct inet_connection_sock *icsk, + void (*cad)(struct sock *sk, u32 ack_seq)) +{ + icsk->icsk_clean_acked = cad; + static_branch_inc(&clean_acked_data_enabled); +} +EXPORT_SYMBOL_GPL(clean_acked_data_enable); + +void clean_acked_data_disable(struct inet_connection_sock *icsk) +{ + static_branch_dec(&clean_acked_data_enabled); + icsk->icsk_clean_acked = NULL; +} +EXPORT_SYMBOL_GPL(clean_acked_data_disable); +#endif + static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, unsigned int len) { @@ -184,21 +203,23 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) } } -static void tcp_incr_quickack(struct sock *sk) +static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned int quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss); if (quickacks == 0) quickacks = 2; + quickacks = min(quickacks, max_quickacks); if (quickacks > icsk->icsk_ack.quick) - icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS); + icsk->icsk_ack.quick = quickacks; } -static void tcp_enter_quickack_mode(struct sock *sk) +static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); - tcp_incr_quickack(sk); + + tcp_incr_quickack(sk, max_quickacks); icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } @@ -233,8 +254,10 @@ static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; } -static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb) +static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); + switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) { case INET_ECN_NOT_ECT: /* Funny extension: if ECT is not set on a segment, @@ -242,31 +265,31 @@ static void __tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb) * it is probably a retransmit. */ if (tp->ecn_flags & TCP_ECN_SEEN) - tcp_enter_quickack_mode((struct sock *)tp); + tcp_enter_quickack_mode(sk, 1); break; case INET_ECN_CE: - if (tcp_ca_needs_ecn((struct sock *)tp)) - tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_IS_CE); + if (tcp_ca_needs_ecn(sk)) + tcp_ca_event(sk, CA_EVENT_ECN_IS_CE); if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) { /* Better not delay acks, sender can have a very low cwnd */ - tcp_enter_quickack_mode((struct sock *)tp); + tcp_enter_quickack_mode(sk, 1); tp->ecn_flags |= TCP_ECN_DEMAND_CWR; } tp->ecn_flags |= TCP_ECN_SEEN; break; default: - if (tcp_ca_needs_ecn((struct sock *)tp)) - tcp_ca_event((struct sock *)tp, CA_EVENT_ECN_NO_CE); + if (tcp_ca_needs_ecn(sk)) + tcp_ca_event(sk, CA_EVENT_ECN_NO_CE); tp->ecn_flags |= TCP_ECN_SEEN; break; } } -static void tcp_ecn_check_ce(struct tcp_sock *tp, const struct sk_buff *skb) +static void tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) { - if (tp->ecn_flags & TCP_ECN_OK) - __tcp_ecn_check_ce(tp, skb); + if (tcp_sk(sk)->ecn_flags & TCP_ECN_OK) + __tcp_ecn_check_ce(sk, skb); } static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th) @@ -582,6 +605,8 @@ void tcp_rcv_space_adjust(struct sock *sk) u32 copied; int time; + trace_tcp_rcv_space_adjust(sk); + tcp_mstamp_refresh(tp); time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0) @@ -665,7 +690,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) /* The _first_ data packet received, initialize * delayed ACK engine. */ - tcp_incr_quickack(sk); + tcp_incr_quickack(sk, TCP_MAX_QUICKACKS); icsk->icsk_ack.ato = TCP_ATO_MIN; } else { int m = now - icsk->icsk_ack.lrcvtime; @@ -681,13 +706,13 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) /* Too long gap. Apparently sender failed to * restart window, so that we send ACKs quickly. */ - tcp_incr_quickack(sk); + tcp_incr_quickack(sk, TCP_MAX_QUICKACKS); sk_mem_reclaim(sk); } } icsk->icsk_ack.lrcvtime = now; - tcp_ecn_check_ce(tp, skb); + tcp_ecn_check_ce(sk, skb); if (skb->len >= 128) tcp_grow_window(sk, skb); @@ -1896,19 +1921,54 @@ static inline void tcp_init_undo(struct tcp_sock *tp) tp->undo_retrans = tp->retrans_out ? : -1; } -/* Enter Loss state. If we detect SACK reneging, forget all SACK information +static bool tcp_is_rack(const struct sock *sk) +{ + return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION; +} + +/* If we detect SACK reneging, forget all SACK information * and reset tags completely, otherwise preserve SACKs. If receiver * dropped its ofo queue, we will know this due to reneging detection. */ +static void tcp_timeout_mark_lost(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb, *head; + bool is_reneg; /* is receiver reneging on SACKs? */ + + head = tcp_rtx_queue_head(sk); + is_reneg = head && (TCP_SKB_CB(head)->sacked & TCPCB_SACKED_ACKED); + if (is_reneg) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); + tp->sacked_out = 0; + /* Mark SACK reneging until we recover from this loss event. */ + tp->is_sack_reneg = 1; + } else if (tcp_is_reno(tp)) { + tcp_reset_reno_sack(tp); + } + + skb = head; + skb_rbtree_walk_from(skb) { + if (is_reneg) + TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; + else if (tcp_is_rack(sk) && skb != head && + tcp_rack_skb_timeout(tp, skb, 0) > 0) + continue; /* Don't mark recently sent ones lost yet */ + tcp_mark_skb_lost(sk, skb); + } + tcp_verify_left_out(tp); + tcp_clear_all_retrans_hints(tp); +} + +/* Enter Loss state. */ void tcp_enter_loss(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); - struct sk_buff *skb; bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; - bool is_reneg; /* is receiver reneging on SACKs? */ - bool mark_lost; + + tcp_timeout_mark_lost(sk); /* Reduce ssthresh if it has not yet been made inside this window. */ if (icsk->icsk_ca_state <= TCP_CA_Disorder || @@ -1920,40 +1980,10 @@ void tcp_enter_loss(struct sock *sk) tcp_ca_event(sk, CA_EVENT_LOSS); tcp_init_undo(tp); } - tp->snd_cwnd = 1; + tp->snd_cwnd = tcp_packets_in_flight(tp) + 1; tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_jiffies32; - tp->retrans_out = 0; - tp->lost_out = 0; - - if (tcp_is_reno(tp)) - tcp_reset_reno_sack(tp); - - skb = tcp_rtx_queue_head(sk); - is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED); - if (is_reneg) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING); - tp->sacked_out = 0; - /* Mark SACK reneging until we recover from this loss event. */ - tp->is_sack_reneg = 1; - } - tcp_clear_all_retrans_hints(tp); - - skb_rbtree_walk_from(skb) { - mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) || - is_reneg); - if (mark_lost) - tcp_sum_lost(tp, skb); - TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; - if (mark_lost) { - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; - TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; - tp->lost_out += tcp_skb_pcount(skb); - } - } - tcp_verify_left_out(tp); - /* Timeout in disordered state after receiving substantial DUPACKs * suggests that the degree of reordering is over-estimated. */ @@ -2120,7 +2150,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag) return true; /* Not-A-Trick#2 : Classic rule... */ - if (tcp_dupack_heuristics(tp) > tp->reordering) + if (!tcp_is_rack(sk) && tcp_dupack_heuristics(tp) > tp->reordering) return true; return false; @@ -2197,9 +2227,7 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit) { struct tcp_sock *tp = tcp_sk(sk); - if (tcp_is_reno(tp)) { - tcp_mark_head_lost(sk, 1, 1); - } else { + if (tcp_is_sack(tp)) { int sacked_upto = tp->sacked_out - tp->reordering; if (sacked_upto >= 0) tcp_mark_head_lost(sk, sacked_upto, 0); @@ -2697,12 +2725,16 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) return false; } -static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag) +static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag) { struct tcp_sock *tp = tcp_sk(sk); - /* Use RACK to detect loss */ - if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) { + if (tcp_rtx_queue_empty(sk)) + return; + + if (unlikely(tcp_is_reno(tp))) { + tcp_newreno_mark_lost(sk, *ack_flag & FLAG_SND_UNA_ADVANCED); + } else if (tcp_is_rack(sk)) { u32 prior_retrans = tp->retrans_out; tcp_rack_mark_lost(sk); @@ -2798,11 +2830,11 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, tcp_try_keep_open(sk); return; } - tcp_rack_identify_loss(sk, ack_flag); + tcp_identify_packet_loss(sk, ack_flag); break; case TCP_CA_Loss: tcp_process_loss(sk, flag, is_dupack, rexmit); - tcp_rack_identify_loss(sk, ack_flag); + tcp_identify_packet_loss(sk, ack_flag); if (!(icsk->icsk_ca_state == TCP_CA_Open || (*ack_flag & FLAG_LOST_RETRANS))) return; @@ -2819,7 +2851,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); - tcp_rack_identify_loss(sk, ack_flag); + tcp_identify_packet_loss(sk, ack_flag); if (!tcp_time_to_recover(sk, flag)) { tcp_try_to_open(sk, flag); return; @@ -2841,7 +2873,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, fast_rexmit = 1; } - if (do_lost) + if (!tcp_is_rack(sk) && do_lost) tcp_update_scoreboard(sk, fast_rexmit); *rexmit = REXMIT_LOST; } @@ -3496,6 +3528,22 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit) tcp_xmit_retransmit_queue(sk); } +/* Returns the number of packets newly acked or sacked by the current ACK */ +static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag) +{ + const struct net *net = sock_net(sk); + struct tcp_sock *tp = tcp_sk(sk); + u32 delivered; + + delivered = tp->delivered - prior_delivered; + NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered); + if (flag & FLAG_ECE) { + tp->delivered_ce += delivered; + NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered); + } + return delivered; +} + /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { @@ -3542,6 +3590,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; icsk->icsk_retransmits = 0; + +#if IS_ENABLED(CONFIG_TLS_DEVICE) + if (static_branch_unlikely(&clean_acked_data_enabled)) + if (icsk->icsk_clean_acked) + icsk->icsk_clean_acked(sk, ack); +#endif } prior_fack = tcp_is_sack(tp) ? tcp_highest_sack_seq(tp) : tp->snd_una; @@ -3619,7 +3673,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) sk_dst_confirm(sk); - delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */ + delivered = tcp_newly_delivered(sk, delivered, flag); lost = tp->lost - lost; /* freshly marked lost */ rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED); tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate); @@ -3629,9 +3683,11 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) no_queue: /* If data was DSACKed, see if we can undo a cwnd reduction. */ - if (flag & FLAG_DSACKING_ACK) + if (flag & FLAG_DSACKING_ACK) { tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag, &rexmit); + tcp_newly_delivered(sk, delivered, flag); + } /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. @@ -3655,6 +3711,7 @@ old_ack: &sack_state); tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag, &rexmit); + tcp_newly_delivered(sk, delivered, flag); tcp_xmit_recovery(sk, rexmit); } @@ -4126,7 +4183,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); - tcp_enter_quickack_mode(sk); + tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; @@ -4196,6 +4253,8 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq) * If the sack array is full, forget about the last one. */ if (this_sack >= TCP_NUM_SACKS) { + if (tp->compressed_ack) + tcp_send_ack(sk); this_sack--; tp->rx_opt.num_sacks--; sp--; @@ -4377,7 +4436,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) u32 seq, end_seq; bool fragstolen; - tcp_ecn_check_ce(tp, skb); + tcp_ecn_check_ce(sk, skb); if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); @@ -4573,6 +4632,17 @@ err: } +void tcp_data_ready(struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + int avail = tp->rcv_nxt - tp->copied_seq; + + if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE)) + return; + + sk->sk_data_ready(sk); +} + static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -4630,7 +4700,7 @@ queue_and_out: if (eaten > 0) kfree_skb_partial(skb, fragstolen); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + tcp_data_ready(sk); return; } @@ -4640,7 +4710,7 @@ queue_and_out: tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); out_of_window: - tcp_enter_quickack_mode(sk); + tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); inet_csk_schedule_ack(sk); drop: tcp_drop(sk, skb); @@ -4651,8 +4721,6 @@ drop: if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp))) goto out_of_window; - tcp_enter_quickack_mode(sk); - if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { /* Partial packet, seq < rcv_next < end_seq */ SOCK_DEBUG(sk, "partial packet: rcv_next %X seq %X - %X\n", @@ -5019,23 +5087,48 @@ static inline void tcp_data_snd_check(struct sock *sk) static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) { struct tcp_sock *tp = tcp_sk(sk); + unsigned long rtt, delay; /* More than one full frame received... */ if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss && /* ... and right edge of window advances far enough. - * (tcp_recvmsg() will send ACK otherwise). Or... + * (tcp_recvmsg() will send ACK otherwise). + * If application uses SO_RCVLOWAT, we want send ack now if + * we have not received enough bytes to satisfy the condition. */ - __tcp_select_window(sk) >= tp->rcv_wnd) || + (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat || + __tcp_select_window(sk) >= tp->rcv_wnd)) || /* We ACK each frame or... */ - tcp_in_quickack_mode(sk) || - /* We have out of order data. */ - (ofo_possible && !RB_EMPTY_ROOT(&tp->out_of_order_queue))) { - /* Then ack it now */ + tcp_in_quickack_mode(sk)) { +send_now: tcp_send_ack(sk); - } else { - /* Else, send delayed ack. */ + return; + } + + if (!ofo_possible || RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tcp_send_delayed_ack(sk); + return; } + + if (!tcp_is_sack(tp) || + tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr) + goto send_now; + tp->compressed_ack++; + + if (hrtimer_is_queued(&tp->compressed_ack_timer)) + return; + + /* compress ack timer : 5 % of rtt, but no more than tcp_comp_sack_delay_ns */ + + rtt = tp->rcv_rtt_est.rtt_us; + if (tp->srtt_us && tp->srtt_us < rtt) + rtt = tp->srtt_us; + + delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns, + rtt * (NSEC_PER_USEC >> 3)/20); + sock_hold(sk); + hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay), + HRTIMER_MODE_REL_PINNED_SOFT); } static inline void tcp_ack_snd_check(struct sock *sk) @@ -5299,11 +5392,11 @@ discard: * the rest is checked inline. Fast processing is turned on in * tcp_data_queue when everything is OK. */ -void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th) +void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) { - unsigned int len = skb->len; + const struct tcphdr *th = (const struct tcphdr *)skb->data; struct tcp_sock *tp = tcp_sk(sk); + unsigned int len = skb->len; /* TCP congestion window tracking */ trace_tcp_probe(sk, skb); @@ -5428,7 +5521,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, no_ack: if (eaten) kfree_skb_partial(skb, fragstolen); - sk->sk_data_ready(sk); + tcp_data_ready(sk); return; } } @@ -5550,9 +5643,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, return true; } tp->syn_data_acked = tp->syn_data; - if (tp->syn_data_acked) - NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPFASTOPENACTIVE); + if (tp->syn_data_acked) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); + /* SYN-data is counted as two separate packets in tcp_ack() */ + if (tp->delivered > 1) + --tp->delivered; + } tcp_fastopen_add_skb(sk, synack); @@ -5698,7 +5794,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * to stand against the temptation 8) --ANK */ inet_csk_schedule_ack(sk); - tcp_enter_quickack_mode(sk); + tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, TCP_DELACK_MAX, TCP_RTO_MAX); @@ -5884,6 +5980,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) } switch (sk->sk_state) { case TCP_SYN_RECV: + tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */ if (!tp->srtt_us) tcp_synack_rtt_meas(sk, req); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2c970626b3988..fed3f1c661670 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -110,8 +110,38 @@ static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) { + const struct inet_timewait_sock *tw = inet_twsk(sktw); const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); + int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse; + + if (reuse == 2) { + /* Still does not detect *everything* that goes through + * lo, since we require a loopback src or dst address + * or direct binding to 'lo' interface. + */ + bool loopback = false; + if (tw->tw_bound_dev_if == LOOPBACK_IFINDEX) + loopback = true; +#if IS_ENABLED(CONFIG_IPV6) + if (tw->tw_family == AF_INET6) { + if (ipv6_addr_loopback(&tw->tw_v6_daddr) || + (ipv6_addr_v4mapped(&tw->tw_v6_daddr) && + (tw->tw_v6_daddr.s6_addr[12] == 127)) || + ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) || + (ipv6_addr_v4mapped(&tw->tw_v6_rcv_saddr) && + (tw->tw_v6_rcv_saddr.s6_addr[12] == 127))) + loopback = true; + } else +#endif + { + if (ipv4_is_loopback(tw->tw_daddr) || + ipv4_is_loopback(tw->tw_rcv_saddr)) + loopback = true; + } + if (!loopback) + reuse = 0; + } /* With PAWS, it is safe from the viewpoint of data integrity. Even without PAWS it is safe provided sequence @@ -125,8 +155,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) and use initial timestamp retrieved from peer table. */ if (tcptw->tw_ts_recent_stamp && - (!twp || (sock_net(sk)->ipv4.sysctl_tcp_tw_reuse && - get_seconds() - tcptw->tw_ts_recent_stamp > 1))) { + (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) { tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; if (tp->write_seq == 0) tp->write_seq = 1; @@ -621,6 +650,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) struct sock *sk1 = NULL; #endif struct net *net; + struct sock *ctl_sk; /* Never send a reset in response to a reset. */ if (th->rst) @@ -723,11 +753,16 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); + if (sk) + ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_mark : sk->sk_mark; + ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); + ctl_sk->sk_mark = 0; __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); local_bh_enable(); @@ -759,6 +794,7 @@ static void tcp_v4_send_ack(const struct sock *sk, } rep; struct net *net = sock_net(sk); struct ip_reply_arg arg; + struct sock *ctl_sk; memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); @@ -809,11 +845,16 @@ static void tcp_v4_send_ack(const struct sock *sk, arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); + if (sk) + ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_mark : sk->sk_mark; + ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); + ctl_sk->sk_mark = 0; __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); } @@ -1474,7 +1515,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) sk->sk_rx_dst = NULL; } } - tcp_rcv_established(sk, skb, tcp_hdr(skb)); + tcp_rcv_established(sk, skb); return 0; } @@ -2481,7 +2522,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_orphan_retries = 0; net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; - net->ipv4.sysctl_tcp_tw_reuse = 0; + net->ipv4.sysctl_tcp_tw_reuse = 2; cnt = tcp_hashinfo.ehash_mask + 1; net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2; @@ -2524,6 +2565,8 @@ static int __net_init tcp_sk_init(struct net *net) init_net.ipv4.sysctl_tcp_wmem, sizeof(init_net.ipv4.sysctl_tcp_wmem)); } + net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC; + net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 57b5468b51398..1dda1341a2239 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -263,6 +263,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct inet_sock *inet = inet_sk(sk); tw->tw_transparent = inet->transparent; + tw->tw_mark = sk->sk_mark; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; @@ -306,7 +307,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (timeo < rto) timeo = rto; - tw->tw_timeout = TCP_TIMEWAIT_LEN; if (state == TCP_TIME_WAIT) timeo = TCP_TIMEWAIT_LEN; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d07e34f8e3091..8e08b409c71e1 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -162,6 +162,15 @@ static void tcp_event_data_sent(struct tcp_sock *tp, /* Account for an ACK we sent. */ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) { + struct tcp_sock *tp = tcp_sk(sk); + + if (unlikely(tp->compressed_ack)) { + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, + tp->compressed_ack); + tp->compressed_ack = 0; + if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) + __sock_put(sk); + } tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -229,11 +238,9 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, } } - if (mss > (1 << *rcv_wscale)) { - if (!init_rcv_wnd) /* Use default unless specified otherwise */ - init_rcv_wnd = tcp_default_init_rwnd(mss); - *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); - } + if (!init_rcv_wnd) /* Use default unless specified otherwise */ + init_rcv_wnd = tcp_default_init_rwnd(mss); + *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); /* Set the clamp no higher than max representable value */ (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); @@ -585,14 +592,15 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, unsigned int remaining = MAX_TCP_OPTION_SPACE; struct tcp_fastopen_request *fastopen = tp->fastopen_req; + *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - *md5 = tp->af_specific->md5_lookup(sk, sk); - if (*md5) { - opts->options |= OPTION_MD5; - remaining -= TCPOLEN_MD5SIG_ALIGNED; + if (unlikely(rcu_access_pointer(tp->md5sig_info))) { + *md5 = tp->af_specific->md5_lookup(sk, sk); + if (*md5) { + opts->options |= OPTION_MD5; + remaining -= TCPOLEN_MD5SIG_ALIGNED; + } } -#else - *md5 = NULL; #endif /* We always get an MSS option. The option bytes which will be seen in @@ -720,14 +728,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb opts->options = 0; + *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - *md5 = tp->af_specific->md5_lookup(sk, sk); - if (unlikely(*md5)) { - opts->options |= OPTION_MD5; - size += TCPOLEN_MD5SIG_ALIGNED; + if (unlikely(rcu_access_pointer(tp->md5sig_info))) { + *md5 = tp->af_specific->md5_lookup(sk, sk); + if (*md5) { + opts->options |= OPTION_MD5; + size += TCPOLEN_MD5SIG_ALIGNED; + } } -#else - *md5 = NULL; #endif if (likely(tp->rx_opt.tstamp_ok)) { @@ -772,7 +781,7 @@ struct tsq_tasklet { }; static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); -static void tcp_tsq_handler(struct sock *sk) +static void tcp_tsq_write(struct sock *sk) { if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | @@ -789,6 +798,16 @@ static void tcp_tsq_handler(struct sock *sk) 0, GFP_ATOMIC); } } + +static void tcp_tsq_handler(struct sock *sk) +{ + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) + tcp_tsq_write(sk); + else if (!test_and_set_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) + sock_hold(sk); + bh_unlock_sock(sk); +} /* * One tasklet per cpu tries to send more skbs. * We run in tasklet context but need to disable irqs when @@ -816,16 +835,7 @@ static void tcp_tasklet_func(unsigned long data) smp_mb__before_atomic(); clear_bit(TSQ_QUEUED, &sk->sk_tsq_flags); - if (!sk->sk_lock.owned && - test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) { - bh_lock_sock(sk); - if (!sock_owned_by_user(sk)) { - clear_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags); - tcp_tsq_handler(sk); - } - bh_unlock_sock(sk); - } - + tcp_tsq_handler(sk); sk_free(sk); } } @@ -853,9 +863,10 @@ void tcp_release_cb(struct sock *sk) nflags = flags & ~TCP_DEFERRED_ALL; } while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags); - if (flags & TCPF_TSQ_DEFERRED) - tcp_tsq_handler(sk); - + if (flags & TCPF_TSQ_DEFERRED) { + tcp_tsq_write(sk); + __sock_put(sk); + } /* Here begins the tricky part : * We are called from release_sock() with : * 1) BH disabled @@ -929,7 +940,7 @@ void tcp_wfree(struct sk_buff *skb) if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED)) goto out; - nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED; + nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED; nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); if (nval != oval) continue; @@ -948,37 +959,17 @@ out: sk_free(sk); } -/* Note: Called under hard irq. - * We can not call TCP stack right away. +/* Note: Called under soft irq. + * We can call TCP stack right away, unless socket is owned by user. */ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) { struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer); struct sock *sk = (struct sock *)tp; - unsigned long nval, oval; - for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { - struct tsq_tasklet *tsq; - bool empty; - - if (oval & TSQF_QUEUED) - break; - - nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED; - nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); - if (nval != oval) - continue; + tcp_tsq_handler(sk); + sock_put(sk); - if (!refcount_inc_not_zero(&sk->sk_wmem_alloc)) - break; - /* queue this socket to tasklet queue */ - tsq = this_cpu_ptr(&tsq_tasklet); - empty = list_empty(&tsq->head); - list_add(&tp->tsq_node, &tsq->head); - if (empty) - tasklet_schedule(&tsq->tasklet); - break; - } return HRTIMER_NORESTART; } @@ -1011,7 +1002,8 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) do_div(len_ns, rate); hrtimer_start(&tcp_sk(sk)->pacing_timer, ktime_add_ns(ktime_get(), len_ns), - HRTIMER_MODE_ABS_PINNED); + HRTIMER_MODE_ABS_PINNED_SOFT); + sock_hold(sk); } static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) @@ -1078,7 +1070,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, /* if no packet is in qdisc/device queue, then allow XPS to select * another queue. We can be called from tcp_tsq_handler() - * which holds one reference to sk_wmem_alloc. + * which holds one reference to sk. * * TODO: Ideally, in-flight pure ACK packets should not matter here. * One way to get this would be to set skb->truesize = 2 on them. @@ -2185,7 +2177,7 @@ static int tcp_mtu_probe(struct sock *sk) static bool tcp_pacing_check(const struct sock *sk) { return tcp_needs_internal_pacing(sk) && - hrtimer_active(&tcp_sk(sk)->pacing_timer); + hrtimer_is_queued(&tcp_sk(sk)->pacing_timer); } /* TCP Small Queues : @@ -2365,8 +2357,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, skb, limit, mss_now, gfp))) break; - if (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) - clear_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags); if (tcp_small_queue_check(sk, skb, 0)) break; diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 3a81720ac0c40..71593e4400abe 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -2,7 +2,7 @@ #include <linux/tcp.h> #include <net/tcp.h> -static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb) +void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -21,6 +21,38 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) return t1 > t2 || (t1 == t2 && after(seq1, seq2)); } +static u32 tcp_rack_reo_wnd(const struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!tp->rack.reord) { + /* If reordering has not been observed, be aggressive during + * the recovery or starting the recovery by DUPACK threshold. + */ + if (inet_csk(sk)->icsk_ca_state >= TCP_CA_Recovery) + return 0; + + if (tp->sacked_out >= tp->reordering && + !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH)) + return 0; + } + + /* To be more reordering resilient, allow min_rtt/4 settling delay. + * Use min_rtt instead of the smoothed RTT because reordering is + * often a path property and less related to queuing or delayed ACKs. + * Upon receiving DSACKs, linearly increase the window up to the + * smoothed RTT. + */ + return min((tcp_min_rtt(tp) >> 2) * tp->rack.reo_wnd_steps, + tp->srtt_us >> 3); +} + +s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd) +{ + return tp->rack.rtt_us + reo_wnd - + tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp); +} + /* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01): * * Marks a packet lost, if some packet sent later has been (s)acked. @@ -44,23 +76,11 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) { struct tcp_sock *tp = tcp_sk(sk); - u32 min_rtt = tcp_min_rtt(tp); struct sk_buff *skb, *n; u32 reo_wnd; *reo_timeout = 0; - /* To be more reordering resilient, allow min_rtt/4 settling delay - * (lower-bounded to 1000uS). We use min_rtt instead of the smoothed - * RTT because reordering is often a path property and less related - * to queuing or delayed ACKs. - */ - reo_wnd = 1000; - if ((tp->rack.reord || inet_csk(sk)->icsk_ca_state < TCP_CA_Recovery) && - min_rtt != ~0U) { - reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd); - reo_wnd = min(reo_wnd, tp->srtt_us >> 3); - } - + reo_wnd = tcp_rack_reo_wnd(sk); list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue, tcp_tsorted_anchor) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); @@ -78,10 +98,9 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) /* A packet is lost if it has not been s/acked beyond * the recent RTT plus the reordering window. */ - remaining = tp->rack.rtt_us + reo_wnd - - tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp); + remaining = tcp_rack_skb_timeout(tp, skb, reo_wnd); if (remaining <= 0) { - tcp_rack_mark_skb_lost(sk, skb); + tcp_mark_skb_lost(sk, skb); list_del_init(&skb->tcp_tsorted_anchor); } else { /* Record maximum wait time */ @@ -202,3 +221,30 @@ void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs) tp->rack.reo_wnd_steps = 1; } } + +/* RFC6582 NewReno recovery for non-SACK connection. It simply retransmits + * the next unacked packet upon receiving + * a) three or more DUPACKs to start the fast recovery + * b) an ACK acknowledging new data during the fast recovery. + */ +void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced) +{ + const u8 state = inet_csk(sk)->icsk_ca_state; + struct tcp_sock *tp = tcp_sk(sk); + + if ((state < TCP_CA_Recovery && tp->sacked_out >= tp->reordering) || + (state == TCP_CA_Recovery && snd_una_advanced)) { + struct sk_buff *skb = tcp_rtx_queue_head(sk); + u32 mss; + + if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) + return; + + mss = tcp_skb_mss(skb); + if (tcp_skb_pcount(skb) > 1 && skb->len > mss) + tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, + mss, mss, GFP_ATOMIC); + + tcp_skb_mark_lost_uncond_verify(tp, skb); + } +} diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index f7d944855f8eb..3b3611729928f 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -708,11 +708,36 @@ out: sock_put(sk); } +static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer) +{ + struct tcp_sock *tp = container_of(timer, struct tcp_sock, compressed_ack_timer); + struct sock *sk = (struct sock *)tp; + + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) { + if (tp->compressed_ack) + tcp_send_ack(sk); + } else { + if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, + &sk->sk_tsq_flags)) + sock_hold(sk); + } + bh_unlock_sock(sk); + + sock_put(sk); + + return HRTIMER_NORESTART; +} + void tcp_init_xmit_timers(struct sock *sk) { inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS_PINNED); + HRTIMER_MODE_ABS_PINNED_SOFT); tcp_sk(sk)->pacing_timer.function = tcp_pace_kick; + + hrtimer_init(&tcp_sk(sk)->compressed_ack_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED_SOFT); + tcp_sk(sk)->compressed_ack_timer.function = tcp_compressed_ack_kick; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 675433eb53a81..3365362cac881 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -544,9 +544,7 @@ EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb); /* Must be called under rcu_read_lock(). * Does increment socket refcount. */ -#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \ - IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY) || \ - IS_ENABLED(CONFIG_NF_SOCKET_IPV4) +#if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4) struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { @@ -757,7 +755,8 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, } EXPORT_SYMBOL(udp_set_csum); -static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) +static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, + struct inet_cork *cork) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); @@ -777,6 +776,27 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) uh->len = htons(len); uh->check = 0; + if (cork->gso_size) { + const int hlen = skb_network_header_len(skb) + + sizeof(struct udphdr); + + if (hlen + cork->gso_size > cork->fragsize) + return -EINVAL; + if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) + return -EINVAL; + if (sk->sk_no_check_tx) + return -EINVAL; + if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || + dst_xfrm(skb_dst(skb))) + return -EIO; + + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(uh), + cork->gso_size); + goto csum_partial; + } + if (is_udplite) /* UDP-Lite */ csum = udplite_csum(skb); @@ -786,6 +806,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ +csum_partial: udp4_hwcsum(skb, fl4->saddr, fl4->daddr); goto send; @@ -828,7 +849,7 @@ int udp_push_pending_frames(struct sock *sk) if (!skb) goto out; - err = udp_send_skb(skb, fl4); + err = udp_send_skb(skb, fl4, &inet->cork.base); out: up->len = 0; @@ -837,10 +858,48 @@ out: } EXPORT_SYMBOL(udp_push_pending_frames); +static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size) +{ + switch (cmsg->cmsg_type) { + case UDP_SEGMENT: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u16))) + return -EINVAL; + *gso_size = *(__u16 *)CMSG_DATA(cmsg); + return 0; + default: + return -EINVAL; + } +} + +int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size) +{ + struct cmsghdr *cmsg; + bool need_ip = false; + int err; + + for_each_cmsghdr(cmsg, msg) { + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + + if (cmsg->cmsg_level != SOL_UDP) { + need_ip = true; + continue; + } + + err = __udp_cmsg_send(cmsg, gso_size); + if (err) + return err; + } + + return need_ip; +} +EXPORT_SYMBOL_GPL(udp_cmsg_send); + int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); + DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); struct flowi4 fl4_stack; struct flowi4 *fl4; int ulen = len; @@ -895,8 +954,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* * Get and verify the address. */ - if (msg->msg_name) { - DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); + if (usin) { if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { @@ -922,10 +980,14 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.sockc.tsflags = sk->sk_tsflags; ipc.addr = inet->inet_saddr; ipc.oif = sk->sk_bound_dev_if; + ipc.gso_size = up->gso_size; if (msg->msg_controllen) { - err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); - if (unlikely(err)) { + err = udp_cmsg_send(sk, msg, &ipc.gso_size); + if (err > 0) + err = ip_cmsg_send(sk, msg, &ipc, + sk->sk_family == AF_INET6); + if (unlikely(err < 0)) { kfree(ipc.opt); return err; } @@ -946,6 +1008,22 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rcu_read_unlock(); } + if (cgroup_bpf_enabled && !connected) { + err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, + (struct sockaddr *)usin, &ipc.addr); + if (err) + goto out_free; + if (usin) { + if (usin->sin_port == 0) { + /* BPF program set invalid port. Reject it. */ + err = -EINVAL; + goto out_free; + } + daddr = usin->sin_addr.s_addr; + dport = usin->sin_port; + } + } + saddr = ipc.addr; ipc.addr = faddr = daddr; @@ -1032,12 +1110,14 @@ back_from_confirm: /* Lockless fast path for the non-corking case. */ if (!corkreq) { + struct inet_cork cork; + skb = ip_make_skb(sk, fl4, getfrag, msg, ulen, sizeof(struct udphdr), &ipc, &rt, - msg->msg_flags); + &cork, msg->msg_flags); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) - err = udp_send_skb(skb, fl4); + err = udp_send_skb(skb, fl4, &cork); goto out; } @@ -1813,10 +1893,10 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) return 0; } -static struct static_key udp_encap_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); void udp_encap_enable(void) { - static_key_enable(&udp_encap_needed); + static_branch_enable(&udp_encap_needed_key); } EXPORT_SYMBOL(udp_encap_enable); @@ -1840,7 +1920,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto drop; nf_reset(skb); - if (static_key_false(&udp_encap_needed) && up->encap_type) { + if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -2303,7 +2383,7 @@ void udp_destroy_sock(struct sock *sk) bool slow = lock_sock_fast(sk); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); - if (static_key_false(&udp_encap_needed) && up->encap_type) { + if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { void (*encap_destroy)(struct sock *sk); encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) @@ -2368,6 +2448,12 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, up->no_check6_rx = valbool; break; + case UDP_SEGMENT: + if (val < 0 || val > USHRT_MAX) + return -EINVAL; + up->gso_size = val; + break; + /* * UDP-Lite's partial checksum coverage (RFC 3828). */ @@ -2458,6 +2544,10 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, val = up->no_check6_rx; break; + case UDP_SEGMENT: + val = up->gso_size; + break; + /* The following two cannot be changed on UDP sockets, the return is * always 0 (which corresponds to the full checksum coverage of UDP). */ case UDPLITE_SEND_CSCOV: diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index ea6e6e7df0eec..92dc9e5a7ff3d 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -187,6 +187,102 @@ out_unlock: } EXPORT_SYMBOL(skb_udp_tunnel_segment); +struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, + netdev_features_t features) +{ + struct sock *sk = gso_skb->sk; + unsigned int sum_truesize = 0; + struct sk_buff *segs, *seg; + struct udphdr *uh; + unsigned int mss; + bool copy_dtor; + __sum16 check; + __be16 newlen; + + mss = skb_shinfo(gso_skb)->gso_size; + if (gso_skb->len <= sizeof(*uh) + mss) + return ERR_PTR(-EINVAL); + + skb_pull(gso_skb, sizeof(*uh)); + + /* clear destructor to avoid skb_segment assigning it to tail */ + copy_dtor = gso_skb->destructor == sock_wfree; + if (copy_dtor) + gso_skb->destructor = NULL; + + segs = skb_segment(gso_skb, features); + if (unlikely(IS_ERR_OR_NULL(segs))) { + if (copy_dtor) + gso_skb->destructor = sock_wfree; + return segs; + } + + /* GSO partial and frag_list segmentation only requires splitting + * the frame into an MSS multiple and possibly a remainder, both + * cases return a GSO skb. So update the mss now. + */ + if (skb_is_gso(segs)) + mss *= skb_shinfo(segs)->gso_segs; + + seg = segs; + uh = udp_hdr(seg); + + /* compute checksum adjustment based on old length versus new */ + newlen = htons(sizeof(*uh) + mss); + check = csum16_add(csum16_sub(uh->check, uh->len), newlen); + + for (;;) { + if (copy_dtor) { + seg->destructor = sock_wfree; + seg->sk = sk; + sum_truesize += seg->truesize; + } + + if (!seg->next) + break; + + uh->len = newlen; + uh->check = check; + + if (seg->ip_summed == CHECKSUM_PARTIAL) + gso_reset_checksum(seg, ~check); + else + uh->check = gso_make_checksum(seg, ~check) ? : + CSUM_MANGLED_0; + + seg = seg->next; + uh = udp_hdr(seg); + } + + /* last packet can be partial gso_size, account for that in checksum */ + newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) + + seg->data_len); + check = csum16_add(csum16_sub(uh->check, uh->len), newlen); + + uh->len = newlen; + uh->check = check; + + if (seg->ip_summed == CHECKSUM_PARTIAL) + gso_reset_checksum(seg, ~check); + else + uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; + + /* update refcount for the packet */ + if (copy_dtor) { + int delta = sum_truesize - gso_skb->truesize; + + /* In some pathological cases, delta can be negative. + * We need to either use refcount_add() or refcount_sub_and_test() + */ + if (likely(delta >= 0)) + refcount_add(delta, &sk->sk_wmem_alloc); + else + WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); + } + return segs; +} +EXPORT_SYMBOL_GPL(__udp_gso_segment); + static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { @@ -203,12 +299,15 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, goto out; } - if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP)) + if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + return __udp_gso_segment(skb, features); + mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 11e4e80cf7e98..0eff75525da10 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -329,4 +329,9 @@ config IPV6_SEG6_HMAC If unsure, say N. +config IPV6_SEG6_BPF + def_bool y + depends on IPV6_SEG6_LWTUNNEL + depends on IPV6 = y + endif # IPV6 diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1b5ea3379d9bc..89019bf59f465 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -170,7 +170,7 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event); static int addrconf_ifdown(struct net_device *dev, int how); -static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, +static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, int plen, const struct net_device *dev, u32 flags, u32 noflags); @@ -916,7 +916,6 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) pr_warn("Freeing alive inet6 address %p\n", ifp); return; } - ip6_rt_put(ifp->rt); kfree_rcu(ifp, rcu); } @@ -987,17 +986,15 @@ static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) /* On success it returns ifp with increased reference count */ static struct inet6_ifaddr * -ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, - const struct in6_addr *peer_addr, int pfxlen, - int scope, u32 flags, u32 valid_lft, u32 prefered_lft, +ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, bool can_block, struct netlink_ext_ack *extack) { gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC; + int addr_type = ipv6_addr_type(cfg->pfx); struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; - struct rt6_info *rt = NULL; + struct fib6_info *f6i = NULL; int err = 0; - int addr_type = ipv6_addr_type(addr); if (addr_type == IPV6_ADDR_ANY || addr_type & IPV6_ADDR_MULTICAST || @@ -1020,7 +1017,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, */ if (can_block) { struct in6_validator_info i6vi = { - .i6vi_addr = *addr, + .i6vi_addr = *cfg->pfx, .i6vi_dev = idev, .extack = extack, }; @@ -1037,38 +1034,39 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, goto out; } - rt = addrconf_dst_alloc(idev, addr, false); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - rt = NULL; + f6i = addrconf_f6i_alloc(net, idev, cfg->pfx, false, gfp_flags); + if (IS_ERR(f6i)) { + err = PTR_ERR(f6i); + f6i = NULL; goto out; } if (net->ipv6.devconf_all->disable_policy || idev->cnf.disable_policy) - rt->dst.flags |= DST_NOPOLICY; + f6i->dst_nopolicy = true; neigh_parms_data_state_setall(idev->nd_parms); - ifa->addr = *addr; - if (peer_addr) - ifa->peer_addr = *peer_addr; + ifa->addr = *cfg->pfx; + if (cfg->peer_pfx) + ifa->peer_addr = *cfg->peer_pfx; spin_lock_init(&ifa->lock); INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work); INIT_HLIST_NODE(&ifa->addr_lst); - ifa->scope = scope; - ifa->prefix_len = pfxlen; - ifa->flags = flags; + ifa->scope = cfg->scope; + ifa->prefix_len = cfg->plen; + ifa->rt_priority = cfg->rt_priority; + ifa->flags = cfg->ifa_flags; /* No need to add the TENTATIVE flag for addresses with NODAD */ - if (!(flags & IFA_F_NODAD)) + if (!(cfg->ifa_flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; - ifa->valid_lft = valid_lft; - ifa->prefered_lft = prefered_lft; + ifa->valid_lft = cfg->valid_lft; + ifa->prefered_lft = cfg->preferred_lft; ifa->cstamp = ifa->tstamp = jiffies; ifa->tokenized = false; - ifa->rt = rt; + ifa->rt = f6i; ifa->idev = idev; in6_dev_hold(idev); @@ -1102,8 +1100,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, inet6addr_notifier_call_chain(NETDEV_UP, ifa); out: if (unlikely(err < 0)) { - if (rt) - ip6_rt_put(rt); + fib6_info_release(f6i); + if (ifa) { if (ifa->idev) in6_dev_put(ifa->idev); @@ -1179,19 +1177,19 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) static void cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt) { - struct rt6_info *rt; + struct fib6_info *f6i; - rt = addrconf_get_prefix_route(&ifp->addr, + f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev, 0, RTF_GATEWAY | RTF_DEFAULT); - if (rt) { + if (f6i) { if (del_rt) - ip6_del_rt(rt); + ip6_del_rt(dev_net(ifp->idev->dev), f6i); else { - if (!(rt->rt6i_flags & RTF_EXPIRES)) - rt6_set_expires(rt, expires); - ip6_rt_put(rt); + if (!(f6i->fib6_flags & RTF_EXPIRES)) + fib6_set_expires(f6i, expires); + fib6_info_release(f6i); } } } @@ -1261,11 +1259,10 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, { struct inet6_dev *idev = ifp->idev; struct in6_addr addr, *tmpaddr; - unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_tstamp, age; + unsigned long tmp_tstamp, age; unsigned long regen_advance; - int tmp_plen; + struct ifa6_config cfg; int ret = 0; - u32 addr_flags; unsigned long now = jiffies; long max_desync_factor; s32 cnf_temp_preferred_lft; @@ -1327,13 +1324,12 @@ retry: } } - tmp_valid_lft = min_t(__u32, - ifp->valid_lft, + cfg.valid_lft = min_t(__u32, ifp->valid_lft, idev->cnf.temp_valid_lft + age); - tmp_prefered_lft = cnf_temp_preferred_lft + age - - idev->desync_factor; - tmp_prefered_lft = min_t(__u32, ifp->prefered_lft, tmp_prefered_lft); - tmp_plen = ifp->prefix_len; + cfg.preferred_lft = cnf_temp_preferred_lft + age - idev->desync_factor; + cfg.preferred_lft = min_t(__u32, ifp->prefered_lft, cfg.preferred_lft); + + cfg.plen = ifp->prefix_len; tmp_tstamp = ifp->tstamp; spin_unlock_bh(&ifp->lock); @@ -1347,21 +1343,23 @@ retry: * temporary addresses being generated. */ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; - if (tmp_prefered_lft <= regen_advance + age) { + if (cfg.preferred_lft <= regen_advance + age) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; goto out; } - addr_flags = IFA_F_TEMPORARY; + cfg.ifa_flags = IFA_F_TEMPORARY; /* set in addrconf_prefix_rcv() */ if (ifp->flags & IFA_F_OPTIMISTIC) - addr_flags |= IFA_F_OPTIMISTIC; + cfg.ifa_flags |= IFA_F_OPTIMISTIC; - ift = ipv6_add_addr(idev, &addr, NULL, tmp_plen, - ipv6_addr_scope(&addr), addr_flags, - tmp_valid_lft, tmp_prefered_lft, block, NULL); + cfg.pfx = &addr; + cfg.scope = ipv6_addr_scope(cfg.pfx); + cfg.rt_priority = 0; + + ift = ipv6_add_addr(idev, &cfg, block, NULL); if (IS_ERR(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); @@ -2032,13 +2030,17 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) spin_lock_bh(&ifp->lock); if (ifp->flags & IFA_F_STABLE_PRIVACY) { - int scope = ifp->scope; - u32 flags = ifp->flags; struct in6_addr new_addr; struct inet6_ifaddr *ifp2; - u32 valid_lft, preferred_lft; - int pfxlen = ifp->prefix_len; int retries = ifp->stable_privacy_retry + 1; + struct ifa6_config cfg = { + .pfx = &new_addr, + .plen = ifp->prefix_len, + .ifa_flags = ifp->flags, + .valid_lft = ifp->valid_lft, + .preferred_lft = ifp->prefered_lft, + .scope = ifp->scope, + }; if (retries > net->ipv6.sysctl.idgen_retries) { net_info_ratelimited("%s: privacy stable address generation failed because of DAD conflicts!\n", @@ -2051,9 +2053,6 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) idev)) goto errdad; - valid_lft = ifp->valid_lft; - preferred_lft = ifp->prefered_lft; - spin_unlock_bh(&ifp->lock); if (idev->cnf.max_addresses && @@ -2064,9 +2063,7 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) net_info_ratelimited("%s: generating new stable privacy address because of DAD conflict\n", ifp->idev->dev->name); - ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen, - scope, flags, valid_lft, - preferred_lft, false, NULL); + ifp2 = ipv6_add_addr(idev, &cfg, false, NULL); if (IS_ERR(ifp2)) goto lock_errdad; @@ -2254,6 +2251,7 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) return addrconf_ifid_ieee1394(eui, dev); case ARPHRD_TUNNEL6: case ARPHRD_IP6GRE: + case ARPHRD_RAWIP: return addrconf_ifid_ip6tnl(eui, dev); } return -1; @@ -2319,18 +2317,20 @@ static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpad */ static void -addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, - unsigned long expires, u32 flags) +addrconf_prefix_route(struct in6_addr *pfx, int plen, u32 metric, + struct net_device *dev, unsigned long expires, + u32 flags, gfp_t gfp_flags) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX, - .fc_metric = IP6_RT_PRIO_ADDRCONF, + .fc_metric = metric ? : IP6_RT_PRIO_ADDRCONF, .fc_ifindex = dev->ifindex, .fc_expires = expires, .fc_dst_len = plen, .fc_flags = RTF_UP | flags, .fc_nlinfo.nl_net = dev_net(dev), .fc_protocol = RTPROT_KERNEL, + .fc_type = RTN_UNICAST, }; cfg.fc_dst = *pfx; @@ -2344,17 +2344,17 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, cfg.fc_flags |= RTF_NONEXTHOP; #endif - ip6_route_add(&cfg, NULL); + ip6_route_add(&cfg, gfp_flags, NULL); } -static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, +static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, int plen, const struct net_device *dev, u32 flags, u32 noflags) { struct fib6_node *fn; - struct rt6_info *rt = NULL; + struct fib6_info *rt = NULL; struct fib6_table *table; u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX; @@ -2368,14 +2368,13 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, goto out; for_each_fib6_node_rt_rcu(fn) { - if (rt->dst.dev->ifindex != dev->ifindex) + if (rt->fib6_nh.nh_dev->ifindex != dev->ifindex) continue; - if ((rt->rt6i_flags & flags) != flags) + if ((rt->fib6_flags & flags) != flags) continue; - if ((rt->rt6i_flags & noflags) != 0) + if ((rt->fib6_flags & noflags) != 0) continue; - if (!dst_hold_safe(&rt->dst)) - rt = NULL; + fib6_info_hold(rt); break; } out: @@ -2394,12 +2393,13 @@ static void addrconf_add_mroute(struct net_device *dev) .fc_ifindex = dev->ifindex, .fc_dst_len = 8, .fc_flags = RTF_UP, + .fc_type = RTN_UNICAST, .fc_nlinfo.nl_net = dev_net(dev), }; ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); - ip6_route_add(&cfg, NULL); + ip6_route_add(&cfg, GFP_ATOMIC, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) @@ -2507,12 +2507,20 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, if (!ifp && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; + struct ifa6_config cfg = { + .pfx = addr, + .plen = pinfo->prefix_len, + .ifa_flags = addr_flags, + .valid_lft = valid_lft, + .preferred_lft = prefered_lft, + .scope = addr_type & IPV6_ADDR_SCOPE_MASK, + }; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if ((net->ipv6.devconf_all->optimistic_dad || in6_dev->cnf.optimistic_dad) && !net->ipv6.devconf_all->forwarding && sllao) - addr_flags |= IFA_F_OPTIMISTIC; + cfg.ifa_flags |= IFA_F_OPTIMISTIC; #endif /* Do not allow to create too much of autoconfigured @@ -2520,16 +2528,11 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, */ if (!max_addresses || ipv6_count_addresses(in6_dev) < max_addresses) - ifp = ipv6_add_addr(in6_dev, addr, NULL, - pinfo->prefix_len, - addr_type&IPV6_ADDR_SCOPE_MASK, - addr_flags, valid_lft, - prefered_lft, false, NULL); + ifp = ipv6_add_addr(in6_dev, &cfg, false, NULL); if (IS_ERR_OR_NULL(ifp)) return -1; - update_lft = 0; create = 1; spin_lock_bh(&ifp->lock); ifp->flags |= IFA_F_MANAGETEMPADDR; @@ -2551,7 +2554,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; else stored_lft = 0; - if (!update_lft && !create && stored_lft) { + if (!create && stored_lft) { const u32 minimum_lft = min_t(u32, stored_lft, MIN_VALID_LIFETIME); valid_lft = max(valid_lft, minimum_lft); @@ -2642,7 +2645,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) */ if (pinfo->onlink) { - struct rt6_info *rt; + struct fib6_info *rt; unsigned long rt_expires; /* Avoid arithmetic overflow. Really, we could @@ -2667,13 +2670,13 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) if (rt) { /* Autoconf prefix route */ if (valid_lft == 0) { - ip6_del_rt(rt); + ip6_del_rt(net, rt); rt = NULL; } else if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ - rt6_set_expires(rt, jiffies + rt_expires); + fib6_set_expires(rt, jiffies + rt_expires); } else { - rt6_clean_expires(rt); + fib6_clean_expires(rt); } } else if (valid_lft) { clock_t expires = 0; @@ -2684,9 +2687,10 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) expires = jiffies_to_clock_t(rt_expires); } addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len, - dev, expires, flags); + 0, dev, expires, flags, + GFP_ATOMIC); } - ip6_rt_put(rt); + fib6_info_release(rt); } /* Try to figure out our local address for this prefix */ @@ -2831,10 +2835,7 @@ static int ipv6_mc_config(struct sock *sk, bool join, * Manual configuration of address on an interface */ static int inet6_addr_add(struct net *net, int ifindex, - const struct in6_addr *pfx, - const struct in6_addr *peer_pfx, - unsigned int plen, __u32 ifa_flags, - __u32 prefered_lft, __u32 valid_lft, + struct ifa6_config *cfg, struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; @@ -2842,19 +2843,18 @@ static int inet6_addr_add(struct net *net, int ifindex, struct net_device *dev; unsigned long timeout; clock_t expires; - int scope; u32 flags; ASSERT_RTNL(); - if (plen > 128) + if (cfg->plen > 128) return -EINVAL; /* check the lifetime */ - if (!valid_lft || prefered_lft > valid_lft) + if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft) return -EINVAL; - if (ifa_flags & IFA_F_MANAGETEMPADDR && plen != 64) + if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64) return -EINVAL; dev = __dev_get_by_index(net, ifindex); @@ -2865,58 +2865,62 @@ static int inet6_addr_add(struct net *net, int ifindex, if (IS_ERR(idev)) return PTR_ERR(idev); - if (ifa_flags & IFA_F_MCAUTOJOIN) { + if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk, - true, pfx, ifindex); + true, cfg->pfx, ifindex); if (ret < 0) return ret; } - scope = ipv6_addr_scope(pfx); + cfg->scope = ipv6_addr_scope(cfg->pfx); - timeout = addrconf_timeout_fixup(valid_lft, HZ); + timeout = addrconf_timeout_fixup(cfg->valid_lft, HZ); if (addrconf_finite_timeout(timeout)) { expires = jiffies_to_clock_t(timeout * HZ); - valid_lft = timeout; + cfg->valid_lft = timeout; flags = RTF_EXPIRES; } else { expires = 0; flags = 0; - ifa_flags |= IFA_F_PERMANENT; + cfg->ifa_flags |= IFA_F_PERMANENT; } - timeout = addrconf_timeout_fixup(prefered_lft, HZ); + timeout = addrconf_timeout_fixup(cfg->preferred_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) - ifa_flags |= IFA_F_DEPRECATED; - prefered_lft = timeout; + cfg->ifa_flags |= IFA_F_DEPRECATED; + cfg->preferred_lft = timeout; } - ifp = ipv6_add_addr(idev, pfx, peer_pfx, plen, scope, ifa_flags, - valid_lft, prefered_lft, true, extack); - + ifp = ipv6_add_addr(idev, cfg, true, extack); if (!IS_ERR(ifp)) { - if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev, - expires, flags); + if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + ifp->rt_priority, dev, expires, + flags, GFP_KERNEL); } + /* Send a netlink notification if DAD is enabled and + * optimistic flag is not set + */ + if (!(ifp->flags & (IFA_F_OPTIMISTIC | IFA_F_NODAD))) + ipv6_ifa_notify(0, ifp); /* * Note that section 3.1 of RFC 4429 indicates * that the Optimistic flag should not be set for * manually configured addresses */ addrconf_dad_start(ifp); - if (ifa_flags & IFA_F_MANAGETEMPADDR) - manage_tempaddrs(idev, ifp, valid_lft, prefered_lft, - true, jiffies); + if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR) + manage_tempaddrs(idev, ifp, cfg->valid_lft, + cfg->preferred_lft, true, jiffies); in6_ifa_put(ifp); addrconf_verify_rtnl(); return 0; - } else if (ifa_flags & IFA_F_MCAUTOJOIN) { - ipv6_mc_config(net->ipv6.mc_autojoin_sk, - false, pfx, ifindex); + } else if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { + ipv6_mc_config(net->ipv6.mc_autojoin_sk, false, + cfg->pfx, ifindex); } return PTR_ERR(ifp); @@ -2967,6 +2971,11 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, int addrconf_add_ifaddr(struct net *net, void __user *arg) { + struct ifa6_config cfg = { + .ifa_flags = IFA_F_PERMANENT, + .preferred_lft = INFINITY_LIFE_TIME, + .valid_lft = INFINITY_LIFE_TIME, + }; struct in6_ifreq ireq; int err; @@ -2976,10 +2985,11 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg) if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) return -EFAULT; + cfg.pfx = &ireq.ifr6_addr; + cfg.plen = ireq.ifr6_prefixlen; + rtnl_lock(); - err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL, - ireq.ifr6_prefixlen, IFA_F_PERMANENT, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, NULL); + err = inet6_addr_add(net, ireq.ifr6_ifindex, &cfg, NULL); rtnl_unlock(); return err; } @@ -3006,11 +3016,16 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int plen, int scope) { struct inet6_ifaddr *ifp; + struct ifa6_config cfg = { + .pfx = addr, + .plen = plen, + .ifa_flags = IFA_F_PERMANENT, + .valid_lft = INFINITY_LIFE_TIME, + .preferred_lft = INFINITY_LIFE_TIME, + .scope = scope + }; - ifp = ipv6_add_addr(idev, addr, NULL, plen, - scope, IFA_F_PERMANENT, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, - true, NULL); + ifp = ipv6_add_addr(idev, &cfg, true, NULL); if (!IS_ERR(ifp)) { spin_lock_bh(&ifp->lock); ifp->flags &= ~IFA_F_TENTATIVE; @@ -3047,7 +3062,8 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) if (addr.s6_addr32[3]) { add_addr(idev, &addr, plen, scope); - addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags); + addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, + GFP_ATOMIC); return; } @@ -3071,8 +3087,8 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) } add_addr(idev, &addr, plen, flag); - addrconf_prefix_route(&addr, plen, idev->dev, 0, - pflags); + addrconf_prefix_route(&addr, plen, 0, idev->dev, + 0, pflags, GFP_ATOMIC); } } } @@ -3099,20 +3115,27 @@ static void init_loopback(struct net_device *dev) void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr, u32 flags) { + struct ifa6_config cfg = { + .pfx = addr, + .plen = 64, + .ifa_flags = flags | IFA_F_PERMANENT, + .valid_lft = INFINITY_LIFE_TIME, + .preferred_lft = INFINITY_LIFE_TIME, + .scope = IFA_LINK + }; struct inet6_ifaddr *ifp; - u32 addr_flags = flags | IFA_F_PERMANENT; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if ((dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad || idev->cnf.optimistic_dad) && !dev_net(idev->dev)->ipv6.devconf_all->forwarding) - addr_flags |= IFA_F_OPTIMISTIC; + cfg.ifa_flags |= IFA_F_OPTIMISTIC; #endif - ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, - INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, true, NULL); + ifp = ipv6_add_addr(idev, &cfg, true, NULL); if (!IS_ERR(ifp)) { - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0); + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, 0, idev->dev, + 0, 0, GFP_ATOMIC); addrconf_dad_start(ifp); in6_ifa_put(ifp); } @@ -3227,7 +3250,8 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) addrconf_add_linklocal(idev, &addr, IFA_F_STABLE_PRIVACY); else if (prefix_route) - addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + addrconf_prefix_route(&addr, 64, 0, idev->dev, + 0, 0, GFP_KERNEL); break; case IN6_ADDR_GEN_MODE_EUI64: /* addrconf_add_linklocal also adds a prefix_route and we @@ -3237,7 +3261,8 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0) addrconf_add_linklocal(idev, &addr, 0); else if (prefix_route) - addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + addrconf_prefix_route(&addr, 64, 0, idev->dev, + 0, 0, GFP_KERNEL); break; case IN6_ADDR_GEN_MODE_NONE: default: @@ -3262,7 +3287,8 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_IP6GRE) && (dev->type != ARPHRD_IPGRE) && (dev->type != ARPHRD_TUNNEL) && - (dev->type != ARPHRD_NONE)) { + (dev->type != ARPHRD_NONE) && + (dev->type != ARPHRD_RAWIP)) { /* Alas, we support only Ethernet autoconfiguration. */ return; } @@ -3329,32 +3355,35 @@ static void addrconf_gre_config(struct net_device *dev) } #endif -static int fixup_permanent_addr(struct inet6_dev *idev, +static int fixup_permanent_addr(struct net *net, + struct inet6_dev *idev, struct inet6_ifaddr *ifp) { - /* !rt6i_node means the host route was removed from the + /* !fib6_node means the host route was removed from the * FIB, for example, if 'lo' device is taken down. In that * case regenerate the host route. */ - if (!ifp->rt || !ifp->rt->rt6i_node) { - struct rt6_info *rt, *prev; + if (!ifp->rt || !ifp->rt->fib6_node) { + struct fib6_info *f6i, *prev; - rt = addrconf_dst_alloc(idev, &ifp->addr, false); - if (IS_ERR(rt)) - return PTR_ERR(rt); + f6i = addrconf_f6i_alloc(net, idev, &ifp->addr, false, + GFP_ATOMIC); + if (IS_ERR(f6i)) + return PTR_ERR(f6i); /* ifp->rt can be accessed outside of rtnl */ spin_lock(&ifp->lock); prev = ifp->rt; - ifp->rt = rt; + ifp->rt = f6i; spin_unlock(&ifp->lock); - ip6_rt_put(prev); + fib6_info_release(prev); } if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, - idev->dev, 0, 0); + ifp->rt_priority, idev->dev, 0, 0, + GFP_ATOMIC); } if (ifp->state == INET6_IFADDR_STATE_PREDAD) @@ -3363,7 +3392,7 @@ static int fixup_permanent_addr(struct inet6_dev *idev, return 0; } -static void addrconf_permanent_addr(struct net_device *dev) +static void addrconf_permanent_addr(struct net *net, struct net_device *dev) { struct inet6_ifaddr *ifp, *tmp; struct inet6_dev *idev; @@ -3376,7 +3405,7 @@ static void addrconf_permanent_addr(struct net_device *dev) list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { if ((ifp->flags & IFA_F_PERMANENT) && - fixup_permanent_addr(idev, ifp) < 0) { + fixup_permanent_addr(net, idev, ifp) < 0) { write_unlock_bh(&idev->lock); in6_ifa_hold(ifp); ipv6_del_addr(ifp); @@ -3445,7 +3474,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (event == NETDEV_UP) { /* restore routes for permanent addresses */ - addrconf_permanent_addr(dev); + addrconf_permanent_addr(net, dev); if (!addrconf_link_ready(dev)) { /* device is not ready yet. */ @@ -3612,8 +3641,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; - int _keep_addr; - bool keep_addr; + bool keep_addr = false; int state, i; ASSERT_RTNL(); @@ -3639,15 +3667,18 @@ static int addrconf_ifdown(struct net_device *dev, int how) } - /* aggregate the system setting and interface setting */ - _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; - if (!_keep_addr) - _keep_addr = idev->cnf.keep_addr_on_down; - /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ - keep_addr = !(how || _keep_addr <= 0 || idev->cnf.disable_ipv6); + if (!how && !idev->cnf.disable_ipv6) { + /* aggregate the system setting and interface setting */ + int _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; + + if (!_keep_addr) + _keep_addr = idev->cnf.keep_addr_on_down; + + keep_addr = (_keep_addr > 0); + } /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { @@ -3697,13 +3728,8 @@ restart: write_lock_bh(&idev->lock); } - /* re-combine the user config with event to determine if permanent - * addresses are to be removed from the interface list - */ - keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); - list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { - struct rt6_info *rt = NULL; + struct fib6_info *rt = NULL; bool keep; addrconf_del_dad_work(ifa); @@ -3731,7 +3757,7 @@ restart: spin_unlock_bh(&ifa->lock); if (rt) - ip6_del_rt(rt); + ip6_del_rt(net, rt); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); @@ -3849,6 +3875,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; bool bump_id, notify = false; + struct net *net; addrconf_join_solict(dev, &ifp->addr); @@ -3859,8 +3886,9 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) if (ifp->state == INET6_IFADDR_STATE_DEAD) goto out; + net = dev_net(dev); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || - (dev_net(dev)->ipv6.devconf_all->accept_dad < 1 && + (net->ipv6.devconf_all->accept_dad < 1 && idev->cnf.accept_dad < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { @@ -3896,8 +3924,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) * Frames right away */ if (ifp->flags & IFA_F_OPTIMISTIC) { - ip6_ins_rt(ifp->rt); - if (ipv6_use_optimistic_addr(dev_net(dev), idev)) { + ip6_ins_rt(net, ifp->rt); + if (ipv6_use_optimistic_addr(net, idev)) { /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ @@ -4463,6 +4491,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .len = sizeof(u32) }, + [IFA_RT_PRIORITY] = { .len = sizeof(u32) }, }; static int @@ -4495,8 +4524,38 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, ifm->ifa_prefixlen); } -static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, - u32 prefered_lft, u32 valid_lft) +static int modify_prefix_route(struct inet6_ifaddr *ifp, + unsigned long expires, u32 flags) +{ + struct fib6_info *f6i; + + f6i = addrconf_get_prefix_route(&ifp->addr, + ifp->prefix_len, + ifp->idev->dev, + 0, RTF_GATEWAY | RTF_DEFAULT); + if (!f6i) + return -ENOENT; + + if (f6i->fib6_metric != ifp->rt_priority) { + /* add new one */ + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + ifp->rt_priority, ifp->idev->dev, + expires, flags, GFP_KERNEL); + /* delete old one */ + ip6_del_rt(dev_net(ifp->idev->dev), f6i); + } else { + if (!expires) + fib6_clean_expires(f6i); + else + fib6_set_expires(f6i, expires); + + fib6_info_release(f6i); + } + + return 0; +} + +static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) { u32 flags; clock_t expires; @@ -4506,32 +4565,32 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, ASSERT_RTNL(); - if (!valid_lft || (prefered_lft > valid_lft)) + if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft) return -EINVAL; - if (ifa_flags & IFA_F_MANAGETEMPADDR && + if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && (ifp->flags & IFA_F_TEMPORARY || ifp->prefix_len != 64)) return -EINVAL; if (!(ifp->flags & IFA_F_TENTATIVE) || ifp->flags & IFA_F_DADFAILED) - ifa_flags &= ~IFA_F_OPTIMISTIC; + cfg->ifa_flags &= ~IFA_F_OPTIMISTIC; - timeout = addrconf_timeout_fixup(valid_lft, HZ); + timeout = addrconf_timeout_fixup(cfg->valid_lft, HZ); if (addrconf_finite_timeout(timeout)) { expires = jiffies_to_clock_t(timeout * HZ); - valid_lft = timeout; + cfg->valid_lft = timeout; flags = RTF_EXPIRES; } else { expires = 0; flags = 0; - ifa_flags |= IFA_F_PERMANENT; + cfg->ifa_flags |= IFA_F_PERMANENT; } - timeout = addrconf_timeout_fixup(prefered_lft, HZ); + timeout = addrconf_timeout_fixup(cfg->preferred_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) - ifa_flags |= IFA_F_DEPRECATED; - prefered_lft = timeout; + cfg->ifa_flags |= IFA_F_DEPRECATED; + cfg->preferred_lft = timeout; } spin_lock_bh(&ifp->lock); @@ -4541,18 +4600,30 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, ifp->flags &= ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE); - ifp->flags |= ifa_flags; + ifp->flags |= cfg->ifa_flags; ifp->tstamp = jiffies; - ifp->valid_lft = valid_lft; - ifp->prefered_lft = prefered_lft; + ifp->valid_lft = cfg->valid_lft; + ifp->prefered_lft = cfg->preferred_lft; + + if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) + ifp->rt_priority = cfg->rt_priority; spin_unlock_bh(&ifp->lock); if (!(ifp->flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); - if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev, - expires, flags); + if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) { + int rc = -ENOENT; + + if (had_prefixroute) + rc = modify_prefix_route(ifp, expires, flags); + + /* prefix route could have been deleted; if so restore it */ + if (rc == -ENOENT) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + ifp->rt_priority, ifp->idev->dev, + expires, flags, GFP_KERNEL); + } } else if (had_prefixroute) { enum cleanup_prefix_rt_t action; unsigned long rt_expires; @@ -4568,10 +4639,14 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, } if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) { - if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR)) - valid_lft = prefered_lft = 0; - manage_tempaddrs(ifp->idev, ifp, valid_lft, prefered_lft, - !was_managetempaddr, jiffies); + if (was_managetempaddr && + !(ifp->flags & IFA_F_MANAGETEMPADDR)) { + cfg->valid_lft = 0; + cfg->preferred_lft = 0; + } + manage_tempaddrs(ifp->idev, ifp, cfg->valid_lft, + cfg->preferred_lft, !was_managetempaddr, + jiffies); } addrconf_verify_rtnl(); @@ -4586,12 +4661,11 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; - struct in6_addr *pfx, *peer_pfx; + struct in6_addr *peer_pfx; struct inet6_ifaddr *ifa; struct net_device *dev; struct inet6_dev *idev; - u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME; - u32 ifa_flags; + struct ifa6_config cfg; int err; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, @@ -4599,60 +4673,70 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; + memset(&cfg, 0, sizeof(cfg)); + ifm = nlmsg_data(nlh); - pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); - if (!pfx) + cfg.pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); + if (!cfg.pfx) return -EINVAL; + cfg.peer_pfx = peer_pfx; + cfg.plen = ifm->ifa_prefixlen; + if (tb[IFA_RT_PRIORITY]) + cfg.rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); + + cfg.valid_lft = INFINITY_LIFE_TIME; + cfg.preferred_lft = INFINITY_LIFE_TIME; + if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; ci = nla_data(tb[IFA_CACHEINFO]); - valid_lft = ci->ifa_valid; - preferred_lft = ci->ifa_prefered; - } else { - preferred_lft = INFINITY_LIFE_TIME; - valid_lft = INFINITY_LIFE_TIME; + cfg.valid_lft = ci->ifa_valid; + cfg.preferred_lft = ci->ifa_prefered; } dev = __dev_get_by_index(net, ifm->ifa_index); if (!dev) return -ENODEV; - ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; + if (tb[IFA_FLAGS]) + cfg.ifa_flags = nla_get_u32(tb[IFA_FLAGS]); + else + cfg.ifa_flags = ifm->ifa_flags; /* We ignore other flags so far. */ - ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | - IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC; + cfg.ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | + IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE | + IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC; idev = ipv6_find_idev(dev); if (IS_ERR(idev)) return PTR_ERR(idev); if (!ipv6_allow_optimistic_dad(net, idev)) - ifa_flags &= ~IFA_F_OPTIMISTIC; + cfg.ifa_flags &= ~IFA_F_OPTIMISTIC; - if (ifa_flags & IFA_F_NODAD && ifa_flags & IFA_F_OPTIMISTIC) { + if (cfg.ifa_flags & IFA_F_NODAD && + cfg.ifa_flags & IFA_F_OPTIMISTIC) { NL_SET_ERR_MSG(extack, "IFA_F_NODAD and IFA_F_OPTIMISTIC are mutually exclusive"); return -EINVAL; } - ifa = ipv6_get_ifaddr(net, pfx, dev, 1); + ifa = ipv6_get_ifaddr(net, cfg.pfx, dev, 1); if (!ifa) { /* * It would be best to check for !NLM_F_CREATE here but * userspace already relies on not having to provide this. */ - return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx, - ifm->ifa_prefixlen, ifa_flags, - preferred_lft, valid_lft, extack); + return inet6_addr_add(net, ifm->ifa_index, &cfg, extack); } if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) err = -EEXIST; else - err = inet6_addr_modify(ifa, ifa_flags, preferred_lft, valid_lft); + err = inet6_addr_modify(ifa, &cfg); in6_ifa_put(ifa); @@ -4703,7 +4787,8 @@ static inline int inet6_ifaddr_msgsize(void) + nla_total_size(16) /* IFA_LOCAL */ + nla_total_size(16) /* IFA_ADDRESS */ + nla_total_size(sizeof(struct ifa_cacheinfo)) - + nla_total_size(4) /* IFA_FLAGS */; + + nla_total_size(4) /* IFA_FLAGS */ + + nla_total_size(4) /* IFA_RT_PRIORITY */; } static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, @@ -4749,6 +4834,10 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, if (nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->addr) < 0) goto error; + if (ifa->rt_priority && + nla_put_u32(skb, IFA_RT_PRIORITY, ifa->rt_priority)) + goto error; + if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) goto error; @@ -4792,9 +4881,10 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, u32 portid, u32 seq, int event, unsigned int flags) { + struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); + int ifindex = dev ? dev->ifindex : 1; struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; - int ifindex = ifaca->aca_idev->dev->ifindex; if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; @@ -5017,14 +5107,6 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) struct net *net = dev_net(ifa->idev->dev); int err = -ENOBUFS; - /* Don't send DELADDR notification for TENTATIVE address, - * since NEWADDR notification is sent only after removing - * TENTATIVE flag, if DAD has not failed. - */ - if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_DADFAILED) && - event == RTM_DELADDR) - return; - skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); if (!skb) goto errout; @@ -5595,29 +5677,30 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) * our DAD process, so we don't need * to do it again */ - if (!rcu_access_pointer(ifp->rt->rt6i_node)) - ip6_ins_rt(ifp->rt); + if (!rcu_access_pointer(ifp->rt->fib6_node)) + ip6_ins_rt(net, ifp->rt); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); if (!ipv6_addr_any(&ifp->peer_addr)) - addrconf_prefix_route(&ifp->peer_addr, 128, - ifp->idev->dev, 0, 0); + addrconf_prefix_route(&ifp->peer_addr, 128, 0, + ifp->idev->dev, 0, 0, + GFP_ATOMIC); break; case RTM_DELADDR: if (ifp->idev->cnf.forwarding) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); if (!ipv6_addr_any(&ifp->peer_addr)) { - struct rt6_info *rt; + struct fib6_info *rt; rt = addrconf_get_prefix_route(&ifp->peer_addr, 128, ifp->idev->dev, 0, 0); if (rt) - ip6_del_rt(rt); + ip6_del_rt(net, rt); } if (ifp->rt) { - if (dst_hold_safe(&ifp->rt->dst)) - ip6_del_rt(ifp->rt); + ip6_del_rt(net, ifp->rt); + ifp->rt = NULL; } rt_genid_bump_ipv6(net); break; @@ -5964,11 +6047,11 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) list_for_each_entry(ifa, &idev->addr_list, if_list) { spin_lock(&ifa->lock); if (ifa->rt) { - struct rt6_info *rt = ifa->rt; + struct fib6_info *rt = ifa->rt; int cpu; rcu_read_lock(); - addrconf_set_nopolicy(ifa->rt, val); + ifa->rt->dst_nopolicy = val ? true : false; if (rt->rt6i_pcpu) { for_each_possible_cpu(cpu) { struct rt6_info **rtp; diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 32b564dfd02af..5cd0029d930e2 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -134,8 +134,47 @@ static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1, return -EAFNOSUPPORT; } +static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id) +{ + return NULL; +} + +static struct fib6_info * +eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table, + int oif, struct flowi6 *fl6, int flags) +{ + return NULL; +} + +static struct fib6_info * +eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, + int flags) +{ + return NULL; +} + +static struct fib6_info * +eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i, + struct flowi6 *fl6, int oif, + const struct sk_buff *skb, int strict) +{ + return f6i; +} + +static u32 +eafnosupport_ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr, + struct in6_addr *saddr) +{ + return 0; +} + const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { - .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, + .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, + .fib6_get_table = eafnosupport_fib6_get_table, + .fib6_table_lookup = eafnosupport_fib6_table_lookup, + .fib6_lookup = eafnosupport_fib6_lookup, + .fib6_multipath_select = eafnosupport_fib6_multipath_select, + .ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6, }; EXPORT_SYMBOL_GPL(ipv6_stub); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d443c18b45fef..74f2a261e8df4 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -273,33 +273,8 @@ out_rcu_unlock: goto out; } - -/* bind for INET6 API */ -int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) -{ - struct sock *sk = sock->sk; - int err = 0; - - /* If the socket has its own bind function then use it. */ - if (sk->sk_prot->bind) - return sk->sk_prot->bind(sk, uaddr, addr_len); - - if (addr_len < SIN6_LEN_RFC2133) - return -EINVAL; - - /* BPF prog is run before any checks are done so that if the prog - * changes context in a wrong way it will be caught. - */ - err = BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr); - if (err) - return err; - - return __inet6_bind(sk, uaddr, addr_len, false, true); -} -EXPORT_SYMBOL(inet6_bind); - -int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, - bool force_bind_address_no_port, bool with_lock) +static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, + bool force_bind_address_no_port, bool with_lock) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr; struct inet_sock *inet = inet_sk(sk); @@ -444,6 +419,30 @@ out_unlock: goto out; } +/* bind for INET6 API */ +int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +{ + struct sock *sk = sock->sk; + int err = 0; + + /* If the socket has its own bind function then use it. */ + if (sk->sk_prot->bind) + return sk->sk_prot->bind(sk, uaddr, addr_len); + + if (addr_len < SIN6_LEN_RFC2133) + return -EINVAL; + + /* BPF prog is run before any checks are done so that if the prog + * changes context in a wrong way it will be caught. + */ + err = BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr); + if (err) + return err; + + return __inet6_bind(sk, uaddr, addr_len, false, true); +} +EXPORT_SYMBOL(inet6_bind); + int inet6_release(struct socket *sock) { struct sock *sk = sock->sk; @@ -579,7 +578,9 @@ const struct proto_ops inet6_stream_ops = { .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet_sendmsg, /* ok */ .recvmsg = inet_recvmsg, /* ok */ - .mmap = sock_no_mmap, +#ifdef CONFIG_MMU + .mmap = tcp_mmap, +#endif .sendpage = inet_sendpage, .sendmsg_locked = tcp_sendmsg_locked, .sendpage_locked = tcp_sendpage_locked, @@ -590,6 +591,7 @@ const struct proto_ops inet6_stream_ops = { .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, #endif + .set_rcvlowat = tcp_set_rcvlowat, }; const struct proto_ops inet6_dgram_ops = { @@ -887,7 +889,12 @@ static struct pernet_operations inet6_net_ops = { static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_join = ipv6_sock_mc_join, .ipv6_sock_mc_drop = ipv6_sock_mc_drop, - .ipv6_dst_lookup = ip6_dst_lookup, + .ipv6_dst_lookup = ip6_dst_lookup, + .fib6_get_table = fib6_get_table, + .fib6_table_lookup = fib6_table_lookup, + .fib6_lookup = fib6_lookup, + .fib6_multipath_select = fib6_multipath_select, + .ip6_mtu_from_fib6 = ip6_mtu_from_fib6, .udpv6_encap_enable = udpv6_encap_enable, .ndisc_send_na = ndisc_send_na, .nd_tbl = &nd_tbl, diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index ebeaf47d5c8d0..4e0ff7031edd5 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -212,16 +212,14 @@ static void aca_get(struct ifacaddr6 *aca) static void aca_put(struct ifacaddr6 *ac) { if (refcount_dec_and_test(&ac->aca_refcnt)) { - in6_dev_put(ac->aca_idev); - dst_release(&ac->aca_rt->dst); + fib6_info_release(ac->aca_rt); kfree(ac); } } -static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, +static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i, const struct in6_addr *addr) { - struct inet6_dev *idev = rt->rt6i_idev; struct ifacaddr6 *aca; aca = kzalloc(sizeof(*aca), GFP_ATOMIC); @@ -229,9 +227,8 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, return NULL; aca->aca_addr = *addr; - in6_dev_hold(idev); - aca->aca_idev = idev; - aca->aca_rt = rt; + fib6_info_hold(f6i); + aca->aca_rt = f6i; aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; @@ -246,7 +243,8 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca; - struct rt6_info *rt; + struct fib6_info *f6i; + struct net *net; int err; ASSERT_RTNL(); @@ -265,14 +263,15 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) } } - rt = addrconf_dst_alloc(idev, addr, true); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); + net = dev_net(idev->dev); + f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC); + if (IS_ERR(f6i)) { + err = PTR_ERR(f6i); goto out; } - aca = aca_alloc(rt, addr); + aca = aca_alloc(f6i, addr); if (!aca) { - ip6_rt_put(rt); + fib6_info_release(f6i); err = -ENOMEM; goto out; } @@ -286,7 +285,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) aca_get(aca); write_unlock_bh(&idev->lock); - ip6_ins_rt(rt); + ip6_ins_rt(net, f6i); addrconf_join_solict(idev->dev, &aca->aca_addr); @@ -328,8 +327,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) write_unlock_bh(&idev->lock); addrconf_leave_solict(idev, &aca->aca_addr); - dst_hold(&aca->aca_rt->dst); - ip6_del_rt(aca->aca_rt); + ip6_del_rt(dev_net(idev->dev), aca->aca_rt); aca_put(aca); return 0; @@ -356,8 +354,7 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev) addrconf_leave_solict(idev, &aca->aca_addr); - dst_hold(&aca->aca_rt->dst); - ip6_del_rt(aca->aca_rt); + ip6_del_rt(dev_net(idev->dev), aca->aca_rt); aca_put(aca); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index bc68eb661970a..5bc2bf3733abd 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -280,6 +280,7 @@ static const struct tlvtype_proc tlvprocdestopt_lst[] = { static int ipv6_destopt_rcv(struct sk_buff *skb) { + struct inet6_dev *idev = __in6_dev_get(skb->dev); struct inet6_skb_parm *opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) __u16 dstbuf; @@ -291,7 +292,7 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - __IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), + __IP6_INC_STATS(dev_net(dst->dev), idev, IPSTATS_MIB_INHDRERRORS); fail_and_free: kfree_skb(skb); @@ -319,8 +320,7 @@ fail_and_free: return 1; } - __IP6_INC_STATS(dev_net(dst->dev), - ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return -1; } @@ -416,8 +416,7 @@ looped_back: } if (hdr->segments_left >= (hdr->hdrlen >> 1)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); @@ -456,8 +455,7 @@ looped_back: if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); @@ -481,10 +479,10 @@ looped_back: /* called with rcu_read_lock() */ static int ipv6_rthdr_rcv(struct sk_buff *skb) { + struct inet6_dev *idev = __in6_dev_get(skb->dev); struct inet6_skb_parm *opt = IP6CB(skb); struct in6_addr *addr = NULL; struct in6_addr daddr; - struct inet6_dev *idev; int n, i; struct ipv6_rt_hdr *hdr; struct rt0_hdr *rthdr; @@ -498,8 +496,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } @@ -508,8 +505,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) || skb->pkt_type != PACKET_HOST) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INADDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } @@ -527,7 +523,7 @@ looped_back: * processed by own */ if (!addr) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -553,8 +549,7 @@ looped_back: goto unknown_rh; /* Silently discard invalid RTH type 2 */ if (hdr->hdrlen != 2 || hdr->segments_left != 1) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } @@ -572,8 +567,7 @@ looped_back: n = hdr->hdrlen >> 1; if (hdr->segments_left > n) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); @@ -609,14 +603,12 @@ looped_back: if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, (xfrm_address_t *)&ipv6_hdr(skb)->saddr, IPPROTO_ROUTING) < 0) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INADDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } if (!ipv6_chk_home_addr(dev_net(skb_dst(skb)->dev), addr)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INADDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } @@ -627,8 +619,7 @@ looped_back: } if (ipv6_addr_is_multicast(addr)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INADDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } @@ -647,8 +638,7 @@ looped_back: if (skb_dst(skb)->dev->flags&IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); @@ -663,7 +653,7 @@ looped_back: return -1; unknown_rh: - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb_network_header(skb)); return -1; @@ -755,34 +745,31 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); + struct inet6_dev *idev = __in6_dev_get_safely(skb->dev); struct net *net = ipv6_skb_net(skb); u32 pkt_len; if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { net_dbg_ratelimited("ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", nh[optoff+1]); - __IP6_INC_STATS(net, ipv6_skb_idev(skb), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); goto drop; } pkt_len = ntohl(*(__be32 *)(nh + optoff + 2)); if (pkt_len <= IPV6_MAXPLEN) { - __IP6_INC_STATS(net, ipv6_skb_idev(skb), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff+2); return false; } if (ipv6_hdr(skb)->payload_len) { - __IP6_INC_STATS(net, ipv6_skb_idev(skb), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff); return false; } if (pkt_len > skb->len - sizeof(struct ipv6hdr)) { - __IP6_INC_STATS(net, ipv6_skb_idev(skb), - IPSTATS_MIB_INTRUNCATEDPKTS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index b643f5ce6c807..ae365df8abf7b 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -161,7 +161,7 @@ EXPORT_SYMBOL_GPL(ipv6_find_tlv); * if target < 0. "last header" is transport protocol header, ESP, or * "No next header". * - * Note that *offset is used as input/output parameter. an if it is not zero, + * Note that *offset is used as input/output parameter, and if it is not zero, * then it must be a valid offset to an inner IPv6 header. This can be used * to explore inner IPv6 header, eg. ICMPv6 error messages. * diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index df113c7b5fc82..f590446595d8b 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -60,6 +60,39 @@ unsigned int fib6_rules_seq_read(struct net *net) return fib_rules_seq_read(net, AF_INET6); } +/* called with rcu lock held; no reference taken on fib6_info */ +struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, + int flags) +{ + struct fib6_info *f6i; + int err; + + if (net->ipv6.fib6_has_custom_rules) { + struct fib_lookup_arg arg = { + .lookup_ptr = fib6_table_lookup, + .lookup_data = &oif, + .flags = FIB_LOOKUP_NOREF, + }; + + l3mdev_update_flow(net, flowi6_to_flowi(fl6)); + + err = fib_rules_lookup(net->ipv6.fib6_rules_ops, + flowi6_to_flowi(fl6), flags, &arg); + if (err) + return ERR_PTR(err); + + f6i = arg.result ? : net->ipv6.fib6_null_entry; + } else { + f6i = fib6_table_lookup(net, net->ipv6.fib6_local_tbl, + oif, fl6, flags); + if (!f6i || f6i == net->ipv6.fib6_null_entry) + f6i = fib6_table_lookup(net, net->ipv6.fib6_main_tbl, + oif, fl6, flags); + } + + return f6i; +} + struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup) @@ -96,8 +129,73 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, return &net->ipv6.ip6_null_entry->dst; } -static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, - int flags, struct fib_lookup_arg *arg) +static int fib6_rule_saddr(struct net *net, struct fib_rule *rule, int flags, + struct flowi6 *flp6, const struct net_device *dev) +{ + struct fib6_rule *r = (struct fib6_rule *)rule; + + /* If we need to find a source address for this traffic, + * we check the result if it meets requirement of the rule. + */ + if ((rule->flags & FIB_RULE_FIND_SADDR) && + r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) { + struct in6_addr saddr; + + if (ipv6_dev_get_saddr(net, dev, &flp6->daddr, + rt6_flags2srcprefs(flags), &saddr)) + return -EAGAIN; + + if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen)) + return -EAGAIN; + + flp6->saddr = saddr; + } + + return 0; +} + +static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + struct flowi6 *flp6 = &flp->u.ip6; + struct net *net = rule->fr_net; + struct fib6_table *table; + struct fib6_info *f6i; + int err = -EAGAIN, *oif; + u32 tb_id; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + case FR_ACT_UNREACHABLE: + return -ENETUNREACH; + case FR_ACT_PROHIBIT: + return -EACCES; + case FR_ACT_BLACKHOLE: + default: + return -EINVAL; + } + + tb_id = fib_rule_get_table(rule, arg); + table = fib6_get_table(net, tb_id); + if (!table) + return -EAGAIN; + + oif = (int *)arg->lookup_data; + f6i = fib6_table_lookup(net, table, *oif, flp6, flags); + if (f6i != net->ipv6.fib6_null_entry) { + err = fib6_rule_saddr(net, rule, flags, flp6, + fib6_info_nh_dev(f6i)); + + if (likely(!err)) + arg->result = f6i; + } + + return err; +} + +static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) { struct flowi6 *flp6 = &flp->u.ip6; struct rt6_info *rt = NULL; @@ -134,27 +232,12 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, rt = lookup(net, table, flp6, arg->lookup_data, flags); if (rt != net->ipv6.ip6_null_entry) { - struct fib6_rule *r = (struct fib6_rule *)rule; - - /* - * If we need to find a source address for this traffic, - * we check the result if it meets requirement of the rule. - */ - if ((rule->flags & FIB_RULE_FIND_SADDR) && - r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) { - struct in6_addr saddr; - - if (ipv6_dev_get_saddr(net, - ip6_dst_idev(&rt->dst)->dev, - &flp6->daddr, - rt6_flags2srcprefs(flags), - &saddr)) - goto again; - if (!ipv6_prefix_equal(&saddr, &r->src.addr, - r->src.plen)) - goto again; - flp6->saddr = saddr; - } + err = fib6_rule_saddr(net, rule, flags, flp6, + ip6_dst_idev(&rt->dst)->dev); + + if (err == -EAGAIN) + goto again; + err = rt->dst.error; if (err != -EAGAIN) goto out; @@ -172,6 +255,15 @@ out: return err; } +static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + if (arg->lookup_ptr == fib6_table_lookup) + return fib6_rule_action_alt(rule, flp, flags, arg); + + return __fib6_rule_action(rule, flp, flags, arg); +} + static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) { struct rt6_info *rt = (struct rt6_info *) arg->result; @@ -245,15 +337,18 @@ static const struct nla_policy fib6_rule_policy[FRA_MAX+1] = { static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, - struct nlattr **tb) + struct nlattr **tb, + struct netlink_ext_ack *extack) { int err = -EINVAL; struct net *net = sock_net(skb->sk); struct fib6_rule *rule6 = (struct fib6_rule *) rule; if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) { - if (rule->table == RT6_TABLE_UNSPEC) + if (rule->table == RT6_TABLE_UNSPEC) { + NL_SET_ERR_MSG(extack, "Invalid table"); goto errout; + } if (fib6_new_table(net, rule->table) == NULL) { err = -ENOBUFS; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 01372dd74e385..7aa4c41a3bd91 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -43,7 +43,7 @@ static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { struct fib6_walker w; struct net *net; - int (*func)(struct rt6_info *, void *arg); + int (*func)(struct fib6_info *, void *arg); int sernum; void *arg; }; @@ -54,7 +54,7 @@ struct fib6_cleaner { #define FWS_INIT FWS_L #endif -static struct rt6_info *fib6_find_prefix(struct net *net, +static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, @@ -105,13 +105,12 @@ enum { FIB6_NO_SERNUM_CHANGE = 0, }; -void fib6_update_sernum(struct rt6_info *rt) +void fib6_update_sernum(struct net *net, struct fib6_info *f6i) { - struct net *net = dev_net(rt->dst.dev); struct fib6_node *fn; - fn = rcu_dereference_protected(rt->rt6i_node, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + fn = rcu_dereference_protected(f6i->fib6_node, + lockdep_is_held(&f6i->fib6_table->tb6_lock)); if (fn) fn->fn_sernum = fib6_new_sernum(net); } @@ -146,6 +145,69 @@ static __be32 addr_bit_set(const void *token, int fn_bit) addr[fn_bit >> 5]; } +struct fib6_info *fib6_info_alloc(gfp_t gfp_flags) +{ + struct fib6_info *f6i; + + f6i = kzalloc(sizeof(*f6i), gfp_flags); + if (!f6i) + return NULL; + + f6i->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags); + if (!f6i->rt6i_pcpu) { + kfree(f6i); + return NULL; + } + + INIT_LIST_HEAD(&f6i->fib6_siblings); + f6i->fib6_metrics = (struct dst_metrics *)&dst_default_metrics; + + atomic_inc(&f6i->fib6_ref); + + return f6i; +} + +void fib6_info_destroy(struct fib6_info *f6i) +{ + struct rt6_exception_bucket *bucket; + struct dst_metrics *m; + + WARN_ON(f6i->fib6_node); + + bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, 1); + if (bucket) { + f6i->rt6i_exception_bucket = NULL; + kfree(bucket); + } + + if (f6i->rt6i_pcpu) { + int cpu; + + for_each_possible_cpu(cpu) { + struct rt6_info **ppcpu_rt; + struct rt6_info *pcpu_rt; + + ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu); + pcpu_rt = *ppcpu_rt; + if (pcpu_rt) { + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); + *ppcpu_rt = NULL; + } + } + } + + if (f6i->fib6_nh.nh_dev) + dev_put(f6i->fib6_nh.nh_dev); + + m = f6i->fib6_metrics; + if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt)) + kfree(m); + + kfree(f6i); +} +EXPORT_SYMBOL_GPL(fib6_info_destroy); + static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; @@ -176,28 +238,6 @@ static void node_free(struct net *net, struct fib6_node *fn) net->ipv6.rt6_stats->fib_nodes--; } -void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) -{ - int cpu; - - if (!non_pcpu_rt->rt6i_pcpu) - return; - - for_each_possible_cpu(cpu) { - struct rt6_info **ppcpu_rt; - struct rt6_info *pcpu_rt; - - ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu); - pcpu_rt = *ppcpu_rt; - if (pcpu_rt) { - dst_dev_put(&pcpu_rt->dst); - dst_release(&pcpu_rt->dst); - *ppcpu_rt = NULL; - } - } -} -EXPORT_SYMBOL_GPL(rt6_free_pcpu); - static void fib6_free_table(struct fib6_table *table) { inetpeer_invalidate_tree(&table->tb6_peers); @@ -232,7 +272,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) if (table) { table->tb6_id = id; rcu_assign_pointer(table->tb6_root.leaf, - net->ipv6.ip6_null_entry); + net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); } @@ -314,6 +354,13 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, return &rt->dst; } +/* called with rcu lock held; no reference taken on fib6_info */ +struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, + int flags) +{ + return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, flags); +} + static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); @@ -340,7 +387,7 @@ unsigned int fib6_tables_seq_read(struct net *net) static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, enum fib_event_type event_type, - struct rt6_info *rt) + struct fib6_info *rt) { struct fib6_entry_notifier_info info = { .rt = rt, @@ -351,7 +398,7 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, static int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, - struct rt6_info *rt, + struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { @@ -359,7 +406,7 @@ static int call_fib6_entry_notifiers(struct net *net, .rt = rt, }; - rt->rt6i_table->fib_seq++; + rt->fib6_table->fib_seq++; return call_fib6_notifiers(net, event_type, &info.info); } @@ -368,16 +415,16 @@ struct fib6_dump_arg { struct notifier_block *nb; }; -static void fib6_rt_dump(struct rt6_info *rt, struct fib6_dump_arg *arg) +static void fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { - if (rt == arg->net->ipv6.ip6_null_entry) + if (rt == arg->net->ipv6.fib6_null_entry) return; call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt); } static int fib6_node_dump(struct fib6_walker *w) { - struct rt6_info *rt; + struct fib6_info *rt; for_each_fib6_walker_rt(w) fib6_rt_dump(rt, w->args); @@ -426,7 +473,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb) static int fib6_dump_node(struct fib6_walker *w) { int res; - struct rt6_info *rt; + struct fib6_info *rt; for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args); @@ -441,10 +488,10 @@ static int fib6_dump_node(struct fib6_walker *w) * last sibling of this route (no need to dump the * sibling routes again) */ - if (rt->rt6i_nsiblings) - rt = list_last_entry(&rt->rt6i_siblings, - struct rt6_info, - rt6i_siblings); + if (rt->fib6_nsiblings) + rt = list_last_entry(&rt->fib6_siblings, + struct fib6_info, + fib6_siblings); } w->leaf = NULL; return 0; @@ -579,6 +626,24 @@ out: return res; } +void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val) +{ + if (!f6i) + return; + + if (f6i->fib6_metrics == &dst_default_metrics) { + struct dst_metrics *p = kzalloc(sizeof(*p), GFP_ATOMIC); + + if (!p) + return; + + refcount_set(&p->refcnt, 1); + f6i->fib6_metrics = p; + } + + f6i->fib6_metrics->metrics[metric - 1] = val; +} + /* * Routing Table * @@ -608,7 +673,7 @@ static struct fib6_node *fib6_add_1(struct net *net, fn = root; do { - struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); key = (struct rt6key *)((u8 *)leaf + offset); @@ -637,11 +702,11 @@ static struct fib6_node *fib6_add_1(struct net *net, /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { RCU_INIT_POINTER(fn->leaf, NULL); - rt6_release(leaf); + fib6_info_release(leaf); /* remove null_entry in the root node */ } else if (fn->fn_flags & RTN_TL_ROOT && rcu_access_pointer(fn->leaf) == - net->ipv6.ip6_null_entry) { + net->ipv6.fib6_null_entry) { RCU_INIT_POINTER(fn->leaf, NULL); } @@ -750,7 +815,7 @@ insert_above: RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; atomic_inc(&rcu_dereference_protected(in->leaf, - lockdep_is_held(&table->tb6_lock))->rt6i_ref); + lockdep_is_held(&table->tb6_lock))->fib6_ref); /* update parent pointer */ if (dir) @@ -802,44 +867,37 @@ insert_above: return ln; } -static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc) -{ - int i; - - for (i = 0; i < RTAX_MAX; i++) { - if (test_bit(i, mxc->mx_valid)) - mp[i] = mxc->mx[i]; - } -} - -static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc) +static void fib6_drop_pcpu_from(struct fib6_info *f6i, + const struct fib6_table *table) { - if (!mxc->mx) - return 0; - - if (dst->flags & DST_HOST) { - u32 *mp = dst_metrics_write_ptr(dst); + int cpu; - if (unlikely(!mp)) - return -ENOMEM; + /* release the reference to this fib entry from + * all of its cached pcpu routes + */ + for_each_possible_cpu(cpu) { + struct rt6_info **ppcpu_rt; + struct rt6_info *pcpu_rt; - fib6_copy_metrics(mp, mxc); - } else { - dst_init_metrics(dst, mxc->mx, false); + ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu); + pcpu_rt = *ppcpu_rt; + if (pcpu_rt) { + struct fib6_info *from; - /* We've stolen mx now. */ - mxc->mx = NULL; + from = rcu_dereference_protected(pcpu_rt->from, + lockdep_is_held(&table->tb6_lock)); + rcu_assign_pointer(pcpu_rt->from, NULL); + fib6_info_release(from); + } } - - return 0; } -static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, +static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, struct net *net) { - struct fib6_table *table = rt->rt6i_table; + struct fib6_table *table = rt->fib6_table; - if (atomic_read(&rt->rt6i_ref) != 1) { + if (atomic_read(&rt->fib6_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, * which must be released in time. So, scan ascendant nodes @@ -847,18 +905,22 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, * to still alive ones. */ while (fn) { - struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); - struct rt6_info *new_leaf; + struct fib6_info *new_leaf; if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { new_leaf = fib6_find_prefix(net, table, fn); - atomic_inc(&new_leaf->rt6i_ref); + atomic_inc(&new_leaf->fib6_ref); + rcu_assign_pointer(fn->leaf, new_leaf); - rt6_release(rt); + fib6_info_release(rt); } fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); } + + if (rt->rt6i_pcpu) + fib6_drop_pcpu_from(rt, table); } } @@ -866,37 +928,37 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, * Insert routing information in a node. */ -static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc, +static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, + struct nl_info *info, struct netlink_ext_ack *extack) { - struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); - struct rt6_info *iter = NULL; - struct rt6_info __rcu **ins; - struct rt6_info __rcu **fallback_ins = NULL; + struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + struct fib6_info *iter = NULL, *match = NULL; + struct fib6_info __rcu **ins; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); + int append = (info->nlh && + (info->nlh->nlmsg_flags & NLM_F_APPEND)); int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; - bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); u16 nlflags = NLM_F_EXCL; int err; - if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND)) + if (append) nlflags |= NLM_F_APPEND; ins = &fn->leaf; for (iter = leaf; iter; - iter = rcu_dereference_protected(iter->rt6_next, - lockdep_is_held(&rt->rt6i_table->tb6_lock))) { + iter = rcu_dereference_protected(iter->fib6_next, + lockdep_is_held(&rt->fib6_table->tb6_lock))) { /* * Search for duplicates */ - if (iter->rt6i_metric == rt->rt6i_metric) { + if (iter->fib6_metric == rt->fib6_metric) { /* * Same priority level */ @@ -906,56 +968,32 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, nlflags &= ~NLM_F_EXCL; if (replace) { - if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { - found++; - break; - } - if (rt_can_ecmp) - fallback_ins = fallback_ins ?: ins; - goto next_iter; + found++; + break; } if (rt6_duplicate_nexthop(iter, rt)) { - if (rt->rt6i_nsiblings) - rt->rt6i_nsiblings = 0; - if (!(iter->rt6i_flags & RTF_EXPIRES)) + if (rt->fib6_nsiblings) + rt->fib6_nsiblings = 0; + if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; - if (!(rt->rt6i_flags & RTF_EXPIRES)) - rt6_clean_expires(iter); + if (!(rt->fib6_flags & RTF_EXPIRES)) + fib6_clean_expires(iter); else - rt6_set_expires(iter, rt->dst.expires); - iter->rt6i_pmtu = rt->rt6i_pmtu; + fib6_set_expires(iter, rt->expires); + fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); return -EEXIST; } - /* If we have the same destination and the same metric, - * but not the same gateway, then the route we try to - * add is sibling to this route, increment our counter - * of siblings, and later we will add our route to the - * list. - * Only static routes (which don't have flag - * RTF_EXPIRES) are used for ECMPv6. - * - * To avoid long list, we only had siblings if the - * route have a gateway. - */ - if (rt_can_ecmp && - rt6_qualify_for_ecmp(iter)) - rt->rt6i_nsiblings++; + + /* first route that matches */ + if (!match) + match = iter; } - if (iter->rt6i_metric > rt->rt6i_metric) + if (iter->fib6_metric > rt->fib6_metric) break; -next_iter: - ins = &iter->rt6_next; - } - - if (fallback_ins && !found) { - /* No ECMP-able route found, replace first non-ECMP one */ - ins = fallback_ins; - iter = rcu_dereference_protected(*ins, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); - found++; + ins = &iter->fib6_next; } /* Reset round-robin state, if necessary */ @@ -963,59 +1001,56 @@ next_iter: fn->rr_ptr = NULL; /* Link this route to others same route. */ - if (rt->rt6i_nsiblings) { - unsigned int rt6i_nsiblings; - struct rt6_info *sibling, *temp_sibling; - - /* Find the first route that have the same metric */ - sibling = leaf; - while (sibling) { - if (sibling->rt6i_metric == rt->rt6i_metric && - rt6_qualify_for_ecmp(sibling)) { - list_add_tail(&rt->rt6i_siblings, - &sibling->rt6i_siblings); - break; - } - sibling = rcu_dereference_protected(sibling->rt6_next, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + if (append && match) { + struct fib6_info *sibling, *temp_sibling; + + if (rt->fib6_flags & RTF_REJECT) { + NL_SET_ERR_MSG(extack, + "Can not append a REJECT route"); + return -EINVAL; + } else if (match->fib6_flags & RTF_REJECT) { + NL_SET_ERR_MSG(extack, + "Can not append to a REJECT route"); + return -EINVAL; } + rt->fib6_nsiblings = match->fib6_nsiblings; + list_add_tail(&rt->fib6_siblings, &match->fib6_siblings); + match->fib6_nsiblings++; + /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings * is broken! */ - rt6i_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, - &rt->rt6i_siblings, rt6i_siblings) { - sibling->rt6i_nsiblings++; - BUG_ON(sibling->rt6i_nsiblings != rt->rt6i_nsiblings); - rt6i_nsiblings++; + &match->fib6_siblings, fib6_siblings) { + sibling->fib6_nsiblings++; + BUG_ON(sibling->fib6_nsiblings != match->fib6_nsiblings); } - BUG_ON(rt6i_nsiblings != rt->rt6i_nsiblings); - rt6_multipath_rebalance(temp_sibling); + + rt6_multipath_rebalance(match); } /* * insert node */ if (!replace) { + enum fib_event_type event; + if (!add) pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: nlflags |= NLM_F_CREATE; - err = fib6_commit_metrics(&rt->dst, mxc); - if (err) - return err; - err = call_fib6_entry_notifiers(info->nl_net, - FIB_EVENT_ENTRY_ADD, - rt, extack); + event = append ? FIB_EVENT_ENTRY_APPEND : FIB_EVENT_ENTRY_ADD; + err = call_fib6_entry_notifiers(info->nl_net, event, rt, + extack); if (err) return err; - rcu_assign_pointer(rt->rt6_next, iter); - atomic_inc(&rt->rt6i_ref); - rcu_assign_pointer(rt->rt6i_node, fn); + rcu_assign_pointer(rt->fib6_next, iter); + atomic_inc(&rt->fib6_ref); + rcu_assign_pointer(rt->fib6_node, fn); rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); @@ -1027,7 +1062,7 @@ add: } } else { - int nsiblings; + struct fib6_info *tmp; if (!found) { if (add) @@ -1036,67 +1071,72 @@ add: return -ENOENT; } - err = fib6_commit_metrics(&rt->dst, mxc); - if (err) - return err; - err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt, extack); if (err) return err; - atomic_inc(&rt->rt6i_ref); - rcu_assign_pointer(rt->rt6i_node, fn); - rt->rt6_next = iter->rt6_next; + /* if route being replaced has siblings, set tmp to + * last one, otherwise tmp is current route. this is + * used to set fib6_next for new route + */ + if (iter->fib6_nsiblings) + tmp = list_last_entry(&iter->fib6_siblings, + struct fib6_info, + fib6_siblings); + else + tmp = iter; + + /* insert new route */ + atomic_inc(&rt->fib6_ref); + rcu_assign_pointer(rt->fib6_node, fn); + rt->fib6_next = tmp->fib6_next; rcu_assign_pointer(*ins, rt); + if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } - nsiblings = iter->rt6i_nsiblings; - iter->rt6i_node = NULL; - fib6_purge_rt(iter, fn, info->nl_net); - if (rcu_access_pointer(fn->rr_ptr) == iter) - fn->rr_ptr = NULL; - rt6_release(iter); - if (nsiblings) { + /* delete old route */ + rt = iter; + + if (rt->fib6_nsiblings) { + struct fib6_info *tmp; + /* Replacing an ECMP route, remove all siblings */ - ins = &rt->rt6_next; - iter = rcu_dereference_protected(*ins, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); - while (iter) { - if (iter->rt6i_metric > rt->rt6i_metric) - break; - if (rt6_qualify_for_ecmp(iter)) { - *ins = iter->rt6_next; - iter->rt6i_node = NULL; - fib6_purge_rt(iter, fn, info->nl_net); - if (rcu_access_pointer(fn->rr_ptr) == iter) - fn->rr_ptr = NULL; - rt6_release(iter); - nsiblings--; - info->nl_net->ipv6.rt6_stats->fib_rt_entries--; - } else { - ins = &iter->rt6_next; - } - iter = rcu_dereference_protected(*ins, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + list_for_each_entry_safe(iter, tmp, &rt->fib6_siblings, + fib6_siblings) { + iter->fib6_node = NULL; + fib6_purge_rt(iter, fn, info->nl_net); + if (rcu_access_pointer(fn->rr_ptr) == iter) + fn->rr_ptr = NULL; + fib6_info_release(iter); + + rt->fib6_nsiblings--; + info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } - WARN_ON(nsiblings != 0); } + + WARN_ON(rt->fib6_nsiblings != 0); + + rt->fib6_node = NULL; + fib6_purge_rt(rt, fn, info->nl_net); + if (rcu_access_pointer(fn->rr_ptr) == rt) + fn->rr_ptr = NULL; + fib6_info_release(rt); } return 0; } -static void fib6_start_gc(struct net *net, struct rt6_info *rt) +static void fib6_start_gc(struct net *net, struct fib6_info *rt) { if (!timer_pending(&net->ipv6.ip6_fib_timer) && - (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE))) + (rt->fib6_flags & RTF_EXPIRES)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } @@ -1108,22 +1148,22 @@ void fib6_force_start_gc(struct net *net) jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } -static void __fib6_update_sernum_upto_root(struct rt6_info *rt, +static void __fib6_update_sernum_upto_root(struct fib6_info *rt, int sernum) { - struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&rt->fib6_table->tb6_lock)); /* paired with smp_rmb() in rt6_get_cookie_safe() */ smp_wmb(); while (fn) { fn->fn_sernum = sernum; fn = rcu_dereference_protected(fn->parent, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + lockdep_is_held(&rt->fib6_table->tb6_lock)); } } -void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt) +void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt) { __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); } @@ -1135,22 +1175,16 @@ void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt) * Need to own table->tb6_lock */ -int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc, - struct netlink_ext_ack *extack) +int fib6_add(struct fib6_node *root, struct fib6_info *rt, + struct nl_info *info, struct netlink_ext_ack *extack) { - struct fib6_table *table = rt->rt6i_table; + struct fib6_table *table = rt->fib6_table; struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; int allow_create = 1; int replace_required = 0; int sernum = fib6_new_sernum(info->nl_net); - if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt))) - return -EINVAL; - if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE)) - return -EINVAL; - if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) allow_create = 0; @@ -1161,8 +1195,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); fn = fib6_add_1(info->nl_net, table, root, - &rt->rt6i_dst.addr, rt->rt6i_dst.plen, - offsetof(struct rt6_info, rt6i_dst), allow_create, + &rt->fib6_dst.addr, rt->fib6_dst.plen, + offsetof(struct fib6_info, fib6_dst), allow_create, replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); @@ -1173,7 +1207,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, pn = fn; #ifdef CONFIG_IPV6_SUBTREES - if (rt->rt6i_src.plen) { + if (rt->fib6_src.plen) { struct fib6_node *sn; if (!rcu_access_pointer(fn->subtree)) { @@ -1194,16 +1228,16 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (!sfn) goto failure; - atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref); + atomic_inc(&info->nl_net->ipv6.fib6_null_entry->fib6_ref); rcu_assign_pointer(sfn->leaf, - info->nl_net->ipv6.ip6_null_entry); + info->nl_net->ipv6.fib6_null_entry); sfn->fn_flags = RTN_ROOT; /* Now add the first leaf node to new subtree */ sn = fib6_add_1(info->nl_net, table, sfn, - &rt->rt6i_src.addr, rt->rt6i_src.plen, - offsetof(struct rt6_info, rt6i_src), + &rt->fib6_src.addr, rt->fib6_src.plen, + offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { @@ -1221,8 +1255,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, rcu_assign_pointer(fn->subtree, sfn); } else { sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), - &rt->rt6i_src.addr, rt->rt6i_src.plen, - offsetof(struct rt6_info, rt6i_src), + &rt->fib6_src.addr, rt->fib6_src.plen, + offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { @@ -1235,9 +1269,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (fn->fn_flags & RTN_TL_ROOT) { /* put back null_entry for root node */ rcu_assign_pointer(fn->leaf, - info->nl_net->ipv6.ip6_null_entry); + info->nl_net->ipv6.fib6_null_entry); } else { - atomic_inc(&rt->rt6i_ref); + atomic_inc(&rt->fib6_ref); rcu_assign_pointer(fn->leaf, rt); } } @@ -1245,7 +1279,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, } #endif - err = fib6_add_rt2node(fn, rt, info, mxc, extack); + err = fib6_add_rt2node(fn, rt, info, extack); if (!err) { __fib6_update_sernum_upto_root(rt, sernum); fib6_start_gc(info->nl_net, rt); @@ -1259,13 +1293,13 @@ out: * super-tree leaf node we have to find a new one for it. */ if (pn != fn) { - struct rt6_info *pn_leaf = + struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); if (pn_leaf == rt) { pn_leaf = NULL; RCU_INIT_POINTER(pn->leaf, NULL); - atomic_dec(&rt->rt6i_ref); + fib6_info_release(rt); } if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, @@ -1274,10 +1308,10 @@ out: if (!pn_leaf) { WARN_ON(!pn_leaf); pn_leaf = - info->nl_net->ipv6.ip6_null_entry; + info->nl_net->ipv6.fib6_null_entry; } #endif - atomic_inc(&pn_leaf->rt6i_ref); + fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } } @@ -1299,10 +1333,6 @@ failure: (fn->fn_flags & RTN_TL_ROOT && !rcu_access_pointer(fn->leaf)))) fib6_repair_tree(info->nl_net, table, fn); - /* Always release dst as dst->__refcnt is guaranteed - * to be taken before entering this function - */ - dst_release_immediate(&rt->dst); return err; } @@ -1312,12 +1342,12 @@ failure: */ struct lookup_args { - int offset; /* key offset on rt6_info */ + int offset; /* key offset on fib6_info */ 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_node_lookup_1(struct fib6_node *root, + struct lookup_args *args) { struct fib6_node *fn; __be32 dir; @@ -1350,7 +1380,7 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree || fn->fn_flags & RTN_RTINFO) { - struct rt6_info *leaf = rcu_dereference(fn->leaf); + struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; if (!leaf) @@ -1362,7 +1392,8 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, #ifdef CONFIG_IPV6_SUBTREES if (subtree) { struct fib6_node *sfn; - sfn = fib6_lookup_1(subtree, args + 1); + sfn = fib6_node_lookup_1(subtree, + args + 1); if (!sfn) goto backtrack; fn = sfn; @@ -1384,18 +1415,19 @@ backtrack: /* called with rcu_read_lock() held */ -struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr, - const struct in6_addr *saddr) +struct fib6_node *fib6_node_lookup(struct fib6_node *root, + const struct in6_addr *daddr, + const struct in6_addr *saddr) { struct fib6_node *fn; struct lookup_args args[] = { { - .offset = offsetof(struct rt6_info, rt6i_dst), + .offset = offsetof(struct fib6_info, fib6_dst), .addr = daddr, }, #ifdef CONFIG_IPV6_SUBTREES { - .offset = offsetof(struct rt6_info, rt6i_src), + .offset = offsetof(struct fib6_info, fib6_src), .addr = saddr, }, #endif @@ -1404,7 +1436,7 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad } }; - fn = fib6_lookup_1(root, daddr ? args : args + 1); + fn = fib6_node_lookup_1(root, daddr ? args : args + 1); if (!fn || fn->fn_flags & RTN_TL_ROOT) fn = root; @@ -1431,7 +1463,7 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root, struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { - struct rt6_info *leaf = rcu_dereference(fn->leaf); + struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; /* This node is being deleted */ @@ -1480,7 +1512,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root, struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, - offsetof(struct rt6_info, rt6i_dst), + offsetof(struct fib6_info, fib6_dst), exact_match); #ifdef CONFIG_IPV6_SUBTREES @@ -1491,7 +1523,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root, if (subtree) { fn = fib6_locate_1(subtree, saddr, src_len, - offsetof(struct rt6_info, rt6i_src), + offsetof(struct fib6_info, fib6_src), exact_match); } } @@ -1510,14 +1542,14 @@ struct fib6_node *fib6_locate(struct fib6_node *root, * */ -static struct rt6_info *fib6_find_prefix(struct net *net, +static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn) { struct fib6_node *child_left, *child_right; if (fn->fn_flags & RTN_ROOT) - return net->ipv6.ip6_null_entry; + return net->ipv6.fib6_null_entry; while (fn) { child_left = rcu_dereference_protected(fn->left, @@ -1554,7 +1586,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, /* Set fn->leaf to null_entry for root node. */ if (fn->fn_flags & RTN_TL_ROOT) { - rcu_assign_pointer(fn->leaf, net->ipv6.ip6_null_entry); + rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry); return fn; } @@ -1569,11 +1601,11 @@ static struct fib6_node *fib6_repair_tree(struct net *net, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_l = rcu_dereference_protected(pn->left, lockdep_is_held(&table->tb6_lock)); - struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf, + struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); - struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, + struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); - struct rt6_info *new_fn_leaf; + struct fib6_info *new_fn_leaf; RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; @@ -1599,10 +1631,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net, #if RT6_DEBUG >= 2 if (!new_fn_leaf) { WARN_ON(!new_fn_leaf); - new_fn_leaf = net->ipv6.ip6_null_entry; + new_fn_leaf = net->ipv6.fib6_null_entry; } #endif - atomic_inc(&new_fn_leaf->rt6i_ref); + fib6_info_hold(new_fn_leaf); rcu_assign_pointer(fn->leaf, new_fn_leaf); return pn; } @@ -1658,26 +1690,24 @@ static struct fib6_node *fib6_repair_tree(struct net *net, return pn; RCU_INIT_POINTER(pn->leaf, NULL); - rt6_release(pn_leaf); + fib6_info_release(pn_leaf); fn = pn; } } static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, - struct rt6_info __rcu **rtp, struct nl_info *info) + struct fib6_info __rcu **rtp, struct nl_info *info) { struct fib6_walker *w; - struct rt6_info *rt = rcu_dereference_protected(*rtp, + struct fib6_info *rt = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; RT6_TRACE("fib6_del_route\n"); - WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE); - /* Unlink it */ - *rtp = rt->rt6_next; - rt->rt6i_node = NULL; + *rtp = rt->fib6_next; + rt->fib6_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; @@ -1689,14 +1719,14 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, fn->rr_ptr = NULL; /* Remove this entry from other siblings */ - if (rt->rt6i_nsiblings) { - struct rt6_info *sibling, *next_sibling; + if (rt->fib6_nsiblings) { + struct fib6_info *sibling, *next_sibling; list_for_each_entry_safe(sibling, next_sibling, - &rt->rt6i_siblings, rt6i_siblings) - sibling->rt6i_nsiblings--; - rt->rt6i_nsiblings = 0; - list_del_init(&rt->rt6i_siblings); + &rt->fib6_siblings, fib6_siblings) + sibling->fib6_nsiblings--; + rt->fib6_nsiblings = 0; + list_del_init(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } @@ -1705,7 +1735,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); - w->leaf = rcu_dereference_protected(rt->rt6_next, + w->leaf = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; @@ -1730,46 +1760,36 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); - rt6_release(rt); + fib6_info_release(rt); } /* Need to own table->tb6_lock */ -int fib6_del(struct rt6_info *rt, struct nl_info *info) +int fib6_del(struct fib6_info *rt, struct nl_info *info) { - struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); - struct fib6_table *table = rt->rt6i_table; + struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + struct fib6_table *table = rt->fib6_table; struct net *net = info->nl_net; - struct rt6_info __rcu **rtp; - struct rt6_info __rcu **rtp_next; + struct fib6_info __rcu **rtp; + struct fib6_info __rcu **rtp_next; -#if RT6_DEBUG >= 2 - if (rt->dst.obsolete > 0) { - WARN_ON(fn); - return -ENOENT; - } -#endif - if (!fn || rt == net->ipv6.ip6_null_entry) + if (!fn || rt == net->ipv6.fib6_null_entry) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); - /* remove cached dst from exception table */ - if (rt->rt6i_flags & RTF_CACHE) - return rt6_remove_exception_rt(rt); - /* * Walk the leaf entries looking for ourself */ for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { - struct rt6_info *cur = rcu_dereference_protected(*rtp, + struct fib6_info *cur = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); if (rt == cur) { fib6_del_route(table, fn, rtp, info); return 0; } - rtp_next = &cur->rt6_next; + rtp_next = &cur->fib6_next; } return -ENOENT; } @@ -1907,7 +1927,7 @@ static int fib6_walk(struct net *net, struct fib6_walker *w) static int fib6_clean_node(struct fib6_walker *w) { int res; - struct rt6_info *rt; + struct fib6_info *rt; struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w); struct nl_info info = { .nl_net = c->net, @@ -1932,17 +1952,17 @@ static int fib6_clean_node(struct fib6_walker *w) #if RT6_DEBUG >= 2 pr_debug("%s: del failed: rt=%p@%p err=%d\n", __func__, rt, - rcu_access_pointer(rt->rt6i_node), + rcu_access_pointer(rt->fib6_node), res); #endif continue; } return 0; } else if (res == -2) { - if (WARN_ON(!rt->rt6i_nsiblings)) + if (WARN_ON(!rt->fib6_nsiblings)) continue; - rt = list_last_entry(&rt->rt6i_siblings, - struct rt6_info, rt6i_siblings); + rt = list_last_entry(&rt->fib6_siblings, + struct fib6_info, fib6_siblings); continue; } WARN_ON(res != 0); @@ -1961,7 +1981,7 @@ static int fib6_clean_node(struct fib6_walker *w) */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, - int (*func)(struct rt6_info *, void *arg), + int (*func)(struct fib6_info *, void *arg), int sernum, void *arg) { struct fib6_cleaner c; @@ -1979,7 +1999,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root, } static void __fib6_clean_all(struct net *net, - int (*func)(struct rt6_info *, void *), + int (*func)(struct fib6_info *, void *), int sernum, void *arg) { struct fib6_table *table; @@ -1999,7 +2019,7 @@ static void __fib6_clean_all(struct net *net, rcu_read_unlock(); } -void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *), +void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg); @@ -2016,7 +2036,7 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -static int fib6_age(struct rt6_info *rt, void *arg) +static int fib6_age(struct fib6_info *rt, void *arg) { struct fib6_gc_args *gc_args = arg; unsigned long now = jiffies; @@ -2026,8 +2046,8 @@ static int fib6_age(struct rt6_info *rt, void *arg) * Routes are expired even if they are in use. */ - if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) { - if (time_after(now, rt->dst.expires)) { + if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { + if (time_after(now, rt->expires)) { RT6_TRACE("expiring %p\n", rt); return -1; } @@ -2110,7 +2130,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, - net->ipv6.ip6_null_entry); + net->ipv6.fib6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); @@ -2122,7 +2142,7 @@ static int __net_init fib6_net_init(struct net *net) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, - net->ipv6.ip6_null_entry); + net->ipv6.fib6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); @@ -2211,25 +2231,26 @@ void fib6_gc_cleanup(void) #ifdef CONFIG_PROC_FS static int ipv6_route_seq_show(struct seq_file *seq, void *v) { - struct rt6_info *rt = v; + struct fib6_info *rt = v; struct ipv6_route_iter *iter = seq->private; + const struct net_device *dev; - seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); + seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); #ifdef CONFIG_IPV6_SUBTREES - seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen); + seq_printf(seq, "%pi6 %02x ", &rt->fib6_src.addr, rt->fib6_src.plen); #else seq_puts(seq, "00000000000000000000000000000000 00 "); #endif - if (rt->rt6i_flags & RTF_GATEWAY) - seq_printf(seq, "%pi6", &rt->rt6i_gateway); + if (rt->fib6_flags & RTF_GATEWAY) + seq_printf(seq, "%pi6", &rt->fib6_nh.nh_gw); else seq_puts(seq, "00000000000000000000000000000000"); + dev = rt->fib6_nh.nh_dev; seq_printf(seq, " %08x %08x %08x %08x %8s\n", - rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), - rt->dst.__use, rt->rt6i_flags, - rt->dst.dev ? rt->dst.dev->name : ""); + rt->fib6_metric, atomic_read(&rt->fib6_ref), 0, + rt->fib6_flags, dev ? dev->name : ""); iter->w.leaf = NULL; return 0; } @@ -2243,7 +2264,7 @@ static int ipv6_route_yield(struct fib6_walker *w) do { iter->w.leaf = rcu_dereference_protected( - iter->w.leaf->rt6_next, + iter->w.leaf->fib6_next, lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) @@ -2302,14 +2323,14 @@ static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int r; - struct rt6_info *n; + struct fib6_info *n; struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; if (!v) goto iter_table; - n = rcu_dereference_bh(((struct rt6_info *)v)->rt6_next); + n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); if (n) { ++*pos; return n; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 458de353f5d96..c8cf2fdbb13b8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -848,7 +848,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) } /** - * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own + * ip6gre_tnl_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device * @hdr: IPv6 header from the incoming packet * @@ -937,6 +937,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct flowi6 fl6; int err = -EINVAL; __u32 mtu; + int nhoff; + int thoff; if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; @@ -949,6 +951,16 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, truncate = true; } + nhoff = skb_network_header(skb) - skb_mac_header(skb); + if (skb->protocol == htons(ETH_P_IP) && + (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) + truncate = true; + + thoff = skb_transport_header(skb) - skb_mac_header(skb); + if (skb->protocol == htons(ETH_P_IPV6) && + (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)) + truncate = true; + if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen)) goto tx_err; @@ -1376,6 +1388,7 @@ static void ip6gre_dev_free(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); + gro_cells_destroy(&t->gro_cells); dst_cache_destroy(&t->dst_cache); free_percpu(dev->tstats); } @@ -1443,11 +1456,12 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) return -ENOMEM; ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); - if (ret) { - free_percpu(dev->tstats); - dev->tstats = NULL; - return ret; - } + if (ret) + goto cleanup_alloc_pcpu_stats; + + ret = gro_cells_init(&tunnel->gro_cells, dev); + if (ret) + goto cleanup_dst_cache_init; t_hlen = ip6gre_calc_hlen(tunnel); dev->mtu = ETH_DATA_LEN - t_hlen; @@ -1463,6 +1477,13 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) ip6gre_tnl_init_features(dev); return 0; + +cleanup_dst_cache_init: + dst_cache_destroy(&tunnel->dst_cache); +cleanup_alloc_pcpu_stats: + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; } static int ip6gre_tunnel_init(struct net_device *dev) @@ -1822,11 +1843,12 @@ static int ip6erspan_tap_init(struct net_device *dev) return -ENOMEM; ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); - if (ret) { - free_percpu(dev->tstats); - dev->tstats = NULL; - return ret; - } + if (ret) + goto cleanup_alloc_pcpu_stats; + + ret = gro_cells_init(&tunnel->gro_cells, dev); + if (ret) + goto cleanup_dst_cache_init; t_hlen = ip6erspan_calc_hlen(tunnel); dev->mtu = ETH_DATA_LEN - t_hlen; @@ -1839,6 +1861,13 @@ static int ip6erspan_tap_init(struct net_device *dev) ip6erspan_tnl_link_config(tunnel, 1); return 0; + +cleanup_dst_cache_init: + dst_cache_destroy(&tunnel->dst_cache); +cleanup_alloc_pcpu_stats: + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; } static const struct net_device_ops ip6erspan_netdev_ops = { diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 9ee208a348f55..f08d34491ecee 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -336,7 +336,7 @@ int ip6_mc_input(struct sk_buff *skb) bool deliver; __IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev), - ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INMCAST, + __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST, skb->len); hdr = ipv6_hdr(skb); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 4a87f9428ca51..5b3f2f89ef41c 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -88,9 +88,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6)) - udpfrag = proto == IPPROTO_UDP && encap; + udpfrag = proto == IPPROTO_UDP && encap && + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP); else - udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation && + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP); ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 7b6d1689087bd..021e5aef6ba31 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -383,28 +383,6 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk, return dst_output(net, sk, skb); } -unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) -{ - unsigned int mtu; - struct inet6_dev *idev; - - if (dst_metric_locked(dst, RTAX_MTU)) { - mtu = dst_metric_raw(dst, RTAX_MTU); - if (mtu) - return mtu; - } - - mtu = IPV6_MIN_MTU; - rcu_read_lock(); - idev = __in6_dev_get(dst->dev); - if (idev) - mtu = idev->cnf.mtu6; - rcu_read_unlock(); - - return mtu; -} -EXPORT_SYMBOL_GPL(ip6_dst_mtu_forward); - static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) @@ -425,6 +403,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) int ip6_forward(struct sk_buff *skb) { + struct inet6_dev *idev = __in6_dev_get_safely(skb->dev); struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); @@ -444,8 +423,7 @@ int ip6_forward(struct sk_buff *skb) goto drop; if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INDISCARDS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } @@ -476,8 +454,7 @@ int ip6_forward(struct sk_buff *skb) /* Force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -ETIMEDOUT; @@ -490,15 +467,13 @@ int ip6_forward(struct sk_buff *skb) if (proxied > 0) return ip6_input(skb); else if (proxied < 0) { - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INDISCARDS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } } if (!xfrm6_route_forward(skb)) { - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INDISCARDS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } dst = skb_dst(skb); @@ -507,7 +482,8 @@ int ip6_forward(struct sk_buff *skb) send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ - if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) { + if (IP6CB(skb)->iif == dst->dev->ifindex && + opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct inet_peer *peer; struct rt6_info *rt; @@ -554,8 +530,7 @@ int ip6_forward(struct sk_buff *skb) /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INTOOBIGERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS); __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); @@ -579,7 +554,7 @@ int ip6_forward(struct sk_buff *skb) ip6_forward_finish); error: - __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); drop: kfree_skb(skb); return -EINVAL; @@ -966,15 +941,21 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, * that's why we try it again later. */ if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) { + struct fib6_info *from; struct rt6_info *rt; bool had_dst = *dst != NULL; if (!had_dst) *dst = ip6_route_output(net, sk, fl6); rt = (*dst)->error ? NULL : (struct rt6_info *)*dst; - err = ip6_route_get_saddr(net, rt, &fl6->daddr, + + rcu_read_lock(); + from = rt ? rcu_dereference(rt->from) : NULL; + err = ip6_route_get_saddr(net, from, &fl6->daddr, sk ? inet6_sk(sk)->srcprefs : 0, &fl6->saddr); + rcu_read_unlock(); + if (err) goto out_err_release; @@ -1238,6 +1219,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (mtu < IPV6_MIN_MTU) return -EINVAL; cork->base.fragsize = mtu; + cork->base.gso_size = sk->sk_type == SOCK_DGRAM ? ipc6->gso_size : 0; + if (dst_allfrag(xfrm_dst_path(&rt->dst))) cork->base.flags |= IPCORK_ALLFRAG; cork->base.length = 0; @@ -1272,6 +1255,7 @@ static int __ip6_append_data(struct sock *sk, int csummode = CHECKSUM_NONE; unsigned int maxnonfragsize, headersize; unsigned int wmem_alloc_delta = 0; + bool paged; skb = skb_peek_tail(queue); if (!skb) { @@ -1279,7 +1263,8 @@ static int __ip6_append_data(struct sock *sk, dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } - mtu = cork->fragsize; + paged = !!cork->gso_size; + mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1327,7 +1312,7 @@ emsgsize: if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && headersize == sizeof(struct ipv6hdr) && length <= mtu - headersize && - !(flags & MSG_MORE) && + (!(flags & MSG_MORE) || cork->gso_size) && rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; @@ -1370,6 +1355,7 @@ emsgsize: unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; + unsigned int pagedlen = 0; alloc_new_skb: /* There's no room in the current skb */ if (skb) @@ -1392,11 +1378,17 @@ alloc_new_skb: if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; + fraglen = datalen + fragheaderlen; + if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; - else - alloclen = datalen + fragheaderlen; + else if (!paged) + alloclen = fraglen; + else { + alloclen = min_t(int, fraglen, MAX_HEADER); + pagedlen = fraglen - alloclen; + } alloclen += dst_exthdrlen; @@ -1418,7 +1410,7 @@ alloc_new_skb: */ alloclen += sizeof(struct frag_hdr); - copy = datalen - transhdrlen - fraggap; + copy = datalen - transhdrlen - fraggap - pagedlen; if (copy < 0) { err = -EINVAL; goto error; @@ -1457,7 +1449,7 @@ alloc_new_skb: /* * Find where to start putting bytes */ - data = skb_put(skb, fraglen); + data = skb_put(skb, fraglen - pagedlen); skb_set_network_header(skb, exthdrlen); data += fragheaderlen; skb->transport_header = (skb->network_header + @@ -1480,7 +1472,7 @@ alloc_new_skb: } offset += copy; - length -= datalen - fraggap; + length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; dst_exthdrlen = 0; @@ -1754,9 +1746,9 @@ struct sk_buff *ip6_make_skb(struct sock *sk, void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags, + struct inet_cork_full *cork, const struct sockcm_cookie *sockc) { - struct inet_cork_full cork; struct inet6_cork v6_cork; struct sk_buff_head queue; int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); @@ -1767,27 +1759,27 @@ struct sk_buff *ip6_make_skb(struct sock *sk, __skb_queue_head_init(&queue); - cork.base.flags = 0; - cork.base.addr = 0; - cork.base.opt = NULL; - cork.base.dst = NULL; + cork->base.flags = 0; + cork->base.addr = 0; + cork->base.opt = NULL; + cork->base.dst = NULL; v6_cork.opt = NULL; - err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6); + err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6); if (err) { - ip6_cork_release(&cork, &v6_cork); + ip6_cork_release(cork, &v6_cork); return ERR_PTR(err); } if (ipc6->dontfrag < 0) ipc6->dontfrag = inet6_sk(sk)->dontfrag; - err = __ip6_append_data(sk, fl6, &queue, &cork.base, &v6_cork, + err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork, ¤t->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, flags, ipc6, sockc); if (err) { - __ip6_flush_pending_frames(sk, &queue, &cork, &v6_cork); + __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork); return ERR_PTR(err); } - return __ip6_make_skb(sk, &queue, &cork, &v6_cork); + return __ip6_make_skb(sk, &queue, cork, &v6_cork); } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index ca957dd93a298..b7f28deddaeaf 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -743,7 +743,7 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) } /** - * vti6_tnl_ioctl - configure vti6 tunnels from userspace + * vti6_ioctl - configure vti6 tunnels from userspace * @dev: virtual device associated with tunnel * @ifr: parameters passed from userspace * @cmd: command to be performed diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 4a15529d33eb2..0d0f0053bb115 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -180,7 +180,8 @@ static const struct nla_policy ip6mr_rule_policy[FRA_MAX + 1] = { }; static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, - struct fib_rule_hdr *frh, struct nlattr **tb) + struct fib_rule_hdr *frh, struct nlattr **tb, + struct netlink_ext_ack *extack) { return 0; } @@ -227,8 +228,8 @@ static int __net_init ip6mr_rules_init(struct net *net) INIT_LIST_HEAD(&net->ipv6.mr6_tables); mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); - if (!mrt) { - err = -ENOMEM; + if (IS_ERR(mrt)) { + err = PTR_ERR(mrt); goto err1; } @@ -301,8 +302,13 @@ static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6, static int __net_init ip6mr_rules_init(struct net *net) { - net->ipv6.mrt6 = ip6mr_new_table(net, RT6_TABLE_DFLT); - return net->ipv6.mrt6 ? 0 : -ENOMEM; + struct mr_table *mrt; + + mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); + if (IS_ERR(mrt)) + return PTR_ERR(mrt); + net->ipv6.mrt6 = mrt; + return 0; } static void __net_exit ip6mr_rules_exit(struct net *net) @@ -1733,9 +1739,11 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns rtnl_lock(); ret = 0; - if (!ip6mr_new_table(net, v)) - ret = -ENOMEM; - raw6_sk(sk)->ip6mr_table = v; + mrt = ip6mr_new_table(net, v); + if (IS_ERR(mrt)) + ret = PTR_ERR(mrt); + else + raw6_sk(sk)->ip6mr_table = v; rtnl_unlock(); return ret; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 9de4dfb126ba0..e640d2f3c55cf 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1155,7 +1155,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); struct neighbour *neigh = NULL; struct inet6_dev *in6_dev; - struct rt6_info *rt = NULL; + struct fib6_info *rt = NULL; + struct net *net; int lifetime; struct ndisc_options ndopts; int optlen; @@ -1253,9 +1254,9 @@ static void ndisc_router_discovery(struct sk_buff *skb) /* Do not accept RA with source-addr found on local machine unless * accept_ra_from_local is set to true. */ + net = dev_net(in6_dev->dev); if (!in6_dev->cnf.accept_ra_from_local && - ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, - in6_dev->dev, 0)) { + ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: default router ignored\n", skb->dev->name); @@ -1272,20 +1273,22 @@ static void ndisc_router_discovery(struct sk_buff *skb) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif - rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev); + rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev); if (rt) { - neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); + neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw, + rt->fib6_nh.nh_dev, NULL, + &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); - ip6_rt_put(rt); + fib6_info_release(rt); return; } } if (rt && lifetime == 0) { - ip6_del_rt(rt); + ip6_del_rt(net, rt); rt = NULL; } @@ -1294,7 +1297,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); - rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref); + rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, + skb->dev, pref); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", @@ -1302,28 +1306,29 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); + neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw, + rt->fib6_nh.nh_dev, NULL, + &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); - ip6_rt_put(rt); + fib6_info_release(rt); return; } neigh->flags |= NTF_ROUTER; } else if (rt) { - rt->rt6i_flags = (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); + rt->fib6_flags = (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); } if (rt) - rt6_set_expires(rt, jiffies + (HZ * lifetime)); + fib6_set_expires(rt, jiffies + (HZ * lifetime)); if (in6_dev->cnf.accept_ra_min_hop_limit < 256 && ra_msg->icmph.icmp6_hop_limit) { if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; - if (rt) - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, - ra_msg->icmph.icmp6_hop_limit); + fib6_metric_set(rt, RTAX_HOPLIMIT, + ra_msg->icmph.icmp6_hop_limit); } else { ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n"); } @@ -1475,10 +1480,7 @@ skip_routeinfo: ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); } else if (in6_dev->cnf.mtu6 != mtu) { in6_dev->cnf.mtu6 = mtu; - - if (rt) - dst_metric_set(&rt->dst, RTAX_MTU, mtu); - + fib6_metric_set(rt, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } } @@ -1497,7 +1499,7 @@ skip_routeinfo: ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: - ip6_rt_put(rt); + fib6_info_release(rt); if (neigh) neigh_release(neigh); } @@ -1576,6 +1578,12 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL; bool ret; + if (netif_is_l3_master(skb->dev)) { + dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); + if (!dev) + return; + } + if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n", dev->name); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index ce77bcc2490c2..37b14dc9d8638 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -29,7 +29,10 @@ config NF_SOCKET_IPV6 tristate "IPv6 socket lookup support" help This option enables the IPv6 socket lookup infrastructure. This - is used by the ip6tables socket match. + is used by the {ip6,nf}tables socket match. + +config NF_TPROXY_IPV6 + tristate "IPv6 tproxy support" if NF_TABLES @@ -136,10 +139,7 @@ config NF_NAT_IPV6 if NF_NAT_IPV6 config NF_NAT_MASQUERADE_IPV6 - tristate "IPv6 masquerade support" - help - This is the kernel functionality to provide NAT in the masquerade - flavour (automatic source address selection) for IPv6. + bool endif # NF_NAT_IPV6 diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 44273d6f03a57..10a5a1c873208 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -18,14 +18,15 @@ nf_conntrack_ipv6-y := nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_nat_ipv6-y := nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o +nf_nat_ipv6-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o -obj-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o # defrag nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o obj-$(CONFIG_NF_SOCKET_IPV6) += nf_socket_ipv6.o +obj-$(CONFIG_NF_TPROXY_IPV6) += nf_tproxy_ipv6.o # logging obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 97f79dc943d79..0758b5bcfb290 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -529,7 +529,6 @@ static int check_target(struct ip6t_entry *e, struct net *net, const char *name) .family = NFPROTO_IPV6, }; - t = ip6t_get_target(e); return xt_check_target(&par, t->u.target_size - sizeof(*t), e->ipv6.proto, e->ipv6.invflags & IP6T_INV_PROTO); @@ -1794,6 +1793,8 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, /* set res now, will see skbs right after nf_register_net_hooks */ WRITE_ONCE(*res, new_table); + if (!ops) + return 0; ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); if (ret != 0) { @@ -1811,7 +1812,8 @@ out_free: void ip6t_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { - nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); + if (ops) + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); __ip6t_unregister_table(net, table); } diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 92c0047e7e33d..491f808e356a6 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -29,7 +29,7 @@ masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par) static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par) { - const struct nf_nat_range *range = par->targinfo; + const struct nf_nat_range2 *range = par->targinfo; if (range->flags & NF_NAT_RANGE_MAP_IPS) return -EINVAL; diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index d12f511929f53..0fe61ede77c67 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -48,6 +48,8 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, } fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; + if ((flags & XT_RPFILTER_LOOSE) == 0) + fl6.flowi6_oif = dev->ifindex; rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags); if (rt->dst.error) diff --git a/net/ipv6/netfilter/ip6t_srh.c b/net/ipv6/netfilter/ip6t_srh.c index 33719d5560c8a..1059894a6f4c3 100644 --- a/net/ipv6/netfilter/ip6t_srh.c +++ b/net/ipv6/netfilter/ip6t_srh.c @@ -117,6 +117,130 @@ static bool srh_mt6(const struct sk_buff *skb, struct xt_action_param *par) return true; } +static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + int hdrlen, psidoff, nsidoff, lsidoff, srhoff = 0; + const struct ip6t_srh1 *srhinfo = par->matchinfo; + struct in6_addr *psid, *nsid, *lsid; + struct in6_addr _psid, _nsid, _lsid; + struct ipv6_sr_hdr *srh; + struct ipv6_sr_hdr _srh; + + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + return false; + srh = skb_header_pointer(skb, srhoff, sizeof(_srh), &_srh); + if (!srh) + return false; + + hdrlen = ipv6_optlen(srh); + if (skb->len - srhoff < hdrlen) + return false; + + if (srh->type != IPV6_SRCRT_TYPE_4) + return false; + + if (srh->segments_left > srh->first_segment) + return false; + + /* Next Header matching */ + if (srhinfo->mt_flags & IP6T_SRH_NEXTHDR) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NEXTHDR, + !(srh->nexthdr == srhinfo->next_hdr))) + return false; + + /* Header Extension Length matching */ + if (srhinfo->mt_flags & IP6T_SRH_LEN_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_EQ, + !(srh->hdrlen == srhinfo->hdr_len))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LEN_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_GT, + !(srh->hdrlen > srhinfo->hdr_len))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LEN_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_LT, + !(srh->hdrlen < srhinfo->hdr_len))) + return false; + + /* Segments Left matching */ + if (srhinfo->mt_flags & IP6T_SRH_SEGS_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_EQ, + !(srh->segments_left == srhinfo->segs_left))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_SEGS_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_GT, + !(srh->segments_left > srhinfo->segs_left))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_SEGS_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_LT, + !(srh->segments_left < srhinfo->segs_left))) + return false; + + /** + * Last Entry matching + * Last_Entry field was introduced in revision 6 of the SRH draft. + * It was called First_Segment in the previous revision + */ + if (srhinfo->mt_flags & IP6T_SRH_LAST_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_EQ, + !(srh->first_segment == srhinfo->last_entry))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LAST_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_GT, + !(srh->first_segment > srhinfo->last_entry))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LAST_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_LT, + !(srh->first_segment < srhinfo->last_entry))) + return false; + + /** + * Tag matchig + * Tag field was introduced in revision 6 of the SRH draft + */ + if (srhinfo->mt_flags & IP6T_SRH_TAG) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_TAG, + !(srh->tag == srhinfo->tag))) + return false; + + /* Previous SID matching */ + if (srhinfo->mt_flags & IP6T_SRH_PSID) { + if (srh->segments_left == srh->first_segment) + return false; + psidoff = srhoff + sizeof(struct ipv6_sr_hdr) + + ((srh->segments_left + 1) * sizeof(struct in6_addr)); + psid = skb_header_pointer(skb, psidoff, sizeof(_psid), &_psid); + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_PSID, + ipv6_masked_addr_cmp(psid, &srhinfo->psid_msk, + &srhinfo->psid_addr))) + return false; + } + + /* Next SID matching */ + if (srhinfo->mt_flags & IP6T_SRH_NSID) { + if (srh->segments_left == 0) + return false; + nsidoff = srhoff + sizeof(struct ipv6_sr_hdr) + + ((srh->segments_left - 1) * sizeof(struct in6_addr)); + nsid = skb_header_pointer(skb, nsidoff, sizeof(_nsid), &_nsid); + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NSID, + ipv6_masked_addr_cmp(nsid, &srhinfo->nsid_msk, + &srhinfo->nsid_addr))) + return false; + } + + /* Last SID matching */ + if (srhinfo->mt_flags & IP6T_SRH_LSID) { + lsidoff = srhoff + sizeof(struct ipv6_sr_hdr); + lsid = skb_header_pointer(skb, lsidoff, sizeof(_lsid), &_lsid); + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LSID, + ipv6_masked_addr_cmp(lsid, &srhinfo->lsid_msk, + &srhinfo->lsid_addr))) + return false; + } + return true; +} + static int srh_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_srh *srhinfo = par->matchinfo; @@ -136,23 +260,54 @@ static int srh_mt6_check(const struct xt_mtchk_param *par) return 0; } -static struct xt_match srh_mt6_reg __read_mostly = { - .name = "srh", - .family = NFPROTO_IPV6, - .match = srh_mt6, - .matchsize = sizeof(struct ip6t_srh), - .checkentry = srh_mt6_check, - .me = THIS_MODULE, +static int srh1_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_srh1 *srhinfo = par->matchinfo; + + if (srhinfo->mt_flags & ~IP6T_SRH_MASK) { + pr_info_ratelimited("unknown srh match flags %X\n", + srhinfo->mt_flags); + return -EINVAL; + } + + if (srhinfo->mt_invflags & ~IP6T_SRH_INV_MASK) { + pr_info_ratelimited("unknown srh invflags %X\n", + srhinfo->mt_invflags); + return -EINVAL; + } + + return 0; +} + +static struct xt_match srh_mt6_reg[] __read_mostly = { + { + .name = "srh", + .revision = 0, + .family = NFPROTO_IPV6, + .match = srh_mt6, + .matchsize = sizeof(struct ip6t_srh), + .checkentry = srh_mt6_check, + .me = THIS_MODULE, + }, + { + .name = "srh", + .revision = 1, + .family = NFPROTO_IPV6, + .match = srh1_mt6, + .matchsize = sizeof(struct ip6t_srh1), + .checkentry = srh1_mt6_check, + .me = THIS_MODULE, + } }; static int __init srh_mt6_init(void) { - return xt_register_match(&srh_mt6_reg); + return xt_register_matches(srh_mt6_reg, ARRAY_SIZE(srh_mt6_reg)); } static void __exit srh_mt6_exit(void) { - xt_unregister_match(&srh_mt6_reg); + xt_unregister_matches(srh_mt6_reg, ARRAY_SIZE(srh_mt6_reg)); } module_init(srh_mt6_init); diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 47306e45a80ab..67ba70ab9f5c0 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -35,75 +35,63 @@ static const struct xt_table nf_nat_ipv6_table = { static unsigned int ip6table_nat_do_chain(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct) -{ - return ip6t_do_table(skb, state, state->net->ipv6.ip6table_nat); -} - -static unsigned int ip6table_nat_fn(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv6_fn(priv, skb, state, ip6table_nat_do_chain); -} - -static unsigned int ip6table_nat_in(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv6_in(priv, skb, state, ip6table_nat_do_chain); -} - -static unsigned int ip6table_nat_out(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv6_out(priv, skb, state, ip6table_nat_do_chain); -} - -static unsigned int ip6table_nat_local_fn(void *priv, - struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_local_fn(priv, skb, state, ip6table_nat_do_chain); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_nat); } static const struct nf_hook_ops nf_nat_ipv6_ops[] = { - /* Before packet filtering, change destination */ { - .hook = ip6table_nat_in, + .hook = ip6table_nat_do_chain, .pf = NFPROTO_IPV6, - .nat_hook = true, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, - /* After packet filtering, change source */ { - .hook = ip6table_nat_out, + .hook = ip6table_nat_do_chain, .pf = NFPROTO_IPV6, - .nat_hook = true, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, - /* Before packet filtering, change destination */ { - .hook = ip6table_nat_local_fn, + .hook = ip6table_nat_do_chain, .pf = NFPROTO_IPV6, - .nat_hook = true, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, - /* After packet filtering, change source */ { - .hook = ip6table_nat_fn, - .nat_hook = true, + .hook = ip6table_nat_do_chain, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, }, }; +static int ip6t_nat_register_lookups(struct net *net) +{ + int i, ret; + + for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) { + ret = nf_nat_l3proto_ipv6_register_fn(net, &nf_nat_ipv6_ops[i]); + if (ret) { + while (i) + nf_nat_l3proto_ipv6_unregister_fn(net, &nf_nat_ipv6_ops[--i]); + + return ret; + } + } + + return 0; +} + +static void ip6t_nat_unregister_lookups(struct net *net) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(nf_nat_ipv6_ops); i++) + nf_nat_l3proto_ipv6_unregister_fn(net, &nf_nat_ipv6_ops[i]); +} + static int __net_init ip6table_nat_table_init(struct net *net) { struct ip6t_replace *repl; @@ -116,7 +104,17 @@ static int __net_init ip6table_nat_table_init(struct net *net) if (repl == NULL) return -ENOMEM; ret = ip6t_register_table(net, &nf_nat_ipv6_table, repl, - nf_nat_ipv6_ops, &net->ipv6.ip6table_nat); + NULL, &net->ipv6.ip6table_nat); + if (ret < 0) { + kfree(repl); + return ret; + } + + ret = ip6t_nat_register_lookups(net); + if (ret < 0) { + ip6t_unregister_table(net, net->ipv6.ip6table_nat, NULL); + net->ipv6.ip6table_nat = NULL; + } kfree(repl); return ret; } @@ -125,7 +123,8 @@ static void __net_exit ip6table_nat_net_exit(struct net *net) { if (!net->ipv6.ip6table_nat) return; - ip6t_unregister_table(net, net->ipv6.ip6table_nat, nf_nat_ipv6_ops); + ip6t_nat_unregister_lookups(net); + ip6t_unregister_table(net, net->ipv6.ip6table_nat, NULL); net->ipv6.ip6table_nat = NULL; } diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index 207cb35569b1c..c511d206bf9bd 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -3,256 +3,12 @@ #include <linux/module.h> #include <linux/netfilter.h> #include <linux/rhashtable.h> -#include <linux/ipv6.h> -#include <linux/netdevice.h> -#include <net/ipv6.h> -#include <net/ip6_route.h> -#include <net/neighbour.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_tables.h> -/* For layer 4 checksum field offset. */ -#include <linux/tcp.h> -#include <linux/udp.h> - -static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff, - struct in6_addr *addr, - struct in6_addr *new_addr) -{ - struct tcphdr *tcph; - - if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || - skb_try_make_writable(skb, thoff + sizeof(*tcph))) - return -1; - - tcph = (void *)(skb_network_header(skb) + thoff); - inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32, - new_addr->s6_addr32, true); - - return 0; -} - -static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, - struct in6_addr *addr, - struct in6_addr *new_addr) -{ - struct udphdr *udph; - - if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || - skb_try_make_writable(skb, thoff + sizeof(*udph))) - return -1; - - udph = (void *)(skb_network_header(skb) + thoff); - if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { - inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32, - new_addr->s6_addr32, true); - if (!udph->check) - udph->check = CSUM_MANGLED_0; - } - - return 0; -} - -static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, struct in6_addr *addr, - struct in6_addr *new_addr) -{ - switch (ip6h->nexthdr) { - case IPPROTO_TCP: - if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; - break; - case IPPROTO_UDP: - if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; - break; - } - - return 0; -} - -static int nf_flow_snat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, - enum flow_offload_tuple_dir dir) -{ - struct in6_addr addr, new_addr; - - switch (dir) { - case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = ip6h->saddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6; - ip6h->saddr = new_addr; - break; - case FLOW_OFFLOAD_DIR_REPLY: - addr = ip6h->daddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6; - ip6h->daddr = new_addr; - break; - default: - return -1; - } - - return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); -} - -static int nf_flow_dnat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, - enum flow_offload_tuple_dir dir) -{ - struct in6_addr addr, new_addr; - - switch (dir) { - case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = ip6h->daddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6; - ip6h->daddr = new_addr; - break; - case FLOW_OFFLOAD_DIR_REPLY: - addr = ip6h->saddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6; - ip6h->saddr = new_addr; - break; - default: - return -1; - } - - return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); -} - -static int nf_flow_nat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, - enum flow_offload_tuple_dir dir) -{ - struct ipv6hdr *ip6h = ipv6_hdr(skb); - unsigned int thoff = sizeof(*ip6h); - - if (flow->flags & FLOW_OFFLOAD_SNAT && - (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || - nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) - return -1; - if (flow->flags & FLOW_OFFLOAD_DNAT && - (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || - nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) - return -1; - - return 0; -} - -static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, - struct flow_offload_tuple *tuple) -{ - struct flow_ports *ports; - struct ipv6hdr *ip6h; - unsigned int thoff; - - if (!pskb_may_pull(skb, sizeof(*ip6h))) - return -1; - - ip6h = ipv6_hdr(skb); - - if (ip6h->nexthdr != IPPROTO_TCP && - ip6h->nexthdr != IPPROTO_UDP) - return -1; - - thoff = sizeof(*ip6h); - if (!pskb_may_pull(skb, thoff + sizeof(*ports))) - return -1; - - ports = (struct flow_ports *)(skb_network_header(skb) + thoff); - - tuple->src_v6 = ip6h->saddr; - tuple->dst_v6 = ip6h->daddr; - tuple->src_port = ports->source; - tuple->dst_port = ports->dest; - tuple->l3proto = AF_INET6; - tuple->l4proto = ip6h->nexthdr; - tuple->iifidx = dev->ifindex; - - return 0; -} - -/* Based on ip_exceeds_mtu(). */ -static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) -{ - if (skb->len <= mtu) - return false; - - if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) - return false; - - return true; -} - -static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rt6_info *rt) -{ - u32 mtu; - - mtu = ip6_dst_mtu_forward(&rt->dst); - if (__nf_flow_exceeds_mtu(skb, mtu)) - return true; - - return false; -} - -unsigned int -nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct flow_offload_tuple_rhash *tuplehash; - struct nf_flowtable *flow_table = priv; - struct flow_offload_tuple tuple = {}; - enum flow_offload_tuple_dir dir; - struct flow_offload *flow; - struct net_device *outdev; - struct in6_addr *nexthop; - struct ipv6hdr *ip6h; - struct rt6_info *rt; - - if (skb->protocol != htons(ETH_P_IPV6)) - return NF_ACCEPT; - - if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0) - return NF_ACCEPT; - - tuplehash = flow_offload_lookup(flow_table, &tuple); - if (tuplehash == NULL) - return NF_ACCEPT; - - outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx); - if (!outdev) - return NF_ACCEPT; - - dir = tuplehash->tuple.dir; - flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - - rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache; - if (unlikely(nf_flow_exceeds_mtu(skb, rt))) - return NF_ACCEPT; - - if (skb_try_make_writable(skb, sizeof(*ip6h))) - return NF_DROP; - - if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) && - nf_flow_nat_ipv6(flow, skb, dir) < 0) - return NF_DROP; - - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; - ip6h = ipv6_hdr(skb); - ip6h->hop_limit--; - - skb->dev = outdev; - nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); - neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb); - - return NF_STOLEN; -} -EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook); static struct nf_flowtable_type flowtable_ipv6 = { .family = NFPROTO_IPV6, - .params = &nf_flow_offload_rhash_params, - .gc = nf_flow_offload_work_gc, + .init = nf_flow_table_init, .free = nf_flow_table_free, .hook = nf_flow_offload_ipv6_hook, .owner = THIS_MODULE, diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 6b7f075f811f2..ca6d38698b1ad 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -62,7 +62,7 @@ static void nf_nat_ipv6_decode_session(struct sk_buff *skb, #endif static bool nf_nat_ipv6_in_range(const struct nf_conntrack_tuple *t, - const struct nf_nat_range *range) + const struct nf_nat_range2 *range) { return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 && ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0; @@ -151,7 +151,7 @@ static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range *range) + struct nf_nat_range2 *range) { if (tb[CTA_NAT_V6_MINIP]) { nla_memcpy(&range->min_addr.ip6, tb[CTA_NAT_V6_MINIP], @@ -252,18 +252,12 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); -unsigned int +static unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - unsigned int (*do_chain)(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; - struct nf_conn_nat *nat; - enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook); __be16 frag_off; int hdrlen; u8 nexthdr; @@ -277,11 +271,7 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, if (!ct) return NF_ACCEPT; - nat = nfct_nat(ct); - - switch (ctinfo) { - case IP_CT_RELATED: - case IP_CT_RELATED_REPLY: + if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { nexthdr = ipv6_hdr(skb)->nexthdr; hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); @@ -294,77 +284,29 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, else return NF_ACCEPT; } - /* Only ICMPs can be IP_CT_IS_REPLY: */ - /* fall through */ - case IP_CT_NEW: - /* Seen it before? This can happen for loopback, retrans, - * or local packets. - */ - if (!nf_nat_initialized(ct, maniptype)) { - unsigned int ret; - - ret = do_chain(priv, skb, state, ct); - if (ret != NF_ACCEPT) - return ret; - - if (nf_nat_initialized(ct, HOOK2MANIP(state->hook))) - break; - - ret = nf_nat_alloc_null_binding(ct, state->hook); - if (ret != NF_ACCEPT) - return ret; - } else { - pr_debug("Already setup manip %s for ct %p\n", - maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", - ct); - if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) - goto oif_changed; - } - break; - - default: - /* ESTABLISHED */ - WARN_ON(ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) - goto oif_changed; } - return nf_nat_packet(ct, ctinfo, state->hook, skb); - -oif_changed: - nf_ct_kill_acct(ct, ctinfo, skb); - return NF_DROP; + return nf_nat_inet_fn(priv, skb, state); } -EXPORT_SYMBOL_GPL(nf_nat_ipv6_fn); -unsigned int +static unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - unsigned int (*do_chain)(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state) { unsigned int ret; struct in6_addr daddr = ipv6_hdr(skb)->daddr; - ret = nf_nat_ipv6_fn(priv, skb, state, do_chain); + ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_DROP && ret != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); return ret; } -EXPORT_SYMBOL_GPL(nf_nat_ipv6_in); -unsigned int +static unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - unsigned int (*do_chain)(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; @@ -373,7 +315,7 @@ nf_nat_ipv6_out(void *priv, struct sk_buff *skb, #endif unsigned int ret; - ret = nf_nat_ipv6_fn(priv, skb, state, do_chain); + ret = nf_nat_ipv6_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && @@ -393,22 +335,17 @@ nf_nat_ipv6_out(void *priv, struct sk_buff *skb, #endif return ret; } -EXPORT_SYMBOL_GPL(nf_nat_ipv6_out); -unsigned int +static unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - unsigned int (*do_chain)(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; - ret = nf_nat_ipv6_fn(priv, skb, state, do_chain); + ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -432,7 +369,49 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, } return ret; } -EXPORT_SYMBOL_GPL(nf_nat_ipv6_local_fn); + +static const struct nf_hook_ops nf_nat_ipv6_ops[] = { + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv6_in, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP6_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv6_out, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_NAT_SRC, + }, + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv6_local_fn, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP6_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv6_fn, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP6_PRI_NAT_SRC, + }, +}; + +int nf_nat_l3proto_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops) +{ + return nf_nat_register_fn(net, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); +} +EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv6_register_fn); + +void nf_nat_l3proto_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops) +{ + nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); +} +EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv6_unregister_fn); static int __init nf_nat_l3proto_ipv6_init(void) { diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 98f61fcb91088..e6eb7cf9b54fd 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -10,7 +10,6 @@ */ #include <linux/kernel.h> -#include <linux/module.h> #include <linux/atomic.h> #include <linux/netdevice.h> #include <linux/ipv6.h> @@ -26,14 +25,14 @@ static atomic_t v6_worker_count; unsigned int -nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, +nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, const struct net_device *out) { enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; struct in6_addr src; struct nf_conn *ct; - struct nf_nat_range newrange; + struct nf_nat_range2 newrange; ct = nf_ct_get(skb, &ctinfo); WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || @@ -186,6 +185,3 @@ void nf_nat_masquerade_ipv6_unregister_notifier(void) unregister_netdevice_notifier(&masq_dev_notifier); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c index 57593b00c5b43..d9bf42ba44fa1 100644 --- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c @@ -32,7 +32,7 @@ icmpv6_in_range(const struct nf_conntrack_tuple *tuple, static void icmpv6_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c new file mode 100644 index 0000000000000..bf1d6c421e3bd --- /dev/null +++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c @@ -0,0 +1,146 @@ +#include <net/netfilter/nf_tproxy.h> +#include <linux/module.h> +#include <net/inet6_hashtables.h> +#include <net/addrconf.h> +#include <net/udp.h> +#include <net/tcp.h> + +const struct in6_addr * +nf_tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr, + const struct in6_addr *daddr) +{ + struct inet6_dev *indev; + struct inet6_ifaddr *ifa; + struct in6_addr *laddr; + + if (!ipv6_addr_any(user_laddr)) + return user_laddr; + laddr = NULL; + + indev = __in6_dev_get(skb->dev); + if (indev) { + read_lock_bh(&indev->lock); + list_for_each_entry(ifa, &indev->addr_list, if_list) { + if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED)) + continue; + + laddr = &ifa->addr; + break; + } + read_unlock_bh(&indev->lock); + } + + return laddr ? laddr : daddr; +} +EXPORT_SYMBOL_GPL(nf_tproxy_laddr6); + +struct sock * +nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, + struct net *net, + const struct in6_addr *laddr, + const __be16 lport, + struct sock *sk) +{ + const struct ipv6hdr *iph = ipv6_hdr(skb); + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); + if (hp == NULL) { + inet_twsk_put(inet_twsk(sk)); + return NULL; + } + + if (hp->syn && !hp->rst && !hp->ack && !hp->fin) { + /* SYN to a TIME_WAIT socket, we'd rather redirect it + * to a listener socket if there's one */ + struct sock *sk2; + + sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, hp, tproto, + &iph->saddr, + nf_tproxy_laddr6(skb, laddr, &iph->daddr), + hp->source, + lport ? lport : hp->dest, + skb->dev, NF_TPROXY_LOOKUP_LISTENER); + if (sk2) { + inet_twsk_deschedule_put(inet_twsk(sk)); + sk = sk2; + } + } + + return sk; +} +EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait6); + +struct sock * +nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, + const u8 protocol, + const struct in6_addr *saddr, const struct in6_addr *daddr, + const __be16 sport, const __be16 dport, + const struct net_device *in, + const enum nf_tproxy_lookup_t lookup_type) +{ + struct sock *sk; + struct tcphdr *tcph; + + switch (protocol) { + case IPPROTO_TCP: + switch (lookup_type) { + case NF_TPROXY_LOOKUP_LISTENER: + tcph = hp; + sk = inet6_lookup_listener(net, &tcp_hashinfo, skb, + thoff + __tcp_hdrlen(tcph), + saddr, sport, + daddr, ntohs(dport), + in->ifindex, 0); + + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + break; + case NF_TPROXY_LOOKUP_ESTABLISHED: + sk = __inet6_lookup_established(net, &tcp_hashinfo, + saddr, sport, daddr, ntohs(dport), + in->ifindex, 0); + break; + default: + BUG(); + } + break; + case IPPROTO_UDP: + sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, + in->ifindex); + if (sk) { + int connected = (sk->sk_state == TCP_ESTABLISHED); + int wildcard = ipv6_addr_any(&sk->sk_v6_rcv_saddr); + + /* NOTE: we return listeners even if bound to + * 0.0.0.0, those are filtered out in + * xt_socket, since xt_TPROXY needs 0 bound + * listeners too + */ + if ((lookup_type == NF_TPROXY_LOOKUP_ESTABLISHED && (!connected || wildcard)) || + (lookup_type == NF_TPROXY_LOOKUP_LISTENER && connected)) { + sock_put(sk); + sk = NULL; + } + } + break; + default: + WARN_ON(1); + sk = NULL; + } + + pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n", + protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk); + + return sk; +} +EXPORT_SYMBOL_GPL(nf_tproxy_get_sock_v6); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs"); +MODULE_DESCRIPTION("Netfilter IPv4 transparent proxy support"); diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c index 3557b114446c9..8a081ad7d5db8 100644 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -26,8 +26,7 @@ static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct) + const struct nf_hook_state *state) { struct nft_pktinfo pkt; @@ -37,42 +36,14 @@ static unsigned int nft_nat_do_chain(void *priv, return nft_do_chain(&pkt, priv); } -static unsigned int nft_nat_ipv6_fn(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv6_fn(priv, skb, state, nft_nat_do_chain); -} - -static unsigned int nft_nat_ipv6_in(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv6_in(priv, skb, state, nft_nat_do_chain); -} - -static unsigned int nft_nat_ipv6_out(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv6_out(priv, skb, state, nft_nat_do_chain); -} - -static unsigned int nft_nat_ipv6_local_fn(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return nf_nat_ipv6_local_fn(priv, skb, state, nft_nat_do_chain); -} - -static int nft_nat_ipv6_init(struct nft_ctx *ctx) +static int nft_nat_ipv6_reg(struct net *net, const struct nf_hook_ops *ops) { - return nf_ct_netns_get(ctx->net, ctx->family); + return nf_nat_l3proto_ipv6_register_fn(net, ops); } -static void nft_nat_ipv6_free(struct nft_ctx *ctx) +static void nft_nat_ipv6_unreg(struct net *net, const struct nf_hook_ops *ops) { - nf_ct_netns_put(ctx->net, ctx->family); + nf_nat_l3proto_ipv6_unregister_fn(net, ops); } static const struct nft_chain_type nft_chain_nat_ipv6 = { @@ -85,13 +56,13 @@ static const struct nft_chain_type nft_chain_nat_ipv6 = { (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .hooks = { - [NF_INET_PRE_ROUTING] = nft_nat_ipv6_in, - [NF_INET_POST_ROUTING] = nft_nat_ipv6_out, - [NF_INET_LOCAL_OUT] = nft_nat_ipv6_local_fn, - [NF_INET_LOCAL_IN] = nft_nat_ipv6_fn, + [NF_INET_PRE_ROUTING] = nft_nat_do_chain, + [NF_INET_POST_ROUTING] = nft_nat_do_chain, + [NF_INET_LOCAL_OUT] = nft_nat_do_chain, + [NF_INET_LOCAL_IN] = nft_nat_do_chain, }, - .init = nft_nat_ipv6_init, - .free = nft_nat_ipv6_free, + .ops_register = nft_nat_ipv6_reg, + .ops_unregister = nft_nat_ipv6_unreg, }; static int __init nft_chain_nat_ipv6_init(void) diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c index 4146536e9c151..dd0122f3cffea 100644 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -22,7 +22,7 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_masq *priv = nft_expr_priv(expr); - struct nf_nat_range range; + struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); range.flags = priv->flags; diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c index a27e424f690d6..74269865acc84 100644 --- a/net/ipv6/netfilter/nft_redir_ipv6.c +++ b/net/ipv6/netfilter/nft_redir_ipv6.c @@ -22,7 +22,7 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_redir *priv = nft_expr_priv(expr); - struct nf_nat_range range; + struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); if (priv->sreg_proto_min) { diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 4979610287e26..b939b94e7e91d 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -163,7 +163,8 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif) } static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, - struct frag_hdr *fhdr, int nhoff) + struct frag_hdr *fhdr, int nhoff, + u32 *prob_offset) { struct sk_buff *prev, *next; struct net_device *dev; @@ -179,11 +180,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, - ((u8 *)&fhdr->frag_off - - skb_network_header(skb))); + *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb); return -1; } @@ -214,10 +211,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, /* RFC2460 says always send parameter problem in * this case. -DaveM */ - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, - offsetof(struct ipv6hdr, payload_len)); + *prob_offset = offsetof(struct ipv6hdr, payload_len); return -1; } if (end > fq->q.len) { @@ -519,15 +513,22 @@ static int ipv6_frag_rcv(struct sk_buff *skb) iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { + u32 prob_offset = 0; int ret; spin_lock(&fq->q.lock); fq->iif = iif; - ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff); + ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff, + &prob_offset); spin_unlock(&fq->q.lock); inet_frag_put(&fq->q); + if (prob_offset) { + __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset); + } return ret; } @@ -536,7 +537,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return -1; fail_hdr: - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb)); return -1; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a6598762d2c17..fb956989adaf4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -63,14 +63,20 @@ #include <net/lwtunnel.h> #include <net/ip_tunnels.h> #include <net/l3mdev.h> -#include <trace/events/fib6.h> - +#include <net/ip.h> #include <linux/uaccess.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif +static int ip6_rt_type_to_error(u8 fib6_type); + +#define CREATE_TRACE_POINTS +#include <trace/events/fib6.h> +EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup); +#undef CREATE_TRACE_POINTS + enum rt6_nud_state { RT6_NUD_FAIL_HARD = -3, RT6_NUD_FAIL_PROBE = -2, @@ -78,7 +84,6 @@ enum rt6_nud_state { RT6_NUD_SUCCEED = 1 }; -static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); static unsigned int ip6_mtu(const struct dst_entry *dst); @@ -97,25 +102,24 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); -static void rt6_dst_from_metrics_check(struct rt6_info *rt); -static int rt6_score_route(struct rt6_info *rt, int oif, int strict); -static size_t rt6_nlmsg_size(struct rt6_info *rt); -static int rt6_fill_node(struct net *net, - struct sk_buff *skb, struct rt6_info *rt, - struct in6_addr *dst, struct in6_addr *src, +static int rt6_score_route(struct fib6_info *rt, int oif, int strict); +static size_t rt6_nlmsg_size(struct fib6_info *rt); +static int rt6_fill_node(struct net *net, struct sk_buff *skb, + struct fib6_info *rt, struct dst_entry *dst, + struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); -static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, +static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt, struct in6_addr *daddr, struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO -static struct rt6_info *rt6_add_route_info(struct net *net, +static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref); -static struct rt6_info *rt6_get_route_info(struct net *net, +static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev); @@ -184,29 +188,10 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) } } -static u32 *rt6_pcpu_cow_metrics(struct rt6_info *rt) -{ - return dst_metrics_write_ptr(&rt->from->dst); -} - -static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) -{ - struct rt6_info *rt = (struct rt6_info *)dst; - - if (rt->rt6i_flags & RTF_PCPU) - return rt6_pcpu_cow_metrics(rt); - else if (rt->rt6i_flags & RTF_CACHE) - return NULL; - else - return dst_cow_metrics_generic(dst, old); -} - -static inline const void *choose_neigh_daddr(struct rt6_info *rt, +static inline const void *choose_neigh_daddr(const struct in6_addr *p, struct sk_buff *skb, const void *daddr) { - struct in6_addr *p = &rt->rt6i_gateway; - if (!ipv6_addr_any(p)) return (const void *) p; else if (skb) @@ -214,18 +199,27 @@ static inline const void *choose_neigh_daddr(struct rt6_info *rt, return daddr; } -static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, - struct sk_buff *skb, - const void *daddr) +struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, + struct net_device *dev, + struct sk_buff *skb, + const void *daddr) { - struct rt6_info *rt = (struct rt6_info *) dst; struct neighbour *n; - daddr = choose_neigh_daddr(rt, skb, daddr); - n = __ipv6_neigh_lookup(dst->dev, daddr); + daddr = choose_neigh_daddr(gw, skb, daddr); + n = __ipv6_neigh_lookup(dev, daddr); if (n) return n; - return neigh_create(&nd_tbl, daddr, dst->dev); + return neigh_create(&nd_tbl, daddr, dev); +} + +static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) +{ + const struct rt6_info *rt = container_of(dst, struct rt6_info, dst); + + return ip6_neigh_lookup(&rt->rt6i_gateway, dst->dev, skb, daddr); } static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) @@ -233,7 +227,7 @@ static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) struct net_device *dev = dst->dev; struct rt6_info *rt = (struct rt6_info *)dst; - daddr = choose_neigh_daddr(rt, NULL, daddr); + daddr = choose_neigh_daddr(&rt->rt6i_gateway, NULL, daddr); if (!daddr) return; if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) @@ -250,7 +244,7 @@ static struct dst_ops ip6_dst_ops_template = { .check = ip6_dst_check, .default_advmss = ip6_default_advmss, .mtu = ip6_mtu, - .cow_metrics = ipv6_cow_metrics, + .cow_metrics = dst_cow_metrics_generic, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, @@ -258,7 +252,7 @@ static struct dst_ops ip6_dst_ops_template = { .update_pmtu = ip6_rt_update_pmtu, .redirect = rt6_do_redirect, .local_out = __ip6_local_out, - .neigh_lookup = ip6_neigh_lookup, + .neigh_lookup = ip6_dst_neigh_lookup, .confirm_neigh = ip6_confirm_neigh, }; @@ -288,13 +282,22 @@ static struct dst_ops ip6_dst_blackhole_ops = { .update_pmtu = ip6_rt_blackhole_update_pmtu, .redirect = ip6_rt_blackhole_redirect, .cow_metrics = dst_cow_metrics_generic, - .neigh_lookup = ip6_neigh_lookup, + .neigh_lookup = ip6_dst_neigh_lookup, }; static const u32 ip6_template_metrics[RTAX_MAX] = { [RTAX_HOPLIMIT - 1] = 0, }; +static const struct fib6_info fib6_null_entry_template = { + .fib6_flags = (RTF_REJECT | RTF_NONEXTHOP), + .fib6_protocol = RTPROT_KERNEL, + .fib6_metric = ~(u32)0, + .fib6_ref = ATOMIC_INIT(1), + .fib6_type = RTN_UNREACHABLE, + .fib6_metrics = (struct dst_metrics *)&dst_default_metrics, +}; + static const struct rt6_info ip6_null_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), @@ -305,9 +308,6 @@ static const struct rt6_info ip6_null_entry_template = { .output = ip6_pkt_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), - .rt6i_protocol = RTPROT_KERNEL, - .rt6i_metric = ~(u32) 0, - .rt6i_ref = ATOMIC_INIT(1), }; #ifdef CONFIG_IPV6_MULTIPLE_TABLES @@ -322,9 +322,6 @@ static const struct rt6_info ip6_prohibit_entry_template = { .output = ip6_pkt_prohibit_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), - .rt6i_protocol = RTPROT_KERNEL, - .rt6i_metric = ~(u32) 0, - .rt6i_ref = ATOMIC_INIT(1), }; static const struct rt6_info ip6_blk_hole_entry_template = { @@ -337,9 +334,6 @@ static const struct rt6_info ip6_blk_hole_entry_template = { .output = dst_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), - .rt6i_protocol = RTPROT_KERNEL, - .rt6i_metric = ~(u32) 0, - .rt6i_ref = ATOMIC_INIT(1), }; #endif @@ -349,14 +343,12 @@ static void rt6_info_init(struct rt6_info *rt) struct dst_entry *dst = &rt->dst; memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); - INIT_LIST_HEAD(&rt->rt6i_siblings); INIT_LIST_HEAD(&rt->rt6i_uncached); } /* allocate dst with ip6_dst_ops */ -static struct rt6_info *__ip6_dst_alloc(struct net *net, - struct net_device *dev, - int flags) +struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, + int flags) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, flags); @@ -368,34 +360,15 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, return rt; } - -struct rt6_info *ip6_dst_alloc(struct net *net, - struct net_device *dev, - int flags) -{ - struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags); - - if (rt) { - rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC); - if (!rt->rt6i_pcpu) { - dst_release_immediate(&rt->dst); - return NULL; - } - } - - return rt; -} EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; - struct rt6_exception_bucket *bucket; - struct rt6_info *from = rt->from; + struct fib6_info *from; struct inet6_dev *idev; dst_destroy_metrics_generic(dst); - free_percpu(rt->rt6i_pcpu); rt6_uncached_list_del(rt); idev = rt->rt6i_idev; @@ -403,14 +376,12 @@ static void ip6_dst_destroy(struct dst_entry *dst) rt->rt6i_idev = NULL; in6_dev_put(idev); } - bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1); - if (bucket) { - rt->rt6i_exception_bucket = NULL; - kfree(bucket); - } - rt->from = NULL; - dst_release(&from->dst); + rcu_read_lock(); + from = rcu_dereference(rt->from); + rcu_assign_pointer(rt->from, NULL); + fib6_info_release(from); + rcu_read_unlock(); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -440,23 +411,27 @@ static bool __rt6_check_expired(const struct rt6_info *rt) static bool rt6_check_expired(const struct rt6_info *rt) { + struct fib6_info *from; + + from = rcu_dereference(rt->from); + if (rt->rt6i_flags & RTF_EXPIRES) { if (time_after(jiffies, rt->dst.expires)) return true; - } else if (rt->from) { + } else if (from) { return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK || - rt6_check_expired(rt->from); + fib6_check_expired(from); } return false; } -static struct rt6_info *rt6_multipath_select(const struct net *net, - struct rt6_info *match, - struct flowi6 *fl6, int oif, - const struct sk_buff *skb, - int strict) +struct fib6_info *fib6_multipath_select(const struct net *net, + struct fib6_info *match, + struct flowi6 *fl6, int oif, + const struct sk_buff *skb, + int strict) { - struct rt6_info *sibling, *next_sibling; + struct fib6_info *sibling, *next_sibling; /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. @@ -464,12 +439,15 @@ static struct rt6_info *rt6_multipath_select(const struct net *net, if (!fl6->mp_hash) fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL); - if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound)) + if (fl6->mp_hash <= atomic_read(&match->fib6_nh.nh_upper_bound)) return match; - list_for_each_entry_safe(sibling, next_sibling, &match->rt6i_siblings, - rt6i_siblings) { - if (fl6->mp_hash > atomic_read(&sibling->rt6i_nh_upper_bound)) + list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings, + fib6_siblings) { + int nh_upper_bound; + + nh_upper_bound = atomic_read(&sibling->fib6_nh.nh_upper_bound); + if (fl6->mp_hash > nh_upper_bound) continue; if (rt6_score_route(sibling, oif, strict) < 0) break; @@ -484,38 +462,27 @@ static struct rt6_info *rt6_multipath_select(const struct net *net, * Route lookup. rcu_read_lock() should be held. */ -static inline struct rt6_info *rt6_device_match(struct net *net, - struct rt6_info *rt, +static inline struct fib6_info *rt6_device_match(struct net *net, + struct fib6_info *rt, const struct in6_addr *saddr, int oif, int flags) { - struct rt6_info *local = NULL; - struct rt6_info *sprt; + struct fib6_info *sprt; - if (!oif && ipv6_addr_any(saddr) && !(rt->rt6i_nh_flags & RTNH_F_DEAD)) + if (!oif && ipv6_addr_any(saddr) && + !(rt->fib6_nh.nh_flags & RTNH_F_DEAD)) return rt; - for (sprt = rt; sprt; sprt = rcu_dereference(sprt->rt6_next)) { - struct net_device *dev = sprt->dst.dev; + for (sprt = rt; sprt; sprt = rcu_dereference(sprt->fib6_next)) { + const struct net_device *dev = sprt->fib6_nh.nh_dev; - if (sprt->rt6i_nh_flags & RTNH_F_DEAD) + if (sprt->fib6_nh.nh_flags & RTNH_F_DEAD) continue; if (oif) { if (dev->ifindex == oif) return sprt; - if (dev->flags & IFF_LOOPBACK) { - if (!sprt->rt6i_idev || - sprt->rt6i_idev->dev->ifindex != oif) { - if (flags & RT6_LOOKUP_F_IFACE) - continue; - if (local && - local->rt6i_idev->dev->ifindex == oif) - continue; - } - local = sprt; - } } else { if (ipv6_chk_addr(net, saddr, dev, flags & RT6_LOOKUP_F_IFACE)) @@ -523,15 +490,10 @@ static inline struct rt6_info *rt6_device_match(struct net *net, } } - if (oif) { - if (local) - return local; - - if (flags & RT6_LOOKUP_F_IFACE) - return net->ipv6.ip6_null_entry; - } + if (oif && flags & RT6_LOOKUP_F_IFACE) + return net->ipv6.fib6_null_entry; - return rt->rt6i_nh_flags & RTNH_F_DEAD ? net->ipv6.ip6_null_entry : rt; + return rt->fib6_nh.nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt; } #ifdef CONFIG_IPV6_ROUTER_PREF @@ -553,10 +515,13 @@ static void rt6_probe_deferred(struct work_struct *w) kfree(work); } -static void rt6_probe(struct rt6_info *rt) +static void rt6_probe(struct fib6_info *rt) { struct __rt6_probe_work *work; + const struct in6_addr *nh_gw; struct neighbour *neigh; + struct net_device *dev; + /* * Okay, this does not seem to be appropriate * for now, however, we need to check if it @@ -565,20 +530,25 @@ static void rt6_probe(struct rt6_info *rt) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ - if (!rt || !(rt->rt6i_flags & RTF_GATEWAY)) + if (!rt || !(rt->fib6_flags & RTF_GATEWAY)) return; + + nh_gw = &rt->fib6_nh.nh_gw; + dev = rt->fib6_nh.nh_dev; rcu_read_lock_bh(); - neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { + struct inet6_dev *idev; + if (neigh->nud_state & NUD_VALID) goto out; + idev = __in6_dev_get(dev); work = NULL; write_lock(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, - neigh->updated + - rt->rt6i_idev->cnf.rtr_probe_interval)) { + neigh->updated + idev->cnf.rtr_probe_interval)) { work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) __neigh_set_probe_once(neigh); @@ -590,9 +560,9 @@ static void rt6_probe(struct rt6_info *rt) if (work) { INIT_WORK(&work->work, rt6_probe_deferred); - work->target = rt->rt6i_gateway; - dev_hold(rt->dst.dev); - work->dev = rt->dst.dev; + work->target = *nh_gw; + dev_hold(dev); + work->dev = dev; schedule_work(&work->work); } @@ -600,7 +570,7 @@ out: rcu_read_unlock_bh(); } #else -static inline void rt6_probe(struct rt6_info *rt) +static inline void rt6_probe(struct fib6_info *rt) { } #endif @@ -608,28 +578,27 @@ static inline void rt6_probe(struct rt6_info *rt) /* * Default Router Selection (RFC 2461 6.3.6) */ -static inline int rt6_check_dev(struct rt6_info *rt, int oif) +static inline int rt6_check_dev(struct fib6_info *rt, int oif) { - struct net_device *dev = rt->dst.dev; + const struct net_device *dev = rt->fib6_nh.nh_dev; + if (!oif || dev->ifindex == oif) return 2; - if ((dev->flags & IFF_LOOPBACK) && - rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif) - return 1; return 0; } -static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt) +static inline enum rt6_nud_state rt6_check_neigh(struct fib6_info *rt) { - struct neighbour *neigh; enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; + struct neighbour *neigh; - if (rt->rt6i_flags & RTF_NONEXTHOP || - !(rt->rt6i_flags & RTF_GATEWAY)) + if (rt->fib6_flags & RTF_NONEXTHOP || + !(rt->fib6_flags & RTF_GATEWAY)) return RT6_NUD_SUCCEED; rcu_read_lock_bh(); - neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + neigh = __ipv6_neigh_lookup_noref(rt->fib6_nh.nh_dev, + &rt->fib6_nh.nh_gw); if (neigh) { read_lock(&neigh->lock); if (neigh->nud_state & NUD_VALID) @@ -650,8 +619,7 @@ static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt) return ret; } -static int rt6_score_route(struct rt6_info *rt, int oif, - int strict) +static int rt6_score_route(struct fib6_info *rt, int oif, int strict) { int m; @@ -659,7 +627,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif, if (!m && (strict & RT6_LOOKUP_F_IFACE)) return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF - m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; + m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->fib6_flags)) << 2; #endif if (strict & RT6_LOOKUP_F_REACHABLE) { int n = rt6_check_neigh(rt); @@ -669,23 +637,37 @@ static int rt6_score_route(struct rt6_info *rt, int oif, return m; } -static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, - int *mpri, struct rt6_info *match, +/* called with rc_read_lock held */ +static inline bool fib6_ignore_linkdown(const struct fib6_info *f6i) +{ + const struct net_device *dev = fib6_info_nh_dev(f6i); + bool rc = false; + + if (dev) { + const struct inet6_dev *idev = __in6_dev_get(dev); + + rc = !!idev->cnf.ignore_routes_with_linkdown; + } + + return rc; +} + +static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict, + int *mpri, struct fib6_info *match, bool *do_rr) { int m; bool match_do_rr = false; - struct inet6_dev *idev = rt->rt6i_idev; - if (rt->rt6i_nh_flags & RTNH_F_DEAD) + if (rt->fib6_nh.nh_flags & RTNH_F_DEAD) goto out; - if (idev->cnf.ignore_routes_with_linkdown && - rt->rt6i_nh_flags & RTNH_F_LINKDOWN && + if (fib6_ignore_linkdown(rt) && + rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN && !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE)) goto out; - if (rt6_check_expired(rt)) + if (fib6_check_expired(rt)) goto out; m = rt6_score_route(rt, oif, strict); @@ -709,19 +691,19 @@ out: return match; } -static struct rt6_info *find_rr_leaf(struct fib6_node *fn, - struct rt6_info *leaf, - struct rt6_info *rr_head, +static struct fib6_info *find_rr_leaf(struct fib6_node *fn, + struct fib6_info *leaf, + struct fib6_info *rr_head, u32 metric, int oif, int strict, bool *do_rr) { - struct rt6_info *rt, *match, *cont; + struct fib6_info *rt, *match, *cont; int mpri = -1; match = NULL; cont = NULL; - for (rt = rr_head; rt; rt = rcu_dereference(rt->rt6_next)) { - if (rt->rt6i_metric != metric) { + for (rt = rr_head; rt; rt = rcu_dereference(rt->fib6_next)) { + if (rt->fib6_metric != metric) { cont = rt; break; } @@ -730,8 +712,8 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, } for (rt = leaf; rt && rt != rr_head; - rt = rcu_dereference(rt->rt6_next)) { - if (rt->rt6i_metric != metric) { + rt = rcu_dereference(rt->fib6_next)) { + if (rt->fib6_metric != metric) { cont = rt; break; } @@ -742,22 +724,22 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, if (match || !cont) return match; - for (rt = cont; rt; rt = rcu_dereference(rt->rt6_next)) + for (rt = cont; rt; rt = rcu_dereference(rt->fib6_next)) match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; } -static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, +static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn, int oif, int strict) { - struct rt6_info *leaf = rcu_dereference(fn->leaf); - struct rt6_info *match, *rt0; + struct fib6_info *leaf = rcu_dereference(fn->leaf); + struct fib6_info *match, *rt0; bool do_rr = false; int key_plen; - if (!leaf || leaf == net->ipv6.ip6_null_entry) - return net->ipv6.ip6_null_entry; + if (!leaf || leaf == net->ipv6.fib6_null_entry) + return net->ipv6.fib6_null_entry; rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) @@ -768,39 +750,39 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, * (This might happen if all routes under fn are deleted from * the tree and fib6_repair_tree() is called on the node.) */ - key_plen = rt0->rt6i_dst.plen; + key_plen = rt0->fib6_dst.plen; #ifdef CONFIG_IPV6_SUBTREES - if (rt0->rt6i_src.plen) - key_plen = rt0->rt6i_src.plen; + if (rt0->fib6_src.plen) + key_plen = rt0->fib6_src.plen; #endif if (fn->fn_bit != key_plen) - return net->ipv6.ip6_null_entry; + return net->ipv6.fib6_null_entry; - match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict, + match = find_rr_leaf(fn, leaf, rt0, rt0->fib6_metric, oif, strict, &do_rr); if (do_rr) { - struct rt6_info *next = rcu_dereference(rt0->rt6_next); + struct fib6_info *next = rcu_dereference(rt0->fib6_next); /* no entries matched; do round-robin */ - if (!next || next->rt6i_metric != rt0->rt6i_metric) + if (!next || next->fib6_metric != rt0->fib6_metric) next = leaf; if (next != rt0) { - spin_lock_bh(&leaf->rt6i_table->tb6_lock); + spin_lock_bh(&leaf->fib6_table->tb6_lock); /* make sure next is not being deleted from the tree */ - if (next->rt6i_node) + if (next->fib6_node) rcu_assign_pointer(fn->rr_ptr, next); - spin_unlock_bh(&leaf->rt6i_table->tb6_lock); + spin_unlock_bh(&leaf->fib6_table->tb6_lock); } } - return match ? match : net->ipv6.ip6_null_entry; + return match ? match : net->ipv6.fib6_null_entry; } -static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt) +static bool rt6_is_gw_or_nonexthop(const struct fib6_info *rt) { - return (rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)); + return (rt->fib6_flags & (RTF_NONEXTHOP | RTF_GATEWAY)); } #ifdef CONFIG_IPV6_ROUTE_INFO @@ -812,7 +794,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, struct in6_addr prefix_buf, *prefix; unsigned int pref; unsigned long lifetime; - struct rt6_info *rt; + struct fib6_info *rt; if (len < sizeof(struct route_info)) { return -EINVAL; @@ -850,13 +832,13 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, } if (rinfo->prefix_len == 0) - rt = rt6_get_dflt_router(gwaddr, dev); + rt = rt6_get_dflt_router(net, gwaddr, dev); else rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev); if (rt && !lifetime) { - ip6_del_rt(rt); + ip6_del_rt(net, rt); rt = NULL; } @@ -864,21 +846,162 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev, pref); else if (rt) - rt->rt6i_flags = RTF_ROUTEINFO | - (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); + rt->fib6_flags = RTF_ROUTEINFO | + (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { if (!addrconf_finite_timeout(lifetime)) - rt6_clean_expires(rt); + fib6_clean_expires(rt); else - rt6_set_expires(rt, jiffies + HZ * lifetime); + fib6_set_expires(rt, jiffies + HZ * lifetime); - ip6_rt_put(rt); + fib6_info_release(rt); } return 0; } #endif +/* + * Misc support functions + */ + +/* called with rcu_lock held */ +static struct net_device *ip6_rt_get_dev_rcu(struct fib6_info *rt) +{ + struct net_device *dev = rt->fib6_nh.nh_dev; + + if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) { + /* for copies of local routes, dst->dev needs to be the + * device if it is a master device, the master device if + * device is enslaved, and the loopback as the default + */ + if (netif_is_l3_slave(dev) && + !rt6_need_strict(&rt->fib6_dst.addr)) + dev = l3mdev_master_dev_rcu(dev); + else if (!netif_is_l3_master(dev)) + dev = dev_net(dev)->loopback_dev; + /* last case is netif_is_l3_master(dev) is true in which + * case we want dev returned to be dev + */ + } + + return dev; +} + +static const int fib6_prop[RTN_MAX + 1] = { + [RTN_UNSPEC] = 0, + [RTN_UNICAST] = 0, + [RTN_LOCAL] = 0, + [RTN_BROADCAST] = 0, + [RTN_ANYCAST] = 0, + [RTN_MULTICAST] = 0, + [RTN_BLACKHOLE] = -EINVAL, + [RTN_UNREACHABLE] = -EHOSTUNREACH, + [RTN_PROHIBIT] = -EACCES, + [RTN_THROW] = -EAGAIN, + [RTN_NAT] = -EINVAL, + [RTN_XRESOLVE] = -EINVAL, +}; + +static int ip6_rt_type_to_error(u8 fib6_type) +{ + return fib6_prop[fib6_type]; +} + +static unsigned short fib6_info_dst_flags(struct fib6_info *rt) +{ + unsigned short flags = 0; + + if (rt->dst_nocount) + flags |= DST_NOCOUNT; + if (rt->dst_nopolicy) + flags |= DST_NOPOLICY; + if (rt->dst_host) + flags |= DST_HOST; + + return flags; +} + +static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort) +{ + rt->dst.error = ip6_rt_type_to_error(ort->fib6_type); + + switch (ort->fib6_type) { + case RTN_BLACKHOLE: + rt->dst.output = dst_discard_out; + rt->dst.input = dst_discard; + break; + case RTN_PROHIBIT: + rt->dst.output = ip6_pkt_prohibit_out; + rt->dst.input = ip6_pkt_prohibit; + break; + case RTN_THROW: + case RTN_UNREACHABLE: + default: + rt->dst.output = ip6_pkt_discard_out; + rt->dst.input = ip6_pkt_discard; + break; + } +} + +static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) +{ + rt->dst.flags |= fib6_info_dst_flags(ort); + + if (ort->fib6_flags & RTF_REJECT) { + ip6_rt_init_dst_reject(rt, ort); + return; + } + + rt->dst.error = 0; + rt->dst.output = ip6_output; + + if (ort->fib6_type == RTN_LOCAL) { + rt->dst.input = ip6_input; + } else if (ipv6_addr_type(&ort->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { + rt->dst.input = ip6_mc_input; + } else { + rt->dst.input = ip6_forward; + } + + if (ort->fib6_nh.nh_lwtstate) { + rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate); + lwtunnel_set_redirect(&rt->dst); + } + + rt->dst.lastuse = jiffies; +} + +static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) +{ + rt->rt6i_flags &= ~RTF_EXPIRES; + fib6_info_hold(from); + rcu_assign_pointer(rt->from, from); + dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); + if (from->fib6_metrics != &dst_default_metrics) { + rt->dst._metrics |= DST_METRICS_REFCOUNTED; + refcount_inc(&from->fib6_metrics->refcnt); + } +} + +static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) +{ + struct net_device *dev = fib6_info_nh_dev(ort); + + ip6_rt_init_dst(rt, ort); + + rt->rt6i_dst = ort->fib6_dst; + rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL; + rt->rt6i_gateway = ort->fib6_nh.nh_gw; + rt->rt6i_flags = ort->fib6_flags; + rt6_set_from(rt, ort); +#ifdef CONFIG_IPV6_SUBTREES + rt->rt6i_src = ort->fib6_src; +#endif + rt->rt6i_prefsrc = ort->fib6_prefsrc; + rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate); +} + static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { @@ -889,7 +1012,7 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn, pn = rcu_dereference(fn->parent); sn = FIB6_SUBTREE(pn); if (sn && sn != fn) - fn = fib6_lookup(sn, NULL, saddr); + fn = fib6_node_lookup(sn, NULL, saddr); else fn = pn; if (fn->fn_flags & RTN_RTINFO) @@ -914,50 +1037,74 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt, return false; } +/* called with rcu_lock held */ +static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt) +{ + unsigned short flags = fib6_info_dst_flags(rt); + struct net_device *dev = rt->fib6_nh.nh_dev; + struct rt6_info *nrt; + + nrt = ip6_dst_alloc(dev_net(dev), dev, flags); + if (nrt) + ip6_rt_copy_init(nrt, rt); + + return nrt; +} + static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { - struct rt6_info *rt, *rt_cache; + struct fib6_info *f6i; struct fib6_node *fn; + struct rt6_info *rt; if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) flags &= ~RT6_LOOKUP_F_IFACE; rcu_read_lock(); - fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); + fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - rt = rcu_dereference(fn->leaf); - if (!rt) { - rt = net->ipv6.ip6_null_entry; + f6i = rcu_dereference(fn->leaf); + if (!f6i) { + f6i = net->ipv6.fib6_null_entry; } else { - rt = rt6_device_match(net, rt, &fl6->saddr, + f6i = rt6_device_match(net, f6i, &fl6->saddr, fl6->flowi6_oif, flags); - if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) - rt = rt6_multipath_select(net, rt, fl6, fl6->flowi6_oif, - skb, flags); + if (f6i->fib6_nsiblings && fl6->flowi6_oif == 0) + f6i = fib6_multipath_select(net, f6i, fl6, + fl6->flowi6_oif, skb, + flags); } - if (rt == net->ipv6.ip6_null_entry) { + if (f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } - /* Search through exception table */ - rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); - if (rt_cache) - rt = rt_cache; - if (ip6_hold_safe(net, &rt, true)) - dst_use_noref(&rt->dst, jiffies); + trace_fib6_table_lookup(net, f6i, table, fl6); - rcu_read_unlock(); + /* Search through exception table */ + rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr); + if (rt) { + if (ip6_hold_safe(net, &rt, true)) + dst_use_noref(&rt->dst, jiffies); + } else if (f6i == net->ipv6.fib6_null_entry) { + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } else { + rt = ip6_create_rt_rcu(f6i); + if (!rt) { + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } + } - trace_fib6_table_lookup(net, rt, table, fl6); + rcu_read_unlock(); return rt; - } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, @@ -999,55 +1146,28 @@ EXPORT_SYMBOL(rt6_lookup); * Caller must hold dst before calling it. */ -static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, - struct mx6_config *mxc, +static int __ip6_ins_rt(struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { int err; struct fib6_table *table; - table = rt->rt6i_table; + table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, info, mxc, extack); + err = fib6_add(&table->tb6_root, rt, info, extack); spin_unlock_bh(&table->tb6_lock); return err; } -int ip6_ins_rt(struct rt6_info *rt) +int ip6_ins_rt(struct net *net, struct fib6_info *rt) { - struct nl_info info = { .nl_net = dev_net(rt->dst.dev), }; - struct mx6_config mxc = { .mx = NULL, }; + struct nl_info info = { .nl_net = net, }; - /* Hold dst to account for the reference from the fib6 tree */ - dst_hold(&rt->dst); - return __ip6_ins_rt(rt, &info, &mxc, NULL); + return __ip6_ins_rt(rt, &info, NULL); } -/* called with rcu_lock held */ -static struct net_device *ip6_rt_get_dev_rcu(struct rt6_info *rt) -{ - struct net_device *dev = rt->dst.dev; - - if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) { - /* for copies of local routes, dst->dev needs to be the - * device if it is a master device, the master device if - * device is enslaved, and the loopback as the default - */ - if (netif_is_l3_slave(dev) && - !rt6_need_strict(&rt->rt6i_dst.addr)) - dev = l3mdev_master_dev_rcu(dev); - else if (!netif_is_l3_master(dev)) - dev = dev_net(dev)->loopback_dev; - /* last case is netif_is_l3_master(dev) is true in which - * case we want dev returned to be dev - */ - } - - return dev; -} - -static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, +static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort, const struct in6_addr *daddr, const struct in6_addr *saddr) { @@ -1058,26 +1178,20 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, * Clone the route. */ - if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)) - ort = ort->from; - - rcu_read_lock(); dev = ip6_rt_get_dev_rcu(ort); - rt = __ip6_dst_alloc(dev_net(dev), dev, 0); - rcu_read_unlock(); + rt = ip6_dst_alloc(dev_net(dev), dev, 0); if (!rt) return NULL; ip6_rt_copy_init(rt, ort); rt->rt6i_flags |= RTF_CACHE; - rt->rt6i_metric = 0; rt->dst.flags |= DST_HOST; rt->rt6i_dst.addr = *daddr; rt->rt6i_dst.plen = 128; if (!rt6_is_gw_or_nonexthop(ort)) { - if (ort->rt6i_dst.plen != 128 && - ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) + if (ort->fib6_dst.plen != 128 && + ipv6_addr_equal(&ort->fib6_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { @@ -1090,45 +1204,44 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, return rt; } -static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt) +static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt) { + unsigned short flags = fib6_info_dst_flags(rt); struct net_device *dev; struct rt6_info *pcpu_rt; rcu_read_lock(); dev = ip6_rt_get_dev_rcu(rt); - pcpu_rt = __ip6_dst_alloc(dev_net(dev), dev, rt->dst.flags); + pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags); rcu_read_unlock(); if (!pcpu_rt) return NULL; ip6_rt_copy_init(pcpu_rt, rt); - pcpu_rt->rt6i_protocol = rt->rt6i_protocol; pcpu_rt->rt6i_flags |= RTF_PCPU; return pcpu_rt; } /* It should be called with rcu_read_lock() acquired */ -static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) +static struct rt6_info *rt6_get_pcpu_route(struct fib6_info *rt) { struct rt6_info *pcpu_rt, **p; p = this_cpu_ptr(rt->rt6i_pcpu); pcpu_rt = *p; - if (pcpu_rt && ip6_hold_safe(NULL, &pcpu_rt, false)) - rt6_dst_from_metrics_check(pcpu_rt); + if (pcpu_rt) + ip6_hold_safe(NULL, &pcpu_rt, false); return pcpu_rt; } -static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) +static struct rt6_info *rt6_make_pcpu_route(struct net *net, + struct fib6_info *rt) { struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(rt); if (!pcpu_rt) { - struct net *net = dev_net(rt->dst.dev); - dst_hold(&net->ipv6.ip6_null_entry->dst); return net->ipv6.ip6_null_entry; } @@ -1138,7 +1251,6 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) prev = cmpxchg(p, NULL, pcpu_rt); BUG_ON(prev); - rt6_dst_from_metrics_check(pcpu_rt); return pcpu_rt; } @@ -1158,9 +1270,8 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, return; net = dev_net(rt6_ex->rt6i->dst.dev); - rt6_ex->rt6i->rt6i_node = NULL; hlist_del_rcu(&rt6_ex->hlist); - rt6_release(rt6_ex->rt6i); + dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; @@ -1268,20 +1379,36 @@ __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, return NULL; } +static unsigned int fib6_mtu(const struct fib6_info *rt) +{ + unsigned int mtu; + + if (rt->fib6_pmtu) { + mtu = rt->fib6_pmtu; + } else { + struct net_device *dev = fib6_info_nh_dev(rt); + struct inet6_dev *idev; + + rcu_read_lock(); + idev = __in6_dev_get(dev); + mtu = idev->cnf.mtu6; + rcu_read_unlock(); + } + + mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); + + return mtu - lwtunnel_headroom(rt->fib6_nh.nh_lwtstate, mtu); +} + static int rt6_insert_exception(struct rt6_info *nrt, - struct rt6_info *ort) + struct fib6_info *ort) { - struct net *net = dev_net(ort->dst.dev); + struct net *net = dev_net(nrt->dst.dev); struct rt6_exception_bucket *bucket; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; int err = 0; - /* ort can't be a cache or pcpu route */ - if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)) - ort = ort->from; - WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)); - spin_lock_bh(&rt6_exception_lock); if (ort->exception_bucket_flushed) { @@ -1308,19 +1435,19 @@ static int rt6_insert_exception(struct rt6_info *nrt, * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ - if (ort->rt6i_src.plen) + if (ort->fib6_src.plen) src_key = &nrt->rt6i_src.addr; #endif /* Update rt6i_prefsrc as it could be changed * in rt6_remove_prefsrc() */ - nrt->rt6i_prefsrc = ort->rt6i_prefsrc; + nrt->rt6i_prefsrc = ort->fib6_prefsrc; /* rt6_mtu_change() might lower mtu on ort. * Only insert this exception route if its mtu * is less than ort's mtu value. */ - if (nrt->rt6i_pmtu >= dst_mtu(&ort->dst)) { + if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(ort)) { err = -EINVAL; goto out; } @@ -1337,8 +1464,6 @@ static int rt6_insert_exception(struct rt6_info *nrt, } rt6_ex->rt6i = nrt; rt6_ex->stamp = jiffies; - atomic_inc(&nrt->rt6i_ref); - nrt->rt6i_node = ort->rt6i_node; hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); bucket->depth++; net->ipv6.rt6_stats->fib_rt_cache++; @@ -1351,16 +1476,16 @@ out: /* Update fn->fn_sernum to invalidate all cached dst */ if (!err) { - spin_lock_bh(&ort->rt6i_table->tb6_lock); - fib6_update_sernum(ort); - spin_unlock_bh(&ort->rt6i_table->tb6_lock); + spin_lock_bh(&ort->fib6_table->tb6_lock); + fib6_update_sernum(net, ort); + spin_unlock_bh(&ort->fib6_table->tb6_lock); fib6_force_start_gc(net); } return err; } -void rt6_flush_exceptions(struct rt6_info *rt) +void rt6_flush_exceptions(struct fib6_info *rt) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1390,7 +1515,7 @@ out: /* Find cached rt in the hash table inside passed in rt * Caller has to hold rcu_read_lock() */ -static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, +static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt, struct in6_addr *daddr, struct in6_addr *saddr) { @@ -1408,7 +1533,7 @@ static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ - if (rt->rt6i_src.plen) + if (rt->fib6_src.plen) src_key = saddr; #endif rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); @@ -1420,14 +1545,15 @@ static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, } /* Remove the passed in cached rt from the hash table that contains it */ -int rt6_remove_exception_rt(struct rt6_info *rt) +static int rt6_remove_exception_rt(struct rt6_info *rt) { struct rt6_exception_bucket *bucket; - struct rt6_info *from = rt->from; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; + struct fib6_info *from; int err; + from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) return -EINVAL; @@ -1445,7 +1571,7 @@ int rt6_remove_exception_rt(struct rt6_info *rt) * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ - if (from->rt6i_src.plen) + if (from->fib6_src.plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_spinlock(&bucket, @@ -1468,7 +1594,7 @@ int rt6_remove_exception_rt(struct rt6_info *rt) static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct rt6_exception_bucket *bucket; - struct rt6_info *from = rt->from; + struct fib6_info *from = rt->from; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; @@ -1486,7 +1612,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ - if (from->rt6i_src.plen) + if (from->fib6_src.plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_rcu(&bucket, @@ -1498,7 +1624,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) rcu_read_unlock(); } -static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) +static void rt6_exceptions_remove_prefsrc(struct fib6_info *rt) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1540,7 +1666,7 @@ static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, } static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, - struct rt6_info *rt, int mtu) + struct fib6_info *rt, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1557,12 +1683,12 @@ static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, struct rt6_info *entry = rt6_ex->rt6i; /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected - * route), the metrics of its rt->dst.from have already + * route), the metrics of its rt->from have already * been updated. */ - if (entry->rt6i_pmtu && + if (dst_metric_raw(&entry->dst, RTAX_MTU) && rt6_mtu_change_route_allowed(idev, entry, mtu)) - entry->rt6i_pmtu = mtu; + dst_metric_set(&entry->dst, RTAX_MTU, mtu); } bucket++; } @@ -1570,7 +1696,7 @@ static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, #define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) -static void rt6_exceptions_clean_tohost(struct rt6_info *rt, +static void rt6_exceptions_clean_tohost(struct fib6_info *rt, struct in6_addr *gateway) { struct rt6_exception_bucket *bucket; @@ -1649,7 +1775,7 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, gc_args->more++; } -void rt6_age_exceptions(struct rt6_info *rt, +void rt6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args, unsigned long now) { @@ -1680,32 +1806,22 @@ void rt6_age_exceptions(struct rt6_info *rt, rcu_read_unlock_bh(); } -struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, - int oif, struct flowi6 *fl6, - const struct sk_buff *skb, int flags) +/* must be called with rcu lock held */ +struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table, + int oif, struct flowi6 *fl6, int strict) { struct fib6_node *fn, *saved_fn; - struct rt6_info *rt, *rt_cache; - int strict = 0; + struct fib6_info *f6i; - strict |= flags & RT6_LOOKUP_F_IFACE; - strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE; - if (net->ipv6.devconf_all->forwarding == 0) - strict |= RT6_LOOKUP_F_REACHABLE; - - rcu_read_lock(); - - fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); + fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) oif = 0; redo_rt6_select: - rt = rt6_select(net, fn, oif, strict); - if (rt->rt6i_nsiblings) - rt = rt6_multipath_select(net, rt, fl6, oif, skb, strict); - if (rt == net->ipv6.ip6_null_entry) { + f6i = rt6_select(net, fn, oif, strict); + if (f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto redo_rt6_select; @@ -1717,45 +1833,57 @@ redo_rt6_select: } } - /*Search through exception table */ - rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); - if (rt_cache) - rt = rt_cache; + trace_fib6_table_lookup(net, f6i, table, fl6); - if (rt == net->ipv6.ip6_null_entry) { + return f6i; +} + +struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, + int oif, struct flowi6 *fl6, + const struct sk_buff *skb, int flags) +{ + struct fib6_info *f6i; + struct rt6_info *rt; + int strict = 0; + + strict |= flags & RT6_LOOKUP_F_IFACE; + strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE; + if (net->ipv6.devconf_all->forwarding == 0) + strict |= RT6_LOOKUP_F_REACHABLE; + + rcu_read_lock(); + + f6i = fib6_table_lookup(net, table, oif, fl6, strict); + if (f6i->fib6_nsiblings) + f6i = fib6_multipath_select(net, f6i, fl6, oif, skb, strict); + + if (f6i == net->ipv6.fib6_null_entry) { + rt = net->ipv6.ip6_null_entry; rcu_read_unlock(); dst_hold(&rt->dst); - trace_fib6_table_lookup(net, rt, table, fl6); return rt; - } else if (rt->rt6i_flags & RTF_CACHE) { - if (ip6_hold_safe(net, &rt, true)) { + } + + /*Search through exception table */ + rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr); + if (rt) { + if (ip6_hold_safe(net, &rt, true)) dst_use_noref(&rt->dst, jiffies); - rt6_dst_from_metrics_check(rt); - } + rcu_read_unlock(); - trace_fib6_table_lookup(net, rt, table, fl6); return rt; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && - !(rt->rt6i_flags & RTF_GATEWAY))) { + !(f6i->fib6_flags & RTF_GATEWAY))) { /* Create a RTF_CACHE clone which will not be * owned by the fib6 tree. It is for the special case where * the daddr in the skb during the neighbor look-up is different * from the fl6->daddr used to look-up route here. */ - struct rt6_info *uncached_rt; - if (ip6_hold_safe(net, &rt, true)) { - dst_use_noref(&rt->dst, jiffies); - } else { - rcu_read_unlock(); - uncached_rt = rt; - goto uncached_rt_out; - } - rcu_read_unlock(); + uncached_rt = ip6_rt_cache_alloc(f6i, &fl6->daddr, NULL); - uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); - dst_release(&rt->dst); + rcu_read_unlock(); if (uncached_rt) { /* Uncached_rt's refcnt is taken during ip6_rt_cache_alloc() @@ -1768,36 +1896,21 @@ redo_rt6_select: dst_hold(&uncached_rt->dst); } -uncached_rt_out: - trace_fib6_table_lookup(net, uncached_rt, table, fl6); return uncached_rt; - } else { /* Get a percpu copy */ struct rt6_info *pcpu_rt; - dst_use_noref(&rt->dst, jiffies); local_bh_disable(); - pcpu_rt = rt6_get_pcpu_route(rt); - - if (!pcpu_rt) { - /* atomic_inc_not_zero() is needed when using rcu */ - if (atomic_inc_not_zero(&rt->rt6i_ref)) { - /* No dst_hold() on rt is needed because grabbing - * rt->rt6i_ref makes sure rt can't be released. - */ - pcpu_rt = rt6_make_pcpu_route(rt); - rt6_release(rt); - } else { - /* rt is already removed from tree */ - pcpu_rt = net->ipv6.ip6_null_entry; - dst_hold(&pcpu_rt->dst); - } - } + pcpu_rt = rt6_get_pcpu_route(f6i); + + if (!pcpu_rt) + pcpu_rt = rt6_make_pcpu_route(net, f6i); + local_bh_enable(); rcu_read_unlock(); - trace_fib6_table_lookup(net, pcpu_rt, table, fl6); + return pcpu_rt; } } @@ -1868,7 +1981,7 @@ out: } else { keys->addrs.v6addrs.src = key_iph->saddr; keys->addrs.v6addrs.dst = key_iph->daddr; - keys->tags.flow_label = ip6_flowinfo(key_iph); + keys->tags.flow_label = ip6_flowlabel(key_iph); keys->basic.ip_proto = key_iph->nexthdr; } } @@ -1889,7 +2002,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, } else { hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; - hash_keys.tags.flow_label = (__force u32)fl6->flowlabel; + hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } break; @@ -2020,7 +2133,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt->rt6i_idev = in6_dev_get(loopback_dev); rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; - rt->rt6i_metric = 0; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); #ifdef CONFIG_IPV6_SUBTREES @@ -2036,18 +2148,27 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori * Destination cache support functions */ -static void rt6_dst_from_metrics_check(struct rt6_info *rt) +static bool fib6_check(struct fib6_info *f6i, u32 cookie) { - if (rt->from && - dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(&rt->from->dst)) - dst_init_metrics(&rt->dst, dst_metrics_ptr(&rt->from->dst), true); + u32 rt_cookie = 0; + + if (!fib6_get_cookie_safe(f6i, &rt_cookie) || rt_cookie != cookie) + return false; + + if (fib6_check_expired(f6i)) + return false; + + return true; } -static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie) +static struct dst_entry *rt6_check(struct rt6_info *rt, + struct fib6_info *from, + u32 cookie) { u32 rt_cookie = 0; - if (!rt6_get_cookie_safe(rt, &rt_cookie) || rt_cookie != cookie) + if ((from && !fib6_get_cookie_safe(from, &rt_cookie)) || + rt_cookie != cookie) return NULL; if (rt6_check_expired(rt)) @@ -2056,11 +2177,13 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie) return &rt->dst; } -static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie) +static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, + struct fib6_info *from, + u32 cookie) { if (!__rt6_check_expired(rt) && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && - rt6_check(rt->from, cookie)) + fib6_check(from, cookie)) return &rt->dst; else return NULL; @@ -2068,22 +2191,30 @@ static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie) static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) { + struct dst_entry *dst_ret; + struct fib6_info *from; struct rt6_info *rt; - rt = (struct rt6_info *) dst; + rt = container_of(dst, struct rt6_info, dst); + + rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ - rt6_dst_from_metrics_check(rt); + from = rcu_dereference(rt->from); - if (rt->rt6i_flags & RTF_PCPU || - (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->from)) - return rt6_dst_from_check(rt, cookie); + if (from && (rt->rt6i_flags & RTF_PCPU || + unlikely(!list_empty(&rt->rt6i_uncached)))) + dst_ret = rt6_dst_from_check(rt, from, cookie); else - return rt6_check(rt, cookie); + dst_ret = rt6_check(rt, from, cookie); + + rcu_read_unlock(); + + return dst_ret; } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) @@ -2092,10 +2223,12 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) if (rt) { if (rt->rt6i_flags & RTF_CACHE) { + rcu_read_lock(); if (rt6_check_expired(rt)) { - ip6_del_rt(rt); + rt6_remove_exception_rt(rt); dst = NULL; } + rcu_read_unlock(); } else { dst_release(dst); dst = NULL; @@ -2112,35 +2245,60 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { + rcu_read_lock(); if (rt->rt6i_flags & RTF_CACHE) { if (dst_hold_safe(&rt->dst)) - ip6_del_rt(rt); + rt6_remove_exception_rt(rt); } else { + struct fib6_info *from; struct fib6_node *fn; - rcu_read_lock(); - fn = rcu_dereference(rt->rt6i_node); - if (fn && (rt->rt6i_flags & RTF_DEFAULT)) - fn->fn_sernum = -1; - rcu_read_unlock(); + from = rcu_dereference(rt->from); + if (from) { + fn = rcu_dereference(from->fib6_node); + if (fn && (rt->rt6i_flags & RTF_DEFAULT)) + fn->fn_sernum = -1; + } } + rcu_read_unlock(); } } +static void rt6_update_expires(struct rt6_info *rt0, int timeout) +{ + if (!(rt0->rt6i_flags & RTF_EXPIRES)) { + struct fib6_info *from; + + rcu_read_lock(); + from = rcu_dereference(rt0->from); + if (from) + rt0->dst.expires = from->expires; + rcu_read_unlock(); + } + + dst_set_expires(&rt0->dst, timeout); + rt0->rt6i_flags |= RTF_EXPIRES; +} + static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) { struct net *net = dev_net(rt->dst.dev); + dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt->rt6i_flags |= RTF_MODIFIED; - rt->rt6i_pmtu = mtu; rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); } static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) { + bool from_set; + + rcu_read_lock(); + from_set = !!rcu_dereference(rt->from); + rcu_read_unlock(); + return !(rt->rt6i_flags & RTF_CACHE) && - (rt->rt6i_flags & RTF_PCPU || - rcu_access_pointer(rt->rt6i_node)); + (rt->rt6i_flags & RTF_PCPU || from_set); } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, @@ -2176,14 +2334,18 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (rt6->rt6i_flags & RTF_CACHE) rt6_update_exception_stamp_rt(rt6); } else if (daddr) { + struct fib6_info *from; struct rt6_info *nrt6; - nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr); + rcu_read_lock(); + from = rcu_dereference(rt6->from); + nrt6 = ip6_rt_cache_alloc(from, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); - if (rt6_insert_exception(nrt6, rt6)) + if (rt6_insert_exception(nrt6, from)) dst_release_immediate(&nrt6->dst); } + rcu_read_unlock(); } } @@ -2264,7 +2426,8 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; - struct rt6_info *rt, *rt_cache; + struct rt6_info *ret = NULL, *rt_cache; + struct fib6_info *rt; struct fib6_node *fn; /* Get the "current" route for this destination and @@ -2278,32 +2441,32 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, */ rcu_read_lock(); - fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); + fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: for_each_fib6_node_rt_rcu(fn) { - if (rt->rt6i_nh_flags & RTNH_F_DEAD) + if (rt->fib6_nh.nh_flags & RTNH_F_DEAD) continue; - if (rt6_check_expired(rt)) + if (fib6_check_expired(rt)) continue; - if (rt->dst.error) + if (rt->fib6_flags & RTF_REJECT) break; - if (!(rt->rt6i_flags & RTF_GATEWAY)) + if (!(rt->fib6_flags & RTF_GATEWAY)) continue; - if (fl6->flowi6_oif != rt->dst.dev->ifindex) + if (fl6->flowi6_oif != rt->fib6_nh.nh_dev->ifindex) continue; /* rt_cache's gateway might be different from its 'parent' * in the case of an ip redirect. * So we keep searching in the exception table if the gateway * is different. */ - if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) { + if (!ipv6_addr_equal(&rdfl->gateway, &rt->fib6_nh.nh_gw)) { rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); if (rt_cache && ipv6_addr_equal(&rdfl->gateway, &rt_cache->rt6i_gateway)) { - rt = rt_cache; + ret = rt_cache; break; } continue; @@ -2312,25 +2475,28 @@ restart: } if (!rt) - rt = net->ipv6.ip6_null_entry; - else if (rt->dst.error) { - rt = net->ipv6.ip6_null_entry; + rt = net->ipv6.fib6_null_entry; + else if (rt->fib6_flags & RTF_REJECT) { + ret = net->ipv6.ip6_null_entry; goto out; } - if (rt == net->ipv6.ip6_null_entry) { + if (rt == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } out: - ip6_hold_safe(net, &rt, true); + if (ret) + dst_hold(&ret->dst); + else + ret = ip6_create_rt_rcu(rt); rcu_read_unlock(); trace_fib6_table_lookup(net, rt, table, fl6); - return rt; + return ret; }; static struct dst_entry *ip6_route_redirect(struct net *net, @@ -2422,12 +2588,8 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) static unsigned int ip6_mtu(const struct dst_entry *dst) { - const struct rt6_info *rt = (const struct rt6_info *)dst; - unsigned int mtu = rt->rt6i_pmtu; struct inet6_dev *idev; - - if (mtu) - goto out; + unsigned int mtu; mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) @@ -2447,6 +2609,54 @@ out: return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } +/* MTU selection: + * 1. mtu on route is locked - use it + * 2. mtu from nexthop exception + * 3. mtu from egress device + * + * based on ip6_dst_mtu_forward and exception logic of + * rt6_find_cached_rt; called with rcu_read_lock + */ +u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr, + struct in6_addr *saddr) +{ + struct rt6_exception_bucket *bucket; + struct rt6_exception *rt6_ex; + struct in6_addr *src_key; + struct inet6_dev *idev; + u32 mtu = 0; + + if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) { + mtu = f6i->fib6_pmtu; + if (mtu) + goto out; + } + + src_key = NULL; +#ifdef CONFIG_IPV6_SUBTREES + if (f6i->fib6_src.plen) + src_key = saddr; +#endif + + bucket = rcu_dereference(f6i->rt6i_exception_bucket); + rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); + if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) + mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU); + + if (likely(!mtu)) { + struct net_device *dev = fib6_info_nh_dev(f6i); + + mtu = IPV6_MIN_MTU; + idev = __in6_dev_get(dev); + if (idev && idev->cnf.mtu6 > mtu) + mtu = idev->cnf.mtu6; + } + + mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); +out: + return mtu - lwtunnel_headroom(fib6_info_nh_lwt(f6i), mtu); +} + struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6) { @@ -2511,60 +2721,22 @@ out: return entries > rt_max_size; } -static int ip6_convert_metrics(struct mx6_config *mxc, - const struct fib6_config *cfg) +static int ip6_convert_metrics(struct net *net, struct fib6_info *rt, + struct fib6_config *cfg) { - struct net *net = cfg->fc_nlinfo.nl_net; - bool ecn_ca = false; - struct nlattr *nla; - int remaining; - u32 *mp; + struct dst_metrics *p; if (!cfg->fc_mx) return 0; - mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); - if (unlikely(!mp)) + p = kzalloc(sizeof(*rt->fib6_metrics), GFP_KERNEL); + if (unlikely(!p)) return -ENOMEM; - nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { - int type = nla_type(nla); - u32 val; - - if (!type) - continue; - if (unlikely(type > RTAX_MAX)) - goto err; - - if (type == RTAX_CC_ALGO) { - char tmp[TCP_CA_NAME_MAX]; - - nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca); - if (val == TCP_CA_UNSPEC) - goto err; - } else { - val = nla_get_u32(nla); - } - if (type == RTAX_HOPLIMIT && val > 255) - val = 255; - if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) - goto err; - - mp[type - 1] = val; - __set_bit(type - 1, mxc->mx_valid); - } - - if (ecn_ca) { - __set_bit(RTAX_FEATURES - 1, mxc->mx_valid); - mp[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; - } + refcount_set(&p->refcnt, 1); + rt->fib6_metrics = p; - mxc->mx = mp; - return 0; - err: - kfree(mp); - return -EINVAL; + return ip_metrics_convert(net, cfg->fc_mx, cfg->fc_mx_len, p->metrics); } static struct rt6_info *ip6_nh_lookup_table(struct net *net, @@ -2750,11 +2922,12 @@ out: return err; } -static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, +static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, + gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; - struct rt6_info *rt = NULL; + struct fib6_info *rt = NULL; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; struct fib6_table *table; @@ -2773,6 +2946,11 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, goto out; } + if (cfg->fc_type > RTN_MAX) { + NL_SET_ERR_MSG(extack, "Invalid route type"); + goto out; + } + if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto out; @@ -2831,35 +3009,30 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, if (!table) goto out; - rt = ip6_dst_alloc(net, NULL, - (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT); + err = -ENOMEM; + rt = fib6_info_alloc(gfp_flags); + if (!rt) + goto out; + + if (cfg->fc_flags & RTF_ADDRCONF) + rt->dst_nocount = true; - if (!rt) { - err = -ENOMEM; + err = ip6_convert_metrics(net, rt, cfg); + if (err < 0) goto out; - } if (cfg->fc_flags & RTF_EXPIRES) - rt6_set_expires(rt, jiffies + + fib6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); else - rt6_clean_expires(rt); + fib6_clean_expires(rt); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; - rt->rt6i_protocol = cfg->fc_protocol; + rt->fib6_protocol = cfg->fc_protocol; addr_type = ipv6_addr_type(&cfg->fc_dst); - if (addr_type & IPV6_ADDR_MULTICAST) - rt->dst.input = ip6_mc_input; - else if (cfg->fc_flags & RTF_LOCAL) - rt->dst.input = ip6_input; - else - rt->dst.input = ip6_forward; - - rt->dst.output = ip6_output; - if (cfg->fc_encap) { struct lwtunnel_state *lwtstate; @@ -2868,22 +3041,23 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, &lwtstate, extack); if (err) goto out; - rt->dst.lwtstate = lwtstate_get(lwtstate); - lwtunnel_set_redirect(&rt->dst); + rt->fib6_nh.nh_lwtstate = lwtstate_get(lwtstate); } - 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; + ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); + rt->fib6_dst.plen = cfg->fc_dst_len; + if (rt->fib6_dst.plen == 128) + rt->dst_host = true; #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; + ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len); + rt->fib6_src.plen = cfg->fc_src_len; #endif - rt->rt6i_metric = cfg->fc_metric; - rt->rt6i_nh_weight = 1; + rt->fib6_metric = cfg->fc_metric; + rt->fib6_nh.nh_weight = 1; + + rt->fib6_type = cfg->fc_type; /* We cannot add true routes via loopback here, they would result in kernel looping; promote them to reject routes @@ -2906,28 +3080,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, goto out; } } - rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP; - switch (cfg->fc_type) { - case RTN_BLACKHOLE: - rt->dst.error = -EINVAL; - rt->dst.output = dst_discard_out; - rt->dst.input = dst_discard; - break; - case RTN_PROHIBIT: - rt->dst.error = -EACCES; - rt->dst.output = ip6_pkt_prohibit_out; - rt->dst.input = ip6_pkt_prohibit; - break; - case RTN_THROW: - case RTN_UNREACHABLE: - default: - rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN - : (cfg->fc_type == RTN_UNREACHABLE) - ? -EHOSTUNREACH : -ENETUNREACH; - rt->dst.output = ip6_pkt_discard_out; - rt->dst.input = ip6_pkt_discard; - break; - } + rt->fib6_flags = RTF_REJECT|RTF_NONEXTHOP; goto install_route; } @@ -2936,7 +3089,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, if (err) goto out; - rt->rt6i_gateway = cfg->fc_gateway; + rt->fib6_nh.nh_gw = cfg->fc_gateway; } err = -ENODEV; @@ -2961,96 +3114,82 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, err = -EINVAL; goto out; } - rt->rt6i_prefsrc.addr = cfg->fc_prefsrc; - rt->rt6i_prefsrc.plen = 128; + rt->fib6_prefsrc.addr = cfg->fc_prefsrc; + rt->fib6_prefsrc.plen = 128; } else - rt->rt6i_prefsrc.plen = 0; + rt->fib6_prefsrc.plen = 0; - rt->rt6i_flags = cfg->fc_flags; + rt->fib6_flags = cfg->fc_flags; install_route: - if (!(rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) && + if (!(rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) && !netif_carrier_ok(dev)) - rt->rt6i_nh_flags |= RTNH_F_LINKDOWN; - rt->rt6i_nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK); - rt->dst.dev = dev; - rt->rt6i_idev = idev; - rt->rt6i_table = table; + rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN; + rt->fib6_nh.nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK); + rt->fib6_nh.nh_dev = dev; + rt->fib6_table = table; cfg->fc_nlinfo.nl_net = dev_net(dev); + if (idev) + in6_dev_put(idev); + return rt; out: if (dev) dev_put(dev); if (idev) in6_dev_put(idev); - if (rt) - dst_release_immediate(&rt->dst); + fib6_info_release(rt); return ERR_PTR(err); } -int ip6_route_add(struct fib6_config *cfg, +int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { - struct mx6_config mxc = { .mx = NULL, }; - struct rt6_info *rt; + struct fib6_info *rt; int err; - rt = ip6_route_info_create(cfg, extack); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - rt = NULL; - goto out; - } - - err = ip6_convert_metrics(&mxc, cfg); - if (err) - goto out; - - err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc, extack); - - kfree(mxc.mx); + rt = ip6_route_info_create(cfg, gfp_flags, extack); + if (IS_ERR(rt)) + return PTR_ERR(rt); - return err; -out: - if (rt) - dst_release_immediate(&rt->dst); + err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack); + fib6_info_release(rt); return err; } -static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) +static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info) { - int err; + struct net *net = info->nl_net; struct fib6_table *table; - struct net *net = dev_net(rt->dst.dev); + int err; - if (rt == net->ipv6.ip6_null_entry) { + if (rt == net->ipv6.fib6_null_entry) { err = -ENOENT; goto out; } - table = rt->rt6i_table; + table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); spin_unlock_bh(&table->tb6_lock); out: - ip6_rt_put(rt); + fib6_info_release(rt); return err; } -int ip6_del_rt(struct rt6_info *rt) +int ip6_del_rt(struct net *net, struct fib6_info *rt) { - struct nl_info info = { - .nl_net = dev_net(rt->dst.dev), - }; + struct nl_info info = { .nl_net = net }; + return __ip6_del_rt(rt, &info); } -static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) +static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) { struct nl_info *info = &cfg->fc_nlinfo; struct net *net = info->nl_net; @@ -3058,20 +3197,20 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) struct fib6_table *table; int err = -ENOENT; - if (rt == net->ipv6.ip6_null_entry) + if (rt == net->ipv6.fib6_null_entry) goto out_put; - table = rt->rt6i_table; + table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); - if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) { - struct rt6_info *sibling, *next_sibling; + if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { + struct fib6_info *sibling, *next_sibling; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (skb) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; - if (rt6_fill_node(net, skb, rt, + if (rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_DELROUTE, info->portid, seq, 0) < 0) { kfree_skb(skb); @@ -3081,8 +3220,8 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) } list_for_each_entry_safe(sibling, next_sibling, - &rt->rt6i_siblings, - rt6i_siblings) { + &rt->fib6_siblings, + fib6_siblings) { err = fib6_del(sibling, info); if (err) goto out_unlock; @@ -3093,7 +3232,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) out_unlock: spin_unlock_bh(&table->tb6_lock); out_put: - ip6_rt_put(rt); + fib6_info_release(rt); if (skb) { rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, @@ -3102,11 +3241,28 @@ out_put: return err; } +static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg) +{ + int rc = -ESRCH; + + if (cfg->fc_ifindex && rt->dst.dev->ifindex != cfg->fc_ifindex) + goto out; + + if (cfg->fc_flags & RTF_GATEWAY && + !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) + goto out; + if (dst_hold_safe(&rt->dst)) + rc = rt6_remove_exception_rt(rt); +out: + return rc; +} + static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { - struct rt6_info *rt, *rt_cache; + struct rt6_info *rt_cache; struct fib6_table *table; + struct fib6_info *rt; struct fib6_node *fn; int err = -ESRCH; @@ -3126,25 +3282,31 @@ static int ip6_route_del(struct fib6_config *cfg, if (fn) { for_each_fib6_node_rt_rcu(fn) { if (cfg->fc_flags & RTF_CACHE) { + int rc; + rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst, &cfg->fc_src); - if (!rt_cache) - continue; - rt = rt_cache; + if (rt_cache) { + rc = ip6_del_cached_rt(rt_cache, cfg); + if (rc != -ESRCH) { + rcu_read_unlock(); + return rc; + } + } + continue; } if (cfg->fc_ifindex && - (!rt->dst.dev || - rt->dst.dev->ifindex != cfg->fc_ifindex)) + (!rt->fib6_nh.nh_dev || + rt->fib6_nh.nh_dev->ifindex != cfg->fc_ifindex)) continue; if (cfg->fc_flags & RTF_GATEWAY && - !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) + !ipv6_addr_equal(&cfg->fc_gateway, &rt->fib6_nh.nh_gw)) continue; - if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric) + if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric) continue; - if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol) + if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; - if (!dst_hold_safe(&rt->dst)) - break; + fib6_info_hold(rt); rcu_read_unlock(); /* if gateway was specified only delete the one hop */ @@ -3166,6 +3328,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu struct ndisc_options ndopts; struct inet6_dev *in6_dev; struct neighbour *neigh; + struct fib6_info *from; struct rd_msg *msg; int optlen, on_link; u8 *lladdr; @@ -3247,7 +3410,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu NEIGH_UPDATE_F_ISROUTER)), NDISC_REDIRECT, &ndopts); - nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL); + rcu_read_lock(); + from = rcu_dereference(rt->from); + fib6_info_hold(from); + rcu_read_unlock(); + + nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL); if (!nrt) goto out; @@ -3255,14 +3423,13 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; - nrt->rt6i_protocol = RTPROT_REDIRECT; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; /* No need to remove rt from the exception table if rt is * a cached route because rt6_insert_exception() will * takes care of it */ - if (rt6_insert_exception(nrt, rt)) { + if (rt6_insert_exception(nrt, from)) { dst_release_immediate(&nrt->dst); goto out; } @@ -3274,47 +3441,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); out: + fib6_info_release(from); neigh_release(neigh); } -/* - * Misc support functions - */ - -static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from) -{ - BUG_ON(from->from); - - rt->rt6i_flags &= ~RTF_EXPIRES; - dst_hold(&from->dst); - rt->from = from; - dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true); -} - -static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort) -{ - rt->dst.input = ort->dst.input; - rt->dst.output = ort->dst.output; - rt->rt6i_dst = ort->rt6i_dst; - rt->dst.error = ort->dst.error; - rt->rt6i_idev = ort->rt6i_idev; - if (rt->rt6i_idev) - in6_dev_hold(rt->rt6i_idev); - rt->dst.lastuse = jiffies; - rt->rt6i_gateway = ort->rt6i_gateway; - rt->rt6i_flags = ort->rt6i_flags; - rt6_set_from(rt, ort); - rt->rt6i_metric = ort->rt6i_metric; -#ifdef CONFIG_IPV6_SUBTREES - rt->rt6i_src = ort->rt6i_src; -#endif - rt->rt6i_prefsrc = ort->rt6i_prefsrc; - rt->rt6i_table = ort->rt6i_table; - rt->dst.lwtstate = lwtstate_get(ort->dst.lwtstate); -} - #ifdef CONFIG_IPV6_ROUTE_INFO -static struct rt6_info *rt6_get_route_info(struct net *net, +static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev) @@ -3322,7 +3454,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; int ifindex = dev->ifindex; struct fib6_node *fn; - struct rt6_info *rt = NULL; + struct fib6_info *rt = NULL; struct fib6_table *table; table = fib6_get_table(net, tb_id); @@ -3335,13 +3467,13 @@ static struct rt6_info *rt6_get_route_info(struct net *net, goto out; for_each_fib6_node_rt_rcu(fn) { - if (rt->dst.dev->ifindex != ifindex) + if (rt->fib6_nh.nh_dev->ifindex != ifindex) continue; - if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) + if ((rt->fib6_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) continue; - if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr)) + if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr)) continue; - ip6_hold_safe(NULL, &rt, false); + fib6_info_hold(rt); break; } out: @@ -3349,7 +3481,7 @@ out: return rt; } -static struct rt6_info *rt6_add_route_info(struct net *net, +static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, @@ -3362,6 +3494,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), .fc_protocol = RTPROT_RA, + .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, @@ -3375,36 +3508,39 @@ static struct rt6_info *rt6_add_route_info(struct net *net, if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; - ip6_route_add(&cfg, NULL); + ip6_route_add(&cfg, GFP_ATOMIC, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } #endif -struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev) +struct fib6_info *rt6_get_dflt_router(struct net *net, + const struct in6_addr *addr, + struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT; - struct rt6_info *rt; + struct fib6_info *rt; struct fib6_table *table; - table = fib6_get_table(dev_net(dev), tb_id); + table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { - if (dev == rt->dst.dev && - ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && - ipv6_addr_equal(&rt->rt6i_gateway, addr)) + if (dev == rt->fib6_nh.nh_dev && + ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && + ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr)) break; } if (rt) - ip6_hold_safe(NULL, &rt, false); + fib6_info_hold(rt); rcu_read_unlock(); return rt; } -struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, +struct fib6_info *rt6_add_dflt_router(struct net *net, + const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { @@ -3415,14 +3551,15 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), .fc_protocol = RTPROT_RA, + .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, - .fc_nlinfo.nl_net = dev_net(dev), + .fc_nlinfo.nl_net = net, }; cfg.fc_gateway = *gwaddr; - if (!ip6_route_add(&cfg, NULL)) { + if (!ip6_route_add(&cfg, GFP_ATOMIC, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); @@ -3430,24 +3567,25 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, table->flags |= RT6_TABLE_HAS_DFLT_ROUTER; } - return rt6_get_dflt_router(gwaddr, dev); + return rt6_get_dflt_router(net, gwaddr, dev); } -static void __rt6_purge_dflt_routers(struct fib6_table *table) +static void __rt6_purge_dflt_routers(struct net *net, + struct fib6_table *table) { - struct rt6_info *rt; + struct fib6_info *rt; restart: rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && - (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { - if (dst_hold_safe(&rt->dst)) { - rcu_read_unlock(); - ip6_del_rt(rt); - } else { - rcu_read_unlock(); - } + struct net_device *dev = fib6_info_nh_dev(rt); + struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; + + if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && + (!idev || idev->cnf.accept_ra != 2)) { + fib6_info_hold(rt); + rcu_read_unlock(); + ip6_del_rt(net, rt); goto restart; } } @@ -3468,7 +3606,7 @@ void rt6_purge_dflt_routers(struct net *net) head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER) - __rt6_purge_dflt_routers(table); + __rt6_purge_dflt_routers(net, table); } } @@ -3489,6 +3627,7 @@ static void rtmsg_to_fib6_config(struct net *net, cfg->fc_dst_len = rtmsg->rtmsg_dst_len; cfg->fc_src_len = rtmsg->rtmsg_src_len; cfg->fc_flags = rtmsg->rtmsg_flags; + cfg->fc_type = rtmsg->rtmsg_type; cfg->fc_nlinfo.nl_net = net; @@ -3518,7 +3657,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) rtnl_lock(); switch (cmd) { case SIOCADDRT: - err = ip6_route_add(&cfg, NULL); + err = ip6_route_add(&cfg, GFP_KERNEL, NULL); break; case SIOCDELRT: err = ip6_route_del(&cfg, NULL); @@ -3546,7 +3685,8 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); if (type == IPV6_ADDR_ANY) { - IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), + IP6_INC_STATS(dev_net(dst->dev), + __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INADDRERRORS); break; } @@ -3587,40 +3727,40 @@ static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff * Allocate a dst for local (unicast / anycast) address. */ -struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, - const struct in6_addr *addr, - bool anycast) +struct fib6_info *addrconf_f6i_alloc(struct net *net, + struct inet6_dev *idev, + const struct in6_addr *addr, + bool anycast, gfp_t gfp_flags) { u32 tb_id; - struct net *net = dev_net(idev->dev); struct net_device *dev = idev->dev; - struct rt6_info *rt; + struct fib6_info *f6i; - rt = ip6_dst_alloc(net, dev, DST_NOCOUNT); - if (!rt) + f6i = fib6_info_alloc(gfp_flags); + if (!f6i) return ERR_PTR(-ENOMEM); - in6_dev_hold(idev); - - rt->dst.flags |= DST_HOST; - rt->dst.input = ip6_input; - rt->dst.output = ip6_output; - rt->rt6i_idev = idev; - - rt->rt6i_protocol = RTPROT_KERNEL; - rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; - if (anycast) - rt->rt6i_flags |= RTF_ANYCAST; - else - rt->rt6i_flags |= RTF_LOCAL; + f6i->dst_nocount = true; + f6i->dst_host = true; + f6i->fib6_protocol = RTPROT_KERNEL; + f6i->fib6_flags = RTF_UP | RTF_NONEXTHOP; + if (anycast) { + f6i->fib6_type = RTN_ANYCAST; + f6i->fib6_flags |= RTF_ANYCAST; + } else { + f6i->fib6_type = RTN_LOCAL; + f6i->fib6_flags |= RTF_LOCAL; + } - rt->rt6i_gateway = *addr; - rt->rt6i_dst.addr = *addr; - rt->rt6i_dst.plen = 128; + f6i->fib6_nh.nh_gw = *addr; + dev_hold(dev); + f6i->fib6_nh.nh_dev = dev; + f6i->fib6_dst.addr = *addr; + f6i->fib6_dst.plen = 128; tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; - rt->rt6i_table = fib6_get_table(net, tb_id); + f6i->fib6_table = fib6_get_table(net, tb_id); - return rt; + return f6i; } /* remove deleted ip from prefsrc entries */ @@ -3630,18 +3770,18 @@ struct arg_dev_net_ip { struct in6_addr *addr; }; -static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg) +static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) { struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev; struct net *net = ((struct arg_dev_net_ip *)arg)->net; struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; - if (((void *)rt->dst.dev == dev || !dev) && - rt != net->ipv6.ip6_null_entry && - ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) { + if (((void *)rt->fib6_nh.nh_dev == dev || !dev) && + rt != net->ipv6.fib6_null_entry && + ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr)) { spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ - rt->rt6i_prefsrc.plen = 0; + rt->fib6_prefsrc.plen = 0; /* need to update cache as well */ rt6_exceptions_remove_prefsrc(rt); spin_unlock_bh(&rt6_exception_lock); @@ -3663,12 +3803,12 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) /* Remove routers and update dst entries when gateway turn into host. */ -static int fib6_clean_tohost(struct rt6_info *rt, void *arg) +static int fib6_clean_tohost(struct fib6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; - if (((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && - ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { + if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && + ipv6_addr_equal(gateway, &rt->fib6_nh.nh_gw)) { return -1; } @@ -3694,85 +3834,85 @@ struct arg_netdev_event { }; }; -static struct rt6_info *rt6_multipath_first_sibling(const struct rt6_info *rt) +static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) { - struct rt6_info *iter; + struct fib6_info *iter; struct fib6_node *fn; - fn = rcu_dereference_protected(rt->rt6i_node, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&rt->fib6_table->tb6_lock)); iter = rcu_dereference_protected(fn->leaf, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { - if (iter->rt6i_metric == rt->rt6i_metric && - rt6_qualify_for_ecmp(iter)) + if (iter->fib6_metric == rt->fib6_metric && + iter->fib6_nsiblings) return iter; - iter = rcu_dereference_protected(iter->rt6_next, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + iter = rcu_dereference_protected(iter->fib6_next, + lockdep_is_held(&rt->fib6_table->tb6_lock)); } return NULL; } -static bool rt6_is_dead(const struct rt6_info *rt) +static bool rt6_is_dead(const struct fib6_info *rt) { - if (rt->rt6i_nh_flags & RTNH_F_DEAD || - (rt->rt6i_nh_flags & RTNH_F_LINKDOWN && - rt->rt6i_idev->cnf.ignore_routes_with_linkdown)) + if (rt->fib6_nh.nh_flags & RTNH_F_DEAD || + (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN && + fib6_ignore_linkdown(rt))) return true; return false; } -static int rt6_multipath_total_weight(const struct rt6_info *rt) +static int rt6_multipath_total_weight(const struct fib6_info *rt) { - struct rt6_info *iter; + struct fib6_info *iter; int total = 0; if (!rt6_is_dead(rt)) - total += rt->rt6i_nh_weight; + total += rt->fib6_nh.nh_weight; - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) { + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { if (!rt6_is_dead(iter)) - total += iter->rt6i_nh_weight; + total += iter->fib6_nh.nh_weight; } return total; } -static void rt6_upper_bound_set(struct rt6_info *rt, int *weight, int total) +static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total) { int upper_bound = -1; if (!rt6_is_dead(rt)) { - *weight += rt->rt6i_nh_weight; + *weight += rt->fib6_nh.nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31, total) - 1; } - atomic_set(&rt->rt6i_nh_upper_bound, upper_bound); + atomic_set(&rt->fib6_nh.nh_upper_bound, upper_bound); } -static void rt6_multipath_upper_bound_set(struct rt6_info *rt, int total) +static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total) { - struct rt6_info *iter; + struct fib6_info *iter; int weight = 0; rt6_upper_bound_set(rt, &weight, total); - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) rt6_upper_bound_set(iter, &weight, total); } -void rt6_multipath_rebalance(struct rt6_info *rt) +void rt6_multipath_rebalance(struct fib6_info *rt) { - struct rt6_info *first; + struct fib6_info *first; int total; /* In case the entire multipath route was marked for flushing, * then there is no need to rebalance upon the removal of every * sibling route. */ - if (!rt->rt6i_nsiblings || rt->should_flush) + if (!rt->fib6_nsiblings || rt->should_flush) return; /* During lookup routes are evaluated in order, so we need to @@ -3787,14 +3927,14 @@ void rt6_multipath_rebalance(struct rt6_info *rt) rt6_multipath_upper_bound_set(first, total); } -static int fib6_ifup(struct rt6_info *rt, void *p_arg) +static int fib6_ifup(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; - const struct net *net = dev_net(arg->dev); + struct net *net = dev_net(arg->dev); - if (rt != net->ipv6.ip6_null_entry && rt->dst.dev == arg->dev) { - rt->rt6i_nh_flags &= ~arg->nh_flags; - fib6_update_sernum_upto_root(dev_net(rt->dst.dev), rt); + if (rt != net->ipv6.fib6_null_entry && rt->fib6_nh.nh_dev == arg->dev) { + rt->fib6_nh.nh_flags &= ~arg->nh_flags; + fib6_update_sernum_upto_root(net, rt); rt6_multipath_rebalance(rt); } @@ -3816,95 +3956,96 @@ void rt6_sync_up(struct net_device *dev, unsigned int nh_flags) fib6_clean_all(dev_net(dev), fib6_ifup, &arg); } -static bool rt6_multipath_uses_dev(const struct rt6_info *rt, +static bool rt6_multipath_uses_dev(const struct fib6_info *rt, const struct net_device *dev) { - struct rt6_info *iter; + struct fib6_info *iter; - if (rt->dst.dev == dev) + if (rt->fib6_nh.nh_dev == dev) return true; - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) - if (iter->dst.dev == dev) + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) + if (iter->fib6_nh.nh_dev == dev) return true; return false; } -static void rt6_multipath_flush(struct rt6_info *rt) +static void rt6_multipath_flush(struct fib6_info *rt) { - struct rt6_info *iter; + struct fib6_info *iter; rt->should_flush = 1; - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) iter->should_flush = 1; } -static unsigned int rt6_multipath_dead_count(const struct rt6_info *rt, +static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt, const struct net_device *down_dev) { - struct rt6_info *iter; + struct fib6_info *iter; unsigned int dead = 0; - if (rt->dst.dev == down_dev || rt->rt6i_nh_flags & RTNH_F_DEAD) + if (rt->fib6_nh.nh_dev == down_dev || + rt->fib6_nh.nh_flags & RTNH_F_DEAD) dead++; - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) - if (iter->dst.dev == down_dev || - iter->rt6i_nh_flags & RTNH_F_DEAD) + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) + if (iter->fib6_nh.nh_dev == down_dev || + iter->fib6_nh.nh_flags & RTNH_F_DEAD) dead++; return dead; } -static void rt6_multipath_nh_flags_set(struct rt6_info *rt, +static void rt6_multipath_nh_flags_set(struct fib6_info *rt, const struct net_device *dev, unsigned int nh_flags) { - struct rt6_info *iter; + struct fib6_info *iter; - if (rt->dst.dev == dev) - rt->rt6i_nh_flags |= nh_flags; - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) - if (iter->dst.dev == dev) - iter->rt6i_nh_flags |= nh_flags; + if (rt->fib6_nh.nh_dev == dev) + rt->fib6_nh.nh_flags |= nh_flags; + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) + if (iter->fib6_nh.nh_dev == dev) + iter->fib6_nh.nh_flags |= nh_flags; } /* called with write lock held for table with rt */ -static int fib6_ifdown(struct rt6_info *rt, void *p_arg) +static int fib6_ifdown(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; const struct net_device *dev = arg->dev; - const struct net *net = dev_net(dev); + struct net *net = dev_net(dev); - if (rt == net->ipv6.ip6_null_entry) + if (rt == net->ipv6.fib6_null_entry) return 0; switch (arg->event) { case NETDEV_UNREGISTER: - return rt->dst.dev == dev ? -1 : 0; + return rt->fib6_nh.nh_dev == dev ? -1 : 0; case NETDEV_DOWN: if (rt->should_flush) return -1; - if (!rt->rt6i_nsiblings) - return rt->dst.dev == dev ? -1 : 0; + if (!rt->fib6_nsiblings) + return rt->fib6_nh.nh_dev == dev ? -1 : 0; if (rt6_multipath_uses_dev(rt, dev)) { unsigned int count; count = rt6_multipath_dead_count(rt, dev); - if (rt->rt6i_nsiblings + 1 == count) { + if (rt->fib6_nsiblings + 1 == count) { rt6_multipath_flush(rt); return -1; } rt6_multipath_nh_flags_set(rt, dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); - fib6_update_sernum(rt); + fib6_update_sernum(net, rt); rt6_multipath_rebalance(rt); } return -2; case NETDEV_CHANGE: - if (rt->dst.dev != dev || - rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) + if (rt->fib6_nh.nh_dev != dev || + rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) break; - rt->rt6i_nh_flags |= RTNH_F_LINKDOWN; + rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN; rt6_multipath_rebalance(rt); break; } @@ -3936,7 +4077,7 @@ struct rt6_mtu_change_arg { unsigned int mtu; }; -static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) +static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; @@ -3956,12 +4097,15 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) Since RFC 1981 doesn't include administrative MTU increase update PMTU increase is a MUST. (i.e. jumbo frame) */ - if (rt->dst.dev == arg->dev && - !dst_metric_locked(&rt->dst, RTAX_MTU)) { + if (rt->fib6_nh.nh_dev == arg->dev && + !fib6_metric_locked(rt, RTAX_MTU)) { + u32 mtu = rt->fib6_pmtu; + + if (mtu >= arg->mtu || + (mtu < arg->mtu && mtu == idev->cnf.mtu6)) + fib6_metric_set(rt, RTAX_MTU, arg->mtu); + spin_lock_bh(&rt6_exception_lock); - if (dst_metric_raw(&rt->dst, RTAX_MTU) && - rt6_mtu_change_route_allowed(idev, rt, arg->mtu)) - dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); rt6_exceptions_update_pmtu(idev, rt, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } @@ -3993,6 +4137,9 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, + [RTA_IP_PROTO] = { .type = NLA_U8 }, + [RTA_SPORT] = { .type = NLA_U16 }, + [RTA_DPORT] = { .type = NLA_U16 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -4122,9 +4269,8 @@ errout: } struct rt6_nh { - struct rt6_info *rt6_info; + struct fib6_info *fib6_info; struct fib6_config r_cfg; - struct mx6_config mxc; struct list_head next; }; @@ -4139,23 +4285,25 @@ static void ip6_print_replace_route_err(struct list_head *rt6_nh_list) } } -static int ip6_route_info_append(struct list_head *rt6_nh_list, - struct rt6_info *rt, struct fib6_config *r_cfg) +static int ip6_route_info_append(struct net *net, + struct list_head *rt6_nh_list, + struct fib6_info *rt, + struct fib6_config *r_cfg) { struct rt6_nh *nh; int err = -EEXIST; list_for_each_entry(nh, rt6_nh_list, next) { - /* check if rt6_info already exists */ - if (rt6_duplicate_nexthop(nh->rt6_info, rt)) + /* check if fib6_info already exists */ + if (rt6_duplicate_nexthop(nh->fib6_info, rt)) return err; } nh = kzalloc(sizeof(*nh), GFP_KERNEL); if (!nh) return -ENOMEM; - nh->rt6_info = rt; - err = ip6_convert_metrics(&nh->mxc, r_cfg); + nh->fib6_info = rt; + err = ip6_convert_metrics(net, rt, r_cfg); if (err) { kfree(nh); return err; @@ -4166,8 +4314,8 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list, return 0; } -static void ip6_route_mpath_notify(struct rt6_info *rt, - struct rt6_info *rt_last, +static void ip6_route_mpath_notify(struct fib6_info *rt, + struct fib6_info *rt_last, struct nl_info *info, __u16 nlflags) { @@ -4177,10 +4325,10 @@ static void ip6_route_mpath_notify(struct rt6_info *rt, * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ - if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->rt6i_nsiblings) { - rt = list_first_entry(&rt_last->rt6i_siblings, - struct rt6_info, - rt6i_siblings); + if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { + rt = list_first_entry(&rt_last->fib6_siblings, + struct fib6_info, + fib6_siblings); } if (rt) @@ -4190,11 +4338,11 @@ static void ip6_route_mpath_notify(struct rt6_info *rt, static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { - struct rt6_info *rt_notif = NULL, *rt_last = NULL; + struct fib6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; struct fib6_config r_cfg; struct rtnexthop *rtnh; - struct rt6_info *rt; + struct fib6_info *rt; struct rt6_nh *err_nh; struct rt6_nh *nh, *nh_safe; __u16 nlflags; @@ -4214,7 +4362,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry and build a list (rt6_nh_list) of - * rt6_info structs per nexthop + * fib6_info structs per nexthop */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); @@ -4237,18 +4385,19 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, } r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); - rt = ip6_route_info_create(&r_cfg, extack); + rt = ip6_route_info_create(&r_cfg, GFP_KERNEL, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto cleanup; } - rt->rt6i_nh_weight = rtnh->rtnh_hops + 1; + rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1; - err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); + err = ip6_route_info_append(info->nl_net, &rt6_nh_list, + rt, &r_cfg); if (err) { - dst_release_immediate(&rt->dst); + fib6_info_release(rt); goto cleanup; } @@ -4263,14 +4412,20 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { - rt_last = nh->rt6_info; - err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc, extack); - /* save reference to first route for notification */ - if (!rt_notif && !err) - rt_notif = nh->rt6_info; - - /* nh->rt6_info is used or freed at this point, reset to NULL*/ - nh->rt6_info = NULL; + err = __ip6_ins_rt(nh->fib6_info, info, extack); + fib6_info_release(nh->fib6_info); + + if (!err) { + /* save reference to last route successfully inserted */ + rt_last = nh->fib6_info; + + /* save reference to first route for notification */ + if (!rt_notif) + rt_notif = nh->fib6_info; + } + + /* nh->fib6_info is used or freed at this point, reset to NULL*/ + nh->fib6_info = NULL; if (err) { if (replace && nhn) ip6_print_replace_route_err(&rt6_nh_list); @@ -4287,6 +4442,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_APPEND; nhn++; } @@ -4311,9 +4467,8 @@ add_errout: cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { - if (nh->rt6_info) - dst_release_immediate(&nh->rt6_info->dst); - kfree(nh->mxc.mx); + if (nh->fib6_info) + fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } @@ -4390,20 +4545,20 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (cfg.fc_mp) return ip6_route_multipath_add(&cfg, extack); else - return ip6_route_add(&cfg, extack); + return ip6_route_add(&cfg, GFP_KERNEL, extack); } -static size_t rt6_nlmsg_size(struct rt6_info *rt) +static size_t rt6_nlmsg_size(struct fib6_info *rt) { int nexthop_len = 0; - if (rt->rt6i_nsiblings) { + if (rt->fib6_nsiblings) { nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */ + NLA_ALIGN(sizeof(struct rtnexthop)) + nla_total_size(16) /* RTA_GATEWAY */ - + lwtunnel_get_encap_size(rt->dst.lwtstate); + + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate); - nexthop_len *= rt->rt6i_nsiblings; + nexthop_len *= rt->fib6_nsiblings; } return NLMSG_ALIGN(sizeof(struct rtmsg)) @@ -4419,38 +4574,41 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt) + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ + nla_total_size(1) /* RTA_PREF */ - + lwtunnel_get_encap_size(rt->dst.lwtstate) + + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate) + nexthop_len; } -static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt, +static int rt6_nexthop_info(struct sk_buff *skb, struct fib6_info *rt, unsigned int *flags, bool skip_oif) { - if (rt->rt6i_nh_flags & RTNH_F_DEAD) + if (rt->fib6_nh.nh_flags & RTNH_F_DEAD) *flags |= RTNH_F_DEAD; - if (rt->rt6i_nh_flags & RTNH_F_LINKDOWN) { + if (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN) { *flags |= RTNH_F_LINKDOWN; - if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown) + + rcu_read_lock(); + if (fib6_ignore_linkdown(rt)) *flags |= RTNH_F_DEAD; + rcu_read_unlock(); } - if (rt->rt6i_flags & RTF_GATEWAY) { - if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->rt6i_gateway) < 0) + if (rt->fib6_flags & RTF_GATEWAY) { + if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->fib6_nh.nh_gw) < 0) goto nla_put_failure; } - *flags |= (rt->rt6i_nh_flags & RTNH_F_ONLINK); - if (rt->rt6i_nh_flags & RTNH_F_OFFLOAD) + *flags |= (rt->fib6_nh.nh_flags & RTNH_F_ONLINK); + if (rt->fib6_nh.nh_flags & RTNH_F_OFFLOAD) *flags |= RTNH_F_OFFLOAD; /* not needed for multipath encoding b/c it has a rtnexthop struct */ - if (!skip_oif && rt->dst.dev && - nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) + if (!skip_oif && rt->fib6_nh.nh_dev && + nla_put_u32(skb, RTA_OIF, rt->fib6_nh.nh_dev->ifindex)) goto nla_put_failure; - if (rt->dst.lwtstate && - lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0) + if (rt->fib6_nh.nh_lwtstate && + lwtunnel_fill_encap(skb, rt->fib6_nh.nh_lwtstate) < 0) goto nla_put_failure; return 0; @@ -4460,8 +4618,9 @@ nla_put_failure: } /* add multipath next hop */ -static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt) +static int rt6_add_nexthop(struct sk_buff *skb, struct fib6_info *rt) { + const struct net_device *dev = rt->fib6_nh.nh_dev; struct rtnexthop *rtnh; unsigned int flags = 0; @@ -4469,8 +4628,8 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt) if (!rtnh) goto nla_put_failure; - rtnh->rtnh_hops = rt->rt6i_nh_weight - 1; - rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0; + rtnh->rtnh_hops = rt->fib6_nh.nh_weight - 1; + rtnh->rtnh_ifindex = dev ? dev->ifindex : 0; if (rt6_nexthop_info(skb, rt, &flags, true) < 0) goto nla_put_failure; @@ -4486,16 +4645,16 @@ nla_put_failure: return -EMSGSIZE; } -static int rt6_fill_node(struct net *net, - struct sk_buff *skb, struct rt6_info *rt, - struct in6_addr *dst, struct in6_addr *src, +static int rt6_fill_node(struct net *net, struct sk_buff *skb, + struct fib6_info *rt, struct dst_entry *dst, + struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags) { - u32 metrics[RTAX_MAX]; struct rtmsg *rtm; struct nlmsghdr *nlh; - long expires; + long expires = 0; + u32 *pmetrics; u32 table; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); @@ -4504,53 +4663,31 @@ static int rt6_fill_node(struct net *net, rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; - rtm->rtm_dst_len = rt->rt6i_dst.plen; - rtm->rtm_src_len = rt->rt6i_src.plen; + rtm->rtm_dst_len = rt->fib6_dst.plen; + rtm->rtm_src_len = rt->fib6_src.plen; rtm->rtm_tos = 0; - if (rt->rt6i_table) - table = rt->rt6i_table->tb6_id; + if (rt->fib6_table) + table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; rtm->rtm_table = table; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; - if (rt->rt6i_flags & RTF_REJECT) { - switch (rt->dst.error) { - case -EINVAL: - rtm->rtm_type = RTN_BLACKHOLE; - break; - case -EACCES: - rtm->rtm_type = RTN_PROHIBIT; - break; - case -EAGAIN: - rtm->rtm_type = RTN_THROW; - break; - default: - rtm->rtm_type = RTN_UNREACHABLE; - break; - } - } - else if (rt->rt6i_flags & RTF_LOCAL) - rtm->rtm_type = RTN_LOCAL; - else if (rt->rt6i_flags & RTF_ANYCAST) - rtm->rtm_type = RTN_ANYCAST; - else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK)) - rtm->rtm_type = RTN_LOCAL; - else - rtm->rtm_type = RTN_UNICAST; + + rtm->rtm_type = rt->fib6_type; rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; - rtm->rtm_protocol = rt->rt6i_protocol; + rtm->rtm_protocol = rt->fib6_protocol; - if (rt->rt6i_flags & RTF_CACHE) + if (rt->fib6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; - if (dst) { - if (nla_put_in6_addr(skb, RTA_DST, dst)) + if (dest) { + if (nla_put_in6_addr(skb, RTA_DST, dest)) goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - if (nla_put_in6_addr(skb, RTA_DST, &rt->rt6i_dst.addr)) + if (nla_put_in6_addr(skb, RTA_DST, &rt->fib6_dst.addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { @@ -4558,12 +4695,12 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && - nla_put_in6_addr(skb, RTA_SRC, &rt->rt6i_src.addr)) + nla_put_in6_addr(skb, RTA_SRC, &rt->fib6_src.addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE - if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) { + if (ipv6_addr_is_multicast(&rt->fib6_dst.addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) @@ -4574,34 +4711,32 @@ static int rt6_fill_node(struct net *net, #endif if (nla_put_u32(skb, RTA_IIF, iif)) goto nla_put_failure; - } else if (dst) { + } else if (dest) { struct in6_addr saddr_buf; - if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0 && + if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 && nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } - if (rt->rt6i_prefsrc.plen) { + if (rt->fib6_prefsrc.plen) { struct in6_addr saddr_buf; - saddr_buf = rt->rt6i_prefsrc.addr; + saddr_buf = rt->fib6_prefsrc.addr; if (nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } - memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); - if (rt->rt6i_pmtu) - metrics[RTAX_MTU - 1] = rt->rt6i_pmtu; - if (rtnetlink_put_metrics(skb, metrics) < 0) + pmetrics = dst ? dst_metrics_ptr(dst) : rt->fib6_metrics->metrics; + if (rtnetlink_put_metrics(skb, pmetrics) < 0) goto nla_put_failure; - if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric)) + if (nla_put_u32(skb, RTA_PRIORITY, rt->fib6_metric)) goto nla_put_failure; /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ - if (rt->rt6i_nsiblings) { - struct rt6_info *sibling, *next_sibling; + if (rt->fib6_nsiblings) { + struct fib6_info *sibling, *next_sibling; struct nlattr *mp; mp = nla_nest_start(skb, RTA_MULTIPATH); @@ -4612,7 +4747,7 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; list_for_each_entry_safe(sibling, next_sibling, - &rt->rt6i_siblings, rt6i_siblings) { + &rt->fib6_siblings, fib6_siblings) { if (rt6_add_nexthop(skb, sibling) < 0) goto nla_put_failure; } @@ -4623,12 +4758,15 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; } - expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0; + if (rt->fib6_flags & RTF_EXPIRES) { + expires = dst ? dst->expires : rt->expires; + expires -= jiffies; + } - if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) + if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; - if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags))) + if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->fib6_flags))) goto nla_put_failure; @@ -4640,12 +4778,12 @@ nla_put_failure: return -EMSGSIZE; } -int rt6_dump_route(struct rt6_info *rt, void *p_arg) +int rt6_dump_route(struct fib6_info *rt, void *p_arg) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; struct net *net = arg->net; - if (rt == net->ipv6.ip6_null_entry) + if (rt == net->ipv6.fib6_null_entry) return 0; if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) { @@ -4653,16 +4791,15 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg) /* user wants prefix routes only */ if (rtm->rtm_flags & RTM_F_PREFIX && - !(rt->rt6i_flags & RTF_PREFIX_RT)) { + !(rt->fib6_flags & RTF_PREFIX_RT)) { /* success since this is not a prefix route */ return 1; } } - return rt6_fill_node(net, - arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, - NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq, - NLM_F_MULTI); + return rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0, + RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid, + arg->cb->nlh->nlmsg_seq, NLM_F_MULTI); } static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, @@ -4671,6 +4808,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; int err, iif = 0, oif = 0; + struct fib6_info *from; struct dst_entry *dst; struct rt6_info *rt; struct sk_buff *skb; @@ -4718,6 +4856,19 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, else fl6.flowi6_uid = iif ? INVALID_UID : current_uid(); + if (tb[RTA_SPORT]) + fl6.fl6_sport = nla_get_be16(tb[RTA_SPORT]); + + if (tb[RTA_DPORT]) + fl6.fl6_dport = nla_get_be16(tb[RTA_DPORT]); + + if (tb[RTA_IP_PROTO]) { + err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], + &fl6.flowi6_proto, extack); + if (err) + goto errout; + } + if (iif) { struct net_device *dev; int flags = 0; @@ -4759,14 +4910,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout; } - if (fibmatch && rt->from) { - struct rt6_info *ort = rt->from; - - dst_hold(&ort->dst); - ip6_rt_put(rt); - rt = ort; - } - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); @@ -4775,14 +4918,21 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, } skb_dst_set(skb, &rt->dst); + + rcu_read_lock(); + from = rcu_dereference(rt->from); + if (fibmatch) - err = rt6_fill_node(net, skb, rt, NULL, NULL, iif, + err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); else - err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, - RTM_NEWROUTE, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); + err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, + &fl6.saddr, iif, RTM_NEWROUTE, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, + 0); + rcu_read_unlock(); + if (err < 0) { kfree_skb(skb); goto errout; @@ -4793,7 +4943,7 @@ errout: return err; } -void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, +void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int nlm_flags) { struct sk_buff *skb; @@ -4808,8 +4958,8 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, if (!skb) goto errout; - err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, - event, info->portid, seq, nlm_flags); + err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, + event, info->portid, seq, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -4834,6 +4984,7 @@ static int ip6_route_dev_notify(struct notifier_block *this, return NOTIFY_OK; if (event == NETDEV_REGISTER) { + net->ipv6.fib6_null_entry->fib6_nh.nh_dev = dev; net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES @@ -5010,11 +5161,17 @@ static int __net_init ip6_route_net_init(struct net *net) if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) goto out_ip6_dst_ops; + net->ipv6.fib6_null_entry = kmemdup(&fib6_null_entry_template, + sizeof(*net->ipv6.fib6_null_entry), + GFP_KERNEL); + if (!net->ipv6.fib6_null_entry) + goto out_ip6_dst_entries; + net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), GFP_KERNEL); if (!net->ipv6.ip6_null_entry) - goto out_ip6_dst_entries; + goto out_fib6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_null_entry->dst, ip6_template_metrics, true); @@ -5061,6 +5218,8 @@ out_ip6_prohibit_entry: out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif +out_fib6_null_entry: + kfree(net->ipv6.fib6_null_entry); out_ip6_dst_entries: dst_entries_destroy(&net->ipv6.ip6_dst_ops); out_ip6_dst_ops: @@ -5069,6 +5228,7 @@ out_ip6_dst_ops: static void __net_exit ip6_route_net_exit(struct net *net) { + kfree(net->ipv6.fib6_null_entry); kfree(net->ipv6.ip6_null_entry); #ifdef CONFIG_IPV6_MULTIPLE_TABLES kfree(net->ipv6.ip6_prohibit_entry); @@ -5141,6 +5301,7 @@ void __init ip6_route_init_special_entries(void) /* Registering of the loopback is done before this portion of code, * the loopback reference in rt6_info will not be taken, do it * manually for init_net */ + init_net.ipv6.fib6_null_entry->fib6_nh.nh_dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 7f5621d095719..0fdf2a55e746c 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -226,7 +226,6 @@ static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) nla_put_failure: rcu_read_unlock(); - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -ENOMEM; diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index bf4763fd68c22..19ccf0dc996ca 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -91,6 +91,24 @@ static void set_tun_src(struct net *net, struct net_device *dev, rcu_read_unlock(); } +/* Compute flowlabel for outer IPv6 header */ +static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb, + struct ipv6hdr *inner_hdr) +{ + int do_flowlabel = net->ipv6.sysctl.seg6_flowlabel; + __be32 flowlabel = 0; + u32 hash; + + if (do_flowlabel > 0) { + hash = skb_get_hash(skb); + rol32(hash, 16); + flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; + } else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) { + flowlabel = ip6_flowlabel(inner_hdr); + } + return flowlabel; +} + /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) { @@ -99,6 +117,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) struct ipv6hdr *hdr, *inner_hdr; struct ipv6_sr_hdr *isrh; int hdrlen, tot_len, err; + __be32 flowlabel; hdrlen = (osrh->hdrlen + 1) << 3; tot_len = hdrlen + sizeof(*hdr); @@ -108,6 +127,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) return err; inner_hdr = ipv6_hdr(skb); + flowlabel = seg6_make_flowlabel(net, skb, inner_hdr); skb_push(skb, tot_len); skb_reset_network_header(skb); @@ -121,10 +141,10 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) if (skb->protocol == htons(ETH_P_IPV6)) { ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)), - ip6_flowlabel(inner_hdr)); + flowlabel); hdr->hop_limit = inner_hdr->hop_limit; } else { - ip6_flow_hdr(hdr, 0, 0); + ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 45722327375af..cd6e4cab63f6c 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -1,8 +1,9 @@ /* * SR-IPv6 implementation * - * Author: + * Authors: * David Lebrun <david.lebrun@uclouvain.be> + * eBPF support: Mathieu Xhonneux <m.xhonneux@gmail.com> * * * This program is free software; you can redistribute it and/or @@ -30,7 +31,9 @@ #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif +#include <net/seg6_local.h> #include <linux/etherdevice.h> +#include <linux/bpf.h> struct seg6_local_lwt; @@ -41,6 +44,11 @@ struct seg6_action_desc { int static_headroom; }; +struct bpf_lwt_prog { + struct bpf_prog *prog; + char *name; +}; + struct seg6_local_lwt { int action; struct ipv6_sr_hdr *srh; @@ -49,6 +57,7 @@ struct seg6_local_lwt { struct in6_addr nh6; int iif; int oif; + struct bpf_lwt_prog bpf; int headroom; struct seg6_action_desc *desc; @@ -140,8 +149,8 @@ static void advance_nextseg(struct ipv6_sr_hdr *srh, struct in6_addr *daddr) *daddr = *addr; } -static void lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, - u32 tbl_id) +int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, + u32 tbl_id) { struct net *net = dev_net(skb->dev); struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -187,6 +196,7 @@ out: skb_dst_drop(skb); skb_dst_set(skb, dst); + return dst->error; } /* regular endpoint function */ @@ -200,7 +210,7 @@ static int input_action_end(struct sk_buff *skb, struct seg6_local_lwt *slwt) advance_nextseg(srh, &ipv6_hdr(skb)->daddr); - lookup_nexthop(skb, NULL, 0); + seg6_lookup_nexthop(skb, NULL, 0); return dst_input(skb); @@ -220,7 +230,7 @@ static int input_action_end_x(struct sk_buff *skb, struct seg6_local_lwt *slwt) advance_nextseg(srh, &ipv6_hdr(skb)->daddr); - lookup_nexthop(skb, &slwt->nh6, 0); + seg6_lookup_nexthop(skb, &slwt->nh6, 0); return dst_input(skb); @@ -239,7 +249,7 @@ static int input_action_end_t(struct sk_buff *skb, struct seg6_local_lwt *slwt) advance_nextseg(srh, &ipv6_hdr(skb)->daddr); - lookup_nexthop(skb, NULL, slwt->table); + seg6_lookup_nexthop(skb, NULL, slwt->table); return dst_input(skb); @@ -331,7 +341,7 @@ static int input_action_end_dx6(struct sk_buff *skb, if (!ipv6_addr_any(&slwt->nh6)) nhaddr = &slwt->nh6; - lookup_nexthop(skb, nhaddr, 0); + seg6_lookup_nexthop(skb, nhaddr, 0); return dst_input(skb); drop: @@ -380,7 +390,7 @@ static int input_action_end_dt6(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; - lookup_nexthop(skb, NULL, slwt->table); + seg6_lookup_nexthop(skb, NULL, slwt->table); return dst_input(skb); @@ -406,7 +416,7 @@ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt) ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); - lookup_nexthop(skb, NULL, 0); + seg6_lookup_nexthop(skb, NULL, 0); return dst_input(skb); @@ -438,7 +448,7 @@ static int input_action_end_b6_encap(struct sk_buff *skb, ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); - lookup_nexthop(skb, NULL, 0); + seg6_lookup_nexthop(skb, NULL, 0); return dst_input(skb); @@ -447,6 +457,71 @@ drop: return err; } +DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states); + +static int input_action_end_bpf(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + struct seg6_bpf_srh_state *srh_state = + this_cpu_ptr(&seg6_bpf_srh_states); + struct seg6_bpf_srh_state local_srh_state; + struct ipv6_sr_hdr *srh; + int srhoff = 0; + int ret; + + srh = get_and_validate_srh(skb); + if (!srh) + goto drop; + advance_nextseg(srh, &ipv6_hdr(skb)->daddr); + + /* preempt_disable is needed to protect the per-CPU buffer srh_state, + * which is also accessed by the bpf_lwt_seg6_* helpers + */ + preempt_disable(); + srh_state->hdrlen = srh->hdrlen << 3; + srh_state->valid = 1; + + rcu_read_lock(); + bpf_compute_data_pointers(skb); + ret = bpf_prog_run_save_cb(slwt->bpf.prog, skb); + rcu_read_unlock(); + + local_srh_state = *srh_state; + preempt_enable(); + + switch (ret) { + case BPF_OK: + case BPF_REDIRECT: + break; + case BPF_DROP: + goto drop; + default: + pr_warn_once("bpf-seg6local: Illegal return value %u\n", ret); + goto drop; + } + + if (unlikely((local_srh_state.hdrlen & 7) != 0)) + goto drop; + + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + goto drop; + srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); + srh->hdrlen = (u8)(local_srh_state.hdrlen >> 3); + + if (!local_srh_state.valid && + unlikely(!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3))) + goto drop; + + if (ret != BPF_REDIRECT) + seg6_lookup_nexthop(skb, NULL, 0); + + return dst_input(skb); + +drop: + kfree_skb(skb); + return -EINVAL; +} + static struct seg6_action_desc seg6_action_table[] = { { .action = SEG6_LOCAL_ACTION_END, @@ -493,7 +568,13 @@ static struct seg6_action_desc seg6_action_table[] = { .attrs = (1 << SEG6_LOCAL_SRH), .input = input_action_end_b6_encap, .static_headroom = sizeof(struct ipv6hdr), - } + }, + { + .action = SEG6_LOCAL_ACTION_END_BPF, + .attrs = (1 << SEG6_LOCAL_BPF), + .input = input_action_end_bpf, + }, + }; static struct seg6_action_desc *__get_action_desc(int action) @@ -538,6 +619,7 @@ static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = { .len = sizeof(struct in6_addr) }, [SEG6_LOCAL_IIF] = { .type = NLA_U32 }, [SEG6_LOCAL_OIF] = { .type = NLA_U32 }, + [SEG6_LOCAL_BPF] = { .type = NLA_NESTED }, }; static int parse_nla_srh(struct nlattr **attrs, struct seg6_local_lwt *slwt) @@ -715,6 +797,75 @@ static int cmp_nla_oif(struct seg6_local_lwt *a, struct seg6_local_lwt *b) return 0; } +#define MAX_PROG_NAME 256 +static const struct nla_policy bpf_prog_policy[SEG6_LOCAL_BPF_PROG_MAX + 1] = { + [SEG6_LOCAL_BPF_PROG] = { .type = NLA_U32, }, + [SEG6_LOCAL_BPF_PROG_NAME] = { .type = NLA_NUL_STRING, + .len = MAX_PROG_NAME }, +}; + +static int parse_nla_bpf(struct nlattr **attrs, struct seg6_local_lwt *slwt) +{ + struct nlattr *tb[SEG6_LOCAL_BPF_PROG_MAX + 1]; + struct bpf_prog *p; + int ret; + u32 fd; + + ret = nla_parse_nested(tb, SEG6_LOCAL_BPF_PROG_MAX, + attrs[SEG6_LOCAL_BPF], bpf_prog_policy, NULL); + if (ret < 0) + return ret; + + if (!tb[SEG6_LOCAL_BPF_PROG] || !tb[SEG6_LOCAL_BPF_PROG_NAME]) + return -EINVAL; + + slwt->bpf.name = nla_memdup(tb[SEG6_LOCAL_BPF_PROG_NAME], GFP_KERNEL); + if (!slwt->bpf.name) + return -ENOMEM; + + fd = nla_get_u32(tb[SEG6_LOCAL_BPF_PROG]); + p = bpf_prog_get_type(fd, BPF_PROG_TYPE_LWT_SEG6LOCAL); + if (IS_ERR(p)) { + kfree(slwt->bpf.name); + return PTR_ERR(p); + } + + slwt->bpf.prog = p; + return 0; +} + +static int put_nla_bpf(struct sk_buff *skb, struct seg6_local_lwt *slwt) +{ + struct nlattr *nest; + + if (!slwt->bpf.prog) + return 0; + + nest = nla_nest_start(skb, SEG6_LOCAL_BPF); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, SEG6_LOCAL_BPF_PROG, slwt->bpf.prog->aux->id)) + return -EMSGSIZE; + + if (slwt->bpf.name && + nla_put_string(skb, SEG6_LOCAL_BPF_PROG_NAME, slwt->bpf.name)) + return -EMSGSIZE; + + return nla_nest_end(skb, nest); +} + +static int cmp_nla_bpf(struct seg6_local_lwt *a, struct seg6_local_lwt *b) +{ + if (!a->bpf.name && !b->bpf.name) + return 0; + + if (!a->bpf.name || !b->bpf.name) + return 1; + + return strcmp(a->bpf.name, b->bpf.name); +} + struct seg6_action_param { int (*parse)(struct nlattr **attrs, struct seg6_local_lwt *slwt); int (*put)(struct sk_buff *skb, struct seg6_local_lwt *slwt); @@ -745,6 +896,11 @@ static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = { [SEG6_LOCAL_OIF] = { .parse = parse_nla_oif, .put = put_nla_oif, .cmp = cmp_nla_oif }, + + [SEG6_LOCAL_BPF] = { .parse = parse_nla_bpf, + .put = put_nla_bpf, + .cmp = cmp_nla_bpf }, + }; static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt) @@ -830,6 +986,13 @@ static void seg6_local_destroy_state(struct lwtunnel_state *lwt) struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt); kfree(slwt->srh); + + if (slwt->desc->attrs & (1 << SEG6_LOCAL_BPF)) { + kfree(slwt->bpf.name); + bpf_prog_put(slwt->bpf.prog); + } + + return; } static int seg6_local_fill_encap(struct sk_buff *skb, @@ -882,6 +1045,11 @@ static int seg6_local_get_encap_size(struct lwtunnel_state *lwt) if (attrs & (1 << SEG6_LOCAL_OIF)) nlsize += nla_total_size(4); + if (attrs & (1 << SEG6_LOCAL_BPF)) + nlsize += nla_total_size(sizeof(struct nlattr)) + + nla_total_size(MAX_PROG_NAME) + + nla_total_size(4); + return nlsize; } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 6fbdef6301529..e15cd37024fd9 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -152,6 +152,13 @@ static struct ctl_table ipv6_table_template[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "seg6_flowlabel", + .data = &init_net.ipv6.sysctl.seg6_flowlabel, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -217,6 +224,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len; ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len; ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy, + ipv6_table[15].data = &net->ipv6.sysctl.seg6_flowlabel; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d2ce66b23430a..b620d9b72e595 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -803,6 +803,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 unsigned int tot_len = sizeof(struct tcphdr); struct dst_entry *dst; __be32 *topt; + __u32 mark = 0; if (tsecr) tot_len += TCPOLEN_TSTAMP_ALIGNED; @@ -871,7 +872,10 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 fl6.flowi6_oif = oif; } - fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark); + if (sk) + mark = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_mark : sk->sk_mark; + fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark; fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source; fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); @@ -1318,7 +1322,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) } } - tcp_rcv_established(sk, skb, tcp_hdr(skb)); + tcp_rcv_established(sk, skb); if (opt_skb) goto ipv6_pktoptions; return 0; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 00e2112da26d8..164afd31aebf1 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -285,9 +285,7 @@ EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb); /* Must be called under rcu_read_lock(). * Does increment socket refcount. */ -#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \ - IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY) || \ - IS_ENABLED(CONFIG_NF_SOCKET_IPV6) +#if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6) struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif) { @@ -546,10 +544,10 @@ static __inline__ void udpv6_err(struct sk_buff *skb, __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); } -static struct static_key udpv6_encap_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { - static_key_enable(&udpv6_encap_needed); + static_branch_enable(&udpv6_encap_needed_key); } EXPORT_SYMBOL(udpv6_encap_enable); @@ -561,7 +559,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; - if (static_key_false(&udpv6_encap_needed) && up->encap_type) { + if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -1023,7 +1021,8 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, * Sending */ -static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6) +static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, + struct inet_cork *cork) { struct sock *sk = skb->sk; struct udphdr *uh; @@ -1042,12 +1041,32 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6) uh->len = htons(len); uh->check = 0; + if (cork->gso_size) { + const int hlen = skb_network_header_len(skb) + + sizeof(struct udphdr); + + if (hlen + cork->gso_size > cork->fragsize) + return -EINVAL; + if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) + return -EINVAL; + if (udp_sk(sk)->no_check6_tx) + return -EINVAL; + if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || + dst_xfrm(skb_dst(skb))) + return -EIO; + + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + goto csum_partial; + } + if (is_udplite) csum = udplite_csum(skb); else if (udp_sk(sk)->no_check6_tx) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ +csum_partial: udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len); goto send; } else @@ -1093,7 +1112,7 @@ static int udp_v6_push_pending_frames(struct sock *sk) if (!skb) goto out; - err = udp_v6_send_skb(skb, &fl6); + err = udp_v6_send_skb(skb, &fl6, &inet_sk(sk)->cork.base); out: up->len = 0; @@ -1127,6 +1146,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.hlimit = -1; ipc6.tclass = -1; ipc6.dontfrag = -1; + ipc6.gso_size = up->gso_size; sockc.tsflags = sk->sk_tsflags; /* destination address check */ @@ -1259,7 +1279,10 @@ do_udp_sendmsg: opt->tot_len = sizeof(*opt); ipc6.opt = opt; - err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6, &sockc); + err = udp_cmsg_send(sk, msg, &ipc6.gso_size); + if (err > 0) + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, + &ipc6, &sockc); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1291,6 +1314,29 @@ do_udp_sendmsg: fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; + if (cgroup_bpf_enabled && !connected) { + err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, + (struct sockaddr *)sin6, &fl6.saddr); + if (err) + goto out_no_dst; + if (sin6) { + if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { + /* BPF program rewrote IPv6-only by IPv4-mapped + * IPv6. It's currently unsupported. + */ + err = -ENOTSUPP; + goto out_no_dst; + } + if (sin6->sin6_port == 0) { + /* BPF program set invalid port. Reject it. */ + err = -EINVAL; + goto out_no_dst; + } + fl6.fl6_dport = sin6->sin6_port; + fl6.daddr = sin6->sin6_addr; + } + } + final_p = fl6_update_dst(&fl6, opt, &final); if (final_p) connected = false; @@ -1324,15 +1370,16 @@ back_from_confirm: /* Lockless fast path for the non-corking case */ if (!corkreq) { + struct inet_cork_full cork; struct sk_buff *skb; skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, &fl6, (struct rt6_info *)dst, - msg->msg_flags, &sockc); + msg->msg_flags, &cork, &sockc); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) - err = udp_v6_send_skb(skb, &fl6); + err = udp_v6_send_skb(skb, &fl6, &cork.base); goto out; } @@ -1369,6 +1416,7 @@ do_append_data: out: dst_release(dst); +out_no_dst: fl6_sock_release(flowlabel); txopt_put(opt_to_free); if (!err) @@ -1402,7 +1450,7 @@ void udpv6_destroy_sock(struct sock *sk) udp_v6_flush_pending_frames(sk); release_sock(sk); - if (static_key_false(&udpv6_encap_needed) && up->encap_type) { + if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) { void (*encap_destroy)(struct sock *sk); encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 2a04dc9c781b5..03a2ff3fe1e69 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -42,12 +42,15 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, const struct ipv6hdr *ipv6h; struct udphdr *uh; - if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP)) + if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + return __udp_gso_segment(skb, features); + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot * do checksum of UDP packets sent as multiple IP fragments. */ diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 86dba282a147c..ef3defaf43b9a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -107,8 +107,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, * it was magically lost, so this code needs audit */ xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | RTF_LOCAL); - xdst->u.rt6.rt6i_metric = rt->rt6i_metric; - xdst->u.rt6.rt6i_node = rt->rt6i_node; xdst->route_cookie = rt6_get_cookie(rt); xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index 16f434791763f..5bdca3d5d6b73 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -60,11 +60,9 @@ xfrm6_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl, static int __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(void *p), int maxclass) { - int i; + int count[XFRM_MAX_DEPTH] = { }; int class[XFRM_MAX_DEPTH]; - int count[maxclass]; - - memset(count, 0, sizeof(count)); + int i; for (i = 0; i < n; i++) { int c; diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 7f1e842ef05a6..e87686f7d63ca 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -57,6 +57,10 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) { + /* Drop reference taken during previous invocation */ + if (pd->session) + l2tp_session_dec_refcount(pd->session); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); pd->session_idx++; @@ -105,11 +109,16 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v) if (!pd || pd == SEQ_START_TOKEN) return; - /* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */ + /* Drop reference taken by last invocation of l2tp_dfs_next_session() + * or l2tp_dfs_next_tunnel(). + */ + if (pd->session) { + l2tp_session_dec_refcount(pd->session); + pd->session = NULL; + } if (pd->tunnel) { l2tp_tunnel_dec_refcount(pd->tunnel); pd->tunnel = NULL; - pd->session = NULL; } } @@ -250,13 +259,10 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v) goto out; } - /* Show the tunnel or session context */ - if (!pd->session) { + if (!pd->session) l2tp_dfs_seq_tunnel_show(m, pd->tunnel); - } else { + else l2tp_dfs_seq_session_show(m, pd->session); - l2tp_session_dec_refcount(pd->session); - } out: return 0; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 3d8ca1231f8f5..b56cb1df4fc07 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -428,16 +428,6 @@ static void pppol2tp_put_sk(struct rcu_head *head) */ static void pppol2tp_session_close(struct l2tp_session *session) { - struct pppol2tp_session *ps; - - ps = l2tp_session_priv(session); - mutex_lock(&ps->sk_lock); - ps->__sk = rcu_dereference_protected(ps->sk, - lockdep_is_held(&ps->sk_lock)); - RCU_INIT_POINTER(ps->sk, NULL); - if (ps->__sk) - call_rcu(&ps->rcu, pppol2tp_put_sk); - mutex_unlock(&ps->sk_lock); } /* Really kill the session socket. (Called from sock_put() if @@ -480,15 +470,24 @@ static int pppol2tp_release(struct socket *sock) sock_orphan(sk); sock->sk = NULL; - /* If the socket is associated with a session, - * l2tp_session_delete will call pppol2tp_session_close which - * will drop the session's ref on the socket. - */ session = pppol2tp_sock_to_session(sk); if (session) { + struct pppol2tp_session *ps; + l2tp_session_delete(session); - /* drop the ref obtained by pppol2tp_sock_to_session */ - sock_put(sk); + + ps = l2tp_session_priv(session); + mutex_lock(&ps->sk_lock); + ps->__sk = rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock)); + RCU_INIT_POINTER(ps->sk, NULL); + mutex_unlock(&ps->sk_lock); + call_rcu(&ps->rcu, pppol2tp_put_sk); + + /* Rely on the sock_put() call at the end of the function for + * dropping the reference held by pppol2tp_sock_to_session(). + * The last reference will be dropped by pppol2tp_put_sk(). + */ } release_sock(sk); @@ -742,7 +741,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, */ mutex_lock(&ps->sk_lock); if (rcu_dereference_protected(ps->sk, - lockdep_is_held(&ps->sk_lock))) { + lockdep_is_held(&ps->sk_lock)) || + ps->__sk) { mutex_unlock(&ps->sk_lock); error = -EEXIST; goto end; @@ -803,7 +803,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, out_no_ppp: /* This is how we get the session context from the socket. */ - sock_hold(sk); sk->sk_user_data = session; rcu_assign_pointer(ps->sk, sk); mutex_unlock(&ps->sk_lock); @@ -1576,6 +1575,10 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd) { + /* Drop reference taken during previous invocation */ + if (pd->session) + l2tp_session_dec_refcount(pd->session); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); pd->session_idx++; @@ -1624,11 +1627,16 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v) if (!pd || pd == SEQ_START_TOKEN) return; - /* Drop reference taken by last invocation of pppol2tp_next_tunnel() */ + /* Drop reference taken by last invocation of pppol2tp_next_session() + * or pppol2tp_next_tunnel(). + */ + if (pd->session) { + l2tp_session_dec_refcount(pd->session); + pd->session = NULL; + } if (pd->tunnel) { l2tp_tunnel_dec_refcount(pd->tunnel); pd->tunnel = NULL; - pd->session = NULL; } } @@ -1723,14 +1731,10 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v) goto out; } - /* Show the tunnel or session context. - */ - if (!pd->session) { + if (!pd->session) pppol2tp_seq_tunnel_show(m, pd->tunnel); - } else { + else pppol2tp_seq_session_show(m, pd->session); - l2tp_session_dec_refcount(pd->session); - } out: return 0; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 85dbaa8910590..bdf6fa78d0d2b 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -695,7 +695,7 @@ static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev, if (sta) { ret = 0; memcpy(mac, sta->sta.addr, ETH_ALEN); - sta_set_sinfo(sta, sinfo); + sta_set_sinfo(sta, sinfo, true); } mutex_unlock(&local->sta_mtx); @@ -724,7 +724,7 @@ static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev, sta = sta_info_get_bss(sdata, mac); if (sta) { ret = 0; - sta_set_sinfo(sta, sinfo); + sta_set_sinfo(sta, sinfo, true); } mutex_unlock(&local->sta_mtx); @@ -2376,6 +2376,11 @@ static int ieee80211_set_wiphy_params(struct wiphy *wiphy, u32 changed) (WIPHY_PARAM_RETRY_SHORT | WIPHY_PARAM_RETRY_LONG)) ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_RETRY_LIMITS); + if (changed & (WIPHY_PARAM_TXQ_LIMIT | + WIPHY_PARAM_TXQ_MEMORY_LIMIT | + WIPHY_PARAM_TXQ_QUANTUM)) + ieee80211_txq_set_params(local); + return 0; } @@ -3705,6 +3710,99 @@ static int ieee80211_set_multicast_to_unicast(struct wiphy *wiphy, return 0; } +void ieee80211_fill_txq_stats(struct cfg80211_txq_stats *txqstats, + struct txq_info *txqi) +{ + if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_BACKLOG_BYTES))) { + txqstats->filled |= BIT(NL80211_TXQ_STATS_BACKLOG_BYTES); + txqstats->backlog_bytes = txqi->tin.backlog_bytes; + } + + if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_BACKLOG_PACKETS))) { + txqstats->filled |= BIT(NL80211_TXQ_STATS_BACKLOG_PACKETS); + txqstats->backlog_packets = txqi->tin.backlog_packets; + } + + if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_FLOWS))) { + txqstats->filled |= BIT(NL80211_TXQ_STATS_FLOWS); + txqstats->flows = txqi->tin.flows; + } + + if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_DROPS))) { + txqstats->filled |= BIT(NL80211_TXQ_STATS_DROPS); + txqstats->drops = txqi->cstats.drop_count; + } + + if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_ECN_MARKS))) { + txqstats->filled |= BIT(NL80211_TXQ_STATS_ECN_MARKS); + txqstats->ecn_marks = txqi->cstats.ecn_mark; + } + + if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_OVERLIMIT))) { + txqstats->filled |= BIT(NL80211_TXQ_STATS_OVERLIMIT); + txqstats->overlimit = txqi->tin.overlimit; + } + + if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_COLLISIONS))) { + txqstats->filled |= BIT(NL80211_TXQ_STATS_COLLISIONS); + txqstats->collisions = txqi->tin.collisions; + } + + if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_TX_BYTES))) { + txqstats->filled |= BIT(NL80211_TXQ_STATS_TX_BYTES); + txqstats->tx_bytes = txqi->tin.tx_bytes; + } + + if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_TX_PACKETS))) { + txqstats->filled |= BIT(NL80211_TXQ_STATS_TX_PACKETS); + txqstats->tx_packets = txqi->tin.tx_packets; + } +} + +static int ieee80211_get_txq_stats(struct wiphy *wiphy, + struct wireless_dev *wdev, + struct cfg80211_txq_stats *txqstats) +{ + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata; + int ret = 0; + + if (!local->ops->wake_tx_queue) + return 1; + + spin_lock_bh(&local->fq.lock); + rcu_read_lock(); + + if (wdev) { + sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + if (!sdata->vif.txq) { + ret = 1; + goto out; + } + ieee80211_fill_txq_stats(txqstats, to_txq_info(sdata->vif.txq)); + } else { + /* phy stats */ + txqstats->filled |= BIT(NL80211_TXQ_STATS_BACKLOG_PACKETS) | + BIT(NL80211_TXQ_STATS_BACKLOG_BYTES) | + BIT(NL80211_TXQ_STATS_OVERLIMIT) | + BIT(NL80211_TXQ_STATS_OVERMEMORY) | + BIT(NL80211_TXQ_STATS_COLLISIONS) | + BIT(NL80211_TXQ_STATS_MAX_FLOWS); + txqstats->backlog_packets = local->fq.backlog; + txqstats->backlog_bytes = local->fq.memory_usage; + txqstats->overlimit = local->fq.overlimit; + txqstats->overmemory = local->fq.overmemory; + txqstats->collisions = local->fq.collisions; + txqstats->max_flows = local->fq.flows_cnt; + } + +out: + rcu_read_unlock(); + spin_unlock_bh(&local->fq.lock); + + return ret; +} + const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -3798,4 +3896,5 @@ const struct cfg80211_ops mac80211_config_ops = { .del_nan_func = ieee80211_del_nan_func, .set_multicast_to_unicast = ieee80211_set_multicast_to_unicast, .tx_control_port = ieee80211_tx_control_port, + .get_txq_stats = ieee80211_get_txq_stats, }; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 4d82fe7d627c2..8f6998091d26f 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -2,6 +2,7 @@ /* * Portions of this file * Copyright(c) 2016 Intel Deutschland GmbH +* Copyright (C) 2018 Intel Corporation */ #ifndef __MAC80211_DRIVER_OPS @@ -813,7 +814,8 @@ drv_allow_buffered_frames(struct ieee80211_local *local, } static inline void drv_mgd_prepare_tx(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata) + struct ieee80211_sub_if_data *sdata, + u16 duration) { might_sleep(); @@ -821,9 +823,9 @@ static inline void drv_mgd_prepare_tx(struct ieee80211_local *local, return; WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION); - trace_drv_mgd_prepare_tx(local, sdata); + trace_drv_mgd_prepare_tx(local, sdata, duration); if (local->ops->mgd_prepare_tx) - local->ops->mgd_prepare_tx(&local->hw, &sdata->vif); + local->ops->mgd_prepare_tx(&local->hw, &sdata->vif, duration); trace_drv_return_void(local); } diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c index 9cc986deda617..690c142a7a440 100644 --- a/net/mac80211/ethtool.c +++ b/net/mac80211/ethtool.c @@ -4,6 +4,7 @@ * Copied from cfg.c - originally * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2014 Intel Corporation (Author: Johannes Berg) + * Copyright (C) 2018 Intel Corporation * * This file is GPLv2 as found in COPYING. */ @@ -106,8 +107,8 @@ static void ieee80211_get_stats(struct net_device *dev, if (!(sta && !WARN_ON(sta->sdata->dev != dev))) goto do_survey; - sinfo.filled = 0; - sta_set_sinfo(sta, &sinfo); + memset(&sinfo, 0, sizeof(sinfo)); + sta_set_sinfo(sta, &sinfo, false); i = 0; ADD_STA_STATS(sta); @@ -116,11 +117,11 @@ static void ieee80211_get_stats(struct net_device *dev, if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)) - data[i] = 100000 * + data[i] = 100000ULL * cfg80211_calculate_bitrate(&sinfo.txrate); i++; if (sinfo.filled & BIT(NL80211_STA_INFO_RX_BITRATE)) - data[i] = 100000 * + data[i] = 100000ULL * cfg80211_calculate_bitrate(&sinfo.rxrate); i++; @@ -133,8 +134,8 @@ static void ieee80211_get_stats(struct net_device *dev, if (sta->sdata->dev != dev) continue; - sinfo.filled = 0; - sta_set_sinfo(sta, &sinfo); + memset(&sinfo, 0, sizeof(sinfo)); + sta_set_sinfo(sta, &sinfo, false); i = 0; ADD_STA_STATS(sta); } diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index c78036a0ac949..26a7ba3b698f1 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -301,26 +301,27 @@ void ieee80211_sta_tear_down_BA_sessions(struct sta_info *sta, ___ieee80211_stop_tx_ba_session(sta, i, reason); mutex_unlock(&sta->ampdu_mlme.mtx); - /* stopping might queue the work again - so cancel only afterwards */ - cancel_work_sync(&sta->ampdu_mlme.work); - /* * In case the tear down is part of a reconfigure due to HW restart * request, it is possible that the low level driver requested to stop * the BA session, so handle it to properly clean tid_tx data. */ - mutex_lock(&sta->ampdu_mlme.mtx); - for (i = 0; i < IEEE80211_NUM_TIDS; i++) { - struct tid_ampdu_tx *tid_tx = - rcu_dereference_protected_tid_tx(sta, i); + if(reason == AGG_STOP_DESTROY_STA) { + cancel_work_sync(&sta->ampdu_mlme.work); - if (!tid_tx) - continue; + mutex_lock(&sta->ampdu_mlme.mtx); + for (i = 0; i < IEEE80211_NUM_TIDS; i++) { + struct tid_ampdu_tx *tid_tx = + rcu_dereference_protected_tid_tx(sta, i); - if (test_and_clear_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state)) - ieee80211_stop_tx_ba_cb(sta, i, tid_tx); + if (!tid_tx) + continue; + + if (test_and_clear_bit(HT_AGG_STATE_STOP_CB, &tid_tx->state)) + ieee80211_stop_tx_ba_cb(sta, i, tid_tx); + } + mutex_unlock(&sta->ampdu_mlme.mtx); } - mutex_unlock(&sta->ampdu_mlme.mtx); } void ieee80211_ba_session_work(struct work_struct *work) @@ -328,16 +329,11 @@ void ieee80211_ba_session_work(struct work_struct *work) struct sta_info *sta = container_of(work, struct sta_info, ampdu_mlme.work); struct tid_ampdu_tx *tid_tx; + bool blocked; int tid; - /* - * When this flag is set, new sessions should be - * blocked, and existing sessions will be torn - * down by the code that set the flag, so this - * need not run. - */ - if (test_sta_flag(sta, WLAN_STA_BLOCK_BA)) - return; + /* When this flag is set, new sessions should be blocked. */ + blocked = test_sta_flag(sta, WLAN_STA_BLOCK_BA); mutex_lock(&sta->ampdu_mlme.mtx); for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) { @@ -352,7 +348,8 @@ void ieee80211_ba_session_work(struct work_struct *work) sta, tid, WLAN_BACK_RECIPIENT, WLAN_REASON_UNSPECIFIED, true); - if (test_and_clear_bit(tid, + if (!blocked && + test_and_clear_bit(tid, sta->ampdu_mlme.tid_rx_manage_offl)) ___ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid, IEEE80211_MAX_AMPDU_BUF, @@ -367,7 +364,7 @@ void ieee80211_ba_session_work(struct work_struct *work) spin_lock_bh(&sta->lock); tid_tx = sta->ampdu_mlme.tid_start_tx[tid]; - if (tid_tx) { + if (!blocked && tid_tx) { /* * Assign it over to the normal tid_tx array * where it "goes live". @@ -390,7 +387,8 @@ void ieee80211_ba_session_work(struct work_struct *work) if (!tid_tx) continue; - if (test_and_clear_bit(HT_AGG_STATE_START_CB, &tid_tx->state)) + if (!blocked && + test_and_clear_bit(HT_AGG_STATE_START_CB, &tid_tx->state)) ieee80211_start_tx_ba_cb(sta, tid, tid_tx); if (test_and_clear_bit(HT_AGG_STATE_WANT_STOP, &tid_tx->state)) ___ieee80211_stop_tx_ba_session(sta, tid, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 6372dbdadf53e..d1978aa1c15dd 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2012,6 +2012,7 @@ static inline bool ieee80211_can_run_worker(struct ieee80211_local *local) } int ieee80211_txq_setup_flows(struct ieee80211_local *local); +void ieee80211_txq_set_params(struct ieee80211_local *local); void ieee80211_txq_teardown_flows(struct ieee80211_local *local); void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, @@ -2020,6 +2021,8 @@ void ieee80211_txq_purge(struct ieee80211_local *local, struct txq_info *txqi); void ieee80211_txq_remove_vlan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); +void ieee80211_fill_txq_stats(struct cfg80211_txq_stats *txqstats, + struct txq_info *txqi); void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, u16 status, const u8 *extra, size_t extra_len, const u8 *bssid, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 9ea17afaa2379..4d2e797e3f168 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -565,6 +565,9 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, if (!ops->set_key) wiphy->flags |= WIPHY_FLAG_IBSS_RSN; + if (ops->wake_tx_queue) + wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_TXQS); + wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_RRM); wiphy->bss_priv_size = sizeof(struct ieee80211_bss); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 233068756502b..a59187c016e08 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -864,7 +864,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) return; } - drv_mgd_prepare_tx(local, sdata); + drv_mgd_prepare_tx(local, sdata, 0); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) @@ -2022,7 +2022,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, */ if (ieee80211_hw_check(&local->hw, DEAUTH_NEED_MGD_TX_PREP) && !ifmgd->have_beacon) - drv_mgd_prepare_tx(sdata->local, sdata); + drv_mgd_prepare_tx(sdata->local, sdata, 0); ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, stype, reason, tx, frame_buf); @@ -2560,7 +2560,7 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, if (!elems.challenge) return; auth_data->expected_transaction = 4; - drv_mgd_prepare_tx(sdata->local, sdata); + drv_mgd_prepare_tx(sdata->local, sdata, 0); if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) tx_flags = IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_INTFL_MLME_CONN_TX; @@ -3769,6 +3769,7 @@ static int ieee80211_auth(struct ieee80211_sub_if_data *sdata) u32 tx_flags = 0; u16 trans = 1; u16 status = 0; + u16 prepare_tx_duration = 0; sdata_assert_lock(sdata); @@ -3790,7 +3791,11 @@ static int ieee80211_auth(struct ieee80211_sub_if_data *sdata) return -ETIMEDOUT; } - drv_mgd_prepare_tx(local, sdata); + if (auth_data->algorithm == WLAN_AUTH_SAE) + prepare_tx_duration = + jiffies_to_msecs(IEEE80211_AUTH_TIMEOUT_SAE); + + drv_mgd_prepare_tx(local, sdata, prepare_tx_duration); sdata_info(sdata, "send auth to %pM (try %d/%d)\n", auth_data->bss->bssid, auth_data->tries, @@ -4994,7 +4999,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, req->bssid, req->reason_code, ieee80211_get_reason_code_string(req->reason_code)); - drv_mgd_prepare_tx(sdata->local, sdata); + drv_mgd_prepare_tx(sdata->local, sdata, 0); ieee80211_send_deauth_disassoc(sdata, req->bssid, IEEE80211_STYPE_DEAUTH, req->reason_code, tx, @@ -5014,7 +5019,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, req->bssid, req->reason_code, ieee80211_get_reason_code_string(req->reason_code)); - drv_mgd_prepare_tx(sdata->local, sdata); + drv_mgd_prepare_tx(sdata->local, sdata, 0); ieee80211_send_deauth_disassoc(sdata, req->bssid, IEEE80211_STYPE_DEAUTH, req->reason_code, tx, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 03102aff0953f..0a38cc1cbebce 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -5,6 +5,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * 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 @@ -97,27 +98,27 @@ static u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, */ static void remove_monitor_info(struct sk_buff *skb, unsigned int present_fcs_len, - unsigned int rtap_vendor_space) + unsigned int rtap_space) { if (present_fcs_len) __pskb_trim(skb, skb->len - present_fcs_len); - __pskb_pull(skb, rtap_vendor_space); + __pskb_pull(skb, rtap_space); } static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len, - unsigned int rtap_vendor_space) + unsigned int rtap_space) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_hdr *hdr; - hdr = (void *)(skb->data + rtap_vendor_space); + hdr = (void *)(skb->data + rtap_space); if (status->flag & (RX_FLAG_FAILED_FCS_CRC | RX_FLAG_FAILED_PLCP_CRC | RX_FLAG_ONLY_MONITOR)) return true; - if (unlikely(skb->len < 16 + present_fcs_len + rtap_vendor_space)) + if (unlikely(skb->len < 16 + present_fcs_len + rtap_space)) return true; if (ieee80211_is_ctl(hdr->frame_control) && @@ -199,7 +200,7 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - int rtap_vendor_space) + int rtap_space) { struct { struct ieee80211_hdr_3addr hdr; @@ -212,14 +213,14 @@ static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, BUILD_BUG_ON(sizeof(action) != IEEE80211_MIN_ACTION_SIZE + 1); - if (skb->len < rtap_vendor_space + sizeof(action) + + if (skb->len < rtap_space + sizeof(action) + VHT_MUMIMO_GROUPS_DATA_LEN) return; if (!is_valid_ether_addr(sdata->u.mntr.mu_follow_addr)) return; - skb_copy_bits(skb, rtap_vendor_space, &action, sizeof(action)); + skb_copy_bits(skb, rtap_space, &action, sizeof(action)); if (!ieee80211_is_action(action.hdr.frame_control)) return; @@ -545,7 +546,7 @@ static struct sk_buff * ieee80211_make_monitor_skb(struct ieee80211_local *local, struct sk_buff **origskb, struct ieee80211_rate *rate, - int rtap_vendor_space, bool use_origskb) + int rtap_space, bool use_origskb) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(*origskb); int rt_hdrlen, needed_headroom; @@ -553,7 +554,7 @@ ieee80211_make_monitor_skb(struct ieee80211_local *local, /* room for the radiotap header based on driver features */ rt_hdrlen = ieee80211_rx_radiotap_hdrlen(local, status, *origskb); - needed_headroom = rt_hdrlen - rtap_vendor_space; + needed_headroom = rt_hdrlen - rtap_space; if (use_origskb) { /* only need to expand headroom if necessary */ @@ -607,7 +608,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, struct ieee80211_sub_if_data *sdata; struct sk_buff *monskb = NULL; int present_fcs_len = 0; - unsigned int rtap_vendor_space = 0; + unsigned int rtap_space = 0; struct ieee80211_sub_if_data *monitor_sdata = rcu_dereference(local->monitor_sdata); bool only_monitor = false; @@ -615,7 +616,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, if (unlikely(status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)) { struct ieee80211_vendor_radiotap *rtap = (void *)origskb->data; - rtap_vendor_space = sizeof(*rtap) + rtap->len + rtap->pad; + rtap_space += sizeof(*rtap) + rtap->len + rtap->pad; } /* @@ -638,13 +639,12 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, } /* ensure hdr->frame_control and vendor radiotap data are in skb head */ - if (!pskb_may_pull(origskb, 2 + rtap_vendor_space)) { + if (!pskb_may_pull(origskb, 2 + rtap_space)) { dev_kfree_skb(origskb); return NULL; } - only_monitor = should_drop_frame(origskb, present_fcs_len, - rtap_vendor_space); + only_monitor = should_drop_frame(origskb, present_fcs_len, rtap_space); if (!local->monitors || (status->flag & RX_FLAG_SKIP_MONITOR)) { if (only_monitor) { @@ -652,12 +652,11 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, return NULL; } - remove_monitor_info(origskb, present_fcs_len, - rtap_vendor_space); + remove_monitor_info(origskb, present_fcs_len, rtap_space); return origskb; } - ieee80211_handle_mu_mimo_mon(monitor_sdata, origskb, rtap_vendor_space); + ieee80211_handle_mu_mimo_mon(monitor_sdata, origskb, rtap_space); list_for_each_entry_rcu(sdata, &local->mon_list, u.mntr.list) { bool last_monitor = list_is_last(&sdata->u.mntr.list, @@ -665,8 +664,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, if (!monskb) monskb = ieee80211_make_monitor_skb(local, &origskb, - rate, - rtap_vendor_space, + rate, rtap_space, only_monitor && last_monitor); @@ -698,7 +696,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, if (!origskb) return NULL; - remove_monitor_info(origskb, present_fcs_len, rtap_vendor_space); + remove_monitor_info(origskb, present_fcs_len, rtap_space); return origskb; } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 655c3d8b0d80c..6428f1ac37b67 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -3,6 +3,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * 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 @@ -357,6 +358,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->last_connected = ktime_get_seconds(); ewma_signal_init(&sta->rx_stats_avg.signal); + ewma_avg_signal_init(&sta->status_stats.avg_ack_signal); for (i = 0; i < ARRAY_SIZE(sta->rx_stats_avg.chain_signal); i++) ewma_signal_init(&sta->rx_stats_avg.chain_signal[i]); @@ -1006,7 +1008,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta) sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL); if (sinfo) - sta_set_sinfo(sta, sinfo); + sta_set_sinfo(sta, sinfo, true); cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); kfree(sinfo); @@ -1992,7 +1994,6 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, int band = STA_STATS_GET(LEGACY_BAND, rate); int rate_idx = STA_STATS_GET(LEGACY_IDX, rate); - rinfo->flags = 0; sband = local->hw.wiphy->bands[band]; brate = sband->bitrates[rate_idx].bitrate; if (rinfo->bw == RATE_INFO_BW_5) @@ -2051,6 +2052,18 @@ static void sta_set_tidstats(struct sta_info *sta, tidstats->filled |= BIT(NL80211_TID_STATS_TX_MSDU_FAILED); tidstats->tx_msdu_failed = sta->status_stats.msdu_failed[tid]; } + + if (local->ops->wake_tx_queue && tid < IEEE80211_NUM_TIDS) { + spin_lock_bh(&local->fq.lock); + rcu_read_lock(); + + tidstats->filled |= BIT(NL80211_TID_STATS_TXQ_STATS); + ieee80211_fill_txq_stats(&tidstats->txq_stats, + to_txq_info(sta->sta.txq[tid])); + + rcu_read_unlock(); + spin_unlock_bh(&local->fq.lock); + } } static inline u64 sta_get_stats_bytes(struct ieee80211_sta_rx_stats *rxstats) @@ -2066,7 +2079,8 @@ static inline u64 sta_get_stats_bytes(struct ieee80211_sta_rx_stats *rxstats) return value; } -void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) +void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, + bool tidstats) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; @@ -2220,11 +2234,12 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE); } - sinfo->filled |= BIT(NL80211_STA_INFO_TID_STATS); - for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { - struct cfg80211_tid_stats *tidstats = &sinfo->pertid[i]; + if (tidstats && !cfg80211_sinfo_alloc_tid_stats(sinfo, GFP_KERNEL)) { + for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) { + struct cfg80211_tid_stats *tidstats = &sinfo->pertid[i]; - sta_set_tidstats(sta, tidstats, i); + sta_set_tidstats(sta, tidstats, i); + } } if (ieee80211_vif_is_mesh(&sdata->vif)) { @@ -2294,6 +2309,15 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) sinfo->ack_signal = sta->status_stats.last_ack_signal; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL); } + + if (ieee80211_hw_check(&sta->local->hw, REPORTS_TX_ACK_STATUS) && + !(sinfo->filled & BIT_ULL(NL80211_STA_INFO_DATA_ACK_SIGNAL_AVG))) { + sinfo->avg_ack_signal = + -(s8)ewma_avg_signal_read( + &sta->status_stats.avg_ack_signal); + sinfo->filled |= + BIT_ULL(NL80211_STA_INFO_DATA_ACK_SIGNAL_AVG); + } } u32 sta_get_expected_throughput(struct sta_info *sta) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index f64eb86ca64b0..81b35f6237924 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -119,6 +119,7 @@ enum ieee80211_sta_info_flags { #define HT_AGG_STATE_START_CB 6 #define HT_AGG_STATE_STOP_CB 7 +DECLARE_EWMA(avg_signal, 10, 8) enum ieee80211_agg_stop_reason { AGG_STOP_DECLINED, AGG_STOP_LOCAL_REQUEST, @@ -550,6 +551,7 @@ struct sta_info { unsigned long last_ack; s8 last_ack_signal; bool ack_signal_filled; + struct ewma_avg_signal avg_ack_signal; } status_stats; /* Updated from TX path only, no locking requirements */ @@ -742,7 +744,8 @@ static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata) void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo); -void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo); +void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, + bool tidstats); u32 sta_get_expected_throughput(struct sta_info *sta); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 743e89c5926c4..9a6d7208bf4f8 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -195,6 +195,8 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb) sta->status_stats.last_ack_signal = (s8)txinfo->status.ack_signal; sta->status_stats.ack_signal_filled = true; + ewma_avg_signal_add(&sta->status_stats.avg_ack_signal, + -txinfo->status.ack_signal); } } diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 591ad02e1fa4f..80a7edf8d314a 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -2,6 +2,7 @@ /* * Portions of this file * Copyright(c) 2016 Intel Deutschland GmbH +* Copyright (C) 2018 Intel Corporation */ #if !defined(__MAC80211_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) @@ -1413,11 +1414,29 @@ DEFINE_EVENT(release_evt, drv_allow_buffered_frames, TP_ARGS(local, sta, tids, num_frames, reason, more_data) ); -DEFINE_EVENT(local_sdata_evt, drv_mgd_prepare_tx, +TRACE_EVENT(drv_mgd_prepare_tx, TP_PROTO(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata), + struct ieee80211_sub_if_data *sdata, + u16 duration), - TP_ARGS(local, sdata) + TP_ARGS(local, sdata, duration), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + __field(u32, duration) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + __entry->duration = duration; + ), + + TP_printk( + LOCAL_PR_FMT VIF_PR_FMT " duration: %u", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->duration + ) ); DEFINE_EVENT(local_sdata_evt, drv_mgd_protect_tdls_discover, diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 05a265cd573d4..44b5dfe8727d9 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1460,6 +1460,24 @@ void ieee80211_txq_purge(struct ieee80211_local *local, ieee80211_purge_tx_queue(&local->hw, &txqi->frags); } +void ieee80211_txq_set_params(struct ieee80211_local *local) +{ + if (local->hw.wiphy->txq_limit) + local->fq.limit = local->hw.wiphy->txq_limit; + else + local->hw.wiphy->txq_limit = local->fq.limit; + + if (local->hw.wiphy->txq_memory_limit) + local->fq.memory_limit = local->hw.wiphy->txq_memory_limit; + else + local->hw.wiphy->txq_memory_limit = local->fq.memory_limit; + + if (local->hw.wiphy->txq_quantum) + local->fq.quantum = local->hw.wiphy->txq_quantum; + else + local->hw.wiphy->txq_quantum = local->fq.quantum; +} + int ieee80211_txq_setup_flows(struct ieee80211_local *local) { struct fq *fq = &local->fq; @@ -1509,6 +1527,8 @@ int ieee80211_txq_setup_flows(struct ieee80211_local *local) for (i = 0; i < fq->flows_cnt; i++) codel_vars_init(&local->cvars[i]); + ieee80211_txq_set_params(local); + return 0; } @@ -4085,6 +4105,31 @@ unlock: } EXPORT_SYMBOL(ieee80211_csa_update_counter); +void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct beacon_data *beacon = NULL; + + rcu_read_lock(); + + if (sdata->vif.type == NL80211_IFTYPE_AP) + beacon = rcu_dereference(sdata->u.ap.beacon); + else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) + beacon = rcu_dereference(sdata->u.ibss.presp); + else if (ieee80211_vif_is_mesh(&sdata->vif)) + beacon = rcu_dereference(sdata->u.mesh.beacon); + + if (!beacon) + goto unlock; + + if (counter < beacon->csa_current_counter) + beacon->csa_current_counter = counter; + +unlock: + rcu_read_unlock(); +} +EXPORT_SYMBOL(ieee80211_csa_set_counter); + bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 11f9cfc016d98..2d82c88efd0b6 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2793,12 +2793,13 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, memset(&ri, 0, sizeof(ri)); + ri.bw = status->bw; + /* Fill cfg80211 rate info */ switch (status->encoding) { case RX_ENC_HT: ri.mcs = status->rate_idx; ri.flags |= RATE_INFO_FLAGS_MCS; - ri.bw = status->bw; if (status->enc_flags & RX_ENC_FLAG_SHORT_GI) ri.flags |= RATE_INFO_FLAGS_SHORT_GI; break; @@ -2806,7 +2807,6 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, ri.flags |= RATE_INFO_FLAGS_VHT_MCS; ri.mcs = status->rate_idx; ri.nss = status->nss; - ri.bw = status->bw; if (status->enc_flags & RX_ENC_FLAG_SHORT_GI) ri.flags |= RATE_INFO_FLAGS_SHORT_GI; break; @@ -2818,8 +2818,6 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, int shift = 0; int bitrate; - ri.bw = status->bw; - switch (status->bw) { case RATE_INFO_BW_10: shift = 1; diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 8da84312cd3b5..8055e3965cef2 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -68,15 +68,6 @@ enum { NCSI_MODE_MAX }; -enum { - NCSI_FILTER_BASE = 0, - NCSI_FILTER_VLAN = 0, - NCSI_FILTER_UC, - NCSI_FILTER_MC, - NCSI_FILTER_MIXED, - NCSI_FILTER_MAX -}; - struct ncsi_channel_version { u32 version; /* Supported BCD encoded NCSI version */ u32 alpha2; /* Supported BCD encoded NCSI version */ @@ -98,11 +89,18 @@ struct ncsi_channel_mode { u32 data[8]; /* Data entries */ }; -struct ncsi_channel_filter { - u32 index; /* Index of channel filters */ - u32 total; /* Total entries in the filter table */ - u64 bitmap; /* Bitmap of valid entries */ - u32 data[]; /* Data for the valid entries */ +struct ncsi_channel_mac_filter { + u8 n_uc; + u8 n_mc; + u8 n_mixed; + u64 bitmap; + unsigned char *addrs; +}; + +struct ncsi_channel_vlan_filter { + u8 n_vids; + u64 bitmap; + u16 *vids; }; struct ncsi_channel_stats { @@ -186,7 +184,9 @@ struct ncsi_channel { struct ncsi_channel_version version; struct ncsi_channel_cap caps[NCSI_CAP_MAX]; struct ncsi_channel_mode modes[NCSI_MODE_MAX]; - struct ncsi_channel_filter *filters[NCSI_FILTER_MAX]; + /* Filtering Settings */ + struct ncsi_channel_mac_filter mac_filter; + struct ncsi_channel_vlan_filter vlan_filter; struct ncsi_channel_stats stats; struct { struct timer_list timer; @@ -320,10 +320,6 @@ extern spinlock_t ncsi_dev_lock; list_for_each_entry_rcu(nc, &np->channels, node) /* Resources */ -u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index); -int ncsi_find_filter(struct ncsi_channel *nc, int table, void *data); -int ncsi_add_filter(struct ncsi_channel *nc, int table, void *data); -int ncsi_remove_filter(struct ncsi_channel *nc, int table, int index); void ncsi_start_channel_monitor(struct ncsi_channel *nc); void ncsi_stop_channel_monitor(struct ncsi_channel *nc); struct ncsi_channel *ncsi_find_channel(struct ncsi_package *np, diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index c3695ba0cf94f..5561e221b71f1 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -27,125 +27,6 @@ LIST_HEAD(ncsi_dev_list); DEFINE_SPINLOCK(ncsi_dev_lock); -static inline int ncsi_filter_size(int table) -{ - int sizes[] = { 2, 6, 6, 6 }; - - BUILD_BUG_ON(ARRAY_SIZE(sizes) != NCSI_FILTER_MAX); - if (table < NCSI_FILTER_BASE || table >= NCSI_FILTER_MAX) - return -EINVAL; - - return sizes[table]; -} - -u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index) -{ - struct ncsi_channel_filter *ncf; - int size; - - ncf = nc->filters[table]; - if (!ncf) - return NULL; - - size = ncsi_filter_size(table); - if (size < 0) - return NULL; - - return ncf->data + size * index; -} - -/* Find the first active filter in a filter table that matches the given - * data parameter. If data is NULL, this returns the first active filter. - */ -int ncsi_find_filter(struct ncsi_channel *nc, int table, void *data) -{ - struct ncsi_channel_filter *ncf; - void *bitmap; - int index, size; - unsigned long flags; - - ncf = nc->filters[table]; - if (!ncf) - return -ENXIO; - - size = ncsi_filter_size(table); - if (size < 0) - return size; - - spin_lock_irqsave(&nc->lock, flags); - bitmap = (void *)&ncf->bitmap; - index = -1; - while ((index = find_next_bit(bitmap, ncf->total, index + 1)) - < ncf->total) { - if (!data || !memcmp(ncf->data + size * index, data, size)) { - spin_unlock_irqrestore(&nc->lock, flags); - return index; - } - } - spin_unlock_irqrestore(&nc->lock, flags); - - return -ENOENT; -} - -int ncsi_add_filter(struct ncsi_channel *nc, int table, void *data) -{ - struct ncsi_channel_filter *ncf; - int index, size; - void *bitmap; - unsigned long flags; - - size = ncsi_filter_size(table); - if (size < 0) - return size; - - index = ncsi_find_filter(nc, table, data); - if (index >= 0) - return index; - - ncf = nc->filters[table]; - if (!ncf) - return -ENODEV; - - spin_lock_irqsave(&nc->lock, flags); - bitmap = (void *)&ncf->bitmap; - do { - index = find_next_zero_bit(bitmap, ncf->total, 0); - if (index >= ncf->total) { - spin_unlock_irqrestore(&nc->lock, flags); - return -ENOSPC; - } - } while (test_and_set_bit(index, bitmap)); - - memcpy(ncf->data + size * index, data, size); - spin_unlock_irqrestore(&nc->lock, flags); - - return index; -} - -int ncsi_remove_filter(struct ncsi_channel *nc, int table, int index) -{ - struct ncsi_channel_filter *ncf; - int size; - void *bitmap; - unsigned long flags; - - size = ncsi_filter_size(table); - if (size < 0) - return size; - - ncf = nc->filters[table]; - if (!ncf || index >= ncf->total) - return -ENODEV; - - spin_lock_irqsave(&nc->lock, flags); - bitmap = (void *)&ncf->bitmap; - if (test_and_clear_bit(index, bitmap)) - memset(ncf->data + size * index, 0, size); - spin_unlock_irqrestore(&nc->lock, flags); - - return 0; -} - static void ncsi_report_link(struct ncsi_dev_priv *ndp, bool force_down) { struct ncsi_dev *nd = &ndp->ndev; @@ -339,20 +220,13 @@ struct ncsi_channel *ncsi_add_channel(struct ncsi_package *np, unsigned char id) static void ncsi_remove_channel(struct ncsi_channel *nc) { struct ncsi_package *np = nc->package; - struct ncsi_channel_filter *ncf; unsigned long flags; - int i; - /* Release filters */ spin_lock_irqsave(&nc->lock, flags); - for (i = 0; i < NCSI_FILTER_MAX; i++) { - ncf = nc->filters[i]; - if (!ncf) - continue; - nc->filters[i] = NULL; - kfree(ncf); - } + /* Release filters */ + kfree(nc->mac_filter.addrs); + kfree(nc->vlan_filter.vids); nc->state = NCSI_CHANNEL_INACTIVE; spin_unlock_irqrestore(&nc->lock, flags); @@ -670,32 +544,26 @@ error: static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, struct ncsi_cmd_arg *nca) { + struct ncsi_channel_vlan_filter *ncf; + unsigned long flags; + void *bitmap; int index; - u32 *data; u16 vid; - index = ncsi_find_filter(nc, NCSI_FILTER_VLAN, NULL); - if (index < 0) { - /* Filter table empty */ - return -1; - } + ncf = &nc->vlan_filter; + bitmap = &ncf->bitmap; - data = ncsi_get_filter(nc, NCSI_FILTER_VLAN, index); - if (!data) { - netdev_err(ndp->ndev.dev, - "NCSI: failed to retrieve filter %d\n", index); - /* Set the VLAN id to 0 - this will still disable the entry in - * the filter table, but we won't know what it was. - */ - vid = 0; - } else { - vid = *(u16 *)data; + spin_lock_irqsave(&nc->lock, flags); + index = find_next_bit(bitmap, ncf->n_vids, 0); + if (index >= ncf->n_vids) { + spin_unlock_irqrestore(&nc->lock, flags); + return -1; } + vid = ncf->vids[index]; - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "NCSI: removed vlan tag %u at index %d\n", - vid, index + 1); - ncsi_remove_filter(nc, NCSI_FILTER_VLAN, index); + clear_bit(index, bitmap); + ncf->vids[index] = 0; + spin_unlock_irqrestore(&nc->lock, flags); nca->type = NCSI_PKT_CMD_SVF; nca->words[1] = vid; @@ -711,45 +579,55 @@ static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, struct ncsi_cmd_arg *nca) { + struct ncsi_channel_vlan_filter *ncf; struct vlan_vid *vlan = NULL; - int index = 0; + unsigned long flags; + int i, index; + void *bitmap; + u16 vid; + if (list_empty(&ndp->vlan_vids)) + return -1; + + ncf = &nc->vlan_filter; + bitmap = &ncf->bitmap; + + spin_lock_irqsave(&nc->lock, flags); + + rcu_read_lock(); list_for_each_entry_rcu(vlan, &ndp->vlan_vids, list) { - index = ncsi_find_filter(nc, NCSI_FILTER_VLAN, &vlan->vid); - if (index < 0) { - /* New tag to add */ - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "NCSI: new vlan id to set: %u\n", - vlan->vid); + vid = vlan->vid; + for (i = 0; i < ncf->n_vids; i++) + if (ncf->vids[i] == vid) { + vid = 0; + break; + } + if (vid) break; - } - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "vid %u already at filter pos %d\n", - vlan->vid, index); } + rcu_read_unlock(); - if (!vlan || index >= 0) { - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "no vlan ids left to set\n"); + if (!vid) { + /* No VLAN ID is not set */ + spin_unlock_irqrestore(&nc->lock, flags); return -1; } - index = ncsi_add_filter(nc, NCSI_FILTER_VLAN, &vlan->vid); - if (index < 0) { + index = find_next_zero_bit(bitmap, ncf->n_vids, 0); + if (index < 0 || index >= ncf->n_vids) { netdev_err(ndp->ndev.dev, - "Failed to add new VLAN tag, error %d\n", index); - if (index == -ENOSPC) - netdev_err(ndp->ndev.dev, - "Channel %u already has all VLAN filters set\n", - nc->id); + "Channel %u already has all VLAN filters set\n", + nc->id); + spin_unlock_irqrestore(&nc->lock, flags); return -1; } - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "NCSI: set vid %u in packet, index %u\n", - vlan->vid, index + 1); + ncf->vids[index] = vid; + set_bit(index, bitmap); + spin_unlock_irqrestore(&nc->lock, flags); + nca->type = NCSI_PKT_CMD_SVF; - nca->words[1] = vlan->vid; + nca->words[1] = vid; /* HW filter index starts at 1 */ nca->bytes[6] = index + 1; nca->bytes[7] = 0x01; diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 41cede4041d3c..82e6edf9c5d9c 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -58,10 +58,9 @@ static int ncsi_write_channel_info(struct sk_buff *skb, struct ncsi_dev_priv *ndp, struct ncsi_channel *nc) { - struct nlattr *vid_nest; - struct ncsi_channel_filter *ncf; + struct ncsi_channel_vlan_filter *ncf; struct ncsi_channel_mode *m; - u32 *data; + struct nlattr *vid_nest; int i; nla_put_u32(skb, NCSI_CHANNEL_ATTR_ID, nc->id); @@ -79,18 +78,13 @@ static int ncsi_write_channel_info(struct sk_buff *skb, vid_nest = nla_nest_start(skb, NCSI_CHANNEL_ATTR_VLAN_LIST); if (!vid_nest) return -ENOMEM; - ncf = nc->filters[NCSI_FILTER_VLAN]; + ncf = &nc->vlan_filter; i = -1; - if (ncf) { - while ((i = find_next_bit((void *)&ncf->bitmap, ncf->total, - i + 1)) < ncf->total) { - data = ncsi_get_filter(nc, NCSI_FILTER_VLAN, i); - /* Uninitialised channels will have 'zero' vlan ids */ - if (!data || !*data) - continue; + while ((i = find_next_bit((void *)&ncf->bitmap, ncf->n_vids, + i + 1)) < ncf->n_vids) { + if (ncf->vids[i]) nla_put_u16(skb, NCSI_CHANNEL_ATTR_VLAN_ID, - *(u16 *)data); - } + ncf->vids[i]); } nla_nest_end(skb, vid_nest); @@ -207,7 +201,6 @@ static int ncsi_pkg_info_nl(struct sk_buff *msg, struct genl_info *info) return genlmsg_reply(skb, info); err: - genlmsg_cancel(skb, hdr); kfree_skb(skb); return rc; } diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index efd933ff55707..930c1d3796f0f 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -334,9 +334,9 @@ static int ncsi_rsp_handler_svf(struct ncsi_request *nr) struct ncsi_rsp_pkt *rsp; struct ncsi_dev_priv *ndp = nr->ndp; struct ncsi_channel *nc; - struct ncsi_channel_filter *ncf; - unsigned short vlan; - int ret; + struct ncsi_channel_vlan_filter *ncf; + unsigned long flags; + void *bitmap; /* Find the package and channel */ rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); @@ -346,22 +346,23 @@ static int ncsi_rsp_handler_svf(struct ncsi_request *nr) return -ENODEV; cmd = (struct ncsi_cmd_svf_pkt *)skb_network_header(nr->cmd); - ncf = nc->filters[NCSI_FILTER_VLAN]; - if (!ncf) - return -ENOENT; - if (cmd->index >= ncf->total) + ncf = &nc->vlan_filter; + if (cmd->index == 0 || cmd->index > ncf->n_vids) return -ERANGE; - /* Add or remove the VLAN filter */ + /* Add or remove the VLAN filter. Remember HW indexes from 1 */ + spin_lock_irqsave(&nc->lock, flags); + bitmap = &ncf->bitmap; if (!(cmd->enable & 0x1)) { - /* HW indexes from 1 */ - ret = ncsi_remove_filter(nc, NCSI_FILTER_VLAN, cmd->index - 1); + if (test_and_clear_bit(cmd->index - 1, bitmap)) + ncf->vids[cmd->index - 1] = 0; } else { - vlan = ntohs(cmd->vlan); - ret = ncsi_add_filter(nc, NCSI_FILTER_VLAN, &vlan); + set_bit(cmd->index - 1, bitmap); + ncf->vids[cmd->index - 1] = ntohs(cmd->vlan); } + spin_unlock_irqrestore(&nc->lock, flags); - return ret; + return 0; } static int ncsi_rsp_handler_ev(struct ncsi_request *nr) @@ -422,8 +423,12 @@ static int ncsi_rsp_handler_sma(struct ncsi_request *nr) struct ncsi_rsp_pkt *rsp; struct ncsi_dev_priv *ndp = nr->ndp; struct ncsi_channel *nc; - struct ncsi_channel_filter *ncf; + struct ncsi_channel_mac_filter *ncf; + unsigned long flags; void *bitmap; + bool enabled; + int index; + /* Find the package and channel */ rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); @@ -436,31 +441,24 @@ static int ncsi_rsp_handler_sma(struct ncsi_request *nr) * isn't supported yet. */ cmd = (struct ncsi_cmd_sma_pkt *)skb_network_header(nr->cmd); - switch (cmd->at_e >> 5) { - case 0x0: /* UC address */ - ncf = nc->filters[NCSI_FILTER_UC]; - break; - case 0x1: /* MC address */ - ncf = nc->filters[NCSI_FILTER_MC]; - break; - default: - return -EINVAL; - } + enabled = cmd->at_e & 0x1; + ncf = &nc->mac_filter; + bitmap = &ncf->bitmap; - /* Sanity check on the filter */ - if (!ncf) - return -ENOENT; - else if (cmd->index >= ncf->total) + if (cmd->index == 0 || + cmd->index > ncf->n_uc + ncf->n_mc + ncf->n_mixed) return -ERANGE; - bitmap = &ncf->bitmap; - if (cmd->at_e & 0x1) { - set_bit(cmd->index, bitmap); - memcpy(ncf->data + 6 * cmd->index, cmd->mac, 6); + index = (cmd->index - 1) * ETH_ALEN; + spin_lock_irqsave(&nc->lock, flags); + if (enabled) { + set_bit(cmd->index - 1, bitmap); + memcpy(&ncf->addrs[index], cmd->mac, ETH_ALEN); } else { - clear_bit(cmd->index, bitmap); - memset(ncf->data + 6 * cmd->index, 0, 6); + clear_bit(cmd->index - 1, bitmap); + memset(&ncf->addrs[index], 0, ETH_ALEN); } + spin_unlock_irqrestore(&nc->lock, flags); return 0; } @@ -631,9 +629,7 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr) struct ncsi_rsp_gc_pkt *rsp; struct ncsi_dev_priv *ndp = nr->ndp; struct ncsi_channel *nc; - struct ncsi_channel_filter *ncf; - size_t size, entry_size; - int cnt, i; + size_t size; /* Find the channel */ rsp = (struct ncsi_rsp_gc_pkt *)skb_network_header(nr->rsp); @@ -655,64 +651,40 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr) nc->caps[NCSI_CAP_VLAN].cap = rsp->vlan_mode & NCSI_CAP_VLAN_MASK; - /* Build filters */ - for (i = 0; i < NCSI_FILTER_MAX; i++) { - switch (i) { - case NCSI_FILTER_VLAN: - cnt = rsp->vlan_cnt; - entry_size = 2; - break; - case NCSI_FILTER_MIXED: - cnt = rsp->mixed_cnt; - entry_size = 6; - break; - case NCSI_FILTER_MC: - cnt = rsp->mc_cnt; - entry_size = 6; - break; - case NCSI_FILTER_UC: - cnt = rsp->uc_cnt; - entry_size = 6; - break; - default: - continue; - } - - if (!cnt || nc->filters[i]) - continue; - - size = sizeof(*ncf) + cnt * entry_size; - ncf = kzalloc(size, GFP_ATOMIC); - if (!ncf) { - pr_warn("%s: Cannot alloc filter table (%d)\n", - __func__, i); - return -ENOMEM; - } - - ncf->index = i; - ncf->total = cnt; - if (i == NCSI_FILTER_VLAN) { - /* Set VLAN filters active so they are cleared in - * first configuration state - */ - ncf->bitmap = U64_MAX; - } else { - ncf->bitmap = 0x0ul; - } - nc->filters[i] = ncf; - } + size = (rsp->uc_cnt + rsp->mc_cnt + rsp->mixed_cnt) * ETH_ALEN; + nc->mac_filter.addrs = kzalloc(size, GFP_ATOMIC); + if (!nc->mac_filter.addrs) + return -ENOMEM; + nc->mac_filter.n_uc = rsp->uc_cnt; + nc->mac_filter.n_mc = rsp->mc_cnt; + nc->mac_filter.n_mixed = rsp->mixed_cnt; + + nc->vlan_filter.vids = kcalloc(rsp->vlan_cnt, + sizeof(*nc->vlan_filter.vids), + GFP_ATOMIC); + if (!nc->vlan_filter.vids) + return -ENOMEM; + /* Set VLAN filters active so they are cleared in the first + * configuration state + */ + nc->vlan_filter.bitmap = U64_MAX; + nc->vlan_filter.n_vids = rsp->vlan_cnt; return 0; } static int ncsi_rsp_handler_gp(struct ncsi_request *nr) { - struct ncsi_rsp_gp_pkt *rsp; + struct ncsi_channel_vlan_filter *ncvf; + struct ncsi_channel_mac_filter *ncmf; struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_rsp_gp_pkt *rsp; struct ncsi_channel *nc; - unsigned short enable, vlan; + unsigned short enable; unsigned char *pdata; - int table, i; + unsigned long flags; + void *bitmap; + int i; /* Find the channel */ rsp = (struct ncsi_rsp_gp_pkt *)skb_network_header(nr->rsp); @@ -746,36 +718,33 @@ static int ncsi_rsp_handler_gp(struct ncsi_request *nr) /* MAC addresses filter table */ pdata = (unsigned char *)rsp + 48; enable = rsp->mac_enable; + ncmf = &nc->mac_filter; + spin_lock_irqsave(&nc->lock, flags); + bitmap = &ncmf->bitmap; for (i = 0; i < rsp->mac_cnt; i++, pdata += 6) { - if (i >= (nc->filters[NCSI_FILTER_UC]->total + - nc->filters[NCSI_FILTER_MC]->total)) - table = NCSI_FILTER_MIXED; - else if (i >= nc->filters[NCSI_FILTER_UC]->total) - table = NCSI_FILTER_MC; - else - table = NCSI_FILTER_UC; - if (!(enable & (0x1 << i))) - continue; - - if (ncsi_find_filter(nc, table, pdata) >= 0) - continue; + clear_bit(i, bitmap); + else + set_bit(i, bitmap); - ncsi_add_filter(nc, table, pdata); + memcpy(&ncmf->addrs[i * ETH_ALEN], pdata, ETH_ALEN); } + spin_unlock_irqrestore(&nc->lock, flags); /* VLAN filter table */ enable = ntohs(rsp->vlan_enable); + ncvf = &nc->vlan_filter; + bitmap = &ncvf->bitmap; + spin_lock_irqsave(&nc->lock, flags); for (i = 0; i < rsp->vlan_cnt; i++, pdata += 2) { if (!(enable & (0x1 << i))) - continue; - - vlan = ntohs(*(__be16 *)pdata); - if (ncsi_find_filter(nc, NCSI_FILTER_VLAN, &vlan) >= 0) - continue; + clear_bit(i, bitmap); + else + set_bit(i, bitmap); - ncsi_add_filter(nc, NCSI_FILTER_VLAN, &vlan); + ncvf->vids[i] = ntohs(*(__be16 *)pdata); } + spin_unlock_irqrestore(&nc->lock, flags); return 0; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 44d8a55e97212..dbd7d1fad277e 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -433,17 +433,16 @@ config NF_NAT_TFTP default NF_NAT && NF_CONNTRACK_TFTP config NF_NAT_REDIRECT - tristate "IPv4/IPv6 redirect support" - depends on NF_NAT - help - This is the kernel functionality to redirect packets to local - machine through NAT. + bool config NETFILTER_SYNPROXY tristate endif # NF_CONNTRACK +config NF_OSF + tristate + config NF_TABLES select NETFILTER_NETLINK tristate "Netfilter nf_tables support" @@ -474,24 +473,6 @@ config NF_TABLES_NETDEV help This option enables support for the "netdev" table. -config NFT_EXTHDR - tristate "Netfilter nf_tables exthdr module" - help - This option adds the "exthdr" expression that you can use to match - IPv6 extension headers and tcp options. - -config NFT_META - tristate "Netfilter nf_tables meta module" - help - This option adds the "meta" expression that you can use to match and - to set packet metainformation such as the packet mark. - -config NFT_RT - tristate "Netfilter nf_tables routing module" - help - This option adds the "rt" expression that you can use to match - packet routing information such as the packet nexthop. - config NFT_NUMGEN tristate "Netfilter nf_tables number generator module" help @@ -536,6 +517,15 @@ config NFT_COUNTER This option adds the "counter" expression that you can use to include packet and byte counters in a rule. +config NFT_CONNLIMIT + tristate "Netfilter nf_tables connlimit module" + depends on NF_CONNTRACK + depends on NETFILTER_ADVANCED + select NETFILTER_CONNCOUNT + help + This option adds the "connlimit" expression that you can use to + ratelimit rule matchings per connections. + config NFT_LOG tristate "Netfilter nf_tables log module" help @@ -632,6 +622,15 @@ config NFT_FIB_INET The lookup will be delegated to the IPv4 or IPv6 FIB depending on the protocol of the packet. +config NFT_SOCKET + tristate "Netfilter nf_tables socket match support" + depends on IPV6 || IPV6=n + select NF_SOCKET_IPV4 + select NF_SOCKET_IPV6 if IPV6 + help + This option allows matching for the presence or absence of a + corresponding socket and its attributes. + if NF_TABLES_NETDEV config NF_DUP_NETDEV @@ -667,8 +666,7 @@ endif # NF_TABLES config NF_FLOW_TABLE_INET tristate "Netfilter flow table mixed IPv4/IPv6 module" - depends on NF_FLOW_TABLE_IPV4 - depends on NF_FLOW_TABLE_IPV6 + depends on NF_FLOW_TABLE help This option adds the flow table mixed IPv4/IPv6 support. @@ -1000,6 +998,8 @@ config NETFILTER_XT_TARGET_TPROXY depends on IP_NF_MANGLE select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES != n + select NF_TPROXY_IPV4 + select NF_TPROXY_IPV6 if IP6_NF_IPTABLES help This option adds a `TPROXY' target, which is somewhat similar to REDIRECT. It can only be used in the mangle table and is useful @@ -1378,6 +1378,7 @@ config NETFILTER_XT_MATCH_NFACCT config NETFILTER_XT_MATCH_OSF tristate '"osf" Passive OS fingerprint match' depends on NETFILTER_ADVANCED && NETFILTER_NETLINK + select NF_OSF help This option selects the Passive OS Fingerprinting match module that allows to passively match the remote operating system by diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index fd32bd2c95215..44449389e527b 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -55,7 +55,7 @@ obj-$(CONFIG_NF_LOG_COMMON) += nf_log_common.o obj-$(CONFIG_NF_LOG_NETDEV) += nf_log_netdev.o obj-$(CONFIG_NF_NAT) += nf_nat.o -obj-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o +nf_nat-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o # NAT helpers obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o @@ -76,13 +76,11 @@ obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ - nft_dynset.o + nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o -obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o -obj-$(CONFIG_NFT_META) += nft_meta.o -obj-$(CONFIG_NFT_RT) += nft_rt.o +obj-$(CONFIG_NFT_CONNLIMIT) += nft_connlimit.o obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o obj-$(CONFIG_NFT_CT) += nft_ct.o obj-$(CONFIG_NFT_FLOW_OFFLOAD) += nft_flow_offload.o @@ -104,6 +102,8 @@ obj-$(CONFIG_NFT_HASH) += nft_hash.o obj-$(CONFIG_NFT_FIB) += nft_fib.o obj-$(CONFIG_NFT_FIB_INET) += nft_fib_inet.o obj-$(CONFIG_NFT_FIB_NETDEV) += nft_fib_netdev.o +obj-$(CONFIG_NF_OSF) += nf_osf.o +obj-$(CONFIG_NFT_SOCKET) += nft_socket.o # nf_tables netdev obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o @@ -111,6 +111,8 @@ obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o # flow table infrastructure obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o +nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o + obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o # generic X tables diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 206fb2c4c319d..168af54db975d 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -138,11 +138,6 @@ nf_hook_entries_grow(const struct nf_hook_entries *old, continue; } - if (reg->nat_hook && orig_ops[i]->nat_hook) { - kvfree(new); - return ERR_PTR(-EBUSY); - } - if (inserted || reg->priority > orig_ops[i]->priority) { new_ops[nhooks] = (void *)orig_ops[i]; new->hooks[nhooks] = old->hooks[i]; @@ -186,9 +181,31 @@ static void hooks_validate(const struct nf_hook_entries *hooks) #endif } +int nf_hook_entries_insert_raw(struct nf_hook_entries __rcu **pp, + const struct nf_hook_ops *reg) +{ + struct nf_hook_entries *new_hooks; + struct nf_hook_entries *p; + + p = rcu_dereference_raw(*pp); + new_hooks = nf_hook_entries_grow(p, reg); + if (IS_ERR(new_hooks)) + return PTR_ERR(new_hooks); + + hooks_validate(new_hooks); + + rcu_assign_pointer(*pp, new_hooks); + + BUG_ON(p == new_hooks); + nf_hook_entries_free(p); + return 0; +} +EXPORT_SYMBOL_GPL(nf_hook_entries_insert_raw); + /* * __nf_hook_entries_try_shrink - try to shrink hook array * + * @old -- current hook blob at @pp * @pp -- location of hook blob * * Hook unregistration must always succeed, so to-be-removed hooks @@ -201,14 +218,14 @@ static void hooks_validate(const struct nf_hook_entries *hooks) * * Returns address to free, or NULL. */ -static void *__nf_hook_entries_try_shrink(struct nf_hook_entries __rcu **pp) +static void *__nf_hook_entries_try_shrink(struct nf_hook_entries *old, + struct nf_hook_entries __rcu **pp) { - struct nf_hook_entries *old, *new = NULL; unsigned int i, j, skip = 0, hook_entries; + struct nf_hook_entries *new = NULL; struct nf_hook_ops **orig_ops; struct nf_hook_ops **new_ops; - old = nf_entry_dereference(*pp); if (WARN_ON_ONCE(!old)) return NULL; @@ -347,11 +364,10 @@ static int __nf_register_net_hook(struct net *net, int pf, * This cannot fail, hook unregistration must always succeed. * Therefore replace the to-be-removed hook with a dummy hook. */ -static void nf_remove_net_hook(struct nf_hook_entries *old, - const struct nf_hook_ops *unreg, int pf) +static bool nf_remove_net_hook(struct nf_hook_entries *old, + const struct nf_hook_ops *unreg) { struct nf_hook_ops **orig_ops; - bool found = false; unsigned int i; orig_ops = nf_hook_entries_get_hook_ops(old); @@ -360,21 +376,10 @@ static void nf_remove_net_hook(struct nf_hook_entries *old, continue; WRITE_ONCE(old->hooks[i].hook, accept_all); WRITE_ONCE(orig_ops[i], &dummy_ops); - found = true; - break; + return true; } - if (found) { -#ifdef CONFIG_NETFILTER_INGRESS - if (pf == NFPROTO_NETDEV && unreg->hooknum == NF_NETDEV_INGRESS) - net_dec_ingress_queue(); -#endif -#ifdef HAVE_JUMP_LABEL - static_key_slow_dec(&nf_hooks_needed[pf][unreg->hooknum]); -#endif - } else { - WARN_ONCE(1, "hook not found, pf %d num %d", pf, unreg->hooknum); - } + return false; } static void __nf_unregister_net_hook(struct net *net, int pf, @@ -395,9 +400,19 @@ static void __nf_unregister_net_hook(struct net *net, int pf, return; } - nf_remove_net_hook(p, reg, pf); + if (nf_remove_net_hook(p, reg)) { +#ifdef CONFIG_NETFILTER_INGRESS + if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) + net_dec_ingress_queue(); +#endif +#ifdef HAVE_JUMP_LABEL + static_key_slow_dec(&nf_hooks_needed[pf][reg->hooknum]); +#endif + } else { + WARN_ONCE(1, "hook not found, pf %d num %d", pf, reg->hooknum); + } - p = __nf_hook_entries_try_shrink(pp); + p = __nf_hook_entries_try_shrink(p, pp); mutex_unlock(&nf_hook_mutex); if (!p) return; @@ -417,6 +432,19 @@ void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) } EXPORT_SYMBOL(nf_unregister_net_hook); +void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, + const struct nf_hook_ops *reg) +{ + struct nf_hook_entries *p; + + p = rcu_dereference_raw(*pp); + if (nf_remove_net_hook(p, reg)) { + p = __nf_hook_entries_try_shrink(p, pp); + nf_hook_entries_free(p); + } +} +EXPORT_SYMBOL_GPL(nf_hook_entries_delete_raw); + int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) { int err; @@ -535,6 +563,9 @@ EXPORT_SYMBOL(skb_make_writable); struct nfnl_ct_hook __rcu *nfnl_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nfnl_ct_hook); +struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; +EXPORT_SYMBOL_GPL(nf_ct_hook); + #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* This does not belong here, but locally generated errors need it if connection tracking in use: without this, connection may not be in hash table, and hence @@ -543,6 +574,9 @@ void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu __read_mostly; EXPORT_SYMBOL(ip_ct_attach); +struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; +EXPORT_SYMBOL_GPL(nf_nat_hook); + void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) { void (*attach)(struct sk_buff *, const struct sk_buff *); @@ -557,17 +591,14 @@ void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) } EXPORT_SYMBOL(nf_ct_attach); -void (*nf_ct_destroy)(struct nf_conntrack *) __rcu __read_mostly; -EXPORT_SYMBOL(nf_ct_destroy); - void nf_conntrack_destroy(struct nf_conntrack *nfct) { - void (*destroy)(struct nf_conntrack *); + struct nf_ct_hook *ct_hook; rcu_read_lock(); - destroy = rcu_dereference(nf_ct_destroy); - BUG_ON(destroy == NULL); - destroy(nfct); + ct_hook = rcu_dereference(nf_ct_hook); + BUG_ON(ct_hook == NULL); + ct_hook->destroy(nfct); rcu_read_unlock(); } EXPORT_SYMBOL(nf_conntrack_destroy); @@ -580,11 +611,6 @@ const struct nf_conntrack_zone nf_ct_zone_dflt = { EXPORT_SYMBOL_GPL(nf_ct_zone_dflt); #endif /* CONFIG_NF_CONNTRACK */ -#ifdef CONFIG_NF_NAT_NEEDED -void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); -EXPORT_SYMBOL(nf_nat_decode_session_hook); -#endif - static void __net_init __netfilter_net_init(struct nf_hook_entries __rcu **e, int max) { diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index b32fb0dbe237d..05dc1b77e466f 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -225,6 +225,25 @@ config IP_VS_SH If you want to compile it in kernel, say Y. To compile it as a module, choose M here. If unsure, say N. +config IP_VS_MH + tristate "maglev hashing scheduling" + ---help--- + The maglev consistent hashing scheduling algorithm provides the + Google's Maglev hashing algorithm as a IPVS scheduler. It assigns + network connections to the servers through looking up a statically + assigned special hash table called the lookup table. Maglev hashing + is to assign a preference list of all the lookup table positions + to each destination. + + Through this operation, The maglev hashing gives an almost equal + share of the lookup table to each of the destinations and provides + minimal disruption by using the lookup table. When the set of + destinations changes, a connection will likely be sent to the same + destination as it was before. + + If you want to compile it in kernel, say Y. To compile it as a + module, choose M here. If unsure, say N. + config IP_VS_SED tristate "shortest expected delay scheduling" ---help--- @@ -266,6 +285,24 @@ config IP_VS_SH_TAB_BITS needs to be large enough to effectively fit all the destinations multiplied by their respective weights. +comment 'IPVS MH scheduler' + +config IP_VS_MH_TAB_INDEX + int "IPVS maglev hashing table index of size (the prime numbers)" + range 8 17 + default 12 + ---help--- + The maglev hashing scheduler maps source IPs to destinations + stored in a hash table. This table is assigned by a preference + list of the positions to each destination until all slots in + the table are filled. The index determines the prime for size of + the table as 251, 509, 1021, 2039, 4093, 8191, 16381, 32749, + 65521 or 131071. When using weights to allow destinations to + receive more connections, the table is assigned an amount + proportional to the weights specified. The table needs to be large + enough to effectively fit all the destinations multiplied by their + respective weights. + comment 'IPVS application helper' config IP_VS_FTP diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile index c552993fa4b91..bfce2677fda26 100644 --- a/net/netfilter/ipvs/Makefile +++ b/net/netfilter/ipvs/Makefile @@ -33,6 +33,7 @@ obj-$(CONFIG_IP_VS_LBLC) += ip_vs_lblc.o obj-$(CONFIG_IP_VS_LBLCR) += ip_vs_lblcr.o obj-$(CONFIG_IP_VS_DH) += ip_vs_dh.o obj-$(CONFIG_IP_VS_SH) += ip_vs_sh.o +obj-$(CONFIG_IP_VS_MH) += ip_vs_mh.o obj-$(CONFIG_IP_VS_SED) += ip_vs_sed.o obj-$(CONFIG_IP_VS_NQ) += ip_vs_nq.o diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index c3db074fc1f73..7588aeaa605ff 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -355,7 +355,8 @@ static inline void vs_seq_update(struct ip_vs_conn *cp, struct ip_vs_seq *vseq, } static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, - struct ip_vs_app *app) + struct ip_vs_app *app, + struct ip_vs_iphdr *ipvsh) { int diff; const unsigned int tcp_offset = ip_hdrlen(skb); @@ -386,7 +387,7 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, if (app->pkt_out == NULL) return 1; - if (!app->pkt_out(app, cp, skb, &diff)) + if (!app->pkt_out(app, cp, skb, &diff, ipvsh)) return 0; /* @@ -404,7 +405,8 @@ static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, * called by ipvs packet handler, assumes previously checked cp!=NULL * returns false if it can't handle packet (oom) */ -int ip_vs_app_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb) +int ip_vs_app_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, + struct ip_vs_iphdr *ipvsh) { struct ip_vs_app *app; @@ -417,7 +419,7 @@ int ip_vs_app_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb) /* TCP is complicated */ if (cp->protocol == IPPROTO_TCP) - return app_tcp_pkt_out(cp, skb, app); + return app_tcp_pkt_out(cp, skb, app, ipvsh); /* * Call private output hook function @@ -425,12 +427,13 @@ int ip_vs_app_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb) if (app->pkt_out == NULL) return 1; - return app->pkt_out(app, cp, skb, NULL); + return app->pkt_out(app, cp, skb, NULL, ipvsh); } static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, - struct ip_vs_app *app) + struct ip_vs_app *app, + struct ip_vs_iphdr *ipvsh) { int diff; const unsigned int tcp_offset = ip_hdrlen(skb); @@ -461,7 +464,7 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, if (app->pkt_in == NULL) return 1; - if (!app->pkt_in(app, cp, skb, &diff)) + if (!app->pkt_in(app, cp, skb, &diff, ipvsh)) return 0; /* @@ -479,7 +482,8 @@ static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, * called by ipvs packet handler, assumes previously checked cp!=NULL. * returns false if can't handle packet (oom). */ -int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb) +int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, + struct ip_vs_iphdr *ipvsh) { struct ip_vs_app *app; @@ -492,7 +496,7 @@ int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb) /* TCP is complicated */ if (cp->protocol == IPPROTO_TCP) - return app_tcp_pkt_in(cp, skb, app); + return app_tcp_pkt_in(cp, skb, app, ipvsh); /* * Call private input hook function @@ -500,7 +504,7 @@ int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb) if (app->pkt_in == NULL) return 1; - return app->pkt_in(app, cp, skb, NULL); + return app->pkt_in(app, cp, skb, NULL, ipvsh); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 141b1509c9483..0c03c0e16a964 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -821,6 +821,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, if (add && udest->af != svc->af) ipvs->mixed_address_family_dests++; + /* keep the last_weight with latest non-0 weight */ + if (add || udest->weight != 0) + atomic_set(&dest->last_weight, udest->weight); + /* set the weight and the flags */ atomic_set(&dest->weight, udest->weight); conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK; diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index 75f798f8e83b7..07459e71d9072 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -43,6 +43,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> +#include <linux/hash.h> #include <net/ip_vs.h> @@ -81,7 +82,7 @@ static inline unsigned int ip_vs_dh_hashkey(int af, const union nf_inet_addr *ad addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif - return (ntohl(addr_fold)*2654435761UL) & IP_VS_DH_TAB_MASK; + return hash_32(ntohl(addr_fold), IP_VS_DH_TAB_BITS); } diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 58d5d05aec24c..4398a72edec59 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -29,6 +29,8 @@ #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/skbuff.h> +#include <linux/ctype.h> +#include <linux/inet.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/netfilter.h> @@ -44,9 +46,18 @@ #include <net/ip_vs.h> -#define SERVER_STRING "227 " -#define CLIENT_STRING "PORT" +#define SERVER_STRING_PASV "227 " +#define CLIENT_STRING_PORT "PORT" +#define SERVER_STRING_EPSV "229 " +#define CLIENT_STRING_EPRT "EPRT" +enum { + IP_VS_FTP_ACTIVE = 0, + IP_VS_FTP_PORT = 0, + IP_VS_FTP_PASV, + IP_VS_FTP_EPRT, + IP_VS_FTP_EPSV, +}; /* * List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper @@ -58,9 +69,15 @@ module_param_array(ports, ushort, &ports_count, 0444); MODULE_PARM_DESC(ports, "Ports to monitor for FTP control commands"); -/* Dummy variable */ -static int ip_vs_ftp_pasv; +static char *ip_vs_ftp_data_ptr(struct sk_buff *skb, struct ip_vs_iphdr *ipvsh) +{ + struct tcphdr *th = (struct tcphdr *)((char *)skb->data + ipvsh->len); + + if ((th->doff << 2) < sizeof(struct tcphdr)) + return NULL; + return (char *)th + (th->doff << 2); +} static int ip_vs_ftp_init_conn(struct ip_vs_app *app, struct ip_vs_conn *cp) @@ -78,20 +95,20 @@ ip_vs_ftp_done_conn(struct ip_vs_app *app, struct ip_vs_conn *cp) } -/* - * Get <addr,port> from the string "xxx.xxx.xxx.xxx,ppp,ppp", started - * with the "pattern", ignoring before "skip" and terminated with - * the "term" character. - * <addr,port> is in network order. +/* Get <addr,port> from the string "xxx.xxx.xxx.xxx,ppp,ppp", started + * with the "pattern". <addr,port> is in network order. + * Parse extended format depending on ext. In this case addr can be pre-set. */ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, const char *pattern, size_t plen, - char skip, char term, - __be32 *addr, __be16 *port, - char **start, char **end) + char skip, bool ext, int mode, + union nf_inet_addr *addr, __be16 *port, + __u16 af, char **start, char **end) { char *s, c; unsigned char p[6]; + char edelim; + __u16 hport; int i = 0; if (data_limit - data < plen) { @@ -113,6 +130,11 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, if (s == data_limit) return -1; if (!found) { + /* "(" is optional for non-extended format, + * so catch the start of IPv4 address + */ + if (!ext && isdigit(*s)) + break; if (*s == skip) found = 1; } else if (*s != skip) { @@ -120,41 +142,102 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, } } } + /* Old IPv4-only format? */ + if (!ext) { + p[0] = 0; + for (data = s; ; data++) { + if (data == data_limit) + return -1; + c = *data; + if (isdigit(c)) { + p[i] = p[i]*10 + c - '0'; + } else if (c == ',' && i < 5) { + i++; + p[i] = 0; + } else { + /* unexpected character or terminator */ + break; + } + } - for (data = s; ; data++) { - if (data == data_limit) + if (i != 5) return -1; - if (*data == term) - break; + + *start = s; + *end = data; + addr->ip = get_unaligned((__be32 *) p); + *port = get_unaligned((__be16 *) (p + 4)); + return 1; } - *end = data; + if (s == data_limit) + return -1; + *start = s; + edelim = *s++; + if (edelim < 33 || edelim > 126) + return -1; + if (s == data_limit) + return -1; + if (*s == edelim) { + /* Address family is usually missing for EPSV response */ + if (mode != IP_VS_FTP_EPSV) + return -1; + s++; + if (s == data_limit) + return -1; + /* Then address should be missing too */ + if (*s != edelim) + return -1; + /* Caller can pre-set addr, if needed */ + s++; + } else { + const char *ep; - memset(p, 0, sizeof(p)); - for (data = s; ; data++) { - c = *data; - if (c == term) - break; - if (c >= '0' && c <= '9') { - p[i] = p[i]*10 + c - '0'; - } else if (c == ',' && i < 5) { - i++; - } else { - /* unexpected character */ + /* We allow address only from same family */ + if (af == AF_INET6 && *s != '2') return -1; + if (af == AF_INET && *s != '1') + return -1; + s++; + if (s == data_limit) + return -1; + if (*s != edelim) + return -1; + s++; + if (s == data_limit) + return -1; + if (af == AF_INET6) { + if (in6_pton(s, data_limit - s, (u8 *)addr, edelim, + &ep) <= 0) + return -1; + } else { + if (in4_pton(s, data_limit - s, (u8 *)addr, edelim, + &ep) <= 0) + return -1; } + s = (char *) ep; + if (s == data_limit) + return -1; + if (*s != edelim) + return -1; + s++; } - - if (i != 5) + for (hport = 0; ; s++) + { + if (s == data_limit) + return -1; + if (!isdigit(*s)) + break; + hport = hport * 10 + *s - '0'; + } + if (s == data_limit || !hport || *s != edelim) return -1; - - *start = s; - *addr = get_unaligned((__be32 *) p); - *port = get_unaligned((__be16 *) (p + 4)); + s++; + *end = s; + *port = htons(hport); return 1; } -/* - * Look at outgoing ftp packets to catch the response to a PASV command +/* Look at outgoing ftp packets to catch the response to a PASV/EPSV command * from the server (inside-to-outside). * When we see one, we build a connection entry with the client address, * client port 0 (unknown at the moment), the server address and the @@ -165,12 +248,13 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, * The outgoing packet should be something like * "227 Entering Passive Mode (xxx,xxx,xxx,xxx,ppp,ppp)". * xxx,xxx,xxx,xxx is the server address, ppp,ppp is the server port number. + * The extended format for EPSV response provides usually only port: + * "229 Entering Extended Passive Mode (|||ppp|)" */ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, - struct sk_buff *skb, int *diff) + struct sk_buff *skb, int *diff, + struct ip_vs_iphdr *ipvsh) { - struct iphdr *iph; - struct tcphdr *th; char *data, *data_limit; char *start, *end; union nf_inet_addr from; @@ -184,14 +268,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, *diff = 0; -#ifdef CONFIG_IP_VS_IPV6 - /* This application helper doesn't work with IPv6 yet, - * so turn this into a no-op for IPv6 packets - */ - if (cp->af == AF_INET6) - return 1; -#endif - /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; @@ -200,53 +276,77 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, if (!skb_make_writable(skb, skb->len)) return 0; - if (cp->app_data == &ip_vs_ftp_pasv) { - iph = ip_hdr(skb); - th = (struct tcphdr *)&(((char *)iph)[iph->ihl*4]); - data = (char *)th + (th->doff << 2); + if (cp->app_data == (void *) IP_VS_FTP_PASV) { + data = ip_vs_ftp_data_ptr(skb, ipvsh); data_limit = skb_tail_pointer(skb); + if (!data || data >= data_limit) + return 1; + if (ip_vs_ftp_get_addrport(data, data_limit, - SERVER_STRING, - sizeof(SERVER_STRING)-1, - '(', ')', - &from.ip, &port, + SERVER_STRING_PASV, + sizeof(SERVER_STRING_PASV)-1, + '(', false, IP_VS_FTP_PASV, + &from, &port, cp->af, &start, &end) != 1) return 1; - IP_VS_DBG(7, "PASV response (%pI4:%d) -> %pI4:%d detected\n", + IP_VS_DBG(7, "PASV response (%pI4:%u) -> %pI4:%u detected\n", &from.ip, ntohs(port), &cp->caddr.ip, 0); + } else if (cp->app_data == (void *) IP_VS_FTP_EPSV) { + data = ip_vs_ftp_data_ptr(skb, ipvsh); + data_limit = skb_tail_pointer(skb); - /* - * Now update or create an connection entry for it + if (!data || data >= data_limit) + return 1; + + /* Usually, data address is not specified but + * we support different address, so pre-set it. */ - { - struct ip_vs_conn_param p; - ip_vs_conn_fill_param(cp->ipvs, AF_INET, - iph->protocol, &from, port, - &cp->caddr, 0, &p); - n_cp = ip_vs_conn_out_get(&p); - } - if (!n_cp) { - struct ip_vs_conn_param p; - ip_vs_conn_fill_param(cp->ipvs, - AF_INET, IPPROTO_TCP, &cp->caddr, - 0, &cp->vaddr, port, &p); - /* As above, this is ipv4 only */ - n_cp = ip_vs_conn_new(&p, AF_INET, &from, port, - IP_VS_CONN_F_NO_CPORT | - IP_VS_CONN_F_NFCT, - cp->dest, skb->mark); - if (!n_cp) - return 0; + from = cp->daddr; + if (ip_vs_ftp_get_addrport(data, data_limit, + SERVER_STRING_EPSV, + sizeof(SERVER_STRING_EPSV)-1, + '(', true, IP_VS_FTP_EPSV, + &from, &port, cp->af, + &start, &end) != 1) + return 1; - /* add its controller */ - ip_vs_control_add(n_cp, cp); - } + IP_VS_DBG_BUF(7, "EPSV response (%s:%u) -> %s:%u detected\n", + IP_VS_DBG_ADDR(cp->af, &from), ntohs(port), + IP_VS_DBG_ADDR(cp->af, &cp->caddr), 0); + } else { + return 1; + } - /* - * Replace the old passive address with the new one - */ + /* Now update or create a connection entry for it */ + { + struct ip_vs_conn_param p; + + ip_vs_conn_fill_param(cp->ipvs, cp->af, + ipvsh->protocol, &from, port, + &cp->caddr, 0, &p); + n_cp = ip_vs_conn_out_get(&p); + } + if (!n_cp) { + struct ip_vs_conn_param p; + + ip_vs_conn_fill_param(cp->ipvs, + cp->af, ipvsh->protocol, &cp->caddr, + 0, &cp->vaddr, port, &p); + n_cp = ip_vs_conn_new(&p, cp->af, &from, port, + IP_VS_CONN_F_NO_CPORT | + IP_VS_CONN_F_NFCT, + cp->dest, skb->mark); + if (!n_cp) + return 0; + + /* add its controller */ + ip_vs_control_add(n_cp, cp); + } + + /* Replace the old passive address with the new one */ + if (cp->app_data == (void *) IP_VS_FTP_PASV) { from.ip = n_cp->vaddr.ip; port = n_cp->vport; snprintf(buf, sizeof(buf), "%u,%u,%u,%u,%u,%u", @@ -256,50 +356,54 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, ((unsigned char *)&from.ip)[3], ntohs(port) >> 8, ntohs(port) & 0xFF); + } else if (cp->app_data == (void *) IP_VS_FTP_EPSV) { + from = n_cp->vaddr; + port = n_cp->vport; + /* Only port, client will use VIP for the data connection */ + snprintf(buf, sizeof(buf), "|||%u|", + ntohs(port)); + } else { + *buf = 0; + } + buf_len = strlen(buf); - buf_len = strlen(buf); - - ct = nf_ct_get(skb, &ctinfo); - if (ct) { - bool mangled; - - /* If mangling fails this function will return 0 - * which will cause the packet to be dropped. - * Mangling can only fail under memory pressure, - * hopefully it will succeed on the retransmitted - * packet. - */ - mangled = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, - iph->ihl * 4, - start - data, - end - start, - buf, buf_len); - if (mangled) { - ip_vs_nfct_expect_related(skb, ct, n_cp, - IPPROTO_TCP, 0, 0); - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = CHECKSUM_UNNECESSARY; - /* csum is updated */ - ret = 1; - } - } + ct = nf_ct_get(skb, &ctinfo); + if (ct) { + bool mangled; - /* - * Not setting 'diff' is intentional, otherwise the sequence - * would be adjusted twice. + /* If mangling fails this function will return 0 + * which will cause the packet to be dropped. + * Mangling can only fail under memory pressure, + * hopefully it will succeed on the retransmitted + * packet. */ - - cp->app_data = NULL; - ip_vs_tcp_conn_listen(n_cp); - ip_vs_conn_put(n_cp); - return ret; + mangled = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, + ipvsh->len, + start - data, + end - start, + buf, buf_len); + if (mangled) { + ip_vs_nfct_expect_related(skb, ct, n_cp, + ipvsh->protocol, 0, 0); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->ip_summed = CHECKSUM_UNNECESSARY; + /* csum is updated */ + ret = 1; + } } - return 1; + + /* Not setting 'diff' is intentional, otherwise the sequence + * would be adjusted twice. + */ + + cp->app_data = (void *) IP_VS_FTP_ACTIVE; + ip_vs_tcp_conn_listen(n_cp); + ip_vs_conn_put(n_cp); + return ret; } -/* - * Look at incoming ftp packets to catch the PASV/PORT command +/* Look at incoming ftp packets to catch the PASV/PORT/EPRT/EPSV command * (outside-to-inside). * * The incoming packet having the PORT command should be something like @@ -308,12 +412,19 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, * In this case, we create a connection entry using the client address and * port, so that the active ftp data connection from the server can reach * the client. + * Extended format: + * "EPSV\r\n" when client requests server address from same family + * "EPSV 1\r\n" when client requests IPv4 server address + * "EPSV 2\r\n" when client requests IPv6 server address + * "EPSV ALL\r\n" - not supported + * EPRT with specified delimiter (ASCII 33..126), "|" by default: + * "EPRT |1|IPv4ADDR|PORT|\r\n" when client provides IPv4 addrport + * "EPRT |2|IPv6ADDR|PORT|\r\n" when client provides IPv6 addrport */ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, - struct sk_buff *skb, int *diff) + struct sk_buff *skb, int *diff, + struct ip_vs_iphdr *ipvsh) { - struct iphdr *iph; - struct tcphdr *th; char *data, *data_start, *data_limit; char *start, *end; union nf_inet_addr to; @@ -323,14 +434,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, /* no diff required for incoming packets */ *diff = 0; -#ifdef CONFIG_IP_VS_IPV6 - /* This application helper doesn't work with IPv6 yet, - * so turn this into a no-op for IPv6 packets - */ - if (cp->af == AF_INET6) - return 1; -#endif - /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; @@ -339,27 +442,48 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, if (!skb_make_writable(skb, skb->len)) return 0; - /* - * Detecting whether it is passive - */ - iph = ip_hdr(skb); - th = (struct tcphdr *)&(((char *)iph)[iph->ihl*4]); - - /* Since there may be OPTIONS in the TCP packet and the HLEN is - the length of the header in 32-bit multiples, it is accurate - to calculate data address by th+HLEN*4 */ - data = data_start = (char *)th + (th->doff << 2); + data = data_start = ip_vs_ftp_data_ptr(skb, ipvsh); data_limit = skb_tail_pointer(skb); + if (!data || data >= data_limit) + return 1; while (data <= data_limit - 6) { - if (strncasecmp(data, "PASV\r\n", 6) == 0) { + if (cp->af == AF_INET && + strncasecmp(data, "PASV\r\n", 6) == 0) { /* Passive mode on */ IP_VS_DBG(7, "got PASV at %td of %td\n", data - data_start, data_limit - data_start); - cp->app_data = &ip_vs_ftp_pasv; + cp->app_data = (void *) IP_VS_FTP_PASV; return 1; } + + /* EPSV or EPSV<space><net-prt> */ + if (strncasecmp(data, "EPSV", 4) == 0 && + (data[4] == ' ' || data[4] == '\r')) { + if (data[4] == ' ') { + char proto = data[5]; + + if (data > data_limit - 7 || data[6] != '\r') + return 1; + +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6 && proto == '2') { + } else +#endif + if (cp->af == AF_INET && proto == '1') { + } else { + return 1; + } + } + /* Extended Passive mode on */ + IP_VS_DBG(7, "got EPSV at %td of %td\n", + data - data_start, + data_limit - data_start); + cp->app_data = (void *) IP_VS_FTP_EPSV; + return 1; + } + data++; } @@ -370,33 +494,52 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, * then create a new connection entry for the coming data * connection. */ - if (ip_vs_ftp_get_addrport(data_start, data_limit, - CLIENT_STRING, sizeof(CLIENT_STRING)-1, - ' ', '\r', &to.ip, &port, - &start, &end) != 1) + if (cp->af == AF_INET && + ip_vs_ftp_get_addrport(data_start, data_limit, + CLIENT_STRING_PORT, + sizeof(CLIENT_STRING_PORT)-1, + ' ', false, IP_VS_FTP_PORT, + &to, &port, cp->af, + &start, &end) == 1) { + + IP_VS_DBG(7, "PORT %pI4:%u detected\n", &to.ip, ntohs(port)); + + /* Now update or create a connection entry for it */ + IP_VS_DBG(7, "protocol %s %pI4:%u %pI4:%u\n", + ip_vs_proto_name(ipvsh->protocol), + &to.ip, ntohs(port), &cp->vaddr.ip, + ntohs(cp->vport)-1); + } else if (ip_vs_ftp_get_addrport(data_start, data_limit, + CLIENT_STRING_EPRT, + sizeof(CLIENT_STRING_EPRT)-1, + ' ', true, IP_VS_FTP_EPRT, + &to, &port, cp->af, + &start, &end) == 1) { + + IP_VS_DBG_BUF(7, "EPRT %s:%u detected\n", + IP_VS_DBG_ADDR(cp->af, &to), ntohs(port)); + + /* Now update or create a connection entry for it */ + IP_VS_DBG_BUF(7, "protocol %s %s:%u %s:%u\n", + ip_vs_proto_name(ipvsh->protocol), + IP_VS_DBG_ADDR(cp->af, &to), ntohs(port), + IP_VS_DBG_ADDR(cp->af, &cp->vaddr), + ntohs(cp->vport)-1); + } else { return 1; - - IP_VS_DBG(7, "PORT %pI4:%d detected\n", &to.ip, ntohs(port)); + } /* Passive mode off */ - cp->app_data = NULL; - - /* - * Now update or create a connection entry for it - */ - IP_VS_DBG(7, "protocol %s %pI4:%d %pI4:%d\n", - ip_vs_proto_name(iph->protocol), - &to.ip, ntohs(port), &cp->vaddr.ip, 0); + cp->app_data = (void *) IP_VS_FTP_ACTIVE; { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(cp->ipvs, AF_INET, - iph->protocol, &to, port, &cp->vaddr, + ip_vs_conn_fill_param(cp->ipvs, cp->af, + ipvsh->protocol, &to, port, &cp->vaddr, htons(ntohs(cp->vport)-1), &p); n_cp = ip_vs_conn_in_get(&p); if (!n_cp) { - /* This is ipv4 only */ - n_cp = ip_vs_conn_new(&p, AF_INET, &cp->daddr, + n_cp = ip_vs_conn_new(&p, cp->af, &cp->daddr, htons(ntohs(cp->dport)-1), IP_VS_CONN_F_NFCT, cp->dest, skb->mark); @@ -454,7 +597,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net) ret = register_ip_vs_app_inc(ipvs, app, app->protocol, ports[i]); if (ret) goto err_unreg; - pr_info("%s: loaded support on port[%d] = %d\n", + pr_info("%s: loaded support on port[%d] = %u\n", app->name, i, ports[i]); } return 0; diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 3057e453bf317..b9f375e6dc937 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -48,6 +48,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/jiffies.h> +#include <linux/hash.h> /* for sysctl */ #include <linux/fs.h> @@ -160,7 +161,7 @@ ip_vs_lblc_hashkey(int af, const union nf_inet_addr *addr) addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif - return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLC_TAB_MASK; + return hash_32(ntohl(addr_fold), IP_VS_LBLC_TAB_BITS); } @@ -371,6 +372,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) tbl->counter = 1; tbl->dead = false; tbl->svc = svc; + atomic_set(&tbl->entries, 0); /* * Hook periodic timer for garbage collection diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 92adc04557ed9..542c4949937ab 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -47,6 +47,7 @@ #include <linux/jiffies.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/hash.h> /* for sysctl */ #include <linux/fs.h> @@ -323,7 +324,7 @@ ip_vs_lblcr_hashkey(int af, const union nf_inet_addr *addr) addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif - return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLCR_TAB_MASK; + return hash_32(ntohl(addr_fold), IP_VS_LBLCR_TAB_BITS); } @@ -534,6 +535,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) tbl->counter = 1; tbl->dead = false; tbl->svc = svc; + atomic_set(&tbl->entries, 0); /* * Hook periodic timer for garbage collection diff --git a/net/netfilter/ipvs/ip_vs_mh.c b/net/netfilter/ipvs/ip_vs_mh.c new file mode 100644 index 0000000000000..0f795b186eb3d --- /dev/null +++ b/net/netfilter/ipvs/ip_vs_mh.c @@ -0,0 +1,540 @@ +// SPDX-License-Identifier: GPL-2.0 +/* IPVS: Maglev Hashing scheduling module + * + * Authors: Inju Song <inju.song@navercorp.com> + * + */ + +/* The mh algorithm is to assign a preference list of all the lookup + * table positions to each destination and populate the table with + * the most-preferred position of destinations. Then it is to select + * destination with the hash key of source IP address through looking + * up a the lookup table. + * + * The algorithm is detailed in: + * [3.4 Consistent Hasing] +https://www.usenix.org/system/files/conference/nsdi16/nsdi16-paper-eisenbud.pdf + * + */ + +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/ip.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> + +#include <net/ip_vs.h> + +#include <linux/siphash.h> +#include <linux/bitops.h> +#include <linux/gcd.h> + +#define IP_VS_SVC_F_SCHED_MH_FALLBACK IP_VS_SVC_F_SCHED1 /* MH fallback */ +#define IP_VS_SVC_F_SCHED_MH_PORT IP_VS_SVC_F_SCHED2 /* MH use port */ + +struct ip_vs_mh_lookup { + struct ip_vs_dest __rcu *dest; /* real server (cache) */ +}; + +struct ip_vs_mh_dest_setup { + unsigned int offset; /* starting offset */ + unsigned int skip; /* skip */ + unsigned int perm; /* next_offset */ + int turns; /* weight / gcd() and rshift */ +}; + +/* Available prime numbers for MH table */ +static int primes[] = {251, 509, 1021, 2039, 4093, + 8191, 16381, 32749, 65521, 131071}; + +/* For IPVS MH entry hash table */ +#ifndef CONFIG_IP_VS_MH_TAB_INDEX +#define CONFIG_IP_VS_MH_TAB_INDEX 12 +#endif +#define IP_VS_MH_TAB_BITS (CONFIG_IP_VS_MH_TAB_INDEX / 2) +#define IP_VS_MH_TAB_INDEX (CONFIG_IP_VS_MH_TAB_INDEX - 8) +#define IP_VS_MH_TAB_SIZE primes[IP_VS_MH_TAB_INDEX] + +struct ip_vs_mh_state { + struct rcu_head rcu_head; + struct ip_vs_mh_lookup *lookup; + struct ip_vs_mh_dest_setup *dest_setup; + hsiphash_key_t hash1, hash2; + int gcd; + int rshift; +}; + +static inline void generate_hash_secret(hsiphash_key_t *hash1, + hsiphash_key_t *hash2) +{ + hash1->key[0] = 2654435761UL; + hash1->key[1] = 2654435761UL; + + hash2->key[0] = 2654446892UL; + hash2->key[1] = 2654446892UL; +} + +/* Helper function to determine if server is unavailable */ +static inline bool is_unavailable(struct ip_vs_dest *dest) +{ + return atomic_read(&dest->weight) <= 0 || + dest->flags & IP_VS_DEST_F_OVERLOAD; +} + +/* Returns hash value for IPVS MH entry */ +static inline unsigned int +ip_vs_mh_hashkey(int af, const union nf_inet_addr *addr, + __be16 port, hsiphash_key_t *key, unsigned int offset) +{ + unsigned int v; + __be32 addr_fold = addr->ip; + +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + addr_fold = addr->ip6[0] ^ addr->ip6[1] ^ + addr->ip6[2] ^ addr->ip6[3]; +#endif + v = (offset + ntohs(port) + ntohl(addr_fold)); + return hsiphash(&v, sizeof(v), key); +} + +/* Reset all the hash buckets of the specified table. */ +static void ip_vs_mh_reset(struct ip_vs_mh_state *s) +{ + int i; + struct ip_vs_mh_lookup *l; + struct ip_vs_dest *dest; + + l = &s->lookup[0]; + for (i = 0; i < IP_VS_MH_TAB_SIZE; i++) { + dest = rcu_dereference_protected(l->dest, 1); + if (dest) { + ip_vs_dest_put(dest); + RCU_INIT_POINTER(l->dest, NULL); + } + l++; + } +} + +static int ip_vs_mh_permutate(struct ip_vs_mh_state *s, + struct ip_vs_service *svc) +{ + struct list_head *p; + struct ip_vs_mh_dest_setup *ds; + struct ip_vs_dest *dest; + int lw; + + /* If gcd is smaller then 1, number of dests or + * all last_weight of dests are zero. So, skip + * permutation for the dests. + */ + if (s->gcd < 1) + return 0; + + /* Set dest_setup for the dests permutation */ + p = &svc->destinations; + ds = &s->dest_setup[0]; + while ((p = p->next) != &svc->destinations) { + dest = list_entry(p, struct ip_vs_dest, n_list); + + ds->offset = ip_vs_mh_hashkey(svc->af, &dest->addr, + dest->port, &s->hash1, 0) % + IP_VS_MH_TAB_SIZE; + ds->skip = ip_vs_mh_hashkey(svc->af, &dest->addr, + dest->port, &s->hash2, 0) % + (IP_VS_MH_TAB_SIZE - 1) + 1; + ds->perm = ds->offset; + + lw = atomic_read(&dest->last_weight); + ds->turns = ((lw / s->gcd) >> s->rshift) ? : (lw != 0); + ds++; + } + + return 0; +} + +static int ip_vs_mh_populate(struct ip_vs_mh_state *s, + struct ip_vs_service *svc) +{ + int n, c, dt_count; + unsigned long *table; + struct list_head *p; + struct ip_vs_mh_dest_setup *ds; + struct ip_vs_dest *dest, *new_dest; + + /* If gcd is smaller then 1, number of dests or + * all last_weight of dests are zero. So, skip + * the population for the dests and reset lookup table. + */ + if (s->gcd < 1) { + ip_vs_mh_reset(s); + return 0; + } + + table = kcalloc(BITS_TO_LONGS(IP_VS_MH_TAB_SIZE), + sizeof(unsigned long), GFP_KERNEL); + if (!table) + return -ENOMEM; + + p = &svc->destinations; + n = 0; + dt_count = 0; + while (n < IP_VS_MH_TAB_SIZE) { + if (p == &svc->destinations) + p = p->next; + + ds = &s->dest_setup[0]; + while (p != &svc->destinations) { + /* Ignore added server with zero weight */ + if (ds->turns < 1) { + p = p->next; + ds++; + continue; + } + + c = ds->perm; + while (test_bit(c, table)) { + /* Add skip, mod IP_VS_MH_TAB_SIZE */ + ds->perm += ds->skip; + if (ds->perm >= IP_VS_MH_TAB_SIZE) + ds->perm -= IP_VS_MH_TAB_SIZE; + c = ds->perm; + } + + __set_bit(c, table); + + dest = rcu_dereference_protected(s->lookup[c].dest, 1); + new_dest = list_entry(p, struct ip_vs_dest, n_list); + if (dest != new_dest) { + if (dest) + ip_vs_dest_put(dest); + ip_vs_dest_hold(new_dest); + RCU_INIT_POINTER(s->lookup[c].dest, new_dest); + } + + if (++n == IP_VS_MH_TAB_SIZE) + goto out; + + if (++dt_count >= ds->turns) { + dt_count = 0; + p = p->next; + ds++; + } + } + } + +out: + kfree(table); + return 0; +} + +/* Get ip_vs_dest associated with supplied parameters. */ +static inline struct ip_vs_dest * +ip_vs_mh_get(struct ip_vs_service *svc, struct ip_vs_mh_state *s, + const union nf_inet_addr *addr, __be16 port) +{ + unsigned int hash = ip_vs_mh_hashkey(svc->af, addr, port, &s->hash1, 0) + % IP_VS_MH_TAB_SIZE; + struct ip_vs_dest *dest = rcu_dereference(s->lookup[hash].dest); + + return (!dest || is_unavailable(dest)) ? NULL : dest; +} + +/* As ip_vs_mh_get, but with fallback if selected server is unavailable */ +static inline struct ip_vs_dest * +ip_vs_mh_get_fallback(struct ip_vs_service *svc, struct ip_vs_mh_state *s, + const union nf_inet_addr *addr, __be16 port) +{ + unsigned int offset, roffset; + unsigned int hash, ihash; + struct ip_vs_dest *dest; + + /* First try the dest it's supposed to go to */ + ihash = ip_vs_mh_hashkey(svc->af, addr, port, + &s->hash1, 0) % IP_VS_MH_TAB_SIZE; + dest = rcu_dereference(s->lookup[ihash].dest); + if (!dest) + return NULL; + if (!is_unavailable(dest)) + return dest; + + IP_VS_DBG_BUF(6, "MH: selected unavailable server %s:%u, reselecting", + IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port)); + + /* If the original dest is unavailable, loop around the table + * starting from ihash to find a new dest + */ + for (offset = 0; offset < IP_VS_MH_TAB_SIZE; offset++) { + roffset = (offset + ihash) % IP_VS_MH_TAB_SIZE; + hash = ip_vs_mh_hashkey(svc->af, addr, port, &s->hash1, + roffset) % IP_VS_MH_TAB_SIZE; + dest = rcu_dereference(s->lookup[hash].dest); + if (!dest) + break; + if (!is_unavailable(dest)) + return dest; + IP_VS_DBG_BUF(6, + "MH: selected unavailable server %s:%u (offset %u), reselecting", + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port), roffset); + } + + return NULL; +} + +/* Assign all the hash buckets of the specified table with the service. */ +static int ip_vs_mh_reassign(struct ip_vs_mh_state *s, + struct ip_vs_service *svc) +{ + int ret; + + if (svc->num_dests > IP_VS_MH_TAB_SIZE) + return -EINVAL; + + if (svc->num_dests >= 1) { + s->dest_setup = kcalloc(svc->num_dests, + sizeof(struct ip_vs_mh_dest_setup), + GFP_KERNEL); + if (!s->dest_setup) + return -ENOMEM; + } + + ip_vs_mh_permutate(s, svc); + + ret = ip_vs_mh_populate(s, svc); + if (ret < 0) + goto out; + + IP_VS_DBG_BUF(6, "MH: reassign lookup table of %s:%u\n", + IP_VS_DBG_ADDR(svc->af, &svc->addr), + ntohs(svc->port)); + +out: + if (svc->num_dests >= 1) { + kfree(s->dest_setup); + s->dest_setup = NULL; + } + return ret; +} + +static int ip_vs_mh_gcd_weight(struct ip_vs_service *svc) +{ + struct ip_vs_dest *dest; + int weight; + int g = 0; + + list_for_each_entry(dest, &svc->destinations, n_list) { + weight = atomic_read(&dest->last_weight); + if (weight > 0) { + if (g > 0) + g = gcd(weight, g); + else + g = weight; + } + } + return g; +} + +/* To avoid assigning huge weight for the MH table, + * calculate shift value with gcd. + */ +static int ip_vs_mh_shift_weight(struct ip_vs_service *svc, int gcd) +{ + struct ip_vs_dest *dest; + int new_weight, weight = 0; + int mw, shift; + + /* If gcd is smaller then 1, number of dests or + * all last_weight of dests are zero. So, return + * shift value as zero. + */ + if (gcd < 1) + return 0; + + list_for_each_entry(dest, &svc->destinations, n_list) { + new_weight = atomic_read(&dest->last_weight); + if (new_weight > weight) + weight = new_weight; + } + + /* Because gcd is greater than zero, + * the maximum weight and gcd are always greater than zero + */ + mw = weight / gcd; + + /* shift = occupied bits of weight/gcd - MH highest bits */ + shift = fls(mw) - IP_VS_MH_TAB_BITS; + return (shift >= 0) ? shift : 0; +} + +static void ip_vs_mh_state_free(struct rcu_head *head) +{ + struct ip_vs_mh_state *s; + + s = container_of(head, struct ip_vs_mh_state, rcu_head); + kfree(s->lookup); + kfree(s); +} + +static int ip_vs_mh_init_svc(struct ip_vs_service *svc) +{ + int ret; + struct ip_vs_mh_state *s; + + /* Allocate the MH table for this service */ + s = kzalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + s->lookup = kcalloc(IP_VS_MH_TAB_SIZE, sizeof(struct ip_vs_mh_lookup), + GFP_KERNEL); + if (!s->lookup) { + kfree(s); + return -ENOMEM; + } + + generate_hash_secret(&s->hash1, &s->hash2); + s->gcd = ip_vs_mh_gcd_weight(svc); + s->rshift = ip_vs_mh_shift_weight(svc, s->gcd); + + IP_VS_DBG(6, + "MH lookup table (memory=%zdbytes) allocated for current service\n", + sizeof(struct ip_vs_mh_lookup) * IP_VS_MH_TAB_SIZE); + + /* Assign the lookup table with current dests */ + ret = ip_vs_mh_reassign(s, svc); + if (ret < 0) { + ip_vs_mh_reset(s); + ip_vs_mh_state_free(&s->rcu_head); + return ret; + } + + /* No more failures, attach state */ + svc->sched_data = s; + return 0; +} + +static void ip_vs_mh_done_svc(struct ip_vs_service *svc) +{ + struct ip_vs_mh_state *s = svc->sched_data; + + /* Got to clean up lookup entry here */ + ip_vs_mh_reset(s); + + call_rcu(&s->rcu_head, ip_vs_mh_state_free); + IP_VS_DBG(6, "MH lookup table (memory=%zdbytes) released\n", + sizeof(struct ip_vs_mh_lookup) * IP_VS_MH_TAB_SIZE); +} + +static int ip_vs_mh_dest_changed(struct ip_vs_service *svc, + struct ip_vs_dest *dest) +{ + struct ip_vs_mh_state *s = svc->sched_data; + + s->gcd = ip_vs_mh_gcd_weight(svc); + s->rshift = ip_vs_mh_shift_weight(svc, s->gcd); + + /* Assign the lookup table with the updated service */ + return ip_vs_mh_reassign(s, svc); +} + +/* Helper function to get port number */ +static inline __be16 +ip_vs_mh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph) +{ + __be16 _ports[2], *ports; + + /* At this point we know that we have a valid packet of some kind. + * Because ICMP packets are only guaranteed to have the first 8 + * bytes, let's just grab the ports. Fortunately they're in the + * same position for all three of the protocols we care about. + */ + switch (iph->protocol) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_SCTP: + ports = skb_header_pointer(skb, iph->len, sizeof(_ports), + &_ports); + if (unlikely(!ports)) + return 0; + + if (likely(!ip_vs_iph_inverse(iph))) + return ports[0]; + else + return ports[1]; + default: + return 0; + } +} + +/* Maglev Hashing scheduling */ +static struct ip_vs_dest * +ip_vs_mh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) +{ + struct ip_vs_dest *dest; + struct ip_vs_mh_state *s; + __be16 port = 0; + const union nf_inet_addr *hash_addr; + + hash_addr = ip_vs_iph_inverse(iph) ? &iph->daddr : &iph->saddr; + + IP_VS_DBG(6, "%s : Scheduling...\n", __func__); + + if (svc->flags & IP_VS_SVC_F_SCHED_MH_PORT) + port = ip_vs_mh_get_port(skb, iph); + + s = (struct ip_vs_mh_state *)svc->sched_data; + + if (svc->flags & IP_VS_SVC_F_SCHED_MH_FALLBACK) + dest = ip_vs_mh_get_fallback(svc, s, hash_addr, port); + else + dest = ip_vs_mh_get(svc, s, hash_addr, port); + + if (!dest) { + ip_vs_scheduler_err(svc, "no destination available"); + return NULL; + } + + IP_VS_DBG_BUF(6, "MH: source IP address %s:%u --> server %s:%u\n", + IP_VS_DBG_ADDR(svc->af, hash_addr), + ntohs(port), + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port)); + + return dest; +} + +/* IPVS MH Scheduler structure */ +static struct ip_vs_scheduler ip_vs_mh_scheduler = { + .name = "mh", + .refcnt = ATOMIC_INIT(0), + .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_mh_scheduler.n_list), + .init_service = ip_vs_mh_init_svc, + .done_service = ip_vs_mh_done_svc, + .add_dest = ip_vs_mh_dest_changed, + .del_dest = ip_vs_mh_dest_changed, + .upd_dest = ip_vs_mh_dest_changed, + .schedule = ip_vs_mh_schedule, +}; + +static int __init ip_vs_mh_init(void) +{ + return register_ip_vs_scheduler(&ip_vs_mh_scheduler); +} + +static void __exit ip_vs_mh_cleanup(void) +{ + unregister_ip_vs_scheduler(&ip_vs_mh_scheduler); + rcu_barrier(); +} + +module_init(ip_vs_mh_init); +module_exit(ip_vs_mh_cleanup); +MODULE_DESCRIPTION("Maglev hashing ipvs scheduler"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Inju Song <inju.song@navercorp.com>"); diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 6cf3fd81a5eca..eb8b9c883889c 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -67,15 +67,20 @@ #include <net/netfilter/nf_conntrack_zones.h> -#define FMT_TUPLE "%pI4:%u->%pI4:%u/%u" -#define ARG_TUPLE(T) &(T)->src.u3.ip, ntohs((T)->src.u.all), \ - &(T)->dst.u3.ip, ntohs((T)->dst.u.all), \ +#define FMT_TUPLE "%s:%u->%s:%u/%u" +#define ARG_TUPLE(T) IP_VS_DBG_ADDR((T)->src.l3num, &(T)->src.u3), \ + ntohs((T)->src.u.all), \ + IP_VS_DBG_ADDR((T)->src.l3num, &(T)->dst.u3), \ + ntohs((T)->dst.u.all), \ (T)->dst.protonum -#define FMT_CONN "%pI4:%u->%pI4:%u->%pI4:%u/%u:%u" -#define ARG_CONN(C) &((C)->caddr.ip), ntohs((C)->cport), \ - &((C)->vaddr.ip), ntohs((C)->vport), \ - &((C)->daddr.ip), ntohs((C)->dport), \ +#define FMT_CONN "%s:%u->%s:%u->%s:%u/%u:%u" +#define ARG_CONN(C) IP_VS_DBG_ADDR((C)->af, &((C)->caddr)), \ + ntohs((C)->cport), \ + IP_VS_DBG_ADDR((C)->af, &((C)->vaddr)), \ + ntohs((C)->vport), \ + IP_VS_DBG_ADDR((C)->daf, &((C)->daddr)), \ + ntohs((C)->dport), \ (C)->protocol, (C)->state void @@ -127,13 +132,17 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin) new_tuple.dst.protonum != IPPROTO_ICMPV6) new_tuple.dst.u.tcp.port = cp->vport; } - IP_VS_DBG(7, "%s: Updating conntrack ct=%p, status=0x%lX, " - "ctinfo=%d, old reply=" FMT_TUPLE - ", new reply=" FMT_TUPLE ", cp=" FMT_CONN "\n", - __func__, ct, ct->status, ctinfo, - ARG_TUPLE(&ct->tuplehash[IP_CT_DIR_REPLY].tuple), - ARG_TUPLE(&new_tuple), ARG_CONN(cp)); + IP_VS_DBG_BUF(7, "%s: Updating conntrack ct=%p, status=0x%lX, " + "ctinfo=%d, old reply=" FMT_TUPLE "\n", + __func__, ct, ct->status, ctinfo, + ARG_TUPLE(&ct->tuplehash[IP_CT_DIR_REPLY].tuple)); + IP_VS_DBG_BUF(7, "%s: Updating conntrack ct=%p, status=0x%lX, " + "ctinfo=%d, new reply=" FMT_TUPLE "\n", + __func__, ct, ct->status, ctinfo, + ARG_TUPLE(&new_tuple)); nf_conntrack_alter_reply(ct, &new_tuple); + IP_VS_DBG_BUF(7, "%s: Updated conntrack ct=%p for cp=" FMT_CONN "\n", + __func__, ct, ARG_CONN(cp)); } int ip_vs_confirm_conntrack(struct sk_buff *skb) @@ -152,9 +161,6 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, struct ip_vs_conn_param p; struct net *net = nf_ct_net(ct); - if (exp->tuple.src.l3num != PF_INET) - return; - /* * We assume that no NF locks are held before this callback. * ip_vs_conn_out_get and ip_vs_conn_in_get should match their @@ -171,19 +177,15 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, cp = ip_vs_conn_out_get(&p); if (cp) { /* Change reply CLIENT->RS to CLIENT->VS */ + IP_VS_DBG_BUF(7, "%s: for ct=%p, status=0x%lX found inout cp=" + FMT_CONN "\n", + __func__, ct, ct->status, ARG_CONN(cp)); new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - IP_VS_DBG(7, "%s: ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", " - FMT_TUPLE ", found inout cp=" FMT_CONN "\n", - __func__, ct, ct->status, - ARG_TUPLE(orig), ARG_TUPLE(&new_reply), - ARG_CONN(cp)); + IP_VS_DBG_BUF(7, "%s: ct=%p before alter: reply tuple=" + FMT_TUPLE "\n", + __func__, ct, ARG_TUPLE(&new_reply)); new_reply.dst.u3 = cp->vaddr; new_reply.dst.u.tcp.port = cp->vport; - IP_VS_DBG(7, "%s: ct=%p, new tuples=" FMT_TUPLE ", " FMT_TUPLE - ", inout cp=" FMT_CONN "\n", - __func__, ct, - ARG_TUPLE(orig), ARG_TUPLE(&new_reply), - ARG_CONN(cp)); goto alter; } @@ -191,25 +193,21 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, cp = ip_vs_conn_in_get(&p); if (cp) { /* Change reply VS->CLIENT to RS->CLIENT */ + IP_VS_DBG_BUF(7, "%s: for ct=%p, status=0x%lX found outin cp=" + FMT_CONN "\n", + __func__, ct, ct->status, ARG_CONN(cp)); new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - IP_VS_DBG(7, "%s: ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", " - FMT_TUPLE ", found outin cp=" FMT_CONN "\n", - __func__, ct, ct->status, - ARG_TUPLE(orig), ARG_TUPLE(&new_reply), - ARG_CONN(cp)); + IP_VS_DBG_BUF(7, "%s: ct=%p before alter: reply tuple=" + FMT_TUPLE "\n", + __func__, ct, ARG_TUPLE(&new_reply)); new_reply.src.u3 = cp->daddr; new_reply.src.u.tcp.port = cp->dport; - IP_VS_DBG(7, "%s: ct=%p, new tuples=" FMT_TUPLE ", " - FMT_TUPLE ", outin cp=" FMT_CONN "\n", - __func__, ct, - ARG_TUPLE(orig), ARG_TUPLE(&new_reply), - ARG_CONN(cp)); goto alter; } - IP_VS_DBG(7, "%s: ct=%p, status=0x%lX, tuple=" FMT_TUPLE - " - unknown expect\n", - __func__, ct, ct->status, ARG_TUPLE(orig)); + IP_VS_DBG_BUF(7, "%s: ct=%p, status=0x%lX, tuple=" FMT_TUPLE + " - unknown expect\n", + __func__, ct, ct->status, ARG_TUPLE(orig)); return; alter: @@ -247,8 +245,8 @@ void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct, exp->expectfn = ip_vs_nfct_expect_callback; - IP_VS_DBG(7, "%s: ct=%p, expect tuple=" FMT_TUPLE "\n", - __func__, ct, ARG_TUPLE(&exp->tuple)); + IP_VS_DBG_BUF(7, "%s: ct=%p, expect tuple=" FMT_TUPLE "\n", + __func__, ct, ARG_TUPLE(&exp->tuple)); nf_ct_expect_related(exp); nf_ct_expect_put(exp); } @@ -274,26 +272,25 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) tuple.dst.u3 = cp->vaddr; tuple.dst.u.all = cp->vport; - IP_VS_DBG(7, "%s: dropping conntrack with tuple=" FMT_TUPLE - " for conn " FMT_CONN "\n", - __func__, ARG_TUPLE(&tuple), ARG_CONN(cp)); + IP_VS_DBG_BUF(7, "%s: dropping conntrack for conn " FMT_CONN "\n", + __func__, ARG_CONN(cp)); h = nf_conntrack_find_get(cp->ipvs->net, &nf_ct_zone_dflt, &tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); if (nf_ct_kill(ct)) { - IP_VS_DBG(7, "%s: ct=%p, deleted conntrack for tuple=" - FMT_TUPLE "\n", - __func__, ct, ARG_TUPLE(&tuple)); + IP_VS_DBG_BUF(7, "%s: ct=%p deleted for tuple=" + FMT_TUPLE "\n", + __func__, ct, ARG_TUPLE(&tuple)); } else { - IP_VS_DBG(7, "%s: ct=%p, no conntrack timer for tuple=" - FMT_TUPLE "\n", - __func__, ct, ARG_TUPLE(&tuple)); + IP_VS_DBG_BUF(7, "%s: ct=%p, no conntrack for tuple=" + FMT_TUPLE "\n", + __func__, ct, ARG_TUPLE(&tuple)); } nf_ct_put(ct); } else { - IP_VS_DBG(7, "%s: no conntrack for tuple=" FMT_TUPLE "\n", - __func__, ARG_TUPLE(&tuple)); + IP_VS_DBG_BUF(7, "%s: no conntrack for tuple=" FMT_TUPLE "\n", + __func__, ARG_TUPLE(&tuple)); } } diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index eff7569824e5b..3250c4a1111e2 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -109,7 +109,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, return 0; /* Call application helper if needed */ - ret = ip_vs_app_pkt_out(cp, skb); + ret = ip_vs_app_pkt_out(cp, skb, iph); if (ret == 0) return 0; /* ret=2: csum update is needed after payload mangling */ @@ -156,7 +156,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, return 0; /* Call application helper if needed */ - ret = ip_vs_app_pkt_in(cp, skb); + ret = ip_vs_app_pkt_in(cp, skb, iph); if (ret == 0) return 0; /* ret=2: csum update is needed after payload mangling */ diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index bcd9b7bde4ee3..80d10ad12a15f 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -170,7 +170,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, return 0; /* Call application helper if needed */ - if (!(ret = ip_vs_app_pkt_out(cp, skb))) + if (!(ret = ip_vs_app_pkt_out(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) @@ -251,7 +251,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, * Attempt ip_vs_app call. * It will fix ip_vs_conn and iph ack_seq stuff */ - if (!(ret = ip_vs_app_pkt_in(cp, skb))) + if (!(ret = ip_vs_app_pkt_in(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) @@ -436,7 +436,7 @@ static bool tcp_state_active(int state) return tcp_state_active_table[state]; } -static struct tcp_states_t tcp_states [] = { +static struct tcp_states_t tcp_states[] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }}, @@ -459,7 +459,7 @@ static struct tcp_states_t tcp_states [] = { /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; -static struct tcp_states_t tcp_states_dos [] = { +static struct tcp_states_t tcp_states_dos[] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }}, diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index c15ef7c2a1fae..e0ef11c3691e4 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -162,7 +162,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, /* * Call application helper if needed */ - if (!(ret = ip_vs_app_pkt_out(cp, skb))) + if (!(ret = ip_vs_app_pkt_out(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) @@ -246,7 +246,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, * Attempt ip_vs_app call. * It will fix ip_vs_conn */ - if (!(ret = ip_vs_app_pkt_in(cp, skb))) + if (!(ret = ip_vs_app_pkt_in(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index 16aaac6eedc96..1e01c782583a6 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -96,7 +96,8 @@ ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr, addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif - return (offset + (ntohs(port) + ntohl(addr_fold))*2654435761UL) & + return (offset + hash_32(ntohs(port) + ntohl(addr_fold), + IP_VS_SH_TAB_BITS)) & IP_VS_SH_TAB_MASK; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 4527921b1c3ac..ba0a0fd045c85 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -266,12 +266,13 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, /* check and decrement ttl */ if (ipv6_hdr(skb)->hop_limit <= 1) { + struct inet6_dev *idev = __in6_dev_get_safely(skb->dev); + /* Force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return false; } diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 153e690e28939..3b5059a8dcdd1 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -79,7 +79,7 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen) return memcmp(a, b, klen * sizeof(u32)); } -static bool add_hlist(struct hlist_head *head, +bool nf_conncount_add(struct hlist_head *head, const struct nf_conntrack_tuple *tuple) { struct nf_conncount_tuple *conn; @@ -91,12 +91,12 @@ static bool add_hlist(struct hlist_head *head, hlist_add_head(&conn->node, head); return true; } +EXPORT_SYMBOL_GPL(nf_conncount_add); -static unsigned int check_hlist(struct net *net, - struct hlist_head *head, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone, - bool *addit) +unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone, + bool *addit) { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn; @@ -141,6 +141,7 @@ static unsigned int check_hlist(struct net *net, return length; } +EXPORT_SYMBOL_GPL(nf_conncount_lookup); static void tree_nodes_free(struct rb_root *root, struct nf_conncount_rb *gc_nodes[], @@ -187,13 +188,15 @@ count_tree(struct net *net, struct rb_root *root, } else { /* same source network -> be counted! */ unsigned int count; - count = check_hlist(net, &rbconn->hhead, tuple, zone, &addit); + + count = nf_conncount_lookup(net, &rbconn->hhead, tuple, + zone, &addit); tree_nodes_free(root, gc_nodes, gc_count); if (!addit) return count; - if (!add_hlist(&rbconn->hhead, tuple)) + if (!nf_conncount_add(&rbconn->hhead, tuple)) return 0; /* hotdrop */ return count + 1; @@ -203,7 +206,7 @@ count_tree(struct net *net, struct rb_root *root, continue; /* only used for GC on hhead, retval and 'addit' ignored */ - check_hlist(net, &rbconn->hhead, tuple, zone, &addit); + nf_conncount_lookup(net, &rbconn->hhead, tuple, zone, &addit); if (hlist_empty(&rbconn->hhead)) gc_nodes[gc_count++] = rbconn; } @@ -303,11 +306,19 @@ struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family } EXPORT_SYMBOL_GPL(nf_conncount_init); -static void destroy_tree(struct rb_root *r) +void nf_conncount_cache_free(struct hlist_head *hhead) { struct nf_conncount_tuple *conn; - struct nf_conncount_rb *rbconn; struct hlist_node *n; + + hlist_for_each_entry_safe(conn, n, hhead, node) + kmem_cache_free(conncount_conn_cachep, conn); +} +EXPORT_SYMBOL_GPL(nf_conncount_cache_free); + +static void destroy_tree(struct rb_root *r) +{ + struct nf_conncount_rb *rbconn; struct rb_node *node; while ((node = rb_first(r)) != NULL) { @@ -315,8 +326,7 @@ static void destroy_tree(struct rb_root *r) rb_erase(node, r); - hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node) - kmem_cache_free(conncount_conn_cachep, conn); + nf_conncount_cache_free(&rbconn->hhead); kmem_cache_free(conncount_rb_cachep, rbconn); } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 41ff04ee2554a..3465da2a98bd4 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -58,11 +58,6 @@ #include "nf_internals.h" -int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct, - enum nf_nat_manip_type manip, - const struct nlattr *attr) __read_mostly; -EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook); - __cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; EXPORT_SYMBOL_GPL(nf_conntrack_locks); @@ -186,6 +181,7 @@ unsigned int nf_conntrack_htable_size __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; +EXPORT_SYMBOL_GPL(nf_conntrack_max); seqcount_t nf_conntrack_generation __read_mostly; static unsigned int nf_conntrack_hash_rnd __read_mostly; @@ -1611,6 +1607,82 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) nf_conntrack_get(skb_nfct(nskb)); } +static int nf_conntrack_update(struct net *net, struct sk_buff *skb) +{ + const struct nf_conntrack_l3proto *l3proto; + const struct nf_conntrack_l4proto *l4proto; + struct nf_conntrack_tuple_hash *h; + struct nf_conntrack_tuple tuple; + enum ip_conntrack_info ctinfo; + struct nf_nat_hook *nat_hook; + unsigned int dataoff, status; + struct nf_conn *ct; + u16 l3num; + u8 l4num; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || nf_ct_is_confirmed(ct)) + return 0; + + l3num = nf_ct_l3num(ct); + l3proto = nf_ct_l3proto_find_get(l3num); + + if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff, + &l4num) <= 0) + return -1; + + l4proto = nf_ct_l4proto_find_get(l3num, l4num); + + if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, + l4num, net, &tuple, l3proto, l4proto)) + return -1; + + if (ct->status & IPS_SRC_NAT) { + memcpy(tuple.src.u3.all, + ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.all, + sizeof(tuple.src.u3.all)); + tuple.src.u.all = + ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.all; + } + + if (ct->status & IPS_DST_NAT) { + memcpy(tuple.dst.u3.all, + ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.all, + sizeof(tuple.dst.u3.all)); + tuple.dst.u.all = + ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.all; + } + + h = nf_conntrack_find_get(net, nf_ct_zone(ct), &tuple); + if (!h) + return 0; + + /* Store status bits of the conntrack that is clashing to re-do NAT + * mangling according to what it has been done already to this packet. + */ + status = ct->status; + + nf_ct_put(ct); + ct = nf_ct_tuplehash_to_ctrack(h); + nf_ct_set(skb, ct, ctinfo); + + nat_hook = rcu_dereference(nf_nat_hook); + if (!nat_hook) + return 0; + + if (status & IPS_SRC_NAT && + nat_hook->manip_pkt(skb, ct, NF_NAT_MANIP_SRC, + IP_CT_DIR_ORIGINAL) == NF_DROP) + return -1; + + if (status & IPS_DST_NAT && + nat_hook->manip_pkt(skb, ct, NF_NAT_MANIP_DST, + IP_CT_DIR_ORIGINAL) == NF_DROP) + return -1; + + return 0; +} + /* Bring out ya dead! */ static struct nf_conn * get_next_corpse(int (*iter)(struct nf_conn *i, void *data), @@ -1812,8 +1884,7 @@ void nf_conntrack_cleanup_start(void) void nf_conntrack_cleanup_end(void) { - RCU_INIT_POINTER(nf_ct_destroy, NULL); - + RCU_INIT_POINTER(nf_ct_hook, NULL); cancel_delayed_work_sync(&conntrack_gc_work.dwork); nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size); @@ -2130,11 +2201,16 @@ err_cachep: return ret; } +static struct nf_ct_hook nf_conntrack_hook = { + .update = nf_conntrack_update, + .destroy = destroy_conntrack, +}; + void nf_conntrack_init_end(void) { /* For use by REJECT target */ RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); - RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack); + RCU_INIT_POINTER(nf_ct_hook, &nf_conntrack_hook); } /* diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index f0e9a7511e1ac..a11c304fb7713 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -566,8 +566,7 @@ static const struct nf_conntrack_expect_policy ftp_exp_policy = { .timeout = 5 * 60, }; -/* don't make this __exit, since it's called from __init ! */ -static void nf_conntrack_ftp_fini(void) +static void __exit nf_conntrack_ftp_fini(void) { nf_conntrack_helpers_unregister(ftp, ports_c * 2); kfree(ftp_buffer); diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 5523acce9d699..4099f4d79bae7 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -232,8 +232,6 @@ static int help(struct sk_buff *skb, unsigned int protoff, static struct nf_conntrack_helper irc[MAX_PORTS] __read_mostly; static struct nf_conntrack_expect_policy irc_exp_policy; -static void nf_conntrack_irc_fini(void); - static int __init nf_conntrack_irc_init(void) { int i, ret; @@ -276,9 +274,7 @@ static int __init nf_conntrack_irc_init(void) return 0; } -/* This function is intentionally _NOT_ defined as __exit, because - * it is needed by the init function */ -static void nf_conntrack_irc_fini(void) +static void __exit nf_conntrack_irc_fini(void) { nf_conntrack_helpers_unregister(irc, ports_c); kfree(irc_buffer); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 4c1d0c5bc2680..39327a42879f7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1431,11 +1431,11 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) { - typeof(nfnetlink_parse_nat_setup_hook) parse_nat_setup; + struct nf_nat_hook *nat_hook; int err; - parse_nat_setup = rcu_dereference(nfnetlink_parse_nat_setup_hook); - if (!parse_nat_setup) { + nat_hook = rcu_dereference(nf_nat_hook); + if (!nat_hook) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); @@ -1446,13 +1446,13 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, } nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); - if (nfnetlink_parse_nat_setup_hook) + if (nat_hook->parse_nat_setup) return -EAGAIN; #endif return -EOPNOTSUPP; } - err = parse_nat_setup(ct, manip, attr); + err = nat_hook->parse_nat_setup(ct, manip, attr); if (err == -EAGAIN) { #ifdef CONFIG_MODULES rcu_read_unlock(); @@ -2205,6 +2205,9 @@ ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks))) goto nla_put_failure; + if (nla_put_be32(skb, CTA_STATS_GLOBAL_MAX_ENTRIES, htonl(nf_conntrack_max))) + goto nla_put_failure; + nlmsg_end(skb, nlh); return skb->len; diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index ae457f39d5ceb..5072ff96ab334 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -173,8 +173,7 @@ static const struct nf_conntrack_expect_policy sane_exp_policy = { .timeout = 5 * 60, }; -/* don't make this __exit, since it's called from __init ! */ -static void nf_conntrack_sane_fini(void) +static void __exit nf_conntrack_sane_fini(void) { nf_conntrack_helpers_unregister(sane, ports_c * 2); kfree(sane_buffer); diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 908e51e2dc2b3..c8d2b6688a2a0 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1617,7 +1617,7 @@ static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1 }, }; -static void nf_conntrack_sip_fini(void) +static void __exit nf_conntrack_sip_fini(void) { nf_conntrack_helpers_unregister(sip, ports_c * 4); } diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index 0ec6779fd5d94..548b673b3625c 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -104,7 +104,7 @@ static const struct nf_conntrack_expect_policy tftp_exp_policy = { .timeout = 5 * 60, }; -static void nf_conntrack_tftp_fini(void) +static void __exit nf_conntrack_tftp_fini(void) { nf_conntrack_helpers_unregister(tftp, ports_c * 2); } diff --git a/net/netfilter/nf_flow_table.c b/net/netfilter/nf_flow_table_core.c index ec410cae93071..eb0d1658ac055 100644 --- a/net/netfilter/nf_flow_table.c +++ b/net/netfilter/nf_flow_table_core.c @@ -4,6 +4,8 @@ #include <linux/netfilter.h> #include <linux/rhashtable.h> #include <linux/netdevice.h> +#include <net/ip.h> +#include <net/ip6_route.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_conntrack.h> @@ -16,6 +18,43 @@ struct flow_offload_entry { struct rcu_head rcu_head; }; +static DEFINE_MUTEX(flowtable_lock); +static LIST_HEAD(flowtables); + +static void +flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct, + struct nf_flow_route *route, + enum flow_offload_tuple_dir dir) +{ + struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple; + struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple; + struct dst_entry *dst = route->tuple[dir].dst; + + ft->dir = dir; + + switch (ctt->src.l3num) { + case NFPROTO_IPV4: + ft->src_v4 = ctt->src.u3.in; + ft->dst_v4 = ctt->dst.u3.in; + ft->mtu = ip_dst_mtu_maybe_forward(dst, true); + break; + case NFPROTO_IPV6: + ft->src_v6 = ctt->src.u3.in6; + ft->dst_v6 = ctt->dst.u3.in6; + ft->mtu = ip6_dst_mtu_forward(dst); + break; + } + + ft->l3proto = ctt->src.l3num; + ft->l4proto = ctt->dst.protonum; + ft->src_port = ctt->src.u.tcp.port; + ft->dst_port = ctt->dst.u.tcp.port; + + ft->iifidx = route->tuple[dir].ifindex; + ft->oifidx = route->tuple[!dir].ifindex; + ft->dst_cache = dst; +} + struct flow_offload * flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route) { @@ -40,69 +79,12 @@ flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route) entry->ct = ct; - switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num) { - case NFPROTO_IPV4: - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4 = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in; - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4 = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4 = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4 = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in; - break; - case NFPROTO_IPV6: - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6 = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6; - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6 = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6 = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in6; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6 = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in6; - break; - } - - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l3proto = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l3proto = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l4proto = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum; - - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache = - route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache = - route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst; - - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port; - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.tcp.port; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port; - - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dir = - FLOW_OFFLOAD_DIR_ORIGINAL; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dir = - FLOW_OFFLOAD_DIR_REPLY; - - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx = - route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex; - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.oifidx = - route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx = - route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.oifidx = - route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex; + flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_ORIGINAL); + flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_REPLY); if (ct->status & IPS_SRC_NAT) flow->flags |= FLOW_OFFLOAD_SNAT; - else if (ct->status & IPS_DST_NAT) + if (ct->status & IPS_DST_NAT) flow->flags |= FLOW_OFFLOAD_DNAT; return flow; @@ -118,6 +100,43 @@ err_ct_refcnt: } EXPORT_SYMBOL_GPL(flow_offload_alloc); +static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) +{ + tcp->state = TCP_CONNTRACK_ESTABLISHED; + tcp->seen[0].td_maxwin = 0; + tcp->seen[1].td_maxwin = 0; +} + +static void flow_offload_fixup_ct_state(struct nf_conn *ct) +{ + const struct nf_conntrack_l4proto *l4proto; + struct net *net = nf_ct_net(ct); + unsigned int *timeouts; + unsigned int timeout; + int l4num; + + l4num = nf_ct_protonum(ct); + if (l4num == IPPROTO_TCP) + flow_offload_fixup_tcp(&ct->proto.tcp); + + l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), l4num); + if (!l4proto) + return; + + timeouts = l4proto->get_timeouts(net); + if (!timeouts) + return; + + if (l4num == IPPROTO_TCP) + timeout = timeouts[TCP_CONNTRACK_ESTABLISHED]; + else if (l4num == IPPROTO_UDP) + timeout = timeouts[UDP_CT_REPLIED]; + else + return; + + ct->timeout = nfct_time_stamp + timeout; +} + void flow_offload_free(struct flow_offload *flow) { struct flow_offload_entry *e; @@ -125,17 +144,46 @@ void flow_offload_free(struct flow_offload *flow) dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache); dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache); e = container_of(flow, struct flow_offload_entry, flow); - nf_ct_delete(e->ct, 0, 0); + if (flow->flags & FLOW_OFFLOAD_DYING) + nf_ct_delete(e->ct, 0, 0); nf_ct_put(e->ct); kfree_rcu(e, rcu_head); } EXPORT_SYMBOL_GPL(flow_offload_free); -void flow_offload_dead(struct flow_offload *flow) +static u32 flow_offload_hash(const void *data, u32 len, u32 seed) +{ + const struct flow_offload_tuple *tuple = data; + + return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed); +} + +static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed) +{ + const struct flow_offload_tuple_rhash *tuplehash = data; + + return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed); +} + +static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) { - flow->flags |= FLOW_OFFLOAD_DYING; + const struct flow_offload_tuple *tuple = arg->key; + const struct flow_offload_tuple_rhash *x = ptr; + + if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir))) + return 1; + + return 0; } -EXPORT_SYMBOL_GPL(flow_offload_dead); + +static const struct rhashtable_params nf_flow_offload_rhash_params = { + .head_offset = offsetof(struct flow_offload_tuple_rhash, node), + .hashfn = flow_offload_hash, + .obj_hashfn = flow_offload_hash_obj, + .obj_cmpfn = flow_offload_hash_cmp, + .automatic_shrinking = true, +}; int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) { @@ -143,10 +191,10 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node, - *flow_table->type->params); + nf_flow_offload_rhash_params); rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, - *flow_table->type->params); + nf_flow_offload_rhash_params); return 0; } EXPORT_SYMBOL_GPL(flow_offload_add); @@ -154,22 +202,51 @@ EXPORT_SYMBOL_GPL(flow_offload_add); static void flow_offload_del(struct nf_flowtable *flow_table, struct flow_offload *flow) { + struct flow_offload_entry *e; + rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node, - *flow_table->type->params); + nf_flow_offload_rhash_params); rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, - *flow_table->type->params); + nf_flow_offload_rhash_params); + + e = container_of(flow, struct flow_offload_entry, flow); + clear_bit(IPS_OFFLOAD_BIT, &e->ct->status); flow_offload_free(flow); } +void flow_offload_teardown(struct flow_offload *flow) +{ + struct flow_offload_entry *e; + + flow->flags |= FLOW_OFFLOAD_TEARDOWN; + + e = container_of(flow, struct flow_offload_entry, flow); + flow_offload_fixup_ct_state(e->ct); +} +EXPORT_SYMBOL_GPL(flow_offload_teardown); + struct flow_offload_tuple_rhash * flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple) { - return rhashtable_lookup_fast(&flow_table->rhashtable, tuple, - *flow_table->type->params); + struct flow_offload_tuple_rhash *tuplehash; + struct flow_offload *flow; + int dir; + + tuplehash = rhashtable_lookup_fast(&flow_table->rhashtable, tuple, + nf_flow_offload_rhash_params); + if (!tuplehash) + return NULL; + + dir = tuplehash->tuple.dir; + flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); + if (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN)) + return NULL; + + return tuplehash; } EXPORT_SYMBOL_GPL(flow_offload_lookup); @@ -216,11 +293,6 @@ static inline bool nf_flow_has_expired(const struct flow_offload *flow) return (__s32)(flow->timeout - (u32)jiffies) <= 0; } -static inline bool nf_flow_is_dying(const struct flow_offload *flow) -{ - return flow->flags & FLOW_OFFLOAD_DYING; -} - static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table) { struct flow_offload_tuple_rhash *tuplehash; @@ -248,7 +320,8 @@ static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table) flow = container_of(tuplehash, struct flow_offload, tuplehash[0]); if (nf_flow_has_expired(flow) || - nf_flow_is_dying(flow)) + (flow->flags & (FLOW_OFFLOAD_DYING | + FLOW_OFFLOAD_TEARDOWN))) flow_offload_del(flow_table, flow); } out: @@ -258,7 +331,7 @@ out: return 1; } -void nf_flow_offload_work_gc(struct work_struct *work) +static void nf_flow_offload_work_gc(struct work_struct *work) { struct nf_flowtable *flow_table; @@ -266,42 +339,6 @@ void nf_flow_offload_work_gc(struct work_struct *work) nf_flow_offload_gc_step(flow_table); queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } -EXPORT_SYMBOL_GPL(nf_flow_offload_work_gc); - -static u32 flow_offload_hash(const void *data, u32 len, u32 seed) -{ - const struct flow_offload_tuple *tuple = data; - - return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed); -} - -static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed) -{ - const struct flow_offload_tuple_rhash *tuplehash = data; - - return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed); -} - -static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg, - const void *ptr) -{ - const struct flow_offload_tuple *tuple = arg->key; - const struct flow_offload_tuple_rhash *x = ptr; - - if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir))) - return 1; - - return 0; -} - -const struct rhashtable_params nf_flow_offload_rhash_params = { - .head_offset = offsetof(struct flow_offload_tuple_rhash, node), - .hashfn = flow_offload_hash, - .obj_hashfn = flow_offload_hash_obj, - .obj_cmpfn = flow_offload_hash_cmp, - .automatic_shrinking = true, -}; -EXPORT_SYMBOL_GPL(nf_flow_offload_rhash_params); static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, __be16 port, __be16 new_port) @@ -419,33 +456,69 @@ int nf_flow_dnat_port(const struct flow_offload *flow, } EXPORT_SYMBOL_GPL(nf_flow_dnat_port); +int nf_flow_table_init(struct nf_flowtable *flowtable) +{ + int err; + + INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc); + + err = rhashtable_init(&flowtable->rhashtable, + &nf_flow_offload_rhash_params); + if (err < 0) + return err; + + queue_delayed_work(system_power_efficient_wq, + &flowtable->gc_work, HZ); + + mutex_lock(&flowtable_lock); + list_add(&flowtable->list, &flowtables); + mutex_unlock(&flowtable_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(nf_flow_table_init); + static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data) { struct net_device *dev = data; - if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex) + if (!dev) { + flow_offload_teardown(flow); return; + } - flow_offload_dead(flow); + if (flow->tuplehash[0].tuple.iifidx == dev->ifindex || + flow->tuplehash[1].tuple.iifidx == dev->ifindex) + flow_offload_dead(flow); } static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable, - void *data) + struct net_device *dev) { - nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, data); + nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev); flush_delayed_work(&flowtable->gc_work); } void nf_flow_table_cleanup(struct net *net, struct net_device *dev) { - nft_flow_table_iterate(net, nf_flow_table_iterate_cleanup, dev); + struct nf_flowtable *flowtable; + + mutex_lock(&flowtable_lock); + list_for_each_entry(flowtable, &flowtables, list) + nf_flow_table_iterate_cleanup(flowtable, dev); + mutex_unlock(&flowtable_lock); } EXPORT_SYMBOL_GPL(nf_flow_table_cleanup); void nf_flow_table_free(struct nf_flowtable *flow_table) { + mutex_lock(&flowtable_lock); + list_del(&flow_table->list); + mutex_unlock(&flowtable_lock); + cancel_delayed_work_sync(&flow_table->gc_work); nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL); WARN_ON(!nf_flow_offload_gc_step(flow_table)); + rhashtable_destroy(&flow_table->rhashtable); } EXPORT_SYMBOL_GPL(nf_flow_table_free); diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 375a1881d93de..99771aa7e7eab 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -22,8 +22,7 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, static struct nf_flowtable_type flowtable_inet = { .family = NFPROTO_INET, - .params = &nf_flow_offload_rhash_params, - .gc = nf_flow_offload_work_gc, + .init = nf_flow_table_init, .free = nf_flow_table_free, .hook = nf_flow_offload_inet_hook, .owner = THIS_MODULE, diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c new file mode 100644 index 0000000000000..15ed91309992e --- /dev/null +++ b/net/netfilter/nf_flow_table_ip.c @@ -0,0 +1,489 @@ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netfilter.h> +#include <linux/rhashtable.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/netdevice.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/neighbour.h> +#include <net/netfilter/nf_flow_table.h> +/* For layer 4 checksum field offset. */ +#include <linux/tcp.h> +#include <linux/udp.h> + +static int nf_flow_state_check(struct flow_offload *flow, int proto, + struct sk_buff *skb, unsigned int thoff) +{ + struct tcphdr *tcph; + + if (proto != IPPROTO_TCP) + return 0; + + if (!pskb_may_pull(skb, thoff + sizeof(*tcph))) + return -1; + + tcph = (void *)(skb_network_header(skb) + thoff); + if (unlikely(tcph->fin || tcph->rst)) { + flow_offload_teardown(flow); + return -1; + } + + return 0; +} + +static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff, + __be32 addr, __be32 new_addr) +{ + struct tcphdr *tcph; + + if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || + skb_try_make_writable(skb, thoff + sizeof(*tcph))) + return -1; + + tcph = (void *)(skb_network_header(skb) + thoff); + inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true); + + return 0; +} + +static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, + __be32 addr, __be32 new_addr) +{ + struct udphdr *udph; + + if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || + skb_try_make_writable(skb, thoff + sizeof(*udph))) + return -1; + + udph = (void *)(skb_network_header(skb) + thoff); + if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { + inet_proto_csum_replace4(&udph->check, skb, addr, + new_addr, true); + if (!udph->check) + udph->check = CSUM_MANGLED_0; + } + + return 0; +} + +static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph, + unsigned int thoff, __be32 addr, + __be32 new_addr) +{ + switch (iph->protocol) { + case IPPROTO_TCP: + if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0) + return NF_DROP; + break; + case IPPROTO_UDP: + if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0) + return NF_DROP; + break; + } + + return 0; +} + +static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb, + struct iphdr *iph, unsigned int thoff, + enum flow_offload_tuple_dir dir) +{ + __be32 addr, new_addr; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = iph->saddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr; + iph->saddr = new_addr; + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = iph->daddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr; + iph->daddr = new_addr; + break; + default: + return -1; + } + csum_replace4(&iph->check, addr, new_addr); + + return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); +} + +static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, + struct iphdr *iph, unsigned int thoff, + enum flow_offload_tuple_dir dir) +{ + __be32 addr, new_addr; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = iph->daddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr; + iph->daddr = new_addr; + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = iph->saddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr; + iph->saddr = new_addr; + break; + default: + return -1; + } + csum_replace4(&iph->check, addr, new_addr); + + return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); +} + +static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, + unsigned int thoff, enum flow_offload_tuple_dir dir) +{ + struct iphdr *iph = ip_hdr(skb); + + if (flow->flags & FLOW_OFFLOAD_SNAT && + (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 || + nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0)) + return -1; + if (flow->flags & FLOW_OFFLOAD_DNAT && + (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 || + nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0)) + return -1; + + return 0; +} + +static bool ip_has_options(unsigned int thoff) +{ + return thoff != sizeof(struct iphdr); +} + +static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, + struct flow_offload_tuple *tuple) +{ + struct flow_ports *ports; + unsigned int thoff; + struct iphdr *iph; + + if (!pskb_may_pull(skb, sizeof(*iph))) + return -1; + + iph = ip_hdr(skb); + thoff = iph->ihl * 4; + + if (ip_is_fragment(iph) || + unlikely(ip_has_options(thoff))) + return -1; + + if (iph->protocol != IPPROTO_TCP && + iph->protocol != IPPROTO_UDP) + return -1; + + thoff = iph->ihl * 4; + if (!pskb_may_pull(skb, thoff + sizeof(*ports))) + return -1; + + ports = (struct flow_ports *)(skb_network_header(skb) + thoff); + + tuple->src_v4.s_addr = iph->saddr; + tuple->dst_v4.s_addr = iph->daddr; + tuple->src_port = ports->source; + tuple->dst_port = ports->dest; + tuple->l3proto = AF_INET; + tuple->l4proto = iph->protocol; + tuple->iifidx = dev->ifindex; + + return 0; +} + +/* Based on ip_exceeds_mtu(). */ +static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu) + return false; + + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) + return false; + + return true; +} + +unsigned int +nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct flow_offload_tuple_rhash *tuplehash; + struct nf_flowtable *flow_table = priv; + struct flow_offload_tuple tuple = {}; + enum flow_offload_tuple_dir dir; + struct flow_offload *flow; + struct net_device *outdev; + struct rtable *rt; + unsigned int thoff; + struct iphdr *iph; + __be32 nexthop; + + if (skb->protocol != htons(ETH_P_IP)) + return NF_ACCEPT; + + if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0) + return NF_ACCEPT; + + tuplehash = flow_offload_lookup(flow_table, &tuple); + if (tuplehash == NULL) + return NF_ACCEPT; + + outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx); + if (!outdev) + return NF_ACCEPT; + + dir = tuplehash->tuple.dir; + flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); + rt = (struct rtable *)flow->tuplehash[dir].tuple.dst_cache; + + if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)) && + (ip_hdr(skb)->frag_off & htons(IP_DF)) != 0) + return NF_ACCEPT; + + if (skb_try_make_writable(skb, sizeof(*iph))) + return NF_DROP; + + thoff = ip_hdr(skb)->ihl * 4; + if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff)) + return NF_ACCEPT; + + if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) && + nf_flow_nat_ip(flow, skb, thoff, dir) < 0) + return NF_DROP; + + flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + iph = ip_hdr(skb); + ip_decrease_ttl(iph); + + skb->dev = outdev; + nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); + skb_dst_set_noref(skb, &rt->dst); + neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb); + + return NF_STOLEN; +} +EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook); + +static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff, + struct in6_addr *addr, + struct in6_addr *new_addr) +{ + struct tcphdr *tcph; + + if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || + skb_try_make_writable(skb, thoff + sizeof(*tcph))) + return -1; + + tcph = (void *)(skb_network_header(skb) + thoff); + inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32, + new_addr->s6_addr32, true); + + return 0; +} + +static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, + struct in6_addr *addr, + struct in6_addr *new_addr) +{ + struct udphdr *udph; + + if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || + skb_try_make_writable(skb, thoff + sizeof(*udph))) + return -1; + + udph = (void *)(skb_network_header(skb) + thoff); + if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { + inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32, + new_addr->s6_addr32, true); + if (!udph->check) + udph->check = CSUM_MANGLED_0; + } + + return 0; +} + +static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, struct in6_addr *addr, + struct in6_addr *new_addr) +{ + switch (ip6h->nexthdr) { + case IPPROTO_TCP: + if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0) + return NF_DROP; + break; + case IPPROTO_UDP: + if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0) + return NF_DROP; + break; + } + + return 0; +} + +static int nf_flow_snat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, + enum flow_offload_tuple_dir dir) +{ + struct in6_addr addr, new_addr; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = ip6h->saddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6; + ip6h->saddr = new_addr; + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = ip6h->daddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6; + ip6h->daddr = new_addr; + break; + default: + return -1; + } + + return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); +} + +static int nf_flow_dnat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, + enum flow_offload_tuple_dir dir) +{ + struct in6_addr addr, new_addr; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = ip6h->daddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6; + ip6h->daddr = new_addr; + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = ip6h->saddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6; + ip6h->saddr = new_addr; + break; + default: + return -1; + } + + return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); +} + +static int nf_flow_nat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, + enum flow_offload_tuple_dir dir) +{ + struct ipv6hdr *ip6h = ipv6_hdr(skb); + unsigned int thoff = sizeof(*ip6h); + + if (flow->flags & FLOW_OFFLOAD_SNAT && + (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || + nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) + return -1; + if (flow->flags & FLOW_OFFLOAD_DNAT && + (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || + nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) + return -1; + + return 0; +} + +static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, + struct flow_offload_tuple *tuple) +{ + struct flow_ports *ports; + struct ipv6hdr *ip6h; + unsigned int thoff; + + if (!pskb_may_pull(skb, sizeof(*ip6h))) + return -1; + + ip6h = ipv6_hdr(skb); + + if (ip6h->nexthdr != IPPROTO_TCP && + ip6h->nexthdr != IPPROTO_UDP) + return -1; + + thoff = sizeof(*ip6h); + if (!pskb_may_pull(skb, thoff + sizeof(*ports))) + return -1; + + ports = (struct flow_ports *)(skb_network_header(skb) + thoff); + + tuple->src_v6 = ip6h->saddr; + tuple->dst_v6 = ip6h->daddr; + tuple->src_port = ports->source; + tuple->dst_port = ports->dest; + tuple->l3proto = AF_INET6; + tuple->l4proto = ip6h->nexthdr; + tuple->iifidx = dev->ifindex; + + return 0; +} + +unsigned int +nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct flow_offload_tuple_rhash *tuplehash; + struct nf_flowtable *flow_table = priv; + struct flow_offload_tuple tuple = {}; + enum flow_offload_tuple_dir dir; + struct flow_offload *flow; + struct net_device *outdev; + struct in6_addr *nexthop; + struct ipv6hdr *ip6h; + struct rt6_info *rt; + + if (skb->protocol != htons(ETH_P_IPV6)) + return NF_ACCEPT; + + if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0) + return NF_ACCEPT; + + tuplehash = flow_offload_lookup(flow_table, &tuple); + if (tuplehash == NULL) + return NF_ACCEPT; + + outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx); + if (!outdev) + return NF_ACCEPT; + + dir = tuplehash->tuple.dir; + flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); + rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache; + + if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu))) + return NF_ACCEPT; + + if (nf_flow_state_check(flow, ipv6_hdr(skb)->nexthdr, skb, + sizeof(*ip6h))) + return NF_ACCEPT; + + if (skb_try_make_writable(skb, sizeof(*ip6h))) + return NF_DROP; + + if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) && + nf_flow_nat_ipv6(flow, skb, dir) < 0) + return NF_DROP; + + flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + ip6h = ipv6_hdr(skb); + ip6h->hop_limit--; + + skb->dev = outdev; + nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); + skb_dst_set_noref(skb, &rt->dst); + neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb); + + return NF_STOLEN; +} +EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook); diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 18f6d7ae995bd..e15779fd58e3a 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -15,4 +15,9 @@ void nf_queue_nf_hook_drop(struct net *net); /* nf_log.c */ int __init netfilter_log_init(void); +/* core.c */ +void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, + const struct nf_hook_ops *reg); +int nf_hook_entries_insert_raw(struct nf_hook_entries __rcu **pp, + const struct nf_hook_ops *reg); #endif diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 617693ff9f4cb..b7df32a56e7ed 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -32,6 +32,8 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <linux/netfilter/nf_nat.h> +#include "nf_internals.h" + static spinlock_t nf_nat_locks[CONNTRACK_LOCKS]; static DEFINE_MUTEX(nf_nat_proto_mutex); @@ -39,11 +41,27 @@ static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO] __read_mostly; static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO] __read_mostly; +static unsigned int nat_net_id __read_mostly; static struct hlist_head *nf_nat_bysource __read_mostly; static unsigned int nf_nat_htable_size __read_mostly; static unsigned int nf_nat_hash_rnd __read_mostly; +struct nf_nat_lookup_hook_priv { + struct nf_hook_entries __rcu *entries; + + struct rcu_head rcu_head; +}; + +struct nf_nat_hooks_net { + struct nf_hook_ops *nat_hook_ops; + unsigned int users; +}; + +struct nat_net { + struct nf_nat_hooks_net nat_proto_net[NFPROTO_NUMPROTO]; +}; + inline const struct nf_nat_l3proto * __nf_nat_l3proto_find(u8 family) { @@ -157,7 +175,7 @@ EXPORT_SYMBOL(nf_nat_used_tuple); static int in_range(const struct nf_nat_l3proto *l3proto, const struct nf_nat_l4proto *l4proto, const struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range) + const struct nf_nat_range2 *range) { /* If we are supposed to map IPs, then we must be in the * range specified, otherwise let this drag us onto a new src IP. @@ -194,7 +212,7 @@ find_appropriate_src(struct net *net, const struct nf_nat_l4proto *l4proto, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *result, - const struct nf_nat_range *range) + const struct nf_nat_range2 *range) { unsigned int h = hash_by_src(net, tuple); const struct nf_conn *ct; @@ -224,7 +242,7 @@ find_appropriate_src(struct net *net, static void find_best_ips_proto(const struct nf_conntrack_zone *zone, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, const struct nf_conn *ct, enum nf_nat_manip_type maniptype) { @@ -298,7 +316,7 @@ find_best_ips_proto(const struct nf_conntrack_zone *zone, static void get_unique_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig_tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, struct nf_conn *ct, enum nf_nat_manip_type maniptype) { @@ -349,9 +367,10 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, /* Only bother mapping if it's not already in range and unique */ if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) { if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { - if (l4proto->in_range(tuple, maniptype, - &range->min_proto, - &range->max_proto) && + if (!(range->flags & NF_NAT_RANGE_PROTO_OFFSET) && + l4proto->in_range(tuple, maniptype, + &range->min_proto, + &range->max_proto) && (range->min_proto.all == range->max_proto.all || !nf_nat_used_tuple(tuple, ct))) goto out; @@ -360,7 +379,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, } } - /* Last change: get protocol to try to obtain unique tuple. */ + /* Last chance: get protocol to try to obtain unique tuple. */ l4proto->unique_tuple(l3proto, tuple, range, maniptype, ct); out: rcu_read_unlock(); @@ -381,7 +400,7 @@ EXPORT_SYMBOL_GPL(nf_ct_nat_ext_add); unsigned int nf_nat_setup_info(struct nf_conn *ct, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype) { struct net *net = nf_ct_net(ct); @@ -459,7 +478,7 @@ __nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip) (manip == NF_NAT_MANIP_SRC ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3); - struct nf_nat_range range = { + struct nf_nat_range2 range = { .flags = NF_NAT_RANGE_MAP_IPS, .min_addr = ip, .max_addr = ip, @@ -474,17 +493,36 @@ nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) } EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding); +static unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct, + enum nf_nat_manip_type mtype, + enum ip_conntrack_dir dir) +{ + const struct nf_nat_l3proto *l3proto; + const struct nf_nat_l4proto *l4proto; + struct nf_conntrack_tuple target; + + /* We are aiming to look like inverse of other direction. */ + nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + + l3proto = __nf_nat_l3proto_find(target.src.l3num); + l4proto = __nf_nat_l4proto_find(target.src.l3num, + target.dst.protonum); + if (!l3proto->manip_pkt(skb, 0, l4proto, &target, mtype)) + return NF_DROP; + + return NF_ACCEPT; +} + /* Do packet manipulations according to nf_nat_setup_info. */ unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, struct sk_buff *skb) { - const struct nf_nat_l3proto *l3proto; - const struct nf_nat_l4proto *l4proto; + enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + unsigned int verdict = NF_ACCEPT; unsigned long statusbit; - enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum); if (mtype == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; @@ -496,21 +534,87 @@ unsigned int nf_nat_packet(struct nf_conn *ct, statusbit ^= IPS_NAT_MASK; /* Non-atomic: these bits don't change. */ - if (ct->status & statusbit) { - struct nf_conntrack_tuple target; + if (ct->status & statusbit) + verdict = nf_nat_manip_pkt(skb, ct, mtype, dir); + + return verdict; +} +EXPORT_SYMBOL_GPL(nf_nat_packet); + +unsigned int +nf_nat_inet_fn(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + struct nf_conn_nat *nat; + /* maniptype == SRC for postrouting. */ + enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook); + + ct = nf_ct_get(skb, &ctinfo); + /* Can't track? It's not due to stress, or conntrack would + * have dropped it. Hence it's the user's responsibilty to + * packet filter it out, or implement conntrack/NAT for that + * protocol. 8) --RR + */ + if (!ct) + return NF_ACCEPT; - /* We are aiming to look like inverse of other direction. */ - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + nat = nfct_nat(ct); - l3proto = __nf_nat_l3proto_find(target.src.l3num); - l4proto = __nf_nat_l4proto_find(target.src.l3num, - target.dst.protonum); - if (!l3proto->manip_pkt(skb, 0, l4proto, &target, mtype)) - return NF_DROP; + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + /* Only ICMPs can be IP_CT_IS_REPLY. Fallthrough */ + case IP_CT_NEW: + /* Seen it before? This can happen for loopback, retrans, + * or local packets. + */ + if (!nf_nat_initialized(ct, maniptype)) { + struct nf_nat_lookup_hook_priv *lpriv = priv; + struct nf_hook_entries *e = rcu_dereference(lpriv->entries); + unsigned int ret; + int i; + + if (!e) + goto null_bind; + + for (i = 0; i < e->num_hook_entries; i++) { + ret = e->hooks[i].hook(e->hooks[i].priv, skb, + state); + if (ret != NF_ACCEPT) + return ret; + if (nf_nat_initialized(ct, maniptype)) + goto do_nat; + } +null_bind: + ret = nf_nat_alloc_null_binding(ct, state->hook); + if (ret != NF_ACCEPT) + return ret; + } else { + pr_debug("Already setup manip %s for ct %p (status bits 0x%lx)\n", + maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", + ct, ct->status); + if (nf_nat_oif_changed(state->hook, ctinfo, nat, + state->out)) + goto oif_changed; + } + break; + default: + /* ESTABLISHED */ + WARN_ON(ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY); + if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) + goto oif_changed; } - return NF_ACCEPT; +do_nat: + return nf_nat_packet(ct, ctinfo, state->hook, skb); + +oif_changed: + nf_ct_kill_acct(ct, ctinfo, skb); + return NF_DROP; } -EXPORT_SYMBOL_GPL(nf_nat_packet); +EXPORT_SYMBOL_GPL(nf_nat_inet_fn); struct nf_nat_proto_clean { u8 l3proto; @@ -702,7 +806,7 @@ static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = { static int nfnetlink_parse_nat_proto(struct nlattr *attr, const struct nf_conn *ct, - struct nf_nat_range *range) + struct nf_nat_range2 *range) { struct nlattr *tb[CTA_PROTONAT_MAX+1]; const struct nf_nat_l4proto *l4proto; @@ -730,7 +834,7 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { static int nfnetlink_parse_nat(const struct nlattr *nat, - const struct nf_conn *ct, struct nf_nat_range *range, + const struct nf_conn *ct, struct nf_nat_range2 *range, const struct nf_nat_l3proto *l3proto) { struct nlattr *tb[CTA_NAT_MAX+1]; @@ -758,7 +862,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) { - struct nf_nat_range range; + struct nf_nat_range2 range; const struct nf_nat_l3proto *l3proto; int err; @@ -800,6 +904,146 @@ static struct nf_ct_helper_expectfn follow_master_nat = { .expectfn = nf_nat_follow_master, }; +int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops, + const struct nf_hook_ops *orig_nat_ops, unsigned int ops_count) +{ + struct nat_net *nat_net = net_generic(net, nat_net_id); + struct nf_nat_hooks_net *nat_proto_net; + struct nf_nat_lookup_hook_priv *priv; + unsigned int hooknum = ops->hooknum; + struct nf_hook_ops *nat_ops; + int i, ret; + + if (WARN_ON_ONCE(ops->pf >= ARRAY_SIZE(nat_net->nat_proto_net))) + return -EINVAL; + + nat_proto_net = &nat_net->nat_proto_net[ops->pf]; + + for (i = 0; i < ops_count; i++) { + if (WARN_ON(orig_nat_ops[i].pf != ops->pf)) + return -EINVAL; + if (orig_nat_ops[i].hooknum == hooknum) { + hooknum = i; + break; + } + } + + if (WARN_ON_ONCE(i == ops_count)) + return -EINVAL; + + mutex_lock(&nf_nat_proto_mutex); + if (!nat_proto_net->nat_hook_ops) { + WARN_ON(nat_proto_net->users != 0); + + nat_ops = kmemdup(orig_nat_ops, sizeof(*orig_nat_ops) * ops_count, GFP_KERNEL); + if (!nat_ops) { + mutex_unlock(&nf_nat_proto_mutex); + return -ENOMEM; + } + + for (i = 0; i < ops_count; i++) { + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (priv) { + nat_ops[i].priv = priv; + continue; + } + mutex_unlock(&nf_nat_proto_mutex); + while (i) + kfree(nat_ops[--i].priv); + kfree(nat_ops); + return -ENOMEM; + } + + ret = nf_register_net_hooks(net, nat_ops, ops_count); + if (ret < 0) { + mutex_unlock(&nf_nat_proto_mutex); + for (i = 0; i < ops_count; i++) + kfree(nat_ops[i].priv); + kfree(nat_ops); + return ret; + } + + nat_proto_net->nat_hook_ops = nat_ops; + } + + nat_ops = nat_proto_net->nat_hook_ops; + priv = nat_ops[hooknum].priv; + if (WARN_ON_ONCE(!priv)) { + mutex_unlock(&nf_nat_proto_mutex); + return -EOPNOTSUPP; + } + + ret = nf_hook_entries_insert_raw(&priv->entries, ops); + if (ret == 0) + nat_proto_net->users++; + + mutex_unlock(&nf_nat_proto_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(nf_nat_register_fn); + +void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops, + unsigned int ops_count) +{ + struct nat_net *nat_net = net_generic(net, nat_net_id); + struct nf_nat_hooks_net *nat_proto_net; + struct nf_nat_lookup_hook_priv *priv; + struct nf_hook_ops *nat_ops; + int hooknum = ops->hooknum; + int i; + + if (ops->pf >= ARRAY_SIZE(nat_net->nat_proto_net)) + return; + + nat_proto_net = &nat_net->nat_proto_net[ops->pf]; + + mutex_lock(&nf_nat_proto_mutex); + if (WARN_ON(nat_proto_net->users == 0)) + goto unlock; + + nat_proto_net->users--; + + nat_ops = nat_proto_net->nat_hook_ops; + for (i = 0; i < ops_count; i++) { + if (nat_ops[i].hooknum == hooknum) { + hooknum = i; + break; + } + } + if (WARN_ON_ONCE(i == ops_count)) + goto unlock; + priv = nat_ops[hooknum].priv; + nf_hook_entries_delete_raw(&priv->entries, ops); + + if (nat_proto_net->users == 0) { + nf_unregister_net_hooks(net, nat_ops, ops_count); + + for (i = 0; i < ops_count; i++) { + priv = nat_ops[i].priv; + kfree_rcu(priv, rcu_head); + } + + nat_proto_net->nat_hook_ops = NULL; + kfree(nat_ops); + } +unlock: + mutex_unlock(&nf_nat_proto_mutex); +} +EXPORT_SYMBOL_GPL(nf_nat_unregister_fn); + +static struct pernet_operations nat_net_ops = { + .id = &nat_net_id, + .size = sizeof(struct nat_net), +}; + +static struct nf_nat_hook nat_hook = { + .parse_nat_setup = nfnetlink_parse_nat_setup, +#ifdef CONFIG_XFRM + .decode_session = __nf_nat_decode_session, +#endif + .manip_pkt = nf_nat_manip_pkt, +}; + static int __init nf_nat_init(void) { int ret, i; @@ -823,15 +1067,17 @@ static int __init nf_nat_init(void) for (i = 0; i < CONNTRACK_LOCKS; i++) spin_lock_init(&nf_nat_locks[i]); + ret = register_pernet_subsys(&nat_net_ops); + if (ret < 0) { + nf_ct_extend_unregister(&nat_extend); + return ret; + } + nf_ct_helper_expectfn_register(&follow_master_nat); - BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); - RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, - nfnetlink_parse_nat_setup); -#ifdef CONFIG_XFRM - BUG_ON(nf_nat_decode_session_hook != NULL); - RCU_INIT_POINTER(nf_nat_decode_session_hook, __nf_nat_decode_session); -#endif + WARN_ON(nf_nat_hook != NULL); + RCU_INIT_POINTER(nf_nat_hook, &nat_hook); + return 0; } @@ -844,16 +1090,15 @@ static void __exit nf_nat_cleanup(void) nf_ct_extend_unregister(&nat_extend); nf_ct_helper_expectfn_unregister(&follow_master_nat); - RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); -#ifdef CONFIG_XFRM - RCU_INIT_POINTER(nf_nat_decode_session_hook, NULL); -#endif + RCU_INIT_POINTER(nf_nat_hook, NULL); + synchronize_rcu(); for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); synchronize_net(); nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size); + unregister_pernet_subsys(&nat_net_ops); } MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index 607a373379b40..99606baedda49 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -191,7 +191,7 @@ EXPORT_SYMBOL(nf_nat_mangle_udp_packet); void nf_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *exp) { - struct nf_nat_range range; + struct nf_nat_range2 range; /* This must be a fresh one. */ BUG_ON(ct->status & IPS_NAT_DONE_MASK); diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c index 7d7466dbf6633..5d849d8355617 100644 --- a/net/netfilter/nf_nat_proto_common.c +++ b/net/netfilter/nf_nat_proto_common.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL_GPL(nf_nat_l4proto_in_range); void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct, u16 *rover) @@ -83,6 +83,8 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, : tuple->src.u.all); } else if (range->flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY) { off = prandom_u32(); + } else if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) { + off = (ntohs(*portptr) - ntohs(range->base_proto.all)); } else { off = *rover; } @@ -91,7 +93,8 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, *portptr = htons(min + off % range_size); if (++i != range_size && nf_nat_used_tuple(tuple, ct)) continue; - if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) + if (!(range->flags & (NF_NAT_RANGE_PROTO_RANDOM_ALL| + NF_NAT_RANGE_PROTO_OFFSET))) *rover = off; return; } @@ -100,7 +103,7 @@ EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple); #if IS_ENABLED(CONFIG_NF_CT_NETLINK) int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range *range) + struct nf_nat_range2 *range) { if (tb[CTA_PROTONAT_PORT_MIN]) { range->min_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]); diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c index 269fcd5dc34c4..67ea0d83aa5a8 100644 --- a/net/netfilter/nf_nat_proto_dccp.c +++ b/net/netfilter/nf_nat_proto_dccp.c @@ -23,7 +23,7 @@ static u_int16_t dccp_port_rover; static void dccp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c index c57ee3240b1d5..1c5d9b65fbbab 100644 --- a/net/netfilter/nf_nat_proto_sctp.c +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -17,7 +17,7 @@ static u_int16_t nf_sctp_port_rover; static void sctp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c index 4f8820fc51480..f15fcd475f987 100644 --- a/net/netfilter/nf_nat_proto_tcp.c +++ b/net/netfilter/nf_nat_proto_tcp.c @@ -23,7 +23,7 @@ static u16 tcp_port_rover; static void tcp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c index edd4a77dc09a8..5790f70a83b28 100644 --- a/net/netfilter/nf_nat_proto_udp.c +++ b/net/netfilter/nf_nat_proto_udp.c @@ -22,7 +22,7 @@ static u16 udp_port_rover; static void udp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -100,7 +100,7 @@ static bool udplite_manip_pkt(struct sk_buff *skb, static void udplite_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/netfilter/nf_nat_proto_unknown.c b/net/netfilter/nf_nat_proto_unknown.c index 6e494d5844128..c5db3e251232b 100644 --- a/net/netfilter/nf_nat_proto_unknown.c +++ b/net/netfilter/nf_nat_proto_unknown.c @@ -27,7 +27,7 @@ static bool unknown_in_range(const struct nf_conntrack_tuple *tuple, static void unknown_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/netfilter/nf_nat_redirect.c b/net/netfilter/nf_nat_redirect.c index 25b06b959118d..adee04af8d43f 100644 --- a/net/netfilter/nf_nat_redirect.c +++ b/net/netfilter/nf_nat_redirect.c @@ -15,7 +15,6 @@ #include <linux/inetdevice.h> #include <linux/ip.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/types.h> @@ -36,7 +35,7 @@ nf_nat_redirect_ipv4(struct sk_buff *skb, struct nf_conn *ct; enum ip_conntrack_info ctinfo; __be32 newdst; - struct nf_nat_range newrange; + struct nf_nat_range2 newrange; WARN_ON(hooknum != NF_INET_PRE_ROUTING && hooknum != NF_INET_LOCAL_OUT); @@ -82,10 +81,10 @@ EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv4); static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT; unsigned int -nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, +nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, unsigned int hooknum) { - struct nf_nat_range newrange; + struct nf_nat_range2 newrange; struct in6_addr newdst; enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -124,6 +123,3 @@ nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST); } EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv6); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 791fac4fd7453..1f30860749817 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -316,7 +316,7 @@ static void nf_nat_sip_seq_adjust(struct sk_buff *skb, unsigned int protoff, static void nf_nat_sip_expected(struct nf_conn *ct, struct nf_conntrack_expect *exp) { - struct nf_nat_range range; + struct nf_nat_range2 range; /* This must be a fresh one. */ BUG_ON(ct->status & IPS_NAT_DONE_MASK); diff --git a/net/netfilter/nf_osf.c b/net/netfilter/nf_osf.c new file mode 100644 index 0000000000000..5ba5c7bef2f96 --- /dev/null +++ b/net/netfilter/nf_osf.c @@ -0,0 +1,218 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/kernel.h> + +#include <linux/capability.h> +#include <linux/if.h> +#include <linux/inetdevice.h> +#include <linux/ip.h> +#include <linux/list.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/tcp.h> + +#include <net/ip.h> +#include <net/tcp.h> + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_log.h> +#include <linux/netfilter/nf_osf.h> + +static inline int nf_osf_ttl(const struct sk_buff *skb, + const struct nf_osf_info *info, + unsigned char f_ttl) +{ + const struct iphdr *ip = ip_hdr(skb); + + if (info->flags & NF_OSF_TTL) { + if (info->ttl == NF_OSF_TTL_TRUE) + return ip->ttl == f_ttl; + if (info->ttl == NF_OSF_TTL_NOCHECK) + return 1; + else if (ip->ttl <= f_ttl) + return 1; + else { + struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + int ret = 0; + + for_ifa(in_dev) { + if (inet_ifa_match(ip->saddr, ifa)) { + ret = (ip->ttl == f_ttl); + break; + } + } + endfor_ifa(in_dev); + + return ret; + } + } + + return ip->ttl == f_ttl; +} + +bool +nf_osf_match(const struct sk_buff *skb, u_int8_t family, + int hooknum, struct net_device *in, struct net_device *out, + const struct nf_osf_info *info, struct net *net, + const struct list_head *nf_osf_fingers) +{ + const unsigned char *optp = NULL, *_optp = NULL; + unsigned int optsize = 0, check_WSS = 0; + int fmatch = FMATCH_WRONG, fcount = 0; + const struct iphdr *ip = ip_hdr(skb); + const struct nf_osf_user_finger *f; + unsigned char opts[MAX_IPOPTLEN]; + const struct nf_osf_finger *kf; + u16 window, totlen, mss = 0; + const struct tcphdr *tcp; + struct tcphdr _tcph; + bool df; + + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); + if (!tcp) + return false; + + if (!tcp->syn) + return false; + + totlen = ntohs(ip->tot_len); + df = ntohs(ip->frag_off) & IP_DF; + window = ntohs(tcp->window); + + if (tcp->doff * 4 > sizeof(struct tcphdr)) { + optsize = tcp->doff * 4 - sizeof(struct tcphdr); + + _optp = optp = skb_header_pointer(skb, ip_hdrlen(skb) + + sizeof(struct tcphdr), optsize, opts); + } + + list_for_each_entry_rcu(kf, &nf_osf_fingers[df], finger_entry) { + int foptsize, optnum; + + f = &kf->finger; + + if (!(info->flags & NF_OSF_LOG) && strcmp(info->genre, f->genre)) + continue; + + optp = _optp; + fmatch = FMATCH_WRONG; + + if (totlen != f->ss || !nf_osf_ttl(skb, info, f->ttl)) + continue; + + /* + * Should not happen if userspace parser was written correctly. + */ + if (f->wss.wc >= OSF_WSS_MAX) + continue; + + /* Check options */ + + foptsize = 0; + for (optnum = 0; optnum < f->opt_num; ++optnum) + foptsize += f->opt[optnum].length; + + if (foptsize > MAX_IPOPTLEN || + optsize > MAX_IPOPTLEN || + optsize != foptsize) + continue; + + check_WSS = f->wss.wc; + + for (optnum = 0; optnum < f->opt_num; ++optnum) { + if (f->opt[optnum].kind == (*optp)) { + __u32 len = f->opt[optnum].length; + const __u8 *optend = optp + len; + + fmatch = FMATCH_OK; + + switch (*optp) { + case OSFOPT_MSS: + mss = optp[3]; + mss <<= 8; + mss |= optp[2]; + + mss = ntohs((__force __be16)mss); + break; + case OSFOPT_TS: + break; + } + + optp = optend; + } else + fmatch = FMATCH_OPT_WRONG; + + if (fmatch != FMATCH_OK) + break; + } + + if (fmatch != FMATCH_OPT_WRONG) { + fmatch = FMATCH_WRONG; + + switch (check_WSS) { + case OSF_WSS_PLAIN: + if (f->wss.val == 0 || window == f->wss.val) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MSS: + /* + * Some smart modems decrease mangle MSS to + * SMART_MSS_2, so we check standard, decreased + * and the one provided in the fingerprint MSS + * values. + */ +#define SMART_MSS_1 1460 +#define SMART_MSS_2 1448 + if (window == f->wss.val * mss || + window == f->wss.val * SMART_MSS_1 || + window == f->wss.val * SMART_MSS_2) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MTU: + if (window == f->wss.val * (mss + 40) || + window == f->wss.val * (SMART_MSS_1 + 40) || + window == f->wss.val * (SMART_MSS_2 + 40)) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MODULO: + if ((window % f->wss.val) == 0) + fmatch = FMATCH_OK; + break; + } + } + + if (fmatch != FMATCH_OK) + continue; + + fcount++; + + if (info->flags & NF_OSF_LOG) + nf_log_packet(net, family, hooknum, skb, + in, out, NULL, + "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n", + f->genre, f->version, f->subtype, + &ip->saddr, ntohs(tcp->source), + &ip->daddr, ntohs(tcp->dest), + f->ttl - ip->ttl); + + if ((info->flags & NF_OSF_LOG) && + info->loglevel == NF_OSF_LOGLEVEL_FIRST) + break; + } + + if (!fcount && (info->flags & NF_OSF_LOG)) + nf_log_packet(net, family, hooknum, skb, in, out, NULL, + "Remote OS is not known: %pI4:%u -> %pI4:%u\n", + &ip->saddr, ntohs(tcp->source), + &ip->daddr, ntohs(tcp->dest)); + + if (fcount) + fmatch = FMATCH_OK; + + return fmatch == FMATCH_OK; +} +EXPORT_SYMBOL_GPL(nf_osf_match); + +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 501e48a7965b4..ca4c4d994ddb0 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -28,6 +28,42 @@ static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static u64 table_handle; +enum { + NFT_VALIDATE_SKIP = 0, + NFT_VALIDATE_NEED, + NFT_VALIDATE_DO, +}; + +static u32 nft_chain_hash(const void *data, u32 len, u32 seed); +static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed); +static int nft_chain_hash_cmp(struct rhashtable_compare_arg *, const void *); + +static const struct rhashtable_params nft_chain_ht_params = { + .head_offset = offsetof(struct nft_chain, rhlhead), + .key_offset = offsetof(struct nft_chain, name), + .hashfn = nft_chain_hash, + .obj_hashfn = nft_chain_hash_obj, + .obj_cmpfn = nft_chain_hash_cmp, + .locks_mul = 1, + .automatic_shrinking = true, +}; + +static void nft_validate_state_update(struct net *net, u8 new_validate_state) +{ + switch (net->nft.validate_state) { + case NFT_VALIDATE_SKIP: + WARN_ON_ONCE(new_validate_state == NFT_VALIDATE_DO); + break; + case NFT_VALIDATE_NEED: + break; + case NFT_VALIDATE_DO: + if (new_validate_state == NFT_VALIDATE_NEED) + return; + } + + net->nft.validate_state = new_validate_state; +} + static void nft_ctx_init(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, @@ -74,88 +110,43 @@ static void nft_trans_destroy(struct nft_trans *trans) kfree(trans); } -/* removal requests are queued in the commit_list, but not acted upon - * until after all new rules are in place. - * - * Therefore, nf_register_net_hook(net, &nat_hook) runs before pending - * nf_unregister_net_hook(). - * - * nf_register_net_hook thus fails if a nat hook is already in place - * even if the conflicting hook is about to be removed. - * - * If collision is detected, search commit_log for DELCHAIN matching - * the new nat hooknum; if we find one collision is temporary: - * - * Either transaction is aborted (new/colliding hook is removed), or - * transaction is committed (old hook is removed). - */ -static bool nf_tables_allow_nat_conflict(const struct net *net, - const struct nf_hook_ops *ops) -{ - const struct nft_trans *trans; - bool ret = false; - - if (!ops->nat_hook) - return false; - - list_for_each_entry(trans, &net->nft.commit_list, list) { - const struct nf_hook_ops *pending_ops; - const struct nft_chain *pending; - - if (trans->msg_type != NFT_MSG_NEWCHAIN && - trans->msg_type != NFT_MSG_DELCHAIN) - continue; - - pending = trans->ctx.chain; - if (!nft_is_base_chain(pending)) - continue; - - pending_ops = &nft_base_chain(pending)->ops; - if (pending_ops->nat_hook && - pending_ops->pf == ops->pf && - pending_ops->hooknum == ops->hooknum) { - /* other hook registration already pending? */ - if (trans->msg_type == NFT_MSG_NEWCHAIN) - return false; - - ret = true; - } - } - - return ret; -} - static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) { - struct nf_hook_ops *ops; - int ret; + const struct nft_base_chain *basechain; + const struct nf_hook_ops *ops; if (table->flags & NFT_TABLE_F_DORMANT || !nft_is_base_chain(chain)) return 0; - ops = &nft_base_chain(chain)->ops; - ret = nf_register_net_hook(net, ops); - if (ret == -EBUSY && nf_tables_allow_nat_conflict(net, ops)) { - ops->nat_hook = false; - ret = nf_register_net_hook(net, ops); - ops->nat_hook = true; - } + basechain = nft_base_chain(chain); + ops = &basechain->ops; - return ret; + if (basechain->type->ops_register) + return basechain->type->ops_register(net, ops); + + return nf_register_net_hook(net, ops); } static void nf_tables_unregister_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) { + const struct nft_base_chain *basechain; + const struct nf_hook_ops *ops; + if (table->flags & NFT_TABLE_F_DORMANT || !nft_is_base_chain(chain)) return; + basechain = nft_base_chain(chain); + ops = &basechain->ops; + + if (basechain->type->ops_unregister) + return basechain->type->ops_unregister(net, ops); - nf_unregister_net_hook(net, &nft_base_chain(chain)->ops); + nf_unregister_net_hook(net, ops); } static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) @@ -415,13 +406,17 @@ static struct nft_table *nft_table_lookup(const struct net *net, { struct nft_table *table; - list_for_each_entry(table, &net->nft.tables, list) { + if (nla == NULL) + return ERR_PTR(-EINVAL); + + list_for_each_entry_rcu(table, &net->nft.tables, list) { if (!nla_strcmp(nla, table->name) && table->family == family && nft_active_genmask(table, genmask)) return table; } - return NULL; + + return ERR_PTR(-ENOENT); } static struct nft_table *nft_table_lookup_byhandle(const struct net *net, @@ -435,37 +430,6 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, nft_active_genmask(table, genmask)) return table; } - return NULL; -} - -static struct nft_table *nf_tables_table_lookup(const struct net *net, - const struct nlattr *nla, - u8 family, u8 genmask) -{ - struct nft_table *table; - - if (nla == NULL) - return ERR_PTR(-EINVAL); - - table = nft_table_lookup(net, nla, family, genmask); - if (table != NULL) - return table; - - return ERR_PTR(-ENOENT); -} - -static struct nft_table *nf_tables_table_lookup_byhandle(const struct net *net, - const struct nlattr *nla, - u8 genmask) -{ - struct nft_table *table; - - if (nla == NULL) - return ERR_PTR(-EINVAL); - - table = nft_table_lookup_byhandle(net, nla, genmask); - if (table != NULL) - return table; return ERR_PTR(-ENOENT); } @@ -618,6 +582,24 @@ done: return skb->len; } +static int nft_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct netlink_dump_control *c) +{ + int err; + + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + + rcu_read_unlock(); + err = netlink_dump_start(nlsk, skb, nlh, c); + rcu_read_lock(); + module_put(THIS_MODULE); + + return err; +} + +/* called with rcu_read_lock held */ static int nf_tables_gettable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -633,16 +615,19 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_tables, + .module = THIS_MODULE, }; - return netlink_dump_start(nlsk, skb, nlh, &c); + + return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } - table = nf_tables_table_lookup(net, nla[NFTA_TABLE_NAME], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_TABLE_NAME]); return PTR_ERR(table); + } - skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; @@ -749,6 +734,29 @@ err: return ret; } +static u32 nft_chain_hash(const void *data, u32 len, u32 seed) +{ + const char *name = data; + + return jhash(name, strlen(name), seed); +} + +static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed) +{ + const struct nft_chain *chain = data; + + return nft_chain_hash(chain->name, 0, seed); +} + +static int nft_chain_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct nft_chain *chain = ptr; + const char *name = arg->key; + + return strcmp(chain->name, name); +} + static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -756,21 +764,23 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); - const struct nlattr *name; - struct nft_table *table; int family = nfmsg->nfgen_family; + const struct nlattr *attr; + struct nft_table *table; u32 flags = 0; struct nft_ctx ctx; int err; - name = nla[NFTA_TABLE_NAME]; - table = nf_tables_table_lookup(net, name, family, genmask); + attr = nla[NFTA_TABLE_NAME]; + table = nft_table_lookup(net, attr, family, genmask); if (IS_ERR(table)) { if (PTR_ERR(table) != -ENOENT) return PTR_ERR(table); } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, attr); return -EEXIST; + } if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; @@ -789,10 +799,14 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (table == NULL) goto err_kzalloc; - table->name = nla_strdup(name, GFP_KERNEL); + table->name = nla_strdup(attr, GFP_KERNEL); if (table->name == NULL) goto err_strdup; + err = rhltable_init(&table->chains_ht, &nft_chain_ht_params); + if (err) + goto err_chain_ht; + INIT_LIST_HEAD(&table->chains); INIT_LIST_HEAD(&table->sets); INIT_LIST_HEAD(&table->objects); @@ -809,6 +823,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, list_add_tail_rcu(&table->list, &net->nft.tables); return 0; err_trans: + rhltable_destroy(&table->chains_ht); +err_chain_ht: kfree(table->name); err_strdup: kfree(table); @@ -912,8 +928,9 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); - struct nft_table *table; int family = nfmsg->nfgen_family; + const struct nlattr *attr; + struct nft_table *table; struct nft_ctx ctx; nft_ctx_init(&ctx, net, skb, nlh, 0, NULL, NULL, nla); @@ -921,16 +938,18 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, (!nla[NFTA_TABLE_NAME] && !nla[NFTA_TABLE_HANDLE])) return nft_flush(&ctx, family); - if (nla[NFTA_TABLE_HANDLE]) - table = nf_tables_table_lookup_byhandle(net, - nla[NFTA_TABLE_HANDLE], - genmask); - else - table = nf_tables_table_lookup(net, nla[NFTA_TABLE_NAME], - family, genmask); + if (nla[NFTA_TABLE_HANDLE]) { + attr = nla[NFTA_TABLE_HANDLE]; + table = nft_table_lookup_byhandle(net, attr, genmask); + } else { + attr = nla[NFTA_TABLE_NAME]; + table = nft_table_lookup(net, attr, family, genmask); + } - if (IS_ERR(table)) + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(table); + } if (nlh->nlmsg_flags & NLM_F_NONREC && table->use > 0) @@ -946,6 +965,7 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx) { BUG_ON(ctx->table->use > 0); + rhltable_destroy(&ctx->table->chains_ht); kfree(ctx->table->name); kfree(ctx->table); } @@ -978,8 +998,7 @@ EXPORT_SYMBOL_GPL(nft_unregister_chain_type); */ static struct nft_chain * -nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle, - u8 genmask) +nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) { struct nft_chain *chain; @@ -992,22 +1011,35 @@ nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle, return ERR_PTR(-ENOENT); } -static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table, - const struct nlattr *nla, - u8 genmask) +static struct nft_chain *nft_chain_lookup(struct nft_table *table, + const struct nlattr *nla, u8 genmask) { + char search[NFT_CHAIN_MAXNAMELEN + 1]; + struct rhlist_head *tmp, *list; struct nft_chain *chain; if (nla == NULL) return ERR_PTR(-EINVAL); - list_for_each_entry(chain, &table->chains, list) { - if (!nla_strcmp(nla, chain->name) && - nft_active_genmask(chain, genmask)) - return chain; - } + nla_strlcpy(search, nla, sizeof(search)); - return ERR_PTR(-ENOENT); + WARN_ON(!rcu_read_lock_held() && + !lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + + chain = ERR_PTR(-ENOENT); + rcu_read_lock(); + list = rhltable_lookup(&table->chains_ht, search, nft_chain_ht_params); + if (!list) + goto out_unlock; + + rhl_for_each_entry_rcu(chain, tmp, list, rhlhead) { + if (nft_active_genmask(chain, genmask)) + goto out_unlock; + } + chain = ERR_PTR(-ENOENT); +out_unlock: + rcu_read_unlock(); + return chain; } static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = { @@ -1203,6 +1235,7 @@ done: return skb->len; } +/* called with rcu_read_lock held */ static int nf_tables_getchain(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -1210,8 +1243,8 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_cur(net); - const struct nft_table *table; const struct nft_chain *chain; + struct nft_table *table; struct sk_buff *skb2; int family = nfmsg->nfgen_family; int err; @@ -1219,20 +1252,25 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nf_tables_dump_chains, + .module = THIS_MODULE, }; - return netlink_dump_start(nlsk, skb, nlh, &c); + + return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } - table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); + } - chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); - if (IS_ERR(chain)) + chain = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); return PTR_ERR(chain); + } - skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; @@ -1304,17 +1342,32 @@ static void nft_chain_stats_replace(struct nft_base_chain *chain, } } +static void nf_tables_chain_free_chain_rules(struct nft_chain *chain) +{ + struct nft_rule **g0 = rcu_dereference_raw(chain->rules_gen_0); + struct nft_rule **g1 = rcu_dereference_raw(chain->rules_gen_1); + + if (g0 != g1) + kvfree(g1); + kvfree(g0); + + /* should be NULL either via abort or via successful commit */ + WARN_ON_ONCE(chain->rules_next); + kvfree(chain->rules_next); +} + static void nf_tables_chain_destroy(struct nft_ctx *ctx) { struct nft_chain *chain = ctx->chain; BUG_ON(chain->use > 0); + /* no concurrent access possible anymore */ + nf_tables_chain_free_chain_rules(chain); + if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain); - if (basechain->type->free) - basechain->type->free(ctx); module_put(basechain->type->owner); free_percpu(basechain->stats); if (basechain->stats) @@ -1404,6 +1457,27 @@ static void nft_chain_release_hook(struct nft_chain_hook *hook) module_put(hook->type->owner); } +struct nft_rules_old { + struct rcu_head h; + struct nft_rule **start; +}; + +static struct nft_rule **nf_tables_chain_alloc_rules(const struct nft_chain *chain, + unsigned int alloc) +{ + if (alloc > INT_MAX) + return NULL; + + alloc += 1; /* NULL, ends rules */ + if (sizeof(struct nft_rule *) > INT_MAX / alloc) + return NULL; + + alloc *= sizeof(struct nft_rule *); + alloc += sizeof(struct nft_rules_old); + + return kvmalloc(alloc, GFP_KERNEL); +} + static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, u8 policy, bool create) { @@ -1413,6 +1487,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_stats __percpu *stats; struct net *net = ctx->net; struct nft_chain *chain; + struct nft_rule **rules; int err; if (table->use == UINT_MAX) @@ -1447,9 +1522,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, } basechain->type = hook.type; - if (basechain->type->init) - basechain->type->init(ctx); - chain = &basechain->chain; ops = &basechain->ops; @@ -1460,9 +1532,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, ops->hook = hook.type->hooks[ops->hooknum]; ops->dev = hook.dev; - if (basechain->type->type == NFT_CHAIN_T_NAT) - ops->nat_hook = true; - chain->flags |= NFT_BASE_CHAIN; basechain->policy = policy; } else { @@ -1481,13 +1550,31 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err1; } + rules = nf_tables_chain_alloc_rules(chain, 0); + if (!rules) { + err = -ENOMEM; + goto err1; + } + + *rules = NULL; + rcu_assign_pointer(chain->rules_gen_0, rules); + rcu_assign_pointer(chain->rules_gen_1, rules); + err = nf_tables_register_hook(net, table, chain); if (err < 0) goto err1; + err = rhltable_insert_key(&table->chains_ht, chain->name, + &chain->rhlhead, nft_chain_ht_params); + if (err) + goto err2; + err = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); - if (err < 0) + if (err < 0) { + rhltable_remove(&table->chains_ht, &chain->rhlhead, + nft_chain_ht_params); goto err2; + } table->use++; list_add_tail_rcu(&chain->list, &table->chains); @@ -1544,8 +1631,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, nla[NFTA_CHAIN_NAME]) { struct nft_chain *chain2; - chain2 = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], - genmask); + chain2 = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); if (!IS_ERR(chain2)) return -EEXIST; } @@ -1595,9 +1681,9 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - const struct nlattr * uninitialized_var(name); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; + const struct nlattr *attr; struct nft_table *table; struct nft_chain *chain; u8 policy = NF_ACCEPT; @@ -1607,36 +1693,46 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; - table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); + } chain = NULL; - name = nla[NFTA_CHAIN_NAME]; + attr = nla[NFTA_CHAIN_NAME]; if (nla[NFTA_CHAIN_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE])); - chain = nf_tables_chain_lookup_byhandle(table, handle, genmask); - if (IS_ERR(chain)) + chain = nft_chain_lookup_byhandle(table, handle, genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_HANDLE]); return PTR_ERR(chain); + } + attr = nla[NFTA_CHAIN_HANDLE]; } else { - chain = nf_tables_chain_lookup(table, name, genmask); + chain = nft_chain_lookup(table, attr, genmask); if (IS_ERR(chain)) { - if (PTR_ERR(chain) != -ENOENT) + if (PTR_ERR(chain) != -ENOENT) { + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(chain); + } chain = NULL; } } if (nla[NFTA_CHAIN_POLICY]) { if (chain != NULL && - !nft_is_base_chain(chain)) + !nft_is_base_chain(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]); return -EOPNOTSUPP; + } if (chain == NULL && - nla[NFTA_CHAIN_HOOK] == NULL) + nla[NFTA_CHAIN_HOOK] == NULL) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]); return -EOPNOTSUPP; + } policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY])); switch (policy) { @@ -1651,8 +1747,10 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); if (chain != NULL) { - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, attr); return -EEXIST; + } if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; @@ -1669,28 +1767,34 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); + int family = nfmsg->nfgen_family; + const struct nlattr *attr; struct nft_table *table; struct nft_chain *chain; struct nft_rule *rule; - int family = nfmsg->nfgen_family; struct nft_ctx ctx; u64 handle; u32 use; int err; - table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); + } if (nla[NFTA_CHAIN_HANDLE]) { - handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE])); - chain = nf_tables_chain_lookup_byhandle(table, handle, genmask); + attr = nla[NFTA_CHAIN_HANDLE]; + handle = be64_to_cpu(nla_get_be64(attr)); + chain = nft_chain_lookup_byhandle(table, handle, genmask); } else { - chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); + attr = nla[NFTA_CHAIN_NAME]; + chain = nft_chain_lookup(table, attr, genmask); } - if (IS_ERR(chain)) + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(chain); + } if (nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) @@ -1712,8 +1816,10 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, /* There are rules and elements that are still holding references to us, * we cannot do a recursive removal in this case. */ - if (use > 0) + if (use > 0) { + NL_SET_BAD_ATTR(extack, attr); return -EBUSY; + } return nft_delchain(&ctx); } @@ -1905,19 +2011,7 @@ static int nf_tables_newexpr(const struct nft_ctx *ctx, goto err1; } - if (ops->validate) { - const struct nft_data *data = NULL; - - err = ops->validate(ctx, expr, &data); - if (err < 0) - goto err2; - } - return 0; - -err2: - if (ops->destroy) - ops->destroy(ctx, expr); err1: expr->ops = NULL; return err; @@ -1970,13 +2064,13 @@ void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) * Rules */ -static struct nft_rule *__nf_tables_rule_lookup(const struct nft_chain *chain, - u64 handle) +static struct nft_rule *__nft_rule_lookup(const struct nft_chain *chain, + u64 handle) { struct nft_rule *rule; // FIXME: this sucks - list_for_each_entry(rule, &chain->rules, list) { + list_for_each_entry_rcu(rule, &chain->rules, list) { if (handle == rule->handle) return rule; } @@ -1984,13 +2078,13 @@ static struct nft_rule *__nf_tables_rule_lookup(const struct nft_chain *chain, return ERR_PTR(-ENOENT); } -static struct nft_rule *nf_tables_rule_lookup(const struct nft_chain *chain, - const struct nlattr *nla) +static struct nft_rule *nft_rule_lookup(const struct nft_chain *chain, + const struct nlattr *nla) { if (nla == NULL) return ERR_PTR(-EINVAL); - return __nf_tables_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla))); + return __nft_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla))); } static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { @@ -2172,6 +2266,7 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) return 0; } +/* called with rcu_read_lock held */ static int nf_tables_getrule(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -2179,9 +2274,9 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_cur(net); - const struct nft_table *table; const struct nft_chain *chain; const struct nft_rule *rule; + struct nft_table *table; struct sk_buff *skb2; int family = nfmsg->nfgen_family; int err; @@ -2190,18 +2285,19 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, struct netlink_dump_control c = { .dump = nf_tables_dump_rules, .done = nf_tables_dump_rules_done, + .module = THIS_MODULE, }; if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { struct nft_rule_dump_ctx *ctx; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); if (!ctx) return -ENOMEM; if (nla[NFTA_RULE_TABLE]) { ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], - GFP_KERNEL); + GFP_ATOMIC); if (!ctx->table) { kfree(ctx); return -ENOMEM; @@ -2209,7 +2305,7 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, } if (nla[NFTA_RULE_CHAIN]) { ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], - GFP_KERNEL); + GFP_ATOMIC); if (!ctx->chain) { kfree(ctx->table); kfree(ctx); @@ -2219,23 +2315,28 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, c.data = ctx; } - return netlink_dump_start(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } - table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); + } - chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); - if (IS_ERR(chain)) + chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); + } - rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); - if (IS_ERR(rule)) + rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); + if (IS_ERR(rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); + } - skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; @@ -2276,6 +2377,53 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, nf_tables_rule_destroy(ctx, rule); } +int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) +{ + struct nft_expr *expr, *last; + const struct nft_data *data; + struct nft_rule *rule; + int err; + + list_for_each_entry(rule, &chain->rules, list) { + if (!nft_is_active_next(ctx->net, rule)) + continue; + + nft_rule_for_each_expr(expr, last, rule) { + if (!expr->ops->validate) + continue; + + err = expr->ops->validate(ctx, expr, &data); + if (err < 0) + return err; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(nft_chain_validate); + +static int nft_table_validate(struct net *net, const struct nft_table *table) +{ + struct nft_chain *chain; + struct nft_ctx ctx = { + .net = net, + .family = table->family, + }; + int err; + + list_for_each_entry(chain, &table->chains, list) { + if (!nft_is_base_chain(chain)) + continue; + + ctx.chain = chain; + err = nft_chain_validate(&ctx, chain); + if (err < 0) + return err; + } + + return 0; +} + #define NFT_RULE_MAXEXPRS 128 static struct nft_expr_info *info; @@ -2303,23 +2451,30 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; - table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); + } - chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); - if (IS_ERR(chain)) + chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); + } if (nla[NFTA_RULE_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE])); - rule = __nf_tables_rule_lookup(chain, handle); - if (IS_ERR(rule)) + rule = __nft_rule_lookup(chain, handle); + if (IS_ERR(rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); + } - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return -EEXIST; + } if (nlh->nlmsg_flags & NLM_F_REPLACE) old_rule = rule; else @@ -2338,9 +2493,11 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return -EOPNOTSUPP; pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); - old_rule = __nf_tables_rule_lookup(chain, pos_handle); - if (IS_ERR(old_rule)) + old_rule = __nft_rule_lookup(chain, pos_handle); + if (IS_ERR(old_rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); return PTR_ERR(old_rule); + } } nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); @@ -2394,6 +2551,10 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, err = nf_tables_newexpr(&ctx, &info[i], expr); if (err < 0) goto err2; + + if (info[i].ops->validate) + nft_validate_state_update(net, NFT_VALIDATE_NEED); + info[i].ops = NULL; expr = nft_expr_next(expr); } @@ -2437,8 +2598,11 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } } chain->use++; - return 0; + if (net->nft.validate_state == NFT_VALIDATE_DO) + return nft_table_validate(net, table); + + return 0; err2: nf_tables_rule_release(&ctx, rule); err1: @@ -2478,32 +2642,37 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, int family = nfmsg->nfgen_family, err = 0; struct nft_ctx ctx; - table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); + } if (nla[NFTA_RULE_CHAIN]) { - chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], - genmask); - if (IS_ERR(chain)) + chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); + } } nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); if (chain) { if (nla[NFTA_RULE_HANDLE]) { - rule = nf_tables_rule_lookup(chain, - nla[NFTA_RULE_HANDLE]); - if (IS_ERR(rule)) + rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); + if (IS_ERR(rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); + } err = nft_delrule(&ctx, rule); } else if (nla[NFTA_RULE_ID]) { rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]); - if (IS_ERR(rule)) + if (IS_ERR(rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_ID]); return PTR_ERR(rule); + } err = nft_delrule(&ctx, rule); } else { @@ -2548,14 +2717,12 @@ void nft_unregister_set(struct nft_set_type *type) EXPORT_SYMBOL_GPL(nft_unregister_set); #define NFT_SET_FEATURES (NFT_SET_INTERVAL | NFT_SET_MAP | \ - NFT_SET_TIMEOUT | NFT_SET_OBJECT) + NFT_SET_TIMEOUT | NFT_SET_OBJECT | \ + NFT_SET_EVAL) -static bool nft_set_ops_candidate(const struct nft_set_ops *ops, u32 flags) +static bool nft_set_ops_candidate(const struct nft_set_type *type, u32 flags) { - if ((flags & NFT_SET_EVAL) && !ops->update) - return false; - - return (flags & ops->features) == (flags & NFT_SET_FEATURES); + return (flags & type->features) == (flags & NFT_SET_FEATURES); } /* @@ -2592,14 +2759,9 @@ nft_select_set_ops(const struct nft_ctx *ctx, best.space = ~0; list_for_each_entry(type, &nf_tables_set_types, list) { - if (!type->select_ops) - ops = type->ops; - else - ops = type->select_ops(ctx, desc, flags); - if (!ops) - continue; + ops = &type->ops; - if (!nft_set_ops_candidate(ops, flags)) + if (!nft_set_ops_candidate(type, flags)) continue; if (!ops->estimate(desc, flags, &est)) continue; @@ -2630,7 +2792,7 @@ nft_select_set_ops(const struct nft_ctx *ctx, if (!try_module_get(type->owner)) continue; if (bops != NULL) - module_put(bops->type->owner); + module_put(to_set_type(bops)->owner); bops = ops; best = est; @@ -2671,6 +2833,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], + struct netlink_ext_ack *extack, u8 genmask) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); @@ -2678,25 +2841,27 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, struct nft_table *table = NULL; if (nla[NFTA_SET_TABLE] != NULL) { - table = nf_tables_table_lookup(net, nla[NFTA_SET_TABLE], - family, genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, + genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); + } } nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla); return 0; } -static struct nft_set *nf_tables_set_lookup(const struct nft_table *table, - const struct nlattr *nla, u8 genmask) +static struct nft_set *nft_set_lookup(const struct nft_table *table, + const struct nlattr *nla, u8 genmask) { struct nft_set *set; if (nla == NULL) return ERR_PTR(-EINVAL); - list_for_each_entry(set, &table->sets, list) { + list_for_each_entry_rcu(set, &table->sets, list) { if (!nla_strcmp(nla, set->name) && nft_active_genmask(set, genmask)) return set; @@ -2704,14 +2869,12 @@ static struct nft_set *nf_tables_set_lookup(const struct nft_table *table, return ERR_PTR(-ENOENT); } -static struct nft_set *nf_tables_set_lookup_byhandle(const struct nft_table *table, - const struct nlattr *nla, u8 genmask) +static struct nft_set *nft_set_lookup_byhandle(const struct nft_table *table, + const struct nlattr *nla, + u8 genmask) { struct nft_set *set; - if (nla == NULL) - return ERR_PTR(-EINVAL); - list_for_each_entry(set, &table->sets, list) { if (be64_to_cpu(nla_get_be64(nla)) == set->handle && nft_active_genmask(set, genmask)) @@ -2720,9 +2883,8 @@ static struct nft_set *nf_tables_set_lookup_byhandle(const struct nft_table *tab return ERR_PTR(-ENOENT); } -static struct nft_set *nf_tables_set_lookup_byid(const struct net *net, - const struct nlattr *nla, - u8 genmask) +static struct nft_set *nft_set_lookup_byid(const struct net *net, + const struct nlattr *nla, u8 genmask) { struct nft_trans *trans; u32 id = ntohl(nla_get_be32(nla)); @@ -2746,12 +2908,12 @@ struct nft_set *nft_set_lookup_global(const struct net *net, { struct nft_set *set; - set = nf_tables_set_lookup(table, nla_set_name, genmask); + set = nft_set_lookup(table, nla_set_name, genmask); if (IS_ERR(set)) { if (!nla_set_id) return set; - set = nf_tables_set_lookup_byid(net, nla_set_id, genmask); + set = nft_set_lookup_byid(net, nla_set_id, genmask); } return set; } @@ -2811,6 +2973,27 @@ cont: return 0; } +static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) +{ + u64 ms = be64_to_cpu(nla_get_be64(nla)); + u64 max = (u64)(~((u64)0)); + + max = div_u64(max, NSEC_PER_MSEC); + if (ms >= max) + return -ERANGE; + + ms *= NSEC_PER_MSEC; + *result = nsecs_to_jiffies64(ms); + return 0; +} + +static __be64 nf_jiffies64_to_msecs(u64 input) +{ + u64 ms = jiffies64_to_nsecs(input); + + return cpu_to_be64(div_u64(ms, NSEC_PER_MSEC)); +} + static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { @@ -2858,7 +3041,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, if (set->timeout && nla_put_be64(skb, NFTA_SET_TIMEOUT, - cpu_to_be64(jiffies_to_msecs(set->timeout)), + nf_jiffies64_to_msecs(set->timeout), NFTA_SET_PAD)) goto nla_put_failure; if (set->gc_int && @@ -2983,6 +3166,7 @@ static int nf_tables_dump_sets_done(struct netlink_callback *cb) return 0; } +/* called with rcu_read_lock held */ static int nf_tables_getset(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -2996,7 +3180,8 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, int err; /* Verify existence before starting dump */ - err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, genmask); + err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, + genmask); if (err < 0) return err; @@ -3004,17 +3189,18 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, struct netlink_dump_control c = { .dump = nf_tables_dump_sets, .done = nf_tables_dump_sets_done, + .module = THIS_MODULE, }; struct nft_ctx *ctx_dump; - ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_KERNEL); + ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_ATOMIC); if (ctx_dump == NULL) return -ENOMEM; *ctx_dump = ctx; c.data = ctx_dump; - return netlink_dump_start(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } /* Only accept unspec with dump */ @@ -3023,11 +3209,11 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, if (!nla[NFTA_SET_TABLE]) return -EINVAL; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); + set = nft_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) return PTR_ERR(set); - skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb2 == NULL) return -ENOMEM; @@ -3153,8 +3339,10 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_TIMEOUT] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( - nla[NFTA_SET_TIMEOUT]))); + + err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &timeout); + if (err) + return err; } gc_int = 0; if (nla[NFTA_SET_GC_INTERVAL] != NULL) { @@ -3175,22 +3363,28 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; - table = nf_tables_table_lookup(net, nla[NFTA_SET_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); + } nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); - set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME], genmask); + set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { - if (PTR_ERR(set) != -ENOENT) + if (PTR_ERR(set) != -ENOENT) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return PTR_ERR(set); + } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return -EEXIST; + } if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; + return 0; } @@ -3233,6 +3427,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, } INIT_LIST_HEAD(&set->bindings); + set->table = table; + write_pnet(&set->net, net); set->ops = ops; set->ktype = ktype; set->klen = desc.klen; @@ -3267,14 +3463,14 @@ err3: err2: kvfree(set); err1: - module_put(ops->type->owner); + module_put(to_set_type(ops)->owner); return err; } static void nft_set_destroy(struct nft_set *set) { set->ops->destroy(set); - module_put(set->ops->type->owner); + module_put(to_set_type(set->ops)->owner); kfree(set->name); kvfree(set); } @@ -3293,6 +3489,7 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); + const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; int err; @@ -3302,20 +3499,28 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_TABLE] == NULL) return -EINVAL; - err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, genmask); + err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, + genmask); if (err < 0) return err; - if (nla[NFTA_SET_HANDLE]) - set = nf_tables_set_lookup_byhandle(ctx.table, nla[NFTA_SET_HANDLE], genmask); - else - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); - if (IS_ERR(set)) - return PTR_ERR(set); + if (nla[NFTA_SET_HANDLE]) { + attr = nla[NFTA_SET_HANDLE]; + set = nft_set_lookup_byhandle(ctx.table, attr, genmask); + } else { + attr = nla[NFTA_SET_NAME]; + set = nft_set_lookup(ctx.table, attr, genmask); + } + if (IS_ERR(set)) { + NL_SET_BAD_ATTR(extack, attr); + return PTR_ERR(set); + } if (!list_empty(&set->bindings) || - (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) + (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) { + NL_SET_BAD_ATTR(extack, attr); return -EBUSY; + } return nft_delset(&ctx, set); } @@ -3405,8 +3610,8 @@ const struct nft_set_ext_type nft_set_ext_types[] = { .align = __alignof__(u64), }, [NFT_SET_EXT_EXPIRATION] = { - .len = sizeof(unsigned long), - .align = __alignof__(unsigned long), + .len = sizeof(u64), + .align = __alignof__(u64), }, [NFT_SET_EXT_USERDATA] = { .len = sizeof(struct nft_userdata), @@ -3443,16 +3648,19 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], + struct netlink_ext_ack *extack, u8 genmask) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); int family = nfmsg->nfgen_family; struct nft_table *table; - table = nf_tables_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], - family, genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); + } nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla); return 0; @@ -3496,22 +3704,21 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - cpu_to_be64(jiffies_to_msecs( - *nft_set_ext_timeout(ext))), + nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)), NFTA_SET_ELEM_PAD)) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { - unsigned long expires, now = jiffies; + u64 expires, now = get_jiffies_64(); expires = *nft_set_ext_expiration(ext); - if (time_before(now, expires)) + if (time_before64(now, expires)) expires -= now; else expires = 0; if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION, - cpu_to_be64(jiffies_to_msecs(expires)), + nf_jiffies64_to_msecs(expires), NFTA_SET_ELEM_PAD)) goto nla_put_failure; } @@ -3749,7 +3956,7 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, ext = nft_set_elem_ext(set, &elem); err = -ENOMEM; - skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb == NULL) goto err1; @@ -3771,6 +3978,7 @@ err1: return err == -EAGAIN ? -ENOBUFS : err; } +/* called with rcu_read_lock held */ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -3782,12 +3990,12 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, + genmask); if (err < 0) return err; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], - genmask); + set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); @@ -3795,10 +4003,11 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, struct netlink_dump_control c = { .dump = nf_tables_dump_set, .done = nf_tables_dump_set_done, + .module = THIS_MODULE, }; struct nft_set_dump_ctx *dump_ctx; - dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_KERNEL); + dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_ATOMIC); if (!dump_ctx) return -ENOMEM; @@ -3806,7 +4015,7 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, dump_ctx->ctx = ctx; c.data = dump_ctx; - return netlink_dump_start(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) @@ -3886,7 +4095,7 @@ void *nft_set_elem_init(const struct nft_set *set, memcpy(nft_set_ext_data(ext), data, set->dlen); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) *nft_set_ext_expiration(ext) = - jiffies + timeout; + get_jiffies_64() + timeout; if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) *nft_set_ext_timeout(ext) = timeout; @@ -3897,12 +4106,24 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem); + struct nft_ctx ctx = { + .net = read_pnet(&set->net), + .family = set->table->family, + }; nft_data_release(nft_set_ext_key(ext), NFT_DATA_VALUE); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); - if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) - nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext)); + if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) { + struct nft_expr *expr = nft_set_ext_expr(ext); + + if (expr->ops->destroy_clone) { + expr->ops->destroy_clone(&ctx, expr); + module_put(expr->ops->type->owner); + } else { + nf_tables_expr_destroy(&ctx, expr); + } + } if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) (*nft_set_ext_obj(ext))->use--; kfree(elem); @@ -3912,12 +4133,13 @@ EXPORT_SYMBOL_GPL(nft_set_elem_destroy); /* Only called from commit path, nft_set_elem_deactivate() already deals with * the refcounting from the preparation phase. */ -static void nf_tables_set_elem_destroy(const struct nft_set *set, void *elem) +static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR)) - nf_tables_expr_destroy(NULL, nft_set_ext_expr(ext)); + nf_tables_expr_destroy(ctx, nft_set_ext_expr(ext)); kfree(elem); } @@ -3973,8 +4195,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( - nla[NFTA_SET_ELEM_TIMEOUT]))); + err = nf_msecs_to_jiffies64(nla[NFTA_SET_ELEM_TIMEOUT], + &timeout); + if (err) + return err; } else if (set->flags & NFT_SET_TIMEOUT) { timeout = set->timeout; } @@ -3999,8 +4223,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -EINVAL; goto err2; } - obj = nf_tables_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF], - set->objtype, genmask); + obj = nft_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF], + set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); goto err2; @@ -4035,6 +4259,12 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, d2.type, d2.len); if (err < 0) goto err3; + + if (d2.type == NFT_DATA_VERDICT && + (data.verdict.code == NFT_GOTO || + data.verdict.code == NFT_JUMP)) + nft_validate_state_update(ctx->net, + NFT_VALIDATE_NEED); } nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, d2.len); @@ -4134,12 +4364,13 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; - int rem, err = 0; + int rem, err; if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, + genmask); if (err < 0) return err; @@ -4154,9 +4385,13 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags); if (err < 0) - break; + return err; } - return err; + + if (net->nft.validate_state == NFT_VALIDATE_DO) + return nft_table_validate(net, ctx.table); + + return 0; } /** @@ -4327,12 +4562,12 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, + genmask); if (err < 0) return err; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], - genmask); + set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) @@ -4420,13 +4655,13 @@ void nft_unregister_obj(struct nft_object_type *obj_type) } EXPORT_SYMBOL_GPL(nft_unregister_obj); -struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, - const struct nlattr *nla, - u32 objtype, u8 genmask) +struct nft_object *nft_obj_lookup(const struct nft_table *table, + const struct nlattr *nla, u32 objtype, + u8 genmask) { struct nft_object *obj; - list_for_each_entry(obj, &table->objects, list) { + list_for_each_entry_rcu(obj, &table->objects, list) { if (!nla_strcmp(nla, obj->name) && objtype == obj->ops->type->type && nft_active_genmask(obj, genmask)) @@ -4434,11 +4669,11 @@ struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, } return ERR_PTR(-ENOENT); } -EXPORT_SYMBOL_GPL(nf_tables_obj_lookup); +EXPORT_SYMBOL_GPL(nft_obj_lookup); -static struct nft_object *nf_tables_obj_lookup_byhandle(const struct nft_table *table, - const struct nlattr *nla, - u32 objtype, u8 genmask) +static struct nft_object *nft_obj_lookup_byhandle(const struct nft_table *table, + const struct nlattr *nla, + u32 objtype, u8 genmask) { struct nft_object *obj; @@ -4582,22 +4817,25 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, !nla[NFTA_OBJ_DATA]) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); + } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); - if (err != -ENOENT) + if (err != -ENOENT) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return err; - + } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return -EEXIST; - + } return 0; } @@ -4632,7 +4870,7 @@ err3: kfree(obj->name); err2: if (obj->ops->destroy) - obj->ops->destroy(obj); + obj->ops->destroy(&ctx, obj); kfree(obj); err1: module_put(type->owner); @@ -4753,12 +4991,12 @@ nft_obj_filter_alloc(const struct nlattr * const nla[]) { struct nft_obj_filter *filter; - filter = kzalloc(sizeof(*filter), GFP_KERNEL); + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); if (!filter) return ERR_PTR(-ENOMEM); if (nla[NFTA_OBJ_TABLE]) { - filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_KERNEL); + filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); if (!filter->table) { kfree(filter); return ERR_PTR(-ENOMEM); @@ -4770,6 +5008,7 @@ nft_obj_filter_alloc(const struct nlattr * const nla[]) return filter; } +/* called with rcu_read_lock held */ static int nf_tables_getobj(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -4789,6 +5028,7 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, struct netlink_dump_control c = { .dump = nf_tables_dump_obj, .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, }; if (nla[NFTA_OBJ_TABLE] || @@ -4801,24 +5041,27 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, c.data = filter; } - return netlink_dump_start(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } if (!nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_TYPE]) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); + } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); - if (IS_ERR(obj)) + obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + if (IS_ERR(obj)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return PTR_ERR(obj); + } - skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; @@ -4837,10 +5080,10 @@ err: return err; } -static void nft_obj_destroy(struct nft_object *obj) +static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { if (obj->ops->destroy) - obj->ops->destroy(obj); + obj->ops->destroy(ctx, obj); module_put(obj->ops->type->owner); kfree(obj->name); @@ -4855,6 +5098,7 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; + const struct nlattr *attr; struct nft_table *table; struct nft_object *obj; struct nft_ctx ctx; @@ -4864,22 +5108,29 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, (!nla[NFTA_OBJ_NAME] && !nla[NFTA_OBJ_HANDLE])) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); + } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - if (nla[NFTA_OBJ_HANDLE]) - obj = nf_tables_obj_lookup_byhandle(table, nla[NFTA_OBJ_HANDLE], - objtype, genmask); - else - obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], - objtype, genmask); - if (IS_ERR(obj)) + if (nla[NFTA_OBJ_HANDLE]) { + attr = nla[NFTA_OBJ_HANDLE]; + obj = nft_obj_lookup_byhandle(table, attr, objtype, genmask); + } else { + attr = nla[NFTA_OBJ_NAME]; + obj = nft_obj_lookup(table, attr, objtype, genmask); + } + + if (IS_ERR(obj)) { + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(obj); - if (obj->use > 0) + } + if (obj->use > 0) { + NL_SET_BAD_ATTR(extack, attr); return -EBUSY; + } nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); @@ -4950,24 +5201,23 @@ static const struct nla_policy nft_flowtable_policy[NFTA_FLOWTABLE_MAX + 1] = { [NFTA_FLOWTABLE_HANDLE] = { .type = NLA_U64 }, }; -struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table, - const struct nlattr *nla, - u8 genmask) +struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, + const struct nlattr *nla, u8 genmask) { struct nft_flowtable *flowtable; - list_for_each_entry(flowtable, &table->flowtables, list) { + list_for_each_entry_rcu(flowtable, &table->flowtables, list) { if (!nla_strcmp(nla, flowtable->name) && nft_active_genmask(flowtable, genmask)) return flowtable; } return ERR_PTR(-ENOENT); } -EXPORT_SYMBOL_GPL(nf_tables_flowtable_lookup); +EXPORT_SYMBOL_GPL(nft_flowtable_lookup); static struct nft_flowtable * -nf_tables_flowtable_lookup_byhandle(const struct nft_table *table, - const struct nlattr *nla, u8 genmask) +nft_flowtable_lookup_byhandle(const struct nft_table *table, + const struct nlattr *nla, u8 genmask) { struct nft_flowtable *flowtable; @@ -5066,7 +5316,7 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx, flowtable->ops[i].pf = NFPROTO_NETDEV; flowtable->ops[i].hooknum = hooknum; flowtable->ops[i].priority = priority; - flowtable->ops[i].priv = &flowtable->data.rhashtable; + flowtable->ops[i].priv = &flowtable->data; flowtable->ops[i].hook = flowtable->data.type->hook; flowtable->ops[i].dev = dev_array[i]; flowtable->dev_name[i] = kstrdup(dev_array[i]->name, @@ -5107,23 +5357,6 @@ static const struct nf_flowtable_type *nft_flowtable_type_get(u8 family) return ERR_PTR(-ENOENT); } -void nft_flow_table_iterate(struct net *net, - void (*iter)(struct nf_flowtable *flowtable, void *data), - void *data) -{ - struct nft_flowtable *flowtable; - const struct nft_table *table; - - nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_for_each_entry(table, &net->nft.tables, list) { - list_for_each_entry(flowtable, &table->flowtables, list) { - iter(&flowtable->data, data); - } - } - nfnl_unlock(NFNL_SUBSYS_NFTABLES); -} -EXPORT_SYMBOL_GPL(nft_flow_table_iterate); - static void nft_unregister_flowtable_net_hooks(struct net *net, struct nft_flowtable *flowtable) { @@ -5157,20 +5390,26 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, !nla[NFTA_FLOWTABLE_HOOK]) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], - family, genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, + genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); + } - flowtable = nf_tables_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], - genmask); + flowtable = nft_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], + genmask); if (IS_ERR(flowtable)) { err = PTR_ERR(flowtable); - if (err != -ENOENT) + if (err != -ENOENT) { + NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return err; + } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return -EEXIST; + } return 0; } @@ -5197,14 +5436,14 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, } flowtable->data.type = type; - err = rhashtable_init(&flowtable->data.rhashtable, type->params); + err = type->init(&flowtable->data); if (err < 0) goto err3; err = nf_tables_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], flowtable); if (err < 0) - goto err3; + goto err4; for (i = 0; i < flowtable->ops_len; i++) { if (!flowtable->ops[i].dev) @@ -5218,37 +5457,35 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, if (flowtable->ops[i].dev == ft->ops[k].dev && flowtable->ops[i].pf == ft->ops[k].pf) { err = -EBUSY; - goto err4; + goto err5; } } } err = nf_register_net_hook(net, &flowtable->ops[i]); if (err < 0) - goto err4; + goto err5; } err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (err < 0) - goto err5; - - INIT_DEFERRABLE_WORK(&flowtable->data.gc_work, type->gc); - queue_delayed_work(system_power_efficient_wq, - &flowtable->data.gc_work, HZ); + goto err6; list_add_tail_rcu(&flowtable->list, &table->flowtables); table->use++; return 0; -err5: +err6: i = flowtable->ops_len; -err4: +err5: for (k = i - 1; k >= 0; k--) { kfree(flowtable->dev_name[k]); nf_unregister_net_hook(net, &flowtable->ops[k]); } kfree(flowtable->ops); +err4: + flowtable->data.type->free(&flowtable->data); err3: module_put(type->owner); err2: @@ -5268,6 +5505,7 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; + const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; @@ -5276,23 +5514,29 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, !nla[NFTA_FLOWTABLE_HANDLE])) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], - family, genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, + genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); + } - if (nla[NFTA_FLOWTABLE_HANDLE]) - flowtable = nf_tables_flowtable_lookup_byhandle(table, - nla[NFTA_FLOWTABLE_HANDLE], - genmask); - else - flowtable = nf_tables_flowtable_lookup(table, - nla[NFTA_FLOWTABLE_NAME], - genmask); - if (IS_ERR(flowtable)) - return PTR_ERR(flowtable); - if (flowtable->use > 0) + if (nla[NFTA_FLOWTABLE_HANDLE]) { + attr = nla[NFTA_FLOWTABLE_HANDLE]; + flowtable = nft_flowtable_lookup_byhandle(table, attr, genmask); + } else { + attr = nla[NFTA_FLOWTABLE_NAME]; + flowtable = nft_flowtable_lookup(table, attr, genmask); + } + + if (IS_ERR(flowtable)) { + NL_SET_BAD_ATTR(extack, attr); + return PTR_ERR(flowtable); + } + if (flowtable->use > 0) { + NL_SET_BAD_ATTR(extack, attr); return -EBUSY; + } nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); @@ -5423,13 +5667,13 @@ nft_flowtable_filter_alloc(const struct nlattr * const nla[]) { struct nft_flowtable_filter *filter; - filter = kzalloc(sizeof(*filter), GFP_KERNEL); + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); if (!filter) return ERR_PTR(-ENOMEM); if (nla[NFTA_FLOWTABLE_TABLE]) { filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], - GFP_KERNEL); + GFP_ATOMIC); if (!filter->table) { kfree(filter); return ERR_PTR(-ENOMEM); @@ -5438,6 +5682,7 @@ nft_flowtable_filter_alloc(const struct nlattr * const nla[]) return filter; } +/* called with rcu_read_lock held */ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, @@ -5456,6 +5701,7 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, struct netlink_dump_control c = { .dump = nf_tables_dump_flowtable, .done = nf_tables_dump_flowtable_done, + .module = THIS_MODULE, }; if (nla[NFTA_FLOWTABLE_TABLE]) { @@ -5467,23 +5713,23 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, c.data = filter; } - return netlink_dump_start(nlsk, skb, nlh, &c); + return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } if (!nla[NFTA_FLOWTABLE_NAME]) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], - family, genmask); + table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, + genmask); if (IS_ERR(table)) return PTR_ERR(table); - flowtable = nf_tables_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], - genmask); + flowtable = nft_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], + genmask); if (IS_ERR(flowtable)) return PTR_ERR(flowtable); - skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) return -ENOMEM; @@ -5532,11 +5778,9 @@ err: static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { - cancel_delayed_work_sync(&flowtable->data.gc_work); kfree(flowtable->ops); kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); - rhashtable_destroy(&flowtable->data.rhashtable); module_put(flowtable->data.type->owner); } @@ -5649,7 +5893,7 @@ static int nf_tables_getgen(struct net *net, struct sock *nlsk, struct sk_buff *skb2; int err; - skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb2 == NULL) return -ENOMEM; @@ -5671,7 +5915,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_table_policy, }, [NFT_MSG_GETTABLE] = { - .call = nf_tables_gettable, + .call_rcu = nf_tables_gettable, .attr_count = NFTA_TABLE_MAX, .policy = nft_table_policy, }, @@ -5686,7 +5930,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_chain_policy, }, [NFT_MSG_GETCHAIN] = { - .call = nf_tables_getchain, + .call_rcu = nf_tables_getchain, .attr_count = NFTA_CHAIN_MAX, .policy = nft_chain_policy, }, @@ -5701,7 +5945,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_rule_policy, }, [NFT_MSG_GETRULE] = { - .call = nf_tables_getrule, + .call_rcu = nf_tables_getrule, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, @@ -5716,7 +5960,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_set_policy, }, [NFT_MSG_GETSET] = { - .call = nf_tables_getset, + .call_rcu = nf_tables_getset, .attr_count = NFTA_SET_MAX, .policy = nft_set_policy, }, @@ -5731,7 +5975,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETSETELEM] = { - .call = nf_tables_getsetelem, + .call_rcu = nf_tables_getsetelem, .attr_count = NFTA_SET_ELEM_LIST_MAX, .policy = nft_set_elem_list_policy, }, @@ -5741,7 +5985,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_set_elem_list_policy, }, [NFT_MSG_GETGEN] = { - .call = nf_tables_getgen, + .call_rcu = nf_tables_getgen, }, [NFT_MSG_NEWOBJ] = { .call_batch = nf_tables_newobj, @@ -5749,7 +5993,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ] = { - .call = nf_tables_getobj, + .call_rcu = nf_tables_getobj, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, @@ -5759,7 +6003,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { - .call = nf_tables_getobj, + .call_rcu = nf_tables_getobj, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, }, @@ -5769,7 +6013,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_flowtable_policy, }, [NFT_MSG_GETFLOWTABLE] = { - .call = nf_tables_getflowtable, + .call_rcu = nf_tables_getflowtable, .attr_count = NFTA_FLOWTABLE_MAX, .policy = nft_flowtable_policy, }, @@ -5780,12 +6024,41 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { }, }; +static int nf_tables_validate(struct net *net) +{ + struct nft_table *table; + + switch (net->nft.validate_state) { + case NFT_VALIDATE_SKIP: + break; + case NFT_VALIDATE_NEED: + nft_validate_state_update(net, NFT_VALIDATE_DO); + /* fall through */ + case NFT_VALIDATE_DO: + list_for_each_entry(table, &net->nft.tables, list) { + if (nft_table_validate(net, table) < 0) + return -EAGAIN; + } + break; + } + + return 0; +} + static void nft_chain_commit_update(struct nft_trans *trans) { struct nft_base_chain *basechain; - if (nft_trans_chain_name(trans)) + if (nft_trans_chain_name(trans)) { + rhltable_remove(&trans->ctx.table->chains_ht, + &trans->ctx.chain->rhlhead, + nft_chain_ht_params); swap(trans->ctx.chain->name, nft_trans_chain_name(trans)); + rhltable_insert_key(&trans->ctx.table->chains_ht, + trans->ctx.chain->name, + &trans->ctx.chain->rhlhead, + nft_chain_ht_params); + } if (!nft_is_base_chain(trans->ctx.chain)) return; @@ -5817,11 +6090,12 @@ static void nft_commit_release(struct nft_trans *trans) nft_set_destroy(nft_trans_set(trans)); break; case NFT_MSG_DELSETELEM: - nf_tables_set_elem_destroy(nft_trans_elem_set(trans), + nf_tables_set_elem_destroy(&trans->ctx, + nft_trans_elem_set(trans), nft_trans_elem(trans).priv); break; case NFT_MSG_DELOBJ: - nft_obj_destroy(nft_trans_obj(trans)); + nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); break; case NFT_MSG_DELFLOWTABLE: nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); @@ -5845,21 +6119,175 @@ static void nf_tables_commit_release(struct net *net) } } +static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *chain) +{ + struct nft_rule *rule; + unsigned int alloc = 0; + int i; + + /* already handled or inactive chain? */ + if (chain->rules_next || !nft_is_active_next(net, chain)) + return 0; + + rule = list_entry(&chain->rules, struct nft_rule, list); + i = 0; + + list_for_each_entry_continue(rule, &chain->rules, list) { + if (nft_is_active_next(net, rule)) + alloc++; + } + + chain->rules_next = nf_tables_chain_alloc_rules(chain, alloc); + if (!chain->rules_next) + return -ENOMEM; + + list_for_each_entry_continue(rule, &chain->rules, list) { + if (nft_is_active_next(net, rule)) + chain->rules_next[i++] = rule; + } + + chain->rules_next[i] = NULL; + return 0; +} + +static void nf_tables_commit_chain_prepare_cancel(struct net *net) +{ + struct nft_trans *trans, *next; + + list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + struct nft_chain *chain = trans->ctx.chain; + + if (trans->msg_type == NFT_MSG_NEWRULE || + trans->msg_type == NFT_MSG_DELRULE) { + kvfree(chain->rules_next); + chain->rules_next = NULL; + } + } +} + +static void __nf_tables_commit_chain_free_rules_old(struct rcu_head *h) +{ + struct nft_rules_old *o = container_of(h, struct nft_rules_old, h); + + kvfree(o->start); +} + +static void nf_tables_commit_chain_free_rules_old(struct nft_rule **rules) +{ + struct nft_rule **r = rules; + struct nft_rules_old *old; + + while (*r) + r++; + + r++; /* rcu_head is after end marker */ + old = (void *) r; + old->start = rules; + + call_rcu(&old->h, __nf_tables_commit_chain_free_rules_old); +} + +static void nf_tables_commit_chain_active(struct net *net, struct nft_chain *chain) +{ + struct nft_rule **g0, **g1; + bool next_genbit; + + next_genbit = nft_gencursor_next(net); + + g0 = rcu_dereference_protected(chain->rules_gen_0, + lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + g1 = rcu_dereference_protected(chain->rules_gen_1, + lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + + /* No changes to this chain? */ + if (chain->rules_next == NULL) { + /* chain had no change in last or next generation */ + if (g0 == g1) + return; + /* + * chain had no change in this generation; make sure next + * one uses same rules as current generation. + */ + if (next_genbit) { + rcu_assign_pointer(chain->rules_gen_1, g0); + nf_tables_commit_chain_free_rules_old(g1); + } else { + rcu_assign_pointer(chain->rules_gen_0, g1); + nf_tables_commit_chain_free_rules_old(g0); + } + + return; + } + + if (next_genbit) + rcu_assign_pointer(chain->rules_gen_1, chain->rules_next); + else + rcu_assign_pointer(chain->rules_gen_0, chain->rules_next); + + chain->rules_next = NULL; + + if (g0 == g1) + return; + + if (next_genbit) + nf_tables_commit_chain_free_rules_old(g1); + else + nf_tables_commit_chain_free_rules_old(g0); +} + +static void nft_chain_del(struct nft_chain *chain) +{ + struct nft_table *table = chain->table; + + WARN_ON_ONCE(rhltable_remove(&table->chains_ht, &chain->rhlhead, + nft_chain_ht_params)); + list_del_rcu(&chain->list); +} + static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nft_trans *trans, *next; struct nft_trans_elem *te; + struct nft_chain *chain; + struct nft_table *table; - /* Bump generation counter, invalidate any dump in progress */ - while (++net->nft.base_seq == 0); + /* 0. Validate ruleset, otherwise roll back for error reporting. */ + if (nf_tables_validate(net) < 0) + return -EAGAIN; - /* A new generation has just started */ - net->nft.gencursor = nft_gencursor_next(net); + /* 1. Allocate space for next generation rules_gen_X[] */ + list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + int ret; + + if (trans->msg_type == NFT_MSG_NEWRULE || + trans->msg_type == NFT_MSG_DELRULE) { + chain = trans->ctx.chain; + + ret = nf_tables_commit_chain_prepare(net, chain); + if (ret < 0) { + nf_tables_commit_chain_prepare_cancel(net); + return ret; + } + } + } + + /* step 2. Make rules_gen_X visible to packet path */ + list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(chain, &table->chains, list) { + if (!nft_is_active_next(net, chain)) + continue; + nf_tables_commit_chain_active(net, chain); + } + } - /* Make sure all packets have left the previous generation before - * purging old rules. + /* + * Bump generation counter, invalidate any dump in progress. + * Cannot fail after this point. */ - synchronize_rcu(); + while (++net->nft.base_seq == 0); + + /* step 3. Start new generation, rules_gen_X now in use. */ + net->nft.gencursor = nft_gencursor_next(net); list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { switch (trans->msg_type) { @@ -5890,7 +6318,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELCHAIN: - list_del_rcu(&trans->ctx.chain->list); + nft_chain_del(trans->ctx.chain); nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, @@ -6001,7 +6429,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) nft_trans_elem(trans).priv, true); break; case NFT_MSG_NEWOBJ: - nft_obj_destroy(nft_trans_obj(trans)); + nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); break; case NFT_MSG_NEWFLOWTABLE: nf_tables_flowtable_destroy(nft_trans_flowtable(trans)); @@ -6041,7 +6469,7 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); } else { trans->ctx.table->use--; - list_del_rcu(&trans->ctx.chain->list); + nft_chain_del(trans->ctx.chain); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, trans->ctx.chain); @@ -6121,6 +6549,11 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) return 0; } +static void nf_tables_cleanup(struct net *net) +{ + nft_validate_state_update(net, NFT_VALIDATE_SKIP); +} + static bool nf_tables_valid_genid(struct net *net, u32 genid) { return net->nft.base_seq == genid; @@ -6133,6 +6566,7 @@ static const struct nfnetlink_subsystem nf_tables_subsys = { .cb = nf_tables_cb, .commit = nf_tables_commit, .abort = nf_tables_abort, + .cleanup = nf_tables_cleanup, .valid_genid = nf_tables_valid_genid, }; @@ -6216,19 +6650,18 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, list_for_each_entry(rule, &chain->rules, list) { nft_rule_for_each_expr(expr, last, rule) { - const struct nft_data *data = NULL; + struct nft_immediate_expr *priv; + const struct nft_data *data; int err; - if (!expr->ops->validate) + if (strcmp(expr->ops->type->name, "immediate")) continue; - err = expr->ops->validate(ctx, expr, &data); - if (err < 0) - return err; - - if (data == NULL) + priv = nft_expr_priv(expr); + if (priv->dreg != NFT_REG_VERDICT) continue; + data = &priv->data; switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: @@ -6461,8 +6894,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, case NFT_GOTO: if (!tb[NFTA_VERDICT_CHAIN]) return -EINVAL; - chain = nf_tables_chain_lookup(ctx->table, - tb[NFTA_VERDICT_CHAIN], genmask); + chain = nft_chain_lookup(ctx->table, tb[NFTA_VERDICT_CHAIN], + genmask); if (IS_ERR(chain)) return PTR_ERR(chain); if (nft_is_base_chain(chain)) @@ -6638,7 +7071,7 @@ int __nft_release_basechain(struct nft_ctx *ctx) ctx->chain->use--; nf_tables_rule_release(ctx, rule); } - list_del(&ctx->chain->list); + nft_chain_del(ctx->chain); ctx->table->use--; nf_tables_chain_destroy(ctx); @@ -6690,11 +7123,11 @@ static void __nft_release_tables(struct net *net) list_for_each_entry_safe(obj, ne, &table->objects, list) { list_del(&obj->list); table->use--; - nft_obj_destroy(obj); + nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { ctx.chain = chain; - list_del(&chain->list); + nft_chain_del(chain); table->use--; nf_tables_chain_destroy(&ctx); } @@ -6708,6 +7141,8 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&net->nft.tables); INIT_LIST_HEAD(&net->nft.commit_list); net->nft.base_seq = 1; + net->nft.validate_state = NFT_VALIDATE_SKIP; + return 0; } diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 40e744572283c..deff10adef9c4 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -23,25 +23,9 @@ #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_log.h> -static const char *const comments[__NFT_TRACETYPE_MAX] = { - [NFT_TRACETYPE_POLICY] = "policy", - [NFT_TRACETYPE_RETURN] = "return", - [NFT_TRACETYPE_RULE] = "rule", -}; - -static const struct nf_loginfo trace_loginfo = { - .type = NF_LOG_TYPE_LOG, - .u = { - .log = { - .level = LOGLEVEL_WARNING, - .logflags = NF_LOG_DEFAULT_MASK, - }, - }, -}; - static noinline void __nft_trace_packet(struct nft_traceinfo *info, const struct nft_chain *chain, - int rulenum, enum nft_trace_types type) + enum nft_trace_types type) { const struct nft_pktinfo *pkt = info->pkt; @@ -52,22 +36,16 @@ static noinline void __nft_trace_packet(struct nft_traceinfo *info, info->type = type; nft_trace_notify(info); - - nf_log_trace(nft_net(pkt), nft_pf(pkt), nft_hook(pkt), pkt->skb, - nft_in(pkt), nft_out(pkt), &trace_loginfo, - "TRACE: %s:%s:%s:%u ", - chain->table->name, chain->name, comments[type], rulenum); } static inline void nft_trace_packet(struct nft_traceinfo *info, const struct nft_chain *chain, const struct nft_rule *rule, - int rulenum, enum nft_trace_types type) { if (static_branch_unlikely(&nft_trace_enabled)) { info->rule = rule; - __nft_trace_packet(info, chain, rulenum, type); + __nft_trace_packet(info, chain, type); } } @@ -139,8 +117,7 @@ static noinline void nft_update_chain_stats(const struct nft_chain *chain, struct nft_jumpstack { const struct nft_chain *chain; - const struct nft_rule *rule; - int rulenum; + struct nft_rule *const *rules; }; unsigned int @@ -148,31 +125,29 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) { const struct nft_chain *chain = priv, *basechain = chain; const struct net *net = nft_net(pkt); + struct nft_rule *const *rules; const struct nft_rule *rule; const struct nft_expr *expr, *last; struct nft_regs regs; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; - int rulenum; - unsigned int gencursor = nft_genmask_cur(net); + bool genbit = READ_ONCE(net->nft.gencursor); struct nft_traceinfo info; info.trace = false; if (static_branch_unlikely(&nft_trace_enabled)) nft_trace_init(&info, pkt, ®s.verdict, basechain); do_chain: - rulenum = 0; - rule = list_entry(&chain->rules, struct nft_rule, list); + if (genbit) + rules = rcu_dereference(chain->rules_gen_1); + else + rules = rcu_dereference(chain->rules_gen_0); + next_rule: + rule = *rules; regs.verdict.code = NFT_CONTINUE; - list_for_each_entry_continue_rcu(rule, &chain->rules, list) { - - /* This rule is not active, skip. */ - if (unlikely(rule->genmask & gencursor)) - continue; - - rulenum++; - + for (; *rules ; rules++) { + rule = *rules; nft_rule_for_each_expr(expr, last, rule) { if (expr->ops == &nft_cmp_fast_ops) nft_cmp_fast_eval(expr, ®s); @@ -190,7 +165,7 @@ next_rule: continue; case NFT_CONTINUE: nft_trace_packet(&info, chain, rule, - rulenum, NFT_TRACETYPE_RULE); + NFT_TRACETYPE_RULE); continue; } break; @@ -202,7 +177,7 @@ next_rule: case NF_QUEUE: case NF_STOLEN: nft_trace_packet(&info, chain, rule, - rulenum, NFT_TRACETYPE_RULE); + NFT_TRACETYPE_RULE); return regs.verdict.code; } @@ -210,22 +185,20 @@ next_rule: case NFT_JUMP: BUG_ON(stackptr >= NFT_JUMP_STACK_SIZE); jumpstack[stackptr].chain = chain; - jumpstack[stackptr].rule = rule; - jumpstack[stackptr].rulenum = rulenum; + jumpstack[stackptr].rules = rules + 1; stackptr++; /* fall through */ case NFT_GOTO: nft_trace_packet(&info, chain, rule, - rulenum, NFT_TRACETYPE_RULE); + NFT_TRACETYPE_RULE); chain = regs.verdict.chain; goto do_chain; case NFT_CONTINUE: - rulenum++; /* fall through */ case NFT_RETURN: nft_trace_packet(&info, chain, rule, - rulenum, NFT_TRACETYPE_RETURN); + NFT_TRACETYPE_RETURN); break; default: WARN_ON(1); @@ -234,13 +207,11 @@ next_rule: if (stackptr > 0) { stackptr--; chain = jumpstack[stackptr].chain; - rule = jumpstack[stackptr].rule; - rulenum = jumpstack[stackptr].rulenum; + rules = jumpstack[stackptr].rules; goto next_rule; } - nft_trace_packet(&info, basechain, NULL, -1, - NFT_TRACETYPE_POLICY); + nft_trace_packet(&info, basechain, NULL, NFT_TRACETYPE_POLICY); if (static_branch_unlikely(&nft_counters_enabled)) nft_update_chain_stats(basechain, pkt); @@ -258,6 +229,9 @@ static struct nft_expr_type *nft_basic_types[] = { &nft_payload_type, &nft_dynset_type, &nft_range_type, + &nft_meta_type, + &nft_rt_type, + &nft_exthdr_type, }; int __init nf_tables_core_module_init(void) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 03ead8a9e90cc..4d0da7042affb 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -25,6 +25,7 @@ #include <linux/uaccess.h> #include <net/sock.h> #include <linux/init.h> +#include <linux/sched/signal.h> #include <net/netlink.h> #include <linux/netfilter/nfnetlink.h> @@ -37,6 +38,8 @@ MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER); rcu_dereference_protected(table[(id)].subsys, \ lockdep_nfnl_is_held((id))) +#define NFNL_MAX_ATTR_COUNT 32 + static struct { struct mutex mutex; const struct nfnetlink_subsystem __rcu *subsys; @@ -76,6 +79,13 @@ EXPORT_SYMBOL_GPL(lockdep_nfnl_is_held); int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n) { + u8 cb_id; + + /* Sanity-check attr_count size to avoid stack buffer overflow. */ + for (cb_id = 0; cb_id < n->cb_count; cb_id++) + if (WARN_ON(n->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT)) + return -EINVAL; + nfnl_lock(n->subsys_id); if (table[n->subsys_id].subsys) { nfnl_unlock(n->subsys_id); @@ -185,11 +195,17 @@ replay: { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); - struct nlattr *cda[ss->cb[cb_id].attr_count + 1]; + struct nlattr *cda[NFNL_MAX_ATTR_COUNT + 1]; struct nlattr *attr = (void *)nlh + min_len; int attrlen = nlh->nlmsg_len - min_len; __u8 subsys_id = NFNL_SUBSYS_ID(type); + /* Sanity-check NFNL_MAX_ATTR_COUNT */ + if (ss->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT) { + rcu_read_unlock(); + return -ENOMEM; + } + err = nla_parse(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy, extack); if (err < 0) { @@ -330,6 +346,13 @@ replay: while (skb->len >= nlmsg_total_size(0)) { int msglen, type; + if (fatal_signal_pending(current)) { + nfnl_err_reset(&err_list); + err = -EINTR; + status = NFNL_BATCH_FAILURE; + goto done; + } + memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; @@ -379,10 +402,16 @@ replay: { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); - struct nlattr *cda[ss->cb[cb_id].attr_count + 1]; + struct nlattr *cda[NFNL_MAX_ATTR_COUNT + 1]; struct nlattr *attr = (void *)nlh + min_len; int attrlen = nlh->nlmsg_len - min_len; + /* Sanity-check NFTA_MAX_ATTR */ + if (ss->cb[cb_id].attr_count > NFNL_MAX_ATTR_COUNT) { + err = -ENOMEM; + goto ack; + } + err = nla_parse(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy, NULL); if (err < 0) @@ -441,10 +470,19 @@ done: kfree_skb(skb); goto replay; } else if (status == NFNL_BATCH_DONE) { - ss->commit(net, oskb); + err = ss->commit(net, oskb); + if (err == -EAGAIN) { + status |= NFNL_BATCH_REPLAY; + goto done; + } else if (err) { + ss->abort(net, oskb); + netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); + } } else { ss->abort(net, oskb); } + if (ss->cleanup) + ss->cleanup(net); nfnl_err_deliver(&err_list, oskb); nfnl_unlock(subsys_id); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index c14822b9729ff..332c69d27b478 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -37,7 +37,6 @@ #include <net/sock.h> #include <net/netfilter/nf_log.h> #include <net/netns/generic.h> -#include <net/netfilter/nfnetlink_log.h> #include <linux/atomic.h> #include <linux/refcount.h> @@ -47,6 +46,7 @@ #include "../bridge/br_private.h" #endif +#define NFULNL_COPY_DISABLED 0xff #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ @@ -618,7 +618,7 @@ static const struct nf_loginfo default_loginfo = { }; /* log handler for internal netfilter logging api */ -void +static void nfulnl_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, @@ -633,7 +633,7 @@ nfulnl_log_packet(struct net *net, struct nfulnl_instance *inst; const struct nf_loginfo *li; unsigned int qthreshold; - unsigned int plen; + unsigned int plen = 0; struct nfnl_log_net *log = nfnl_log_pernet(net); const struct nfnl_ct_hook *nfnl_ct = NULL; struct nf_conn *ct = NULL; @@ -648,7 +648,6 @@ nfulnl_log_packet(struct net *net, if (!inst) return; - plen = 0; if (prefix) plen = strlen(prefix) + 1; @@ -760,7 +759,6 @@ alloc_failure: /* FIXME: statistics */ goto unlock_and_release; } -EXPORT_SYMBOL_GPL(nfulnl_log_packet); static int nfulnl_rcv_nl_event(struct notifier_block *this, diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 494a9ab35cb67..4ccd2988f9db6 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -227,6 +227,25 @@ find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) return entry; } +static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) +{ + struct nf_ct_hook *ct_hook; + int err; + + if (verdict == NF_ACCEPT || + verdict == NF_STOP) { + rcu_read_lock(); + ct_hook = rcu_dereference(nf_ct_hook); + if (ct_hook) { + err = ct_hook->update(entry->state.net, entry->skb); + if (err < 0) + verdict = NF_DROP; + } + rcu_read_unlock(); + } + nf_reinject(entry, verdict); +} + static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) { @@ -237,7 +256,7 @@ nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) if (!cmpfn || cmpfn(entry, data)) { list_del(&entry->list); queue->queue_total--; - nf_reinject(entry, NF_DROP); + nfqnl_reinject(entry, NF_DROP); } } spin_unlock_bh(&queue->lock); @@ -686,7 +705,7 @@ err_out_free_nskb: err_out_unlock: spin_unlock_bh(&queue->lock); if (failopen) - nf_reinject(entry, NF_ACCEPT); + nfqnl_reinject(entry, NF_ACCEPT); err_out: return err; } @@ -1085,7 +1104,8 @@ static int nfqnl_recv_verdict_batch(struct net *net, struct sock *ctnl, list_for_each_entry_safe(entry, tmp, &batch_list, list) { if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); - nf_reinject(entry, verdict); + + nfqnl_reinject(entry, verdict); } return 0; } @@ -1208,7 +1228,7 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); - nf_reinject(entry, verdict); + nfqnl_reinject(entry, verdict); return 0; } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 1d99a1efdafcd..8d1ff654e5aff 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -611,10 +611,10 @@ nla_put_failure: return -1; } -static int nfnl_compat_get(struct net *net, struct sock *nfnl, - struct sk_buff *skb, const struct nlmsghdr *nlh, - const struct nlattr * const tb[], - struct netlink_ext_ack *extack) +static int nfnl_compat_get_rcu(struct net *net, struct sock *nfnl, + struct sk_buff *skb, const struct nlmsghdr *nlh, + const struct nlattr * const tb[], + struct netlink_ext_ack *extack) { int ret = 0, target; struct nfgenmsg *nfmsg; @@ -653,16 +653,21 @@ static int nfnl_compat_get(struct net *net, struct sock *nfnl, return -EINVAL; } + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + + rcu_read_unlock(); try_then_request_module(xt_find_revision(nfmsg->nfgen_family, name, rev, target, &ret), fmt, name); - if (ret < 0) - return ret; + goto out_put; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) - return -ENOMEM; + if (skb2 == NULL) { + ret = -ENOMEM; + goto out_put; + } /* include the best revision for this extension in the message */ if (nfnl_compat_fill_info(skb2, NETLINK_CB(skb).portid, @@ -672,14 +677,16 @@ static int nfnl_compat_get(struct net *net, struct sock *nfnl, nfmsg->nfgen_family, name, ret, target) <= 0) { kfree_skb(skb2); - return -ENOSPC; + goto out_put; } ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret > 0) ret = 0; - +out_put: + rcu_read_lock(); + module_put(THIS_MODULE); return ret == -EAGAIN ? -ENOBUFS : ret; } @@ -691,7 +698,7 @@ static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = { }; static const struct nfnl_callback nfnl_nft_compat_cb[NFNL_MSG_COMPAT_MAX] = { - [NFNL_MSG_COMPAT_GET] = { .call = nfnl_compat_get, + [NFNL_MSG_COMPAT_GET] = { .call_rcu = nfnl_compat_get_rcu, .attr_count = NFTA_COMPAT_MAX, .policy = nfnl_compat_policy_get }, }; diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c new file mode 100644 index 0000000000000..50c068d660e54 --- /dev/null +++ b/net/netfilter/nft_connlimit.c @@ -0,0 +1,297 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_count.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_tuple.h> +#include <net/netfilter/nf_conntrack_zones.h> + +struct nft_connlimit { + spinlock_t lock; + struct hlist_head hhead; + u32 limit; + bool invert; +}; + +static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, + struct nft_regs *regs, + const struct nft_pktinfo *pkt, + const struct nft_set_ext *ext) +{ + const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; + const struct nf_conntrack_tuple *tuple_ptr; + struct nf_conntrack_tuple tuple; + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct; + unsigned int count; + bool addit; + + tuple_ptr = &tuple; + + ct = nf_ct_get(pkt->skb, &ctinfo); + if (ct != NULL) { + tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + zone = nf_ct_zone(ct); + } else if (!nf_ct_get_tuplepr(pkt->skb, skb_network_offset(pkt->skb), + nft_pf(pkt), nft_net(pkt), &tuple)) { + regs->verdict.code = NF_DROP; + return; + } + + spin_lock_bh(&priv->lock); + count = nf_conncount_lookup(nft_net(pkt), &priv->hhead, tuple_ptr, zone, + &addit); + + if (!addit) + goto out; + + if (!nf_conncount_add(&priv->hhead, tuple_ptr)) { + regs->verdict.code = NF_DROP; + spin_unlock_bh(&priv->lock); + return; + } + count++; +out: + spin_unlock_bh(&priv->lock); + + if ((count > priv->limit) ^ priv->invert) { + regs->verdict.code = NFT_BREAK; + return; + } +} + +static int nft_connlimit_do_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_connlimit *priv) +{ + bool invert = false; + u32 flags, limit; + + if (!tb[NFTA_CONNLIMIT_COUNT]) + return -EINVAL; + + limit = ntohl(nla_get_be32(tb[NFTA_CONNLIMIT_COUNT])); + + if (tb[NFTA_CONNLIMIT_FLAGS]) { + flags = ntohl(nla_get_be32(tb[NFTA_CONNLIMIT_FLAGS])); + if (flags & ~NFT_CONNLIMIT_F_INV) + return -EOPNOTSUPP; + if (flags & NFT_CONNLIMIT_F_INV) + invert = true; + } + + spin_lock_init(&priv->lock); + INIT_HLIST_HEAD(&priv->hhead); + priv->limit = limit; + priv->invert = invert; + + return nf_ct_netns_get(ctx->net, ctx->family); +} + +static void nft_connlimit_do_destroy(const struct nft_ctx *ctx, + struct nft_connlimit *priv) +{ + nf_ct_netns_put(ctx->net, ctx->family); + nf_conncount_cache_free(&priv->hhead); +} + +static int nft_connlimit_do_dump(struct sk_buff *skb, + struct nft_connlimit *priv) +{ + if (nla_put_be32(skb, NFTA_CONNLIMIT_COUNT, htonl(priv->limit))) + goto nla_put_failure; + if (priv->invert && + nla_put_be32(skb, NFTA_CONNLIMIT_FLAGS, htonl(NFT_CONNLIMIT_F_INV))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static inline void nft_connlimit_obj_eval(struct nft_object *obj, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_connlimit *priv = nft_obj_data(obj); + + nft_connlimit_do_eval(priv, regs, pkt, NULL); +} + +static int nft_connlimit_obj_init(const struct nft_ctx *ctx, + const struct nlattr * const tb[], + struct nft_object *obj) +{ + struct nft_connlimit *priv = nft_obj_data(obj); + + return nft_connlimit_do_init(ctx, tb, priv); +} + +static void nft_connlimit_obj_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) +{ + struct nft_connlimit *priv = nft_obj_data(obj); + + nft_connlimit_do_destroy(ctx, priv); +} + +static int nft_connlimit_obj_dump(struct sk_buff *skb, + struct nft_object *obj, bool reset) +{ + struct nft_connlimit *priv = nft_obj_data(obj); + + return nft_connlimit_do_dump(skb, priv); +} + +static const struct nla_policy nft_connlimit_policy[NFTA_CONNLIMIT_MAX + 1] = { + [NFTA_CONNLIMIT_COUNT] = { .type = NLA_U32 }, + [NFTA_CONNLIMIT_FLAGS] = { .type = NLA_U32 }, +}; + +static struct nft_object_type nft_connlimit_obj_type; +static const struct nft_object_ops nft_connlimit_obj_ops = { + .type = &nft_connlimit_obj_type, + .size = sizeof(struct nft_connlimit), + .eval = nft_connlimit_obj_eval, + .init = nft_connlimit_obj_init, + .destroy = nft_connlimit_obj_destroy, + .dump = nft_connlimit_obj_dump, +}; + +static struct nft_object_type nft_connlimit_obj_type __read_mostly = { + .type = NFT_OBJECT_CONNLIMIT, + .ops = &nft_connlimit_obj_ops, + .maxattr = NFTA_CONNLIMIT_MAX, + .policy = nft_connlimit_policy, + .owner = THIS_MODULE, +}; + +static void nft_connlimit_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_connlimit *priv = nft_expr_priv(expr); + + nft_connlimit_do_eval(priv, regs, pkt, NULL); +} + +static int nft_connlimit_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + struct nft_connlimit *priv = nft_expr_priv(expr); + + return nft_connlimit_do_dump(skb, priv); +} + +static int nft_connlimit_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_connlimit *priv = nft_expr_priv(expr); + + return nft_connlimit_do_init(ctx, tb, priv); +} + +static void nft_connlimit_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_connlimit *priv = nft_expr_priv(expr); + + nft_connlimit_do_destroy(ctx, priv); +} + +static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src) +{ + struct nft_connlimit *priv_dst = nft_expr_priv(dst); + struct nft_connlimit *priv_src = nft_expr_priv(src); + + spin_lock_init(&priv_dst->lock); + INIT_HLIST_HEAD(&priv_dst->hhead); + priv_dst->limit = priv_src->limit; + priv_dst->invert = priv_src->invert; + + return 0; +} + +static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_connlimit *priv = nft_expr_priv(expr); + + nf_conncount_cache_free(&priv->hhead); +} + +static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr) +{ + struct nft_connlimit *priv = nft_expr_priv(expr); + bool addit, ret; + + spin_lock_bh(&priv->lock); + nf_conncount_lookup(net, &priv->hhead, NULL, &nf_ct_zone_dflt, &addit); + + ret = hlist_empty(&priv->hhead); + spin_unlock_bh(&priv->lock); + + return ret; +} + +static struct nft_expr_type nft_connlimit_type; +static const struct nft_expr_ops nft_connlimit_ops = { + .type = &nft_connlimit_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_connlimit)), + .eval = nft_connlimit_eval, + .init = nft_connlimit_init, + .destroy = nft_connlimit_destroy, + .clone = nft_connlimit_clone, + .destroy_clone = nft_connlimit_destroy_clone, + .dump = nft_connlimit_dump, + .gc = nft_connlimit_gc, +}; + +static struct nft_expr_type nft_connlimit_type __read_mostly = { + .name = "connlimit", + .ops = &nft_connlimit_ops, + .policy = nft_connlimit_policy, + .maxattr = NFTA_CONNLIMIT_MAX, + .flags = NFT_EXPR_STATEFUL | NFT_EXPR_GC, + .owner = THIS_MODULE, +}; + +static int __init nft_connlimit_module_init(void) +{ + int err; + + err = nft_register_obj(&nft_connlimit_obj_type); + if (err < 0) + return err; + + err = nft_register_expr(&nft_connlimit_type); + if (err < 0) + goto err1; + + return 0; +err1: + nft_unregister_obj(&nft_connlimit_obj_type); + return err; +} + +static void __exit nft_connlimit_module_exit(void) +{ + nft_unregister_expr(&nft_connlimit_type); + nft_unregister_obj(&nft_connlimit_obj_type); +} + +module_init(nft_connlimit_module_init); +module_exit(nft_connlimit_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso"); +MODULE_ALIAS_NFT_EXPR("connlimit"); +MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CONNLIMIT); diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index eefe3b4099252..a61d7edfc290d 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -96,7 +96,8 @@ static void nft_counter_do_destroy(struct nft_counter_percpu_priv *priv) free_percpu(priv->counter); } -static void nft_counter_obj_destroy(struct nft_object *obj) +static void nft_counter_obj_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) { struct nft_counter_percpu_priv *priv = nft_obj_data(obj); @@ -257,6 +258,7 @@ static const struct nft_expr_ops nft_counter_ops = { .eval = nft_counter_eval, .init = nft_counter_init, .destroy = nft_counter_destroy, + .destroy_clone = nft_counter_destroy, .dump = nft_counter_dump, .clone = nft_counter_clone, }; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 5c0de704bad5a..1435ffc5f57ed 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -826,7 +826,8 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx, return 0; } -static void nft_ct_helper_obj_destroy(struct nft_object *obj) +static void nft_ct_helper_obj_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) { struct nft_ct_helper_obj *priv = nft_obj_data(obj); diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 04863fad05ddd..4d49529cff615 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -36,7 +36,7 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, u64 timeout; void *elem; - if (set->size && !atomic_add_unless(&set->nelems, 1, set->size)) + if (!atomic_add_unless(&set->nelems, 1, set->size)) return NULL; timeout = priv->timeout ? : set->timeout; @@ -81,7 +81,7 @@ static void nft_dynset_eval(const struct nft_expr *expr, if (priv->op == NFT_DYNSET_OP_UPDATE && nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { timeout = priv->timeout ? : set->timeout; - *nft_set_ext_expiration(ext) = jiffies + timeout; + *nft_set_ext_expiration(ext) = get_jiffies_64() + timeout; } if (sexpr != NULL) @@ -195,6 +195,15 @@ static int nft_dynset_init(const struct nft_ctx *ctx, err = -EOPNOTSUPP; if (!(priv->expr->ops->type->flags & NFT_EXPR_STATEFUL)) goto err1; + + if (priv->expr->ops->type->flags & NFT_EXPR_GC) { + if (set->flags & NFT_SET_TIMEOUT) + goto err1; + if (!set->ops->gc_init) + goto err1; + set->ops->gc_init(set); + } + } else if (set->flags & NFT_SET_EVAL) return -EINVAL; @@ -216,6 +225,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (err < 0) goto err1; + if (set->size == 0) + set->size = 0xffff; + priv->set = set; return 0; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 47ec1046ad115..a940c9fd9045e 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -10,11 +10,10 @@ #include <asm/unaligned.h> #include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/tcp.h> @@ -353,7 +352,6 @@ static int nft_exthdr_dump_set(struct sk_buff *skb, const struct nft_expr *expr) return nft_exthdr_dump_common(skb, priv); } -static struct nft_expr_type nft_exthdr_type; static const struct nft_expr_ops nft_exthdr_ipv6_ops = { .type = &nft_exthdr_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), @@ -407,27 +405,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx, return ERR_PTR(-EOPNOTSUPP); } -static struct nft_expr_type nft_exthdr_type __read_mostly = { +struct nft_expr_type nft_exthdr_type __read_mostly = { .name = "exthdr", .select_ops = nft_exthdr_select_ops, .policy = nft_exthdr_policy, .maxattr = NFTA_EXTHDR_MAX, .owner = THIS_MODULE, }; - -static int __init nft_exthdr_module_init(void) -{ - return nft_register_expr(&nft_exthdr_type); -} - -static void __exit nft_exthdr_module_exit(void) -{ - nft_unregister_expr(&nft_exthdr_type); -} - -module_init(nft_exthdr_module_init); -module_exit(nft_exthdr_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_EXPR("exthdr"); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index b65829b2be228..d6bab8c3cbb02 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -142,9 +142,8 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, if (!tb[NFTA_FLOW_TABLE_NAME]) return -EINVAL; - flowtable = nf_tables_flowtable_lookup(ctx->table, - tb[NFTA_FLOW_TABLE_NAME], - genmask); + flowtable = nft_flowtable_lookup(ctx->table, tb[NFTA_FLOW_TABLE_NAME], + genmask); if (IS_ERR(flowtable)) return PTR_ERR(flowtable); diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index ce13a50b91893..8abb9891cdf22 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -12,8 +12,12 @@ #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> +#include <linux/ip.h> +#include <linux/ipv6.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_dup_netdev.h> +#include <net/neighbour.h> +#include <net/ip.h> struct nft_fwd_netdev { enum nft_registers sreg_dev:8; @@ -32,6 +36,8 @@ static void nft_fwd_netdev_eval(const struct nft_expr *expr, static const struct nla_policy nft_fwd_netdev_policy[NFTA_FWD_MAX + 1] = { [NFTA_FWD_SREG_DEV] = { .type = NLA_U32 }, + [NFTA_FWD_SREG_ADDR] = { .type = NLA_U32 }, + [NFTA_FWD_NFPROTO] = { .type = NLA_U32 }, }; static int nft_fwd_netdev_init(const struct nft_ctx *ctx, @@ -62,7 +68,133 @@ nla_put_failure: return -1; } +struct nft_fwd_neigh { + enum nft_registers sreg_dev:8; + enum nft_registers sreg_addr:8; + u8 nfproto; +}; + +static void nft_fwd_neigh_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_fwd_neigh *priv = nft_expr_priv(expr); + void *addr = ®s->data[priv->sreg_addr]; + int oif = regs->data[priv->sreg_dev]; + unsigned int verdict = NF_STOLEN; + struct sk_buff *skb = pkt->skb; + struct net_device *dev; + int neigh_table; + + switch (priv->nfproto) { + case NFPROTO_IPV4: { + struct iphdr *iph; + + if (skb->protocol != htons(ETH_P_IP)) { + verdict = NFT_BREAK; + goto out; + } + if (skb_try_make_writable(skb, sizeof(*iph))) { + verdict = NF_DROP; + goto out; + } + iph = ip_hdr(skb); + ip_decrease_ttl(iph); + neigh_table = NEIGH_ARP_TABLE; + break; + } + case NFPROTO_IPV6: { + struct ipv6hdr *ip6h; + + if (skb->protocol != htons(ETH_P_IPV6)) { + verdict = NFT_BREAK; + goto out; + } + if (skb_try_make_writable(skb, sizeof(*ip6h))) { + verdict = NF_DROP; + goto out; + } + ip6h = ipv6_hdr(skb); + ip6h->hop_limit--; + neigh_table = NEIGH_ND_TABLE; + break; + } + default: + verdict = NFT_BREAK; + goto out; + } + + dev = dev_get_by_index_rcu(nft_net(pkt), oif); + if (dev == NULL) + return; + + skb->dev = dev; + neigh_xmit(neigh_table, dev, addr, skb); +out: + regs->verdict.code = verdict; +} + +static int nft_fwd_neigh_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_fwd_neigh *priv = nft_expr_priv(expr); + unsigned int addr_len; + int err; + + if (!tb[NFTA_FWD_SREG_DEV] || + !tb[NFTA_FWD_SREG_ADDR] || + !tb[NFTA_FWD_NFPROTO]) + return -EINVAL; + + priv->sreg_dev = nft_parse_register(tb[NFTA_FWD_SREG_DEV]); + priv->sreg_addr = nft_parse_register(tb[NFTA_FWD_SREG_ADDR]); + priv->nfproto = ntohl(nla_get_be32(tb[NFTA_FWD_NFPROTO])); + + switch (priv->nfproto) { + case NFPROTO_IPV4: + addr_len = sizeof(struct in_addr); + break; + case NFPROTO_IPV6: + addr_len = sizeof(struct in6_addr); + break; + default: + return -EOPNOTSUPP; + } + + err = nft_validate_register_load(priv->sreg_dev, sizeof(int)); + if (err < 0) + return err; + + return nft_validate_register_load(priv->sreg_addr, addr_len); +} + +static const struct nft_expr_ops nft_fwd_netdev_ingress_ops; + +static int nft_fwd_neigh_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + struct nft_fwd_neigh *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_FWD_SREG_DEV, priv->sreg_dev) || + nft_dump_register(skb, NFTA_FWD_SREG_ADDR, priv->sreg_addr) || + nla_put_be32(skb, NFTA_FWD_NFPROTO, htonl(priv->nfproto))) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + static struct nft_expr_type nft_fwd_netdev_type; +static const struct nft_expr_ops nft_fwd_neigh_netdev_ops = { + .type = &nft_fwd_netdev_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_fwd_neigh)), + .eval = nft_fwd_neigh_eval, + .init = nft_fwd_neigh_init, + .dump = nft_fwd_neigh_dump, +}; + static const struct nft_expr_ops nft_fwd_netdev_ops = { .type = &nft_fwd_netdev_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_fwd_netdev)), @@ -71,10 +203,22 @@ static const struct nft_expr_ops nft_fwd_netdev_ops = { .dump = nft_fwd_netdev_dump, }; +static const struct nft_expr_ops * +nft_fwd_select_ops(const struct nft_ctx *ctx, + const struct nlattr * const tb[]) +{ + if (tb[NFTA_FWD_SREG_ADDR]) + return &nft_fwd_neigh_netdev_ops; + if (tb[NFTA_FWD_SREG_DEV]) + return &nft_fwd_netdev_ops; + + return ERR_PTR(-EOPNOTSUPP); +} + static struct nft_expr_type nft_fwd_netdev_type __read_mostly = { .family = NFPROTO_NETDEV, .name = "fwd", - .ops = &nft_fwd_netdev_ops, + .select_ops = nft_fwd_select_ops, .policy = nft_fwd_netdev_policy, .maxattr = NFTA_FWD_MAX, .owner = THIS_MODULE, diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 24f2f7567ddb7..c2d237144f747 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -25,6 +25,7 @@ struct nft_jhash { u32 modulus; u32 seed; u32 offset; + struct nft_set *map; }; static void nft_jhash_eval(const struct nft_expr *expr, @@ -35,14 +36,39 @@ static void nft_jhash_eval(const struct nft_expr *expr, const void *data = ®s->data[priv->sreg]; u32 h; - h = reciprocal_scale(jhash(data, priv->len, priv->seed), priv->modulus); + h = reciprocal_scale(jhash(data, priv->len, priv->seed), + priv->modulus); + regs->data[priv->dreg] = h + priv->offset; } +static void nft_jhash_map_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_jhash *priv = nft_expr_priv(expr); + const void *data = ®s->data[priv->sreg]; + const struct nft_set *map = priv->map; + const struct nft_set_ext *ext; + u32 result; + bool found; + + result = reciprocal_scale(jhash(data, priv->len, priv->seed), + priv->modulus) + priv->offset; + + found = map->ops->lookup(nft_net(pkt), map, &result, &ext); + if (!found) + return; + + nft_data_copy(®s->data[priv->dreg], + nft_set_ext_data(ext), map->dlen); +} + struct nft_symhash { enum nft_registers dreg:8; u32 modulus; u32 offset; + struct nft_set *map; }; static void nft_symhash_eval(const struct nft_expr *expr, @@ -58,6 +84,28 @@ static void nft_symhash_eval(const struct nft_expr *expr, regs->data[priv->dreg] = h + priv->offset; } +static void nft_symhash_map_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_symhash *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + const struct nft_set *map = priv->map; + const struct nft_set_ext *ext; + u32 result; + bool found; + + result = reciprocal_scale(__skb_get_hash_symmetric(skb), + priv->modulus) + priv->offset; + + found = map->ops->lookup(nft_net(pkt), map, &result, &ext); + if (!found) + return; + + nft_data_copy(®s->data[priv->dreg], + nft_set_ext_data(ext), map->dlen); +} + static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_SREG] = { .type = NLA_U32 }, [NFTA_HASH_DREG] = { .type = NLA_U32 }, @@ -66,6 +114,9 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_SEED] = { .type = NLA_U32 }, [NFTA_HASH_OFFSET] = { .type = NLA_U32 }, [NFTA_HASH_TYPE] = { .type = NLA_U32 }, + [NFTA_HASH_SET_NAME] = { .type = NLA_STRING, + .len = NFT_SET_MAXNAMELEN - 1 }, + [NFTA_HASH_SET_ID] = { .type = NLA_U32 }, }; static int nft_jhash_init(const struct nft_ctx *ctx, @@ -97,7 +148,7 @@ static int nft_jhash_init(const struct nft_ctx *ctx, priv->len = len; priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); - if (priv->modulus <= 1) + if (priv->modulus < 1) return -ERANGE; if (priv->offset + priv->modulus - 1 < priv->offset) @@ -115,6 +166,20 @@ static int nft_jhash_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } +static int nft_jhash_map_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_jhash *priv = nft_expr_priv(expr); + u8 genmask = nft_genmask_next(ctx->net); + + nft_jhash_init(ctx, expr, tb); + priv->map = nft_set_lookup_global(ctx->net, ctx->table, + tb[NFTA_HASH_SET_NAME], + tb[NFTA_HASH_SET_ID], genmask); + return PTR_ERR_OR_ZERO(priv->map); +} + static int nft_symhash_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -141,6 +206,20 @@ static int nft_symhash_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } +static int nft_symhash_map_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_jhash *priv = nft_expr_priv(expr); + u8 genmask = nft_genmask_next(ctx->net); + + nft_symhash_init(ctx, expr, tb); + priv->map = nft_set_lookup_global(ctx->net, ctx->table, + tb[NFTA_HASH_SET_NAME], + tb[NFTA_HASH_SET_ID], genmask); + return PTR_ERR_OR_ZERO(priv->map); +} + static int nft_jhash_dump(struct sk_buff *skb, const struct nft_expr *expr) { @@ -168,6 +247,18 @@ nla_put_failure: return -1; } +static int nft_jhash_map_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_jhash *priv = nft_expr_priv(expr); + + if (nft_jhash_dump(skb, expr) || + nla_put_string(skb, NFTA_HASH_SET_NAME, priv->map->name)) + return -1; + + return 0; +} + static int nft_symhash_dump(struct sk_buff *skb, const struct nft_expr *expr) { @@ -188,6 +279,18 @@ nla_put_failure: return -1; } +static int nft_symhash_map_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_symhash *priv = nft_expr_priv(expr); + + if (nft_symhash_dump(skb, expr) || + nla_put_string(skb, NFTA_HASH_SET_NAME, priv->map->name)) + return -1; + + return 0; +} + static struct nft_expr_type nft_hash_type; static const struct nft_expr_ops nft_jhash_ops = { .type = &nft_hash_type, @@ -197,6 +300,14 @@ static const struct nft_expr_ops nft_jhash_ops = { .dump = nft_jhash_dump, }; +static const struct nft_expr_ops nft_jhash_map_ops = { + .type = &nft_hash_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_jhash)), + .eval = nft_jhash_map_eval, + .init = nft_jhash_map_init, + .dump = nft_jhash_map_dump, +}; + static const struct nft_expr_ops nft_symhash_ops = { .type = &nft_hash_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)), @@ -205,6 +316,14 @@ static const struct nft_expr_ops nft_symhash_ops = { .dump = nft_symhash_dump, }; +static const struct nft_expr_ops nft_symhash_map_ops = { + .type = &nft_hash_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)), + .eval = nft_symhash_map_eval, + .init = nft_symhash_map_init, + .dump = nft_symhash_map_dump, +}; + static const struct nft_expr_ops * nft_hash_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -217,8 +336,12 @@ nft_hash_select_ops(const struct nft_ctx *ctx, type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE])); switch (type) { case NFT_HASH_SYM: + if (tb[NFTA_HASH_SET_NAME]) + return &nft_symhash_map_ops; return &nft_symhash_ops; case NFT_HASH_JENKINS: + if (tb[NFTA_HASH_SET_NAME]) + return &nft_jhash_map_ops; return &nft_jhash_ops; default: break; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index aa87ff8beae82..15adf8ca82c37 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -17,12 +17,6 @@ #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> -struct nft_immediate_expr { - struct nft_data data; - enum nft_registers dreg:8; - u8 dlen; -}; - static void nft_immediate_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -101,12 +95,27 @@ nla_put_failure: static int nft_immediate_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_data **d) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + const struct nft_data *data; + int err; - if (priv->dreg == NFT_REG_VERDICT) - *data = &priv->data; + if (priv->dreg != NFT_REG_VERDICT) + return 0; + + data = &priv->data; + + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + break; + default: + break; + } return 0; } diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index a27be36dc0afb..7eef1cffbf1bc 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -9,12 +9,15 @@ * Development of this code funded by Astaro AG (http://www.astaro.com/) */ +#include <linux/audit.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> +#include <net/ipv6.h> +#include <net/ip.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_log.h> #include <linux/netdevice.h> @@ -26,12 +29,93 @@ struct nft_log { char *prefix; }; +static bool audit_ip4(struct audit_buffer *ab, struct sk_buff *skb) +{ + struct iphdr _iph; + const struct iphdr *ih; + + ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_iph), &_iph); + if (!ih) + return false; + + audit_log_format(ab, " saddr=%pI4 daddr=%pI4 proto=%hhu", + &ih->saddr, &ih->daddr, ih->protocol); + + return true; +} + +static bool audit_ip6(struct audit_buffer *ab, struct sk_buff *skb) +{ + struct ipv6hdr _ip6h; + const struct ipv6hdr *ih; + u8 nexthdr; + __be16 frag_off; + + ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_ip6h), &_ip6h); + if (!ih) + return false; + + nexthdr = ih->nexthdr; + ipv6_skip_exthdr(skb, skb_network_offset(skb) + sizeof(_ip6h), &nexthdr, &frag_off); + + audit_log_format(ab, " saddr=%pI6c daddr=%pI6c proto=%hhu", + &ih->saddr, &ih->daddr, nexthdr); + + return true; +} + +static void nft_log_eval_audit(const struct nft_pktinfo *pkt) +{ + struct sk_buff *skb = pkt->skb; + struct audit_buffer *ab; + int fam = -1; + + if (!audit_enabled) + return; + + ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT); + if (!ab) + return; + + audit_log_format(ab, "mark=%#x", skb->mark); + + switch (nft_pf(pkt)) { + case NFPROTO_BRIDGE: + switch (eth_hdr(skb)->h_proto) { + case htons(ETH_P_IP): + fam = audit_ip4(ab, skb) ? NFPROTO_IPV4 : -1; + break; + case htons(ETH_P_IPV6): + fam = audit_ip6(ab, skb) ? NFPROTO_IPV6 : -1; + break; + } + break; + case NFPROTO_IPV4: + fam = audit_ip4(ab, skb) ? NFPROTO_IPV4 : -1; + break; + case NFPROTO_IPV6: + fam = audit_ip6(ab, skb) ? NFPROTO_IPV6 : -1; + break; + } + + if (fam == -1) + audit_log_format(ab, " saddr=? daddr=? proto=-1"); + + audit_log_end(ab); +} + static void nft_log_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_log *priv = nft_expr_priv(expr); + if (priv->loginfo.type == NF_LOG_TYPE_LOG && + priv->loginfo.u.log.level == LOGLEVEL_AUDIT) { + nft_log_eval_audit(pkt); + return; + } + nf_log_packet(nft_net(pkt), nft_pf(pkt), nft_hook(pkt), pkt->skb, nft_in(pkt), nft_out(pkt), &priv->loginfo, "%s", priv->prefix); @@ -84,7 +168,7 @@ static int nft_log_init(const struct nft_ctx *ctx, } else { li->u.log.level = LOGLEVEL_WARNING; } - if (li->u.log.level > LOGLEVEL_DEBUG) { + if (li->u.log.level > LOGLEVEL_AUDIT) { err = -EINVAL; goto err1; } @@ -112,6 +196,9 @@ static int nft_log_init(const struct nft_ctx *ctx, break; } + if (li->u.log.level == LOGLEVEL_AUDIT) + return 0; + err = nf_logger_find_get(ctx->family, li->type); if (err < 0) goto err1; @@ -133,6 +220,9 @@ static void nft_log_destroy(const struct nft_ctx *ctx, if (priv->prefix != nft_log_null_prefix) kfree(priv->prefix); + if (li->u.log.level == LOGLEVEL_AUDIT) + return; + nf_logger_put(ctx->family, li->type); } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index f52da5e2199fe..42e6fadf1417e 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -149,6 +149,52 @@ nla_put_failure: return -1; } +static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_data *data; + + if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && + *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) + return 0; + + data = nft_set_ext_data(ext); + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + return nft_chain_validate(ctx, data->verdict.chain); + default: + return 0; + } +} + +static int nft_lookup_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **d) +{ + const struct nft_lookup *priv = nft_expr_priv(expr); + struct nft_set_iter iter; + + if (!(priv->set->flags & NFT_SET_MAP) || + priv->set->dtype != NFT_DATA_VERDICT) + return 0; + + iter.genmask = nft_genmask_next(ctx->net); + iter.skip = 0; + iter.count = 0; + iter.err = 0; + iter.fn = nft_lookup_validate_setelem; + + priv->set->ops->walk(ctx, priv->set, &iter); + if (iter.err < 0) + return iter.err; + + return 0; +} + static const struct nft_expr_ops nft_lookup_ops = { .type = &nft_lookup_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)), @@ -156,6 +202,7 @@ static const struct nft_expr_ops nft_lookup_ops = { .init = nft_lookup_init, .destroy = nft_lookup_destroy, .dump = nft_lookup_dump, + .validate = nft_lookup_validate, }; struct nft_expr_type nft_lookup_type __read_mostly = { diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 204af9899482c..1105a23bda5ec 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -1,5 +1,7 @@ /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2014 Intel Corporation + * Author: Tomasz Bursztyka <tomasz.bursztyka@linux.intel.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 @@ -9,8 +11,6 @@ */ #include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> @@ -24,21 +24,35 @@ #include <net/tcp_states.h> /* for TCP_TIME_WAIT */ #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> -#include <net/netfilter/nft_meta.h> #include <uapi/linux/netfilter_bridge.h> /* NF_BR_PRE_ROUTING */ +struct nft_meta { + enum nft_meta_keys key:8; + union { + enum nft_registers dreg:8; + enum nft_registers sreg:8; + }; +}; + static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state); -void nft_meta_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +#ifdef CONFIG_NF_TABLES_BRIDGE +#include "../bridge/br_private.h" +#endif + +static void nft_meta_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; const struct net_device *in = nft_in(pkt), *out = nft_out(pkt); struct sock *sk; u32 *dest = ®s->data[priv->dreg]; +#ifdef CONFIG_NF_TABLES_BRIDGE + const struct net_bridge_port *p; +#endif switch (priv->key) { case NFT_META_LEN: @@ -215,6 +229,18 @@ void nft_meta_get_eval(const struct nft_expr *expr, nft_reg_store8(dest, !!skb->sp); break; #endif +#ifdef CONFIG_NF_TABLES_BRIDGE + case NFT_META_BRI_IIFNAME: + if (in == NULL || (p = br_port_get_rcu(in)) == NULL) + goto err; + strncpy((char *)dest, p->br->dev->name, IFNAMSIZ); + return; + case NFT_META_BRI_OIFNAME: + if (out == NULL || (p = br_port_get_rcu(out)) == NULL) + goto err; + strncpy((char *)dest, p->br->dev->name, IFNAMSIZ); + return; +#endif default: WARN_ON(1); goto err; @@ -224,11 +250,10 @@ void nft_meta_get_eval(const struct nft_expr *expr, err: regs->verdict.code = NFT_BREAK; } -EXPORT_SYMBOL_GPL(nft_meta_get_eval); -void nft_meta_set_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static void nft_meta_set_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_meta *meta = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; @@ -260,18 +285,16 @@ void nft_meta_set_eval(const struct nft_expr *expr, WARN_ON(1); } } -EXPORT_SYMBOL_GPL(nft_meta_set_eval); -const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = { +static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = { [NFTA_META_DREG] = { .type = NLA_U32 }, [NFTA_META_KEY] = { .type = NLA_U32 }, [NFTA_META_SREG] = { .type = NLA_U32 }, }; -EXPORT_SYMBOL_GPL(nft_meta_policy); -int nft_meta_get_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_meta_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; @@ -320,6 +343,14 @@ int nft_meta_get_init(const struct nft_ctx *ctx, len = sizeof(u8); break; #endif +#ifdef CONFIG_NF_TABLES_BRIDGE + case NFT_META_BRI_IIFNAME: + case NFT_META_BRI_OIFNAME: + if (ctx->family != NFPROTO_BRIDGE) + return -EOPNOTSUPP; + len = IFNAMSIZ; + break; +#endif default: return -EOPNOTSUPP; } @@ -328,7 +359,6 @@ int nft_meta_get_init(const struct nft_ctx *ctx, return nft_validate_register_store(ctx, priv->dreg, NULL, NFT_DATA_VALUE, len); } -EXPORT_SYMBOL_GPL(nft_meta_get_init); static int nft_meta_get_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, @@ -362,9 +392,9 @@ static int nft_meta_get_validate(const struct nft_ctx *ctx, #endif } -int nft_meta_set_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) +static int nft_meta_set_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; @@ -390,11 +420,10 @@ int nft_meta_set_validate(const struct nft_ctx *ctx, return nft_chain_validate_hooks(ctx->chain, hooks); } -EXPORT_SYMBOL_GPL(nft_meta_set_validate); -int nft_meta_set_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_meta_set_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; @@ -426,10 +455,9 @@ int nft_meta_set_init(const struct nft_ctx *ctx, return 0; } -EXPORT_SYMBOL_GPL(nft_meta_set_init); -int nft_meta_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) +static int nft_meta_get_dump(struct sk_buff *skb, + const struct nft_expr *expr) { const struct nft_meta *priv = nft_expr_priv(expr); @@ -442,10 +470,8 @@ int nft_meta_get_dump(struct sk_buff *skb, nla_put_failure: return -1; } -EXPORT_SYMBOL_GPL(nft_meta_get_dump); -int nft_meta_set_dump(struct sk_buff *skb, - const struct nft_expr *expr) +static int nft_meta_set_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_meta *priv = nft_expr_priv(expr); @@ -459,19 +485,16 @@ int nft_meta_set_dump(struct sk_buff *skb, nla_put_failure: return -1; } -EXPORT_SYMBOL_GPL(nft_meta_set_dump); -void nft_meta_set_destroy(const struct nft_ctx *ctx, - const struct nft_expr *expr) +static void nft_meta_set_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { const struct nft_meta *priv = nft_expr_priv(expr); if (priv->key == NFT_META_NFTRACE) static_branch_dec(&nft_trace_enabled); } -EXPORT_SYMBOL_GPL(nft_meta_set_destroy); -static struct nft_expr_type nft_meta_type; static const struct nft_expr_ops nft_meta_get_ops = { .type = &nft_meta_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), @@ -510,27 +533,10 @@ nft_meta_select_ops(const struct nft_ctx *ctx, return ERR_PTR(-EINVAL); } -static struct nft_expr_type nft_meta_type __read_mostly = { +struct nft_expr_type nft_meta_type __read_mostly = { .name = "meta", .select_ops = nft_meta_select_ops, .policy = nft_meta_policy, .maxattr = NFTA_META_MAX, .owner = THIS_MODULE, }; - -static int __init nft_meta_module_init(void) -{ - return nft_register_expr(&nft_meta_type); -} - -static void __exit nft_meta_module_exit(void) -{ - nft_unregister_expr(&nft_meta_type); -} - -module_init(nft_meta_module_init); -module_exit(nft_meta_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_EXPR("meta"); diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 1f36954c2ba91..c15807d10b912 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -43,7 +43,7 @@ static void nft_nat_eval(const struct nft_expr *expr, const struct nft_nat *priv = nft_expr_priv(expr); enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo); - struct nf_nat_range range; + struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); if (priv->sreg_addr_min) { diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 5a3a52c71545a..1f4d0854cf70b 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -24,13 +24,11 @@ struct nft_ng_inc { u32 modulus; atomic_t counter; u32 offset; + struct nft_set *map; }; -static void nft_ng_inc_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static u32 nft_ng_inc_gen(struct nft_ng_inc *priv) { - struct nft_ng_inc *priv = nft_expr_priv(expr); u32 nval, oval; do { @@ -38,7 +36,36 @@ static void nft_ng_inc_eval(const struct nft_expr *expr, nval = (oval + 1 < priv->modulus) ? oval + 1 : 0; } while (atomic_cmpxchg(&priv->counter, oval, nval) != oval); - regs->data[priv->dreg] = nval + priv->offset; + return nval + priv->offset; +} + +static void nft_ng_inc_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_ng_inc *priv = nft_expr_priv(expr); + + regs->data[priv->dreg] = nft_ng_inc_gen(priv); +} + +static void nft_ng_inc_map_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_ng_inc *priv = nft_expr_priv(expr); + const struct nft_set *map = priv->map; + const struct nft_set_ext *ext; + u32 result; + bool found; + + result = nft_ng_inc_gen(priv); + found = map->ops->lookup(nft_net(pkt), map, &result, &ext); + + if (!found) + return; + + nft_data_copy(®s->data[priv->dreg], + nft_set_ext_data(ext), map->dlen); } static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { @@ -46,6 +73,9 @@ static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { [NFTA_NG_MODULUS] = { .type = NLA_U32 }, [NFTA_NG_TYPE] = { .type = NLA_U32 }, [NFTA_NG_OFFSET] = { .type = NLA_U32 }, + [NFTA_NG_SET_NAME] = { .type = NLA_STRING, + .len = NFT_SET_MAXNAMELEN - 1 }, + [NFTA_NG_SET_ID] = { .type = NLA_U32 }, }; static int nft_ng_inc_init(const struct nft_ctx *ctx, @@ -71,6 +101,22 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } +static int nft_ng_inc_map_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_ng_inc *priv = nft_expr_priv(expr); + u8 genmask = nft_genmask_next(ctx->net); + + nft_ng_inc_init(ctx, expr, tb); + + priv->map = nft_set_lookup_global(ctx->net, ctx->table, + tb[NFTA_NG_SET_NAME], + tb[NFTA_NG_SET_ID], genmask); + + return PTR_ERR_OR_ZERO(priv->map); +} + static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, u32 modulus, enum nft_ng_types type, u32 offset) { @@ -97,22 +143,63 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } +static int nft_ng_inc_map_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_ng_inc *priv = nft_expr_priv(expr); + + if (nft_ng_dump(skb, priv->dreg, priv->modulus, + NFT_NG_INCREMENTAL, priv->offset) || + nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + struct nft_ng_random { enum nft_registers dreg:8; u32 modulus; u32 offset; + struct nft_set *map; }; +static u32 nft_ng_random_gen(struct nft_ng_random *priv) +{ + struct rnd_state *state = this_cpu_ptr(&nft_numgen_prandom_state); + + return reciprocal_scale(prandom_u32_state(state), priv->modulus) + + priv->offset; +} + static void nft_ng_random_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_ng_random *priv = nft_expr_priv(expr); - struct rnd_state *state = this_cpu_ptr(&nft_numgen_prandom_state); - u32 val; - val = reciprocal_scale(prandom_u32_state(state), priv->modulus); - regs->data[priv->dreg] = val + priv->offset; + regs->data[priv->dreg] = nft_ng_random_gen(priv); +} + +static void nft_ng_random_map_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_ng_random *priv = nft_expr_priv(expr); + const struct nft_set *map = priv->map; + const struct nft_set_ext *ext; + u32 result; + bool found; + + result = nft_ng_random_gen(priv); + found = map->ops->lookup(nft_net(pkt), map, &result, &ext); + if (!found) + return; + + nft_data_copy(®s->data[priv->dreg], + nft_set_ext_data(ext), map->dlen); } static int nft_ng_random_init(const struct nft_ctx *ctx, @@ -139,6 +226,23 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } +static int nft_ng_random_map_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_ng_random *priv = nft_expr_priv(expr); + u8 genmask = nft_genmask_next(ctx->net); + + nft_ng_random_init(ctx, expr, tb); + priv->map = nft_set_lookup_global(ctx->net, ctx->table, + tb[NFTA_NG_SET_NAME], + tb[NFTA_NG_SET_ID], genmask); + if (IS_ERR(priv->map)) + return PTR_ERR(priv->map); + + return 0; +} + static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ng_random *priv = nft_expr_priv(expr); @@ -147,6 +251,22 @@ static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } +static int nft_ng_random_map_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_ng_random *priv = nft_expr_priv(expr); + + if (nft_ng_dump(skb, priv->dreg, priv->modulus, + NFT_NG_RANDOM, priv->offset) || + nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + static struct nft_expr_type nft_ng_type; static const struct nft_expr_ops nft_ng_inc_ops = { .type = &nft_ng_type, @@ -156,6 +276,14 @@ static const struct nft_expr_ops nft_ng_inc_ops = { .dump = nft_ng_inc_dump, }; +static const struct nft_expr_ops nft_ng_inc_map_ops = { + .type = &nft_ng_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)), + .eval = nft_ng_inc_map_eval, + .init = nft_ng_inc_map_init, + .dump = nft_ng_inc_map_dump, +}; + static const struct nft_expr_ops nft_ng_random_ops = { .type = &nft_ng_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), @@ -164,6 +292,14 @@ static const struct nft_expr_ops nft_ng_random_ops = { .dump = nft_ng_random_dump, }; +static const struct nft_expr_ops nft_ng_random_map_ops = { + .type = &nft_ng_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), + .eval = nft_ng_random_map_eval, + .init = nft_ng_random_map_init, + .dump = nft_ng_random_map_dump, +}; + static const struct nft_expr_ops * nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { @@ -178,8 +314,12 @@ nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) switch (type) { case NFT_NG_INCREMENTAL: + if (tb[NFTA_NG_SET_NAME]) + return &nft_ng_inc_map_ops; return &nft_ng_inc_ops; case NFT_NG_RANDOM: + if (tb[NFTA_NG_SET_NAME]) + return &nft_ng_random_map_ops; return &nft_ng_random_ops; } diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 0b02407773ad2..cdf348f751eca 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -38,8 +38,8 @@ static int nft_objref_init(const struct nft_ctx *ctx, return -EINVAL; objtype = ntohl(nla_get_be32(tb[NFTA_OBJREF_IMM_TYPE])); - obj = nf_tables_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype, - genmask); + obj = nft_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype, + genmask); if (IS_ERR(obj)) return -ENOENT; diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index 11a2071b6dd41..76dba9f6b6f62 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -7,8 +7,6 @@ */ #include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> @@ -179,7 +177,6 @@ static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *exp return nft_chain_validate_hooks(ctx->chain, hooks); } -static struct nft_expr_type nft_rt_type; static const struct nft_expr_ops nft_rt_get_ops = { .type = &nft_rt_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_rt)), @@ -189,27 +186,10 @@ static const struct nft_expr_ops nft_rt_get_ops = { .validate = nft_rt_validate, }; -static struct nft_expr_type nft_rt_type __read_mostly = { +struct nft_expr_type nft_rt_type __read_mostly = { .name = "rt", .ops = &nft_rt_get_ops, .policy = nft_rt_policy, .maxattr = NFTA_RT_MAX, .owner = THIS_MODULE, }; - -static int __init nft_rt_module_init(void) -{ - return nft_register_expr(&nft_rt_type); -} - -static void __exit nft_rt_module_exit(void) -{ - nft_unregister_expr(&nft_rt_type); -} - -module_init(nft_rt_module_init); -module_exit(nft_rt_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Anders K. Pedersen <akp@cohaesio.com>"); -MODULE_ALIAS_NFT_EXPR("rt"); diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 45fb2752fb637..d6626e01c7ee6 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -296,27 +296,23 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_bitmap_type; -static struct nft_set_ops nft_bitmap_ops __read_mostly = { - .type = &nft_bitmap_type, - .privsize = nft_bitmap_privsize, - .elemsize = offsetof(struct nft_bitmap_elem, ext), - .estimate = nft_bitmap_estimate, - .init = nft_bitmap_init, - .destroy = nft_bitmap_destroy, - .insert = nft_bitmap_insert, - .remove = nft_bitmap_remove, - .deactivate = nft_bitmap_deactivate, - .flush = nft_bitmap_flush, - .activate = nft_bitmap_activate, - .lookup = nft_bitmap_lookup, - .walk = nft_bitmap_walk, - .get = nft_bitmap_get, -}; - static struct nft_set_type nft_bitmap_type __read_mostly = { - .ops = &nft_bitmap_ops, .owner = THIS_MODULE, + .ops = { + .privsize = nft_bitmap_privsize, + .elemsize = offsetof(struct nft_bitmap_elem, ext), + .estimate = nft_bitmap_estimate, + .init = nft_bitmap_init, + .destroy = nft_bitmap_destroy, + .insert = nft_bitmap_insert, + .remove = nft_bitmap_remove, + .deactivate = nft_bitmap_deactivate, + .flush = nft_bitmap_flush, + .activate = nft_bitmap_activate, + .lookup = nft_bitmap_lookup, + .walk = nft_bitmap_walk, + .get = nft_bitmap_get, + }, }; static int __init nft_bitmap_module_init(void) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index fc9c6d5d64cd7..6f9a1365a09f0 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -311,8 +311,16 @@ static void nft_rhash_gc(struct work_struct *work) continue; } + if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPR)) { + struct nft_expr *expr = nft_set_ext_expr(&he->ext); + + if (expr->ops->gc && + expr->ops->gc(read_pnet(&set->net), expr)) + goto gc; + } if (!nft_set_elem_expired(&he->ext)) continue; +gc: if (nft_set_elem_mark_busy(&he->ext)) continue; @@ -339,6 +347,14 @@ static unsigned int nft_rhash_privsize(const struct nlattr * const nla[], return sizeof(struct nft_rhash); } +static void nft_rhash_gc_init(const struct nft_set *set) +{ + struct nft_rhash *priv = nft_set_priv(set); + + queue_delayed_work(system_power_efficient_wq, &priv->gc_work, + nft_set_gc_interval(set)); +} + static int nft_rhash_init(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const tb[]) @@ -356,8 +372,8 @@ static int nft_rhash_init(const struct nft_set *set, INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc); if (set->flags & NFT_SET_TIMEOUT) - queue_delayed_work(system_power_efficient_wq, &priv->gc_work, - nft_set_gc_interval(set)); + nft_rhash_gc_init(set); + return 0; } @@ -605,6 +621,12 @@ static void nft_hash_destroy(const struct nft_set *set) static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est) { + if (!desc->size) + return false; + + if (desc->klen == 4) + return false; + est->size = sizeof(struct nft_hash) + nft_hash_buckets(desc->size) * sizeof(struct hlist_head) + desc->size * sizeof(struct nft_hash_elem); @@ -614,91 +636,101 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_hash_type; -static struct nft_set_ops nft_rhash_ops __read_mostly = { - .type = &nft_hash_type, - .privsize = nft_rhash_privsize, - .elemsize = offsetof(struct nft_rhash_elem, ext), - .estimate = nft_rhash_estimate, - .init = nft_rhash_init, - .destroy = nft_rhash_destroy, - .insert = nft_rhash_insert, - .activate = nft_rhash_activate, - .deactivate = nft_rhash_deactivate, - .flush = nft_rhash_flush, - .remove = nft_rhash_remove, - .lookup = nft_rhash_lookup, - .update = nft_rhash_update, - .walk = nft_rhash_walk, - .get = nft_rhash_get, - .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, -}; - -static struct nft_set_ops nft_hash_ops __read_mostly = { - .type = &nft_hash_type, - .privsize = nft_hash_privsize, - .elemsize = offsetof(struct nft_hash_elem, ext), - .estimate = nft_hash_estimate, - .init = nft_hash_init, - .destroy = nft_hash_destroy, - .insert = nft_hash_insert, - .activate = nft_hash_activate, - .deactivate = nft_hash_deactivate, - .flush = nft_hash_flush, - .remove = nft_hash_remove, - .lookup = nft_hash_lookup, - .walk = nft_hash_walk, - .get = nft_hash_get, - .features = NFT_SET_MAP | NFT_SET_OBJECT, -}; +static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + if (!desc->size) + return false; -static struct nft_set_ops nft_hash_fast_ops __read_mostly = { - .type = &nft_hash_type, - .privsize = nft_hash_privsize, - .elemsize = offsetof(struct nft_hash_elem, ext), - .estimate = nft_hash_estimate, - .init = nft_hash_init, - .destroy = nft_hash_destroy, - .insert = nft_hash_insert, - .activate = nft_hash_activate, - .deactivate = nft_hash_deactivate, - .flush = nft_hash_flush, - .remove = nft_hash_remove, - .lookup = nft_hash_lookup_fast, - .walk = nft_hash_walk, - .get = nft_hash_get, - .features = NFT_SET_MAP | NFT_SET_OBJECT, -}; + if (desc->klen != 4) + return false; -static const struct nft_set_ops * -nft_hash_select_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, - u32 flags) -{ - if (desc->size && !(flags & (NFT_SET_EVAL | NFT_SET_TIMEOUT))) { - switch (desc->klen) { - case 4: - return &nft_hash_fast_ops; - default: - return &nft_hash_ops; - } - } + est->size = sizeof(struct nft_hash) + + nft_hash_buckets(desc->size) * sizeof(struct hlist_head) + + desc->size * sizeof(struct nft_hash_elem); + est->lookup = NFT_SET_CLASS_O_1; + est->space = NFT_SET_CLASS_O_N; - return &nft_rhash_ops; + return true; } +static struct nft_set_type nft_rhash_type __read_mostly = { + .owner = THIS_MODULE, + .features = NFT_SET_MAP | NFT_SET_OBJECT | + NFT_SET_TIMEOUT | NFT_SET_EVAL, + .ops = { + .privsize = nft_rhash_privsize, + .elemsize = offsetof(struct nft_rhash_elem, ext), + .estimate = nft_rhash_estimate, + .init = nft_rhash_init, + .gc_init = nft_rhash_gc_init, + .destroy = nft_rhash_destroy, + .insert = nft_rhash_insert, + .activate = nft_rhash_activate, + .deactivate = nft_rhash_deactivate, + .flush = nft_rhash_flush, + .remove = nft_rhash_remove, + .lookup = nft_rhash_lookup, + .update = nft_rhash_update, + .walk = nft_rhash_walk, + .get = nft_rhash_get, + }, +}; + static struct nft_set_type nft_hash_type __read_mostly = { - .select_ops = nft_hash_select_ops, .owner = THIS_MODULE, + .features = NFT_SET_MAP | NFT_SET_OBJECT, + .ops = { + .privsize = nft_hash_privsize, + .elemsize = offsetof(struct nft_hash_elem, ext), + .estimate = nft_hash_estimate, + .init = nft_hash_init, + .destroy = nft_hash_destroy, + .insert = nft_hash_insert, + .activate = nft_hash_activate, + .deactivate = nft_hash_deactivate, + .flush = nft_hash_flush, + .remove = nft_hash_remove, + .lookup = nft_hash_lookup, + .walk = nft_hash_walk, + .get = nft_hash_get, + }, +}; + +static struct nft_set_type nft_hash_fast_type __read_mostly = { + .owner = THIS_MODULE, + .features = NFT_SET_MAP | NFT_SET_OBJECT, + .ops = { + .privsize = nft_hash_privsize, + .elemsize = offsetof(struct nft_hash_elem, ext), + .estimate = nft_hash_fast_estimate, + .init = nft_hash_init, + .destroy = nft_hash_destroy, + .insert = nft_hash_insert, + .activate = nft_hash_activate, + .deactivate = nft_hash_deactivate, + .flush = nft_hash_flush, + .remove = nft_hash_remove, + .lookup = nft_hash_lookup_fast, + .walk = nft_hash_walk, + .get = nft_hash_get, + }, }; static int __init nft_hash_module_init(void) { - return nft_register_set(&nft_hash_type); + if (nft_register_set(&nft_hash_fast_type) || + nft_register_set(&nft_hash_type) || + nft_register_set(&nft_rhash_type)) + return 1; + return 0; } static void __exit nft_hash_module_exit(void) { + nft_unregister_set(&nft_rhash_type); nft_unregister_set(&nft_hash_type); + nft_unregister_set(&nft_hash_fast_type); } module_init(nft_hash_module_init); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index e6f08bc5f359b..d260ce2d6671e 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -22,6 +22,7 @@ struct nft_rbtree { struct rb_root root; rwlock_t lock; seqcount_t count; + struct delayed_work gc_work; }; struct nft_rbtree_elem { @@ -265,6 +266,7 @@ static void nft_rbtree_activate(const struct net *net, struct nft_rbtree_elem *rbe = elem->priv; nft_set_elem_change_active(net, set, &rbe->ext); + nft_set_elem_clear_busy(&rbe->ext); } static bool nft_rbtree_flush(const struct net *net, @@ -272,8 +274,12 @@ static bool nft_rbtree_flush(const struct net *net, { struct nft_rbtree_elem *rbe = priv; - nft_set_elem_change_active(net, set, &rbe->ext); - return true; + if (!nft_set_elem_mark_busy(&rbe->ext) || + !nft_is_active(net, &rbe->ext)) { + nft_set_elem_change_active(net, set, &rbe->ext); + return true; + } + return false; } static void *nft_rbtree_deactivate(const struct net *net, @@ -347,6 +353,62 @@ cont: read_unlock_bh(&priv->lock); } +static void nft_rbtree_gc(struct work_struct *work) +{ + struct nft_set_gc_batch *gcb = NULL; + struct rb_node *node, *prev = NULL; + struct nft_rbtree_elem *rbe; + struct nft_rbtree *priv; + struct nft_set *set; + int i; + + priv = container_of(work, struct nft_rbtree, gc_work.work); + set = nft_set_container_of(priv); + + write_lock_bh(&priv->lock); + write_seqcount_begin(&priv->count); + for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + rbe = rb_entry(node, struct nft_rbtree_elem, node); + + if (nft_rbtree_interval_end(rbe)) { + prev = node; + continue; + } + if (!nft_set_elem_expired(&rbe->ext)) + continue; + if (nft_set_elem_mark_busy(&rbe->ext)) + continue; + + gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); + if (!gcb) + goto out; + + atomic_dec(&set->nelems); + nft_set_gc_batch_add(gcb, rbe); + + if (prev) { + rbe = rb_entry(prev, struct nft_rbtree_elem, node); + atomic_dec(&set->nelems); + nft_set_gc_batch_add(gcb, rbe); + } + node = rb_next(node); + } +out: + if (gcb) { + for (i = 0; i < gcb->head.cnt; i++) { + rbe = gcb->elems[i]; + rb_erase(&rbe->node, &priv->root); + } + } + write_seqcount_end(&priv->count); + write_unlock_bh(&priv->lock); + + nft_set_gc_batch_complete(gcb); + + queue_delayed_work(system_power_efficient_wq, &priv->gc_work, + nft_set_gc_interval(set)); +} + static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[], const struct nft_set_desc *desc) { @@ -362,6 +424,12 @@ static int nft_rbtree_init(const struct nft_set *set, rwlock_init(&priv->lock); seqcount_init(&priv->count); priv->root = RB_ROOT; + + INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rbtree_gc); + if (set->flags & NFT_SET_TIMEOUT) + queue_delayed_work(system_power_efficient_wq, &priv->gc_work, + nft_set_gc_interval(set)); + return 0; } @@ -371,6 +439,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) struct nft_rbtree_elem *rbe; struct rb_node *node; + cancel_delayed_work_sync(&priv->gc_work); while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); @@ -393,28 +462,24 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_rbtree_type; -static struct nft_set_ops nft_rbtree_ops __read_mostly = { - .type = &nft_rbtree_type, - .privsize = nft_rbtree_privsize, - .elemsize = offsetof(struct nft_rbtree_elem, ext), - .estimate = nft_rbtree_estimate, - .init = nft_rbtree_init, - .destroy = nft_rbtree_destroy, - .insert = nft_rbtree_insert, - .remove = nft_rbtree_remove, - .deactivate = nft_rbtree_deactivate, - .flush = nft_rbtree_flush, - .activate = nft_rbtree_activate, - .lookup = nft_rbtree_lookup, - .walk = nft_rbtree_walk, - .get = nft_rbtree_get, - .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT, -}; - static struct nft_set_type nft_rbtree_type __read_mostly = { - .ops = &nft_rbtree_ops, .owner = THIS_MODULE, + .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, + .ops = { + .privsize = nft_rbtree_privsize, + .elemsize = offsetof(struct nft_rbtree_elem, ext), + .estimate = nft_rbtree_estimate, + .init = nft_rbtree_init, + .destroy = nft_rbtree_destroy, + .insert = nft_rbtree_insert, + .remove = nft_rbtree_remove, + .deactivate = nft_rbtree_deactivate, + .flush = nft_rbtree_flush, + .activate = nft_rbtree_activate, + .lookup = nft_rbtree_lookup, + .walk = nft_rbtree_walk, + .get = nft_rbtree_get, + }, }; static int __init nft_rbtree_module_init(void) diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c new file mode 100644 index 0000000000000..f28a0b9440879 --- /dev/null +++ b/net/netfilter/nft_socket.c @@ -0,0 +1,144 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/module.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> +#include <net/netfilter/nf_socket.h> +#include <net/inet_sock.h> +#include <net/tcp.h> + +struct nft_socket { + enum nft_socket_keys key:8; + union { + enum nft_registers dreg:8; + }; +}; + +static void nft_socket_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_socket *priv = nft_expr_priv(expr); + struct sk_buff *skb = pkt->skb; + struct sock *sk = skb->sk; + u32 *dest = ®s->data[priv->dreg]; + + if (!sk) + switch(nft_pf(pkt)) { + case NFPROTO_IPV4: + sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, nft_in(pkt)); + break; +#if IS_ENABLED(CONFIG_NF_SOCKET_IPV6) + case NFPROTO_IPV6: + sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, nft_in(pkt)); + break; +#endif + default: + WARN_ON_ONCE(1); + regs->verdict.code = NFT_BREAK; + return; + } + + if(!sk) { + nft_reg_store8(dest, 0); + return; + } + + /* So that subsequent socket matching not to require other lookups. */ + skb->sk = sk; + + switch(priv->key) { + case NFT_SOCKET_TRANSPARENT: + nft_reg_store8(dest, inet_sk_transparent(sk)); + break; + default: + WARN_ON(1); + regs->verdict.code = NFT_BREAK; + } +} + +static const struct nla_policy nft_socket_policy[NFTA_SOCKET_MAX + 1] = { + [NFTA_SOCKET_KEY] = { .type = NLA_U32 }, + [NFTA_SOCKET_DREG] = { .type = NLA_U32 }, +}; + +static int nft_socket_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_socket *priv = nft_expr_priv(expr); + unsigned int len; + + if (!tb[NFTA_SOCKET_DREG] || !tb[NFTA_SOCKET_KEY]) + return -EINVAL; + + switch(ctx->family) { + case NFPROTO_IPV4: +#if IS_ENABLED(CONFIG_NF_SOCKET_IPV6) + case NFPROTO_IPV6: +#endif + case NFPROTO_INET: + break; + default: + return -EOPNOTSUPP; + } + + priv->key = ntohl(nla_get_u32(tb[NFTA_SOCKET_KEY])); + switch(priv->key) { + case NFT_SOCKET_TRANSPARENT: + len = sizeof(u8); + break; + default: + return -EOPNOTSUPP; + } + + priv->dreg = nft_parse_register(tb[NFTA_SOCKET_DREG]); + return nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, len); +} + +static int nft_socket_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_socket *priv = nft_expr_priv(expr); + + if (nla_put_u32(skb, NFTA_SOCKET_KEY, htonl(priv->key))) + return -1; + if (nft_dump_register(skb, NFTA_SOCKET_DREG, priv->dreg)) + return -1; + return 0; +} + +static struct nft_expr_type nft_socket_type; +static const struct nft_expr_ops nft_socket_ops = { + .type = &nft_socket_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_socket)), + .eval = nft_socket_eval, + .init = nft_socket_init, + .dump = nft_socket_dump, +}; + +static struct nft_expr_type nft_socket_type __read_mostly = { + .name = "socket", + .ops = &nft_socket_ops, + .policy = nft_socket_policy, + .maxattr = NFTA_SOCKET_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_socket_module_init(void) +{ + return nft_register_expr(&nft_socket_type); +} + +static void __exit nft_socket_module_exit(void) +{ + nft_unregister_expr(&nft_socket_type); +} + +module_init(nft_socket_module_init); +module_exit(nft_socket_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Máté Eckl"); +MODULE_DESCRIPTION("nf_tables socket match module"); diff --git a/net/netfilter/xt_NETMAP.c b/net/netfilter/xt_NETMAP.c index 58aa9dd3c5b75..1d437875e15a1 100644 --- a/net/netfilter/xt_NETMAP.c +++ b/net/netfilter/xt_NETMAP.c @@ -21,8 +21,8 @@ static unsigned int netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par) { - const struct nf_nat_range *range = par->targinfo; - struct nf_nat_range newrange; + const struct nf_nat_range2 *range = par->targinfo; + struct nf_nat_range2 newrange; struct nf_conn *ct; enum ip_conntrack_info ctinfo; union nf_inet_addr new_addr, netmask; @@ -56,7 +56,7 @@ netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par) static int netmap_tg6_checkentry(const struct xt_tgchk_param *par) { - const struct nf_nat_range *range = par->targinfo; + const struct nf_nat_range2 *range = par->targinfo; if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) return -EINVAL; @@ -75,7 +75,7 @@ netmap_tg4(struct sk_buff *skb, const struct xt_action_param *par) enum ip_conntrack_info ctinfo; __be32 new_ip, netmask; const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - struct nf_nat_range newrange; + struct nf_nat_range2 newrange; WARN_ON(xt_hooknum(par) != NF_INET_PRE_ROUTING && xt_hooknum(par) != NF_INET_POST_ROUTING && diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index c7f8958cea4a9..1ed0cac585c46 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -13,7 +13,6 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_NFLOG.h> #include <net/netfilter/nf_log.h> -#include <net/netfilter/nfnetlink_log.h> MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Xtables: packet logging to netlink using NFLOG"); @@ -37,8 +36,9 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) if (info->flags & XT_NFLOG_F_COPY_LEN) li.u.ulog.flags |= NF_LOG_F_COPY_LEN; - nfulnl_log_packet(net, xt_family(par), xt_hooknum(par), skb, - xt_in(par), xt_out(par), &li, info->prefix); + nf_log_packet(net, xt_family(par), xt_hooknum(par), skb, xt_in(par), + xt_out(par), &li, "%s", info->prefix); + return XT_CONTINUE; } @@ -50,7 +50,13 @@ static int nflog_tg_check(const struct xt_tgchk_param *par) return -EINVAL; if (info->prefix[sizeof(info->prefix) - 1] != '\0') return -EINVAL; - return 0; + + return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); +} + +static void nflog_tg_destroy(const struct xt_tgdtor_param *par) +{ + nf_logger_put(par->family, NF_LOG_TYPE_ULOG); } static struct xt_target nflog_tg_reg __read_mostly = { @@ -58,6 +64,7 @@ static struct xt_target nflog_tg_reg __read_mostly = { .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = nflog_tg_check, + .destroy = nflog_tg_destroy, .target = nflog_tg, .targetsize = sizeof(struct xt_nflog_info), .me = THIS_MODULE, diff --git a/net/netfilter/xt_REDIRECT.c b/net/netfilter/xt_REDIRECT.c index 98a4c6d4f1cb9..5ce9461e979c4 100644 --- a/net/netfilter/xt_REDIRECT.c +++ b/net/netfilter/xt_REDIRECT.c @@ -36,7 +36,7 @@ redirect_tg6(struct sk_buff *skb, const struct xt_action_param *par) static int redirect_tg6_checkentry(const struct xt_tgchk_param *par) { - const struct nf_nat_range *range = par->targinfo; + const struct nf_nat_range2 *range = par->targinfo; if (range->flags & NF_NAT_RANGE_MAP_IPS) return -EINVAL; diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 8c89323c06afe..58fce4e749a97 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -33,264 +33,9 @@ #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif +#include <net/netfilter/nf_tproxy.h> #include <linux/netfilter/xt_TPROXY.h> -enum nf_tproxy_lookup_t { - NFT_LOOKUP_LISTENER, - NFT_LOOKUP_ESTABLISHED, -}; - -static bool tproxy_sk_is_transparent(struct sock *sk) -{ - switch (sk->sk_state) { - case TCP_TIME_WAIT: - if (inet_twsk(sk)->tw_transparent) - return true; - break; - case TCP_NEW_SYN_RECV: - if (inet_rsk(inet_reqsk(sk))->no_srccheck) - return true; - break; - default: - if (inet_sk(sk)->transparent) - return true; - } - - sock_gen_put(sk); - return false; -} - -static inline __be32 -tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) -{ - struct in_device *indev; - __be32 laddr; - - if (user_laddr) - return user_laddr; - - laddr = 0; - indev = __in_dev_get_rcu(skb->dev); - for_primary_ifa(indev) { - laddr = ifa->ifa_local; - break; - } endfor_ifa(indev); - - return laddr ? laddr : daddr; -} - -/* - * This is used when the user wants to intercept a connection matching - * an explicit iptables rule. In this case the sockets are assumed - * matching in preference order: - * - * - match: if there's a fully established connection matching the - * _packet_ tuple, it is returned, assuming the redirection - * already took place and we process a packet belonging to an - * established connection - * - * - match: if there's a listening socket matching the redirection - * (e.g. on-port & on-ip of the connection), it is returned, - * regardless if it was bound to 0.0.0.0 or an explicit - * address. The reasoning is that if there's an explicit rule, it - * does not really matter if the listener is bound to an interface - * or to 0. The user already stated that he wants redirection - * (since he added the rule). - * - * Please note that there's an overlap between what a TPROXY target - * and a socket match will match. Normally if you have both rules the - * "socket" match will be the first one, effectively all packets - * belonging to established connections going through that one. - */ -static inline struct sock * -nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, - const u8 protocol, - const __be32 saddr, const __be32 daddr, - const __be16 sport, const __be16 dport, - const struct net_device *in, - const enum nf_tproxy_lookup_t lookup_type) -{ - struct sock *sk; - struct tcphdr *tcph; - - switch (protocol) { - case IPPROTO_TCP: - switch (lookup_type) { - case NFT_LOOKUP_LISTENER: - tcph = hp; - sk = inet_lookup_listener(net, &tcp_hashinfo, skb, - ip_hdrlen(skb) + - __tcp_hdrlen(tcph), - saddr, sport, - daddr, dport, - in->ifindex, 0); - - if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) - sk = NULL; - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too - */ - break; - case NFT_LOOKUP_ESTABLISHED: - sk = inet_lookup_established(net, &tcp_hashinfo, - saddr, sport, daddr, dport, - in->ifindex); - break; - default: - BUG(); - } - break; - case IPPROTO_UDP: - sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, - in->ifindex); - if (sk) { - int connected = (sk->sk_state == TCP_ESTABLISHED); - int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0); - - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too - */ - if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || - (lookup_type == NFT_LOOKUP_LISTENER && connected)) { - sock_put(sk); - sk = NULL; - } - } - break; - default: - WARN_ON(1); - sk = NULL; - } - - pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n", - protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk); - - return sk; -} - -#ifdef XT_TPROXY_HAVE_IPV6 -static inline struct sock * -nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, - const u8 protocol, - const struct in6_addr *saddr, const struct in6_addr *daddr, - const __be16 sport, const __be16 dport, - const struct net_device *in, - const enum nf_tproxy_lookup_t lookup_type) -{ - struct sock *sk; - struct tcphdr *tcph; - - switch (protocol) { - case IPPROTO_TCP: - switch (lookup_type) { - case NFT_LOOKUP_LISTENER: - tcph = hp; - sk = inet6_lookup_listener(net, &tcp_hashinfo, skb, - thoff + __tcp_hdrlen(tcph), - saddr, sport, - daddr, ntohs(dport), - in->ifindex, 0); - - if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) - sk = NULL; - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too - */ - break; - case NFT_LOOKUP_ESTABLISHED: - sk = __inet6_lookup_established(net, &tcp_hashinfo, - saddr, sport, daddr, ntohs(dport), - in->ifindex, 0); - break; - default: - BUG(); - } - break; - case IPPROTO_UDP: - sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, - in->ifindex); - if (sk) { - int connected = (sk->sk_state == TCP_ESTABLISHED); - int wildcard = ipv6_addr_any(&sk->sk_v6_rcv_saddr); - - /* NOTE: we return listeners even if bound to - * 0.0.0.0, those are filtered out in - * xt_socket, since xt_TPROXY needs 0 bound - * listeners too - */ - if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) || - (lookup_type == NFT_LOOKUP_LISTENER && connected)) { - sock_put(sk); - sk = NULL; - } - } - break; - default: - WARN_ON(1); - sk = NULL; - } - - pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n", - protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk); - - return sk; -} -#endif - -/** - * tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections - * @skb: The skb being processed. - * @laddr: IPv4 address to redirect to or zero. - * @lport: TCP port to redirect to or zero. - * @sk: The TIME_WAIT TCP socket found by the lookup. - * - * We have to handle SYN packets arriving to TIME_WAIT sockets - * differently: instead of reopening the connection we should rather - * redirect the new connection to the proxy if there's a listener - * socket present. - * - * tproxy_handle_time_wait4() consumes the socket reference passed in. - * - * Returns the listener socket if there's one, the TIME_WAIT socket if - * no such listener is found, or NULL if the TCP header is incomplete. - */ -static struct sock * -tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, - __be32 laddr, __be16 lport, struct sock *sk) -{ - const struct iphdr *iph = ip_hdr(skb); - struct tcphdr _hdr, *hp; - - hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); - if (hp == NULL) { - inet_twsk_put(inet_twsk(sk)); - return NULL; - } - - if (hp->syn && !hp->rst && !hp->ack && !hp->fin) { - /* SYN to a TIME_WAIT socket, we'd rather redirect it - * to a listener socket if there's one */ - struct sock *sk2; - - sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, - iph->saddr, laddr ? laddr : iph->daddr, - hp->source, lport ? lport : hp->dest, - skb->dev, NFT_LOOKUP_LISTENER); - if (sk2) { - inet_twsk_deschedule_put(inet_twsk(sk)); - sk = sk2; - } - } - - return sk; -} - /* assign a socket to the skb -- consumes sk */ static void nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) @@ -319,26 +64,26 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, iph->saddr, iph->daddr, hp->source, hp->dest, - skb->dev, NFT_LOOKUP_ESTABLISHED); + skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED); - laddr = tproxy_laddr4(skb, laddr, iph->daddr); + laddr = nf_tproxy_laddr4(skb, laddr, iph->daddr); if (!lport) lport = hp->dest; /* UDP has no TCP_TIME_WAIT state, so we never enter here */ if (sk && sk->sk_state == TCP_TIME_WAIT) /* reopening a TIME_WAIT connection needs special handling */ - sk = tproxy_handle_time_wait4(net, skb, laddr, lport, sk); + sk = nf_tproxy_handle_time_wait4(net, skb, laddr, lport, sk); else if (!sk) /* no, there's no established connection, check if * there's a listener on the redirected addr/port */ sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, iph->saddr, laddr, hp->source, lport, - skb->dev, NFT_LOOKUP_LISTENER); + skb->dev, NF_TPROXY_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ - if (sk && tproxy_sk_is_transparent(sk)) { + if (sk && nf_tproxy_sk_is_transparent(sk)) { /* This should be in a separate target, but we don't do multiple targets on the same rule yet */ skb->mark = (skb->mark & ~mark_mask) ^ mark_value; @@ -377,87 +122,6 @@ tproxy_tg4_v1(struct sk_buff *skb, const struct xt_action_param *par) #ifdef XT_TPROXY_HAVE_IPV6 -static inline const struct in6_addr * -tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr, - const struct in6_addr *daddr) -{ - struct inet6_dev *indev; - struct inet6_ifaddr *ifa; - struct in6_addr *laddr; - - if (!ipv6_addr_any(user_laddr)) - return user_laddr; - laddr = NULL; - - indev = __in6_dev_get(skb->dev); - if (indev) { - read_lock_bh(&indev->lock); - list_for_each_entry(ifa, &indev->addr_list, if_list) { - if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED)) - continue; - - laddr = &ifa->addr; - break; - } - read_unlock_bh(&indev->lock); - } - - return laddr ? laddr : daddr; -} - -/** - * tproxy_handle_time_wait6 - handle IPv6 TCP TIME_WAIT reopen redirections - * @skb: The skb being processed. - * @tproto: Transport protocol. - * @thoff: Transport protocol header offset. - * @par: Iptables target parameters. - * @sk: The TIME_WAIT TCP socket found by the lookup. - * - * We have to handle SYN packets arriving to TIME_WAIT sockets - * differently: instead of reopening the connection we should rather - * redirect the new connection to the proxy if there's a listener - * socket present. - * - * tproxy_handle_time_wait6() consumes the socket reference passed in. - * - * Returns the listener socket if there's one, the TIME_WAIT socket if - * no such listener is found, or NULL if the TCP header is incomplete. - */ -static struct sock * -tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, - const struct xt_action_param *par, - struct sock *sk) -{ - const struct ipv6hdr *iph = ipv6_hdr(skb); - struct tcphdr _hdr, *hp; - const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; - - hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr); - if (hp == NULL) { - inet_twsk_put(inet_twsk(sk)); - return NULL; - } - - if (hp->syn && !hp->rst && !hp->ack && !hp->fin) { - /* SYN to a TIME_WAIT socket, we'd rather redirect it - * to a listener socket if there's one */ - struct sock *sk2; - - sk2 = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto, - &iph->saddr, - tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr), - hp->source, - tgi->lport ? tgi->lport : hp->dest, - skb->dev, NFT_LOOKUP_LISTENER); - if (sk2) { - inet_twsk_deschedule_put(inet_twsk(sk)); - sk = sk2; - } - } - - return sk; -} - static unsigned int tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) { @@ -489,25 +153,31 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto, &iph->saddr, &iph->daddr, hp->source, hp->dest, - xt_in(par), NFT_LOOKUP_ESTABLISHED); + xt_in(par), NF_TPROXY_LOOKUP_ESTABLISHED); - laddr = tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr); + laddr = nf_tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr); lport = tgi->lport ? tgi->lport : hp->dest; /* UDP has no TCP_TIME_WAIT state, so we never enter here */ - if (sk && sk->sk_state == TCP_TIME_WAIT) + if (sk && sk->sk_state == TCP_TIME_WAIT) { + const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; /* reopening a TIME_WAIT connection needs special handling */ - sk = tproxy_handle_time_wait6(skb, tproto, thoff, par, sk); + sk = nf_tproxy_handle_time_wait6(skb, tproto, thoff, + xt_net(par), + &tgi->laddr.in6, + tgi->lport, + sk); + } else if (!sk) /* no there's no established connection, check if * there's a listener on the redirected addr/port */ sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto, &iph->saddr, laddr, hp->source, lport, - xt_in(par), NFT_LOOKUP_LISTENER); + xt_in(par), NF_TPROXY_LOOKUP_LISTENER); /* NOTE: assign_sock consumes our sk reference */ - if (sk && tproxy_sk_is_transparent(sk)) { + if (sk && nf_tproxy_sk_is_transparent(sk)) { /* This should be in a separate target, but we don't do multiple targets on the same rule yet */ skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value; diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c index bdb689cdc829d..8af9707f8789e 100644 --- a/net/netfilter/xt_nat.c +++ b/net/netfilter/xt_nat.c @@ -37,11 +37,12 @@ static void xt_nat_destroy(const struct xt_tgdtor_param *par) nf_ct_netns_put(par->net, par->family); } -static void xt_nat_convert_range(struct nf_nat_range *dst, +static void xt_nat_convert_range(struct nf_nat_range2 *dst, const struct nf_nat_ipv4_range *src) { memset(&dst->min_addr, 0, sizeof(dst->min_addr)); memset(&dst->max_addr, 0, sizeof(dst->max_addr)); + memset(&dst->base_proto, 0, sizeof(dst->base_proto)); dst->flags = src->flags; dst->min_addr.ip = src->min_ip; @@ -54,7 +55,7 @@ static unsigned int xt_snat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - struct nf_nat_range range; + struct nf_nat_range2 range; enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -71,7 +72,7 @@ static unsigned int xt_dnat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - struct nf_nat_range range; + struct nf_nat_range2 range; enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -86,7 +87,8 @@ xt_dnat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) static unsigned int xt_snat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) { - const struct nf_nat_range *range = par->targinfo; + const struct nf_nat_range *range_v1 = par->targinfo; + struct nf_nat_range2 range; enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -95,13 +97,49 @@ xt_snat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY))); - return nf_nat_setup_info(ct, range, NF_NAT_MANIP_SRC); + memcpy(&range, range_v1, sizeof(*range_v1)); + memset(&range.base_proto, 0, sizeof(range.base_proto)); + + return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); } static unsigned int xt_dnat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) { - const struct nf_nat_range *range = par->targinfo; + const struct nf_nat_range *range_v1 = par->targinfo; + struct nf_nat_range2 range; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + WARN_ON(!(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED))); + + memcpy(&range, range_v1, sizeof(*range_v1)); + memset(&range.base_proto, 0, sizeof(range.base_proto)); + + return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); +} + +static unsigned int +xt_snat_target_v2(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range2 *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + WARN_ON(!(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY))); + + return nf_nat_setup_info(ct, range, NF_NAT_MANIP_SRC); +} + +static unsigned int +xt_dnat_target_v2(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range2 *range = par->targinfo; enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -163,6 +201,28 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = { (1 << NF_INET_LOCAL_OUT), .me = THIS_MODULE, }, + { + .name = "SNAT", + .revision = 2, + .checkentry = xt_nat_checkentry, + .destroy = xt_nat_destroy, + .target = xt_snat_target_v2, + .targetsize = sizeof(struct nf_nat_range2), + .table = "nat", + .hooks = (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, + { + .name = "DNAT", + .revision = 2, + .target = xt_dnat_target_v2, + .targetsize = sizeof(struct nf_nat_range2), + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, }; static int __init xt_nat_init(void) diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index a34f314a8c238..9cfef73b41075 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -37,21 +37,6 @@ #include <net/netfilter/nf_log.h> #include <linux/netfilter/xt_osf.h> -struct xt_osf_finger { - struct rcu_head rcu_head; - struct list_head finger_entry; - struct xt_osf_user_finger finger; -}; - -enum osf_fmatch_states { - /* Packet does not match the fingerprint */ - FMATCH_WRONG = 0, - /* Packet matches the fingerprint */ - FMATCH_OK, - /* Options do not match the fingerprint, but header does */ - FMATCH_OPT_WRONG, -}; - /* * Indexed by dont-fragment bit. * It is the only constant value in the fingerprint. @@ -164,200 +149,17 @@ static const struct nfnetlink_subsystem xt_osf_nfnetlink = { .cb = xt_osf_nfnetlink_callbacks, }; -static inline int xt_osf_ttl(const struct sk_buff *skb, const struct xt_osf_info *info, - unsigned char f_ttl) -{ - const struct iphdr *ip = ip_hdr(skb); - - if (info->flags & XT_OSF_TTL) { - if (info->ttl == XT_OSF_TTL_TRUE) - return ip->ttl == f_ttl; - if (info->ttl == XT_OSF_TTL_NOCHECK) - return 1; - else if (ip->ttl <= f_ttl) - return 1; - else { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); - int ret = 0; - - for_ifa(in_dev) { - if (inet_ifa_match(ip->saddr, ifa)) { - ret = (ip->ttl == f_ttl); - break; - } - } - endfor_ifa(in_dev); - - return ret; - } - } - - return ip->ttl == f_ttl; -} - static bool xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) { const struct xt_osf_info *info = p->matchinfo; - const struct iphdr *ip = ip_hdr(skb); - const struct tcphdr *tcp; - struct tcphdr _tcph; - int fmatch = FMATCH_WRONG, fcount = 0; - unsigned int optsize = 0, check_WSS = 0; - u16 window, totlen, mss = 0; - bool df; - const unsigned char *optp = NULL, *_optp = NULL; - unsigned char opts[MAX_IPOPTLEN]; - const struct xt_osf_finger *kf; - const struct xt_osf_user_finger *f; struct net *net = xt_net(p); if (!info) return false; - tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); - if (!tcp) - return false; - - if (!tcp->syn) - return false; - - totlen = ntohs(ip->tot_len); - df = ntohs(ip->frag_off) & IP_DF; - window = ntohs(tcp->window); - - if (tcp->doff * 4 > sizeof(struct tcphdr)) { - optsize = tcp->doff * 4 - sizeof(struct tcphdr); - - _optp = optp = skb_header_pointer(skb, ip_hdrlen(skb) + - sizeof(struct tcphdr), optsize, opts); - } - - list_for_each_entry_rcu(kf, &xt_osf_fingers[df], finger_entry) { - int foptsize, optnum; - - f = &kf->finger; - - if (!(info->flags & XT_OSF_LOG) && strcmp(info->genre, f->genre)) - continue; - - optp = _optp; - fmatch = FMATCH_WRONG; - - if (totlen != f->ss || !xt_osf_ttl(skb, info, f->ttl)) - continue; - - /* - * Should not happen if userspace parser was written correctly. - */ - if (f->wss.wc >= OSF_WSS_MAX) - continue; - - /* Check options */ - - foptsize = 0; - for (optnum = 0; optnum < f->opt_num; ++optnum) - foptsize += f->opt[optnum].length; - - if (foptsize > MAX_IPOPTLEN || - optsize > MAX_IPOPTLEN || - optsize != foptsize) - continue; - - check_WSS = f->wss.wc; - - for (optnum = 0; optnum < f->opt_num; ++optnum) { - if (f->opt[optnum].kind == (*optp)) { - __u32 len = f->opt[optnum].length; - const __u8 *optend = optp + len; - - fmatch = FMATCH_OK; - - switch (*optp) { - case OSFOPT_MSS: - mss = optp[3]; - mss <<= 8; - mss |= optp[2]; - - mss = ntohs((__force __be16)mss); - break; - case OSFOPT_TS: - break; - } - - optp = optend; - } else - fmatch = FMATCH_OPT_WRONG; - - if (fmatch != FMATCH_OK) - break; - } - - if (fmatch != FMATCH_OPT_WRONG) { - fmatch = FMATCH_WRONG; - - switch (check_WSS) { - case OSF_WSS_PLAIN: - if (f->wss.val == 0 || window == f->wss.val) - fmatch = FMATCH_OK; - break; - case OSF_WSS_MSS: - /* - * Some smart modems decrease mangle MSS to - * SMART_MSS_2, so we check standard, decreased - * and the one provided in the fingerprint MSS - * values. - */ -#define SMART_MSS_1 1460 -#define SMART_MSS_2 1448 - if (window == f->wss.val * mss || - window == f->wss.val * SMART_MSS_1 || - window == f->wss.val * SMART_MSS_2) - fmatch = FMATCH_OK; - break; - case OSF_WSS_MTU: - if (window == f->wss.val * (mss + 40) || - window == f->wss.val * (SMART_MSS_1 + 40) || - window == f->wss.val * (SMART_MSS_2 + 40)) - fmatch = FMATCH_OK; - break; - case OSF_WSS_MODULO: - if ((window % f->wss.val) == 0) - fmatch = FMATCH_OK; - break; - } - } - - if (fmatch != FMATCH_OK) - continue; - - fcount++; - - if (info->flags & XT_OSF_LOG) - nf_log_packet(net, xt_family(p), xt_hooknum(p), skb, - xt_in(p), xt_out(p), NULL, - "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n", - f->genre, f->version, f->subtype, - &ip->saddr, ntohs(tcp->source), - &ip->daddr, ntohs(tcp->dest), - f->ttl - ip->ttl); - - if ((info->flags & XT_OSF_LOG) && - info->loglevel == XT_OSF_LOGLEVEL_FIRST) - break; - } - - if (!fcount && (info->flags & XT_OSF_LOG)) - nf_log_packet(net, xt_family(p), xt_hooknum(p), skb, xt_in(p), - xt_out(p), NULL, - "Remote OS is not known: %pI4:%u -> %pI4:%u\n", - &ip->saddr, ntohs(tcp->source), - &ip->daddr, ntohs(tcp->dest)); - - if (fcount) - fmatch = FMATCH_OK; - - return fmatch == FMATCH_OK; + return nf_osf_match(skb, xt_family(p), xt_hooknum(p), xt_in(p), + xt_out(p), info, net, xt_osf_fingers); } static struct xt_match xt_osf_match = { diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 2ac7f674d19b1..5c0779c4fa3cd 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -73,7 +73,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, * if XT_SOCKET_TRANSPARENT is used */ if (info->flags & XT_SOCKET_TRANSPARENT) - transparent = nf_sk_is_transparent(sk); + transparent = inet_sk_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) @@ -130,7 +130,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) * if XT_SOCKET_TRANSPARENT is used */ if (info->flags & XT_SOCKET_TRANSPARENT) - transparent = nf_sk_is_transparent(sk); + transparent = inet_sk_transparent(sk); if (info->flags & XT_SOCKET_RESTORESKMARK && !wildcard && transparent && sk_fullsock(sk)) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index f018eafc2a0de..376181cc1defc 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -206,7 +206,6 @@ int nfc_genl_targets_found(struct nfc_dev *dev) return genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -237,7 +236,6 @@ int nfc_genl_target_lost(struct nfc_dev *dev, u32 target_idx) return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -269,7 +267,6 @@ int nfc_genl_tm_activated(struct nfc_dev *dev, u32 protocol) return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -299,7 +296,6 @@ int nfc_genl_tm_deactivated(struct nfc_dev *dev) return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -340,7 +336,6 @@ int nfc_genl_device_added(struct nfc_dev *dev) return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -370,7 +365,6 @@ int nfc_genl_device_removed(struct nfc_dev *dev) return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -434,8 +428,6 @@ int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list) return genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); nla_put_failure: - genlmsg_cancel(msg, hdr); - free_msg: nlmsg_free(msg); @@ -470,7 +462,6 @@ int nfc_genl_se_added(struct nfc_dev *dev, u32 se_idx, u16 type) return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -501,7 +492,6 @@ int nfc_genl_se_removed(struct nfc_dev *dev, u32 se_idx) return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -546,7 +536,6 @@ int nfc_genl_se_transaction(struct nfc_dev *dev, u8 se_idx, return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: /* evt_transaction is no more used */ devm_kfree(&dev->dev, evt_transaction); @@ -585,7 +574,6 @@ int nfc_genl_se_connectivity(struct nfc_dev *dev, u8 se_idx) return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -703,7 +691,6 @@ int nfc_genl_dep_link_up_event(struct nfc_dev *dev, u32 target_idx, return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -735,7 +722,6 @@ int nfc_genl_dep_link_down_event(struct nfc_dev *dev) return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -1030,7 +1016,6 @@ static int nfc_genl_send_params(struct sk_buff *msg, return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); return -EMSGSIZE; } @@ -1290,7 +1275,6 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, return 0; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); return -EMSGSIZE; @@ -1507,7 +1491,6 @@ static void se_io_cb(void *context, u8 *apdu, size_t apdu_len, int err) return; nla_put_failure: - genlmsg_cancel(msg, hdr); free_msg: nlmsg_free(msg); kfree(ctx); diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 2650205cdaf9f..89da9512ec1e1 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -9,7 +9,8 @@ config OPENVSWITCH (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \ (!NF_NAT || NF_NAT) && \ (!NF_NAT_IPV4 || NF_NAT_IPV4) && \ - (!NF_NAT_IPV6 || NF_NAT_IPV6))) + (!NF_NAT_IPV6 || NF_NAT_IPV6) && \ + (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT))) select LIBCRC32C select MPLS select NET_MPLS_GSO diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c5904f629091d..284aca2a252df 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -16,8 +16,11 @@ #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> +#include <linux/static_key.h> #include <net/ip.h> +#include <net/genetlink.h> #include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_count.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_conntrack_seqadj.h> @@ -72,10 +75,35 @@ struct ovs_conntrack_info { struct md_mark mark; struct md_labels labels; #ifdef CONFIG_NF_NAT_NEEDED - struct nf_nat_range range; /* Only present for SRC NAT and DST NAT. */ + struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */ #endif }; +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) +#define OVS_CT_LIMIT_UNLIMITED 0 +#define OVS_CT_LIMIT_DEFAULT OVS_CT_LIMIT_UNLIMITED +#define CT_LIMIT_HASH_BUCKETS 512 +static DEFINE_STATIC_KEY_FALSE(ovs_ct_limit_enabled); + +struct ovs_ct_limit { + /* Elements in ovs_ct_limit_info->limits hash table */ + struct hlist_node hlist_node; + struct rcu_head rcu; + u16 zone; + u32 limit; +}; + +struct ovs_ct_limit_info { + u32 default_limit; + struct hlist_head *limits; + struct nf_conncount_data *data; +}; + +static const struct nla_policy ct_limit_policy[OVS_CT_LIMIT_ATTR_MAX + 1] = { + [OVS_CT_LIMIT_ATTR_ZONE_LIMIT] = { .type = NLA_NESTED, }, +}; +#endif + static bool labels_nonzero(const struct ovs_key_ct_labels *labels); static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info); @@ -710,7 +738,7 @@ static bool skb_nfct_cached(struct net *net, */ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype) { int hooknum, nh_off, err = NF_ACCEPT; @@ -1036,6 +1064,89 @@ static bool labels_nonzero(const struct ovs_key_ct_labels *labels) return false; } +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) +static struct hlist_head *ct_limit_hash_bucket( + const struct ovs_ct_limit_info *info, u16 zone) +{ + return &info->limits[zone & (CT_LIMIT_HASH_BUCKETS - 1)]; +} + +/* Call with ovs_mutex */ +static void ct_limit_set(const struct ovs_ct_limit_info *info, + struct ovs_ct_limit *new_ct_limit) +{ + struct ovs_ct_limit *ct_limit; + struct hlist_head *head; + + head = ct_limit_hash_bucket(info, new_ct_limit->zone); + hlist_for_each_entry_rcu(ct_limit, head, hlist_node) { + if (ct_limit->zone == new_ct_limit->zone) { + hlist_replace_rcu(&ct_limit->hlist_node, + &new_ct_limit->hlist_node); + kfree_rcu(ct_limit, rcu); + return; + } + } + + hlist_add_head_rcu(&new_ct_limit->hlist_node, head); +} + +/* Call with ovs_mutex */ +static void ct_limit_del(const struct ovs_ct_limit_info *info, u16 zone) +{ + struct ovs_ct_limit *ct_limit; + struct hlist_head *head; + struct hlist_node *n; + + head = ct_limit_hash_bucket(info, zone); + hlist_for_each_entry_safe(ct_limit, n, head, hlist_node) { + if (ct_limit->zone == zone) { + hlist_del_rcu(&ct_limit->hlist_node); + kfree_rcu(ct_limit, rcu); + return; + } + } +} + +/* Call with RCU read lock */ +static u32 ct_limit_get(const struct ovs_ct_limit_info *info, u16 zone) +{ + struct ovs_ct_limit *ct_limit; + struct hlist_head *head; + + head = ct_limit_hash_bucket(info, zone); + hlist_for_each_entry_rcu(ct_limit, head, hlist_node) { + if (ct_limit->zone == zone) + return ct_limit->limit; + } + + return info->default_limit; +} + +static int ovs_ct_check_limit(struct net *net, + const struct ovs_conntrack_info *info, + const struct nf_conntrack_tuple *tuple) +{ + struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + const struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; + u32 per_zone_limit, connections; + u32 conncount_key; + + conncount_key = info->zone.id; + + per_zone_limit = ct_limit_get(ct_limit_info, info->zone.id); + if (per_zone_limit == OVS_CT_LIMIT_UNLIMITED) + return 0; + + connections = nf_conncount_count(net, ct_limit_info->data, + &conncount_key, tuple, &info->zone); + if (connections > per_zone_limit) + return -ENOMEM; + + return 0; +} +#endif + /* Lookup connection and confirm if unconfirmed. */ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, @@ -1054,6 +1165,21 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, if (!ct) return 0; +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) + if (static_branch_unlikely(&ovs_ct_limit_enabled)) { + if (!nf_ct_is_confirmed(ct)) { + err = ovs_ct_check_limit(net, info, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + if (err) { + net_warn_ratelimited("openvswitch: zone: %u " + "execeeds conntrack limit\n", + info->zone.id); + return err; + } + } + } +#endif + /* Set the conntrack event mask if given. NEW and DELETE events have * their own groups, but the NFNLGRP_CONNTRACK_UPDATE group listener * typically would receive many kinds of updates. Setting the event @@ -1655,7 +1781,420 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) nf_ct_tmpl_free(ct_info->ct); } -void ovs_ct_init(struct net *net) +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) +static int ovs_ct_limit_init(struct net *net, struct ovs_net *ovs_net) +{ + int i, err; + + ovs_net->ct_limit_info = kmalloc(sizeof(*ovs_net->ct_limit_info), + GFP_KERNEL); + if (!ovs_net->ct_limit_info) + return -ENOMEM; + + ovs_net->ct_limit_info->default_limit = OVS_CT_LIMIT_DEFAULT; + ovs_net->ct_limit_info->limits = + kmalloc_array(CT_LIMIT_HASH_BUCKETS, sizeof(struct hlist_head), + GFP_KERNEL); + if (!ovs_net->ct_limit_info->limits) { + kfree(ovs_net->ct_limit_info); + return -ENOMEM; + } + + for (i = 0; i < CT_LIMIT_HASH_BUCKETS; i++) + INIT_HLIST_HEAD(&ovs_net->ct_limit_info->limits[i]); + + ovs_net->ct_limit_info->data = + nf_conncount_init(net, NFPROTO_INET, sizeof(u32)); + + if (IS_ERR(ovs_net->ct_limit_info->data)) { + err = PTR_ERR(ovs_net->ct_limit_info->data); + kfree(ovs_net->ct_limit_info->limits); + kfree(ovs_net->ct_limit_info); + pr_err("openvswitch: failed to init nf_conncount %d\n", err); + return err; + } + return 0; +} + +static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) +{ + const struct ovs_ct_limit_info *info = ovs_net->ct_limit_info; + int i; + + nf_conncount_destroy(net, NFPROTO_INET, info->data); + for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { + struct hlist_head *head = &info->limits[i]; + struct ovs_ct_limit *ct_limit; + + hlist_for_each_entry_rcu(ct_limit, head, hlist_node) + kfree_rcu(ct_limit, rcu); + } + kfree(ovs_net->ct_limit_info->limits); + kfree(ovs_net->ct_limit_info); +} + +static struct sk_buff * +ovs_ct_limit_cmd_reply_start(struct genl_info *info, u8 cmd, + struct ovs_header **ovs_reply_header) +{ + struct ovs_header *ovs_header = info->userhdr; + struct sk_buff *skb; + + skb = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return ERR_PTR(-ENOMEM); + + *ovs_reply_header = genlmsg_put(skb, info->snd_portid, + info->snd_seq, + &dp_ct_limit_genl_family, 0, cmd); + + if (!*ovs_reply_header) { + nlmsg_free(skb); + return ERR_PTR(-EMSGSIZE); + } + (*ovs_reply_header)->dp_ifindex = ovs_header->dp_ifindex; + + return skb; +} + +static bool check_zone_id(int zone_id, u16 *pzone) +{ + if (zone_id >= 0 && zone_id <= 65535) { + *pzone = (u16)zone_id; + return true; + } + return false; +} + +static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit, + struct ovs_ct_limit_info *info) +{ + struct ovs_zone_limit *zone_limit; + int rem; + u16 zone; + + rem = NLA_ALIGN(nla_len(nla_zone_limit)); + zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit); + + while (rem >= sizeof(*zone_limit)) { + if (unlikely(zone_limit->zone_id == + OVS_ZONE_LIMIT_DEFAULT_ZONE)) { + ovs_lock(); + info->default_limit = zone_limit->limit; + ovs_unlock(); + } else if (unlikely(!check_zone_id( + zone_limit->zone_id, &zone))) { + OVS_NLERR(true, "zone id is out of range"); + } else { + struct ovs_ct_limit *ct_limit; + + ct_limit = kmalloc(sizeof(*ct_limit), GFP_KERNEL); + if (!ct_limit) + return -ENOMEM; + + ct_limit->zone = zone; + ct_limit->limit = zone_limit->limit; + + ovs_lock(); + ct_limit_set(info, ct_limit); + ovs_unlock(); + } + rem -= NLA_ALIGN(sizeof(*zone_limit)); + zone_limit = (struct ovs_zone_limit *)((u8 *)zone_limit + + NLA_ALIGN(sizeof(*zone_limit))); + } + + if (rem) + OVS_NLERR(true, "set zone limit has %d unknown bytes", rem); + + return 0; +} + +static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, + struct ovs_ct_limit_info *info) +{ + struct ovs_zone_limit *zone_limit; + int rem; + u16 zone; + + rem = NLA_ALIGN(nla_len(nla_zone_limit)); + zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit); + + while (rem >= sizeof(*zone_limit)) { + if (unlikely(zone_limit->zone_id == + OVS_ZONE_LIMIT_DEFAULT_ZONE)) { + ovs_lock(); + info->default_limit = OVS_CT_LIMIT_DEFAULT; + ovs_unlock(); + } else if (unlikely(!check_zone_id( + zone_limit->zone_id, &zone))) { + OVS_NLERR(true, "zone id is out of range"); + } else { + ovs_lock(); + ct_limit_del(info, zone); + ovs_unlock(); + } + rem -= NLA_ALIGN(sizeof(*zone_limit)); + zone_limit = (struct ovs_zone_limit *)((u8 *)zone_limit + + NLA_ALIGN(sizeof(*zone_limit))); + } + + if (rem) + OVS_NLERR(true, "del zone limit has %d unknown bytes", rem); + + return 0; +} + +static int ovs_ct_limit_get_default_limit(struct ovs_ct_limit_info *info, + struct sk_buff *reply) +{ + struct ovs_zone_limit zone_limit; + int err; + + zone_limit.zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE; + zone_limit.limit = info->default_limit; + err = nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit); + if (err) + return err; + + return 0; +} + +static int __ovs_ct_limit_get_zone_limit(struct net *net, + struct nf_conncount_data *data, + u16 zone_id, u32 limit, + struct sk_buff *reply) +{ + struct nf_conntrack_zone ct_zone; + struct ovs_zone_limit zone_limit; + u32 conncount_key = zone_id; + + zone_limit.zone_id = zone_id; + zone_limit.limit = limit; + nf_ct_zone_init(&ct_zone, zone_id, NF_CT_DEFAULT_ZONE_DIR, 0); + + zone_limit.count = nf_conncount_count(net, data, &conncount_key, NULL, + &ct_zone); + return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit); +} + +static int ovs_ct_limit_get_zone_limit(struct net *net, + struct nlattr *nla_zone_limit, + struct ovs_ct_limit_info *info, + struct sk_buff *reply) +{ + struct ovs_zone_limit *zone_limit; + int rem, err; + u32 limit; + u16 zone; + + rem = NLA_ALIGN(nla_len(nla_zone_limit)); + zone_limit = (struct ovs_zone_limit *)nla_data(nla_zone_limit); + + while (rem >= sizeof(*zone_limit)) { + if (unlikely(zone_limit->zone_id == + OVS_ZONE_LIMIT_DEFAULT_ZONE)) { + err = ovs_ct_limit_get_default_limit(info, reply); + if (err) + return err; + } else if (unlikely(!check_zone_id(zone_limit->zone_id, + &zone))) { + OVS_NLERR(true, "zone id is out of range"); + } else { + rcu_read_lock(); + limit = ct_limit_get(info, zone); + rcu_read_unlock(); + + err = __ovs_ct_limit_get_zone_limit( + net, info->data, zone, limit, reply); + if (err) + return err; + } + rem -= NLA_ALIGN(sizeof(*zone_limit)); + zone_limit = (struct ovs_zone_limit *)((u8 *)zone_limit + + NLA_ALIGN(sizeof(*zone_limit))); + } + + if (rem) + OVS_NLERR(true, "get zone limit has %d unknown bytes", rem); + + return 0; +} + +static int ovs_ct_limit_get_all_zone_limit(struct net *net, + struct ovs_ct_limit_info *info, + struct sk_buff *reply) +{ + struct ovs_ct_limit *ct_limit; + struct hlist_head *head; + int i, err = 0; + + err = ovs_ct_limit_get_default_limit(info, reply); + if (err) + return err; + + rcu_read_lock(); + for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { + head = &info->limits[i]; + hlist_for_each_entry_rcu(ct_limit, head, hlist_node) { + err = __ovs_ct_limit_get_zone_limit(net, info->data, + ct_limit->zone, ct_limit->limit, reply); + if (err) + goto exit_err; + } + } + +exit_err: + rcu_read_unlock(); + return err; +} + +static int ovs_ct_limit_cmd_set(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr **a = info->attrs; + struct sk_buff *reply; + struct ovs_header *ovs_reply_header; + struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); + struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; + int err; + + reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_SET, + &ovs_reply_header); + if (IS_ERR(reply)) + return PTR_ERR(reply); + + if (!a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { + err = -EINVAL; + goto exit_err; + } + + err = ovs_ct_limit_set_zone_limit(a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], + ct_limit_info); + if (err) + goto exit_err; + + static_branch_enable(&ovs_ct_limit_enabled); + + genlmsg_end(reply, ovs_reply_header); + return genlmsg_reply(reply, info); + +exit_err: + nlmsg_free(reply); + return err; +} + +static int ovs_ct_limit_cmd_del(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr **a = info->attrs; + struct sk_buff *reply; + struct ovs_header *ovs_reply_header; + struct ovs_net *ovs_net = net_generic(sock_net(skb->sk), ovs_net_id); + struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; + int err; + + reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_DEL, + &ovs_reply_header); + if (IS_ERR(reply)) + return PTR_ERR(reply); + + if (!a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { + err = -EINVAL; + goto exit_err; + } + + err = ovs_ct_limit_del_zone_limit(a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], + ct_limit_info); + if (err) + goto exit_err; + + genlmsg_end(reply, ovs_reply_header); + return genlmsg_reply(reply, info); + +exit_err: + nlmsg_free(reply); + return err; +} + +static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr **a = info->attrs; + struct nlattr *nla_reply; + struct sk_buff *reply; + struct ovs_header *ovs_reply_header; + struct net *net = sock_net(skb->sk); + struct ovs_net *ovs_net = net_generic(net, ovs_net_id); + struct ovs_ct_limit_info *ct_limit_info = ovs_net->ct_limit_info; + int err; + + reply = ovs_ct_limit_cmd_reply_start(info, OVS_CT_LIMIT_CMD_GET, + &ovs_reply_header); + if (IS_ERR(reply)) + return PTR_ERR(reply); + + nla_reply = nla_nest_start(reply, OVS_CT_LIMIT_ATTR_ZONE_LIMIT); + + if (a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) { + err = ovs_ct_limit_get_zone_limit( + net, a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT], ct_limit_info, + reply); + if (err) + goto exit_err; + } else { + err = ovs_ct_limit_get_all_zone_limit(net, ct_limit_info, + reply); + if (err) + goto exit_err; + } + + nla_nest_end(reply, nla_reply); + genlmsg_end(reply, ovs_reply_header); + return genlmsg_reply(reply, info); + +exit_err: + nlmsg_free(reply); + return err; +} + +static struct genl_ops ct_limit_genl_ops[] = { + { .cmd = OVS_CT_LIMIT_CMD_SET, + .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN + * privilege. */ + .policy = ct_limit_policy, + .doit = ovs_ct_limit_cmd_set, + }, + { .cmd = OVS_CT_LIMIT_CMD_DEL, + .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN + * privilege. */ + .policy = ct_limit_policy, + .doit = ovs_ct_limit_cmd_del, + }, + { .cmd = OVS_CT_LIMIT_CMD_GET, + .flags = 0, /* OK for unprivileged users. */ + .policy = ct_limit_policy, + .doit = ovs_ct_limit_cmd_get, + }, +}; + +static const struct genl_multicast_group ovs_ct_limit_multicast_group = { + .name = OVS_CT_LIMIT_MCGROUP, +}; + +struct genl_family dp_ct_limit_genl_family __ro_after_init = { + .hdrsize = sizeof(struct ovs_header), + .name = OVS_CT_LIMIT_FAMILY, + .version = OVS_CT_LIMIT_VERSION, + .maxattr = OVS_CT_LIMIT_ATTR_MAX, + .netnsok = true, + .parallel_ops = true, + .ops = ct_limit_genl_ops, + .n_ops = ARRAY_SIZE(ct_limit_genl_ops), + .mcgrps = &ovs_ct_limit_multicast_group, + .n_mcgrps = 1, + .module = THIS_MODULE, +}; +#endif + +int ovs_ct_init(struct net *net) { unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_net *ovs_net = net_generic(net, ovs_net_id); @@ -1666,12 +2205,22 @@ void ovs_ct_init(struct net *net) } else { ovs_net->xt_label = true; } + +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) + return ovs_ct_limit_init(net, ovs_net); +#else + return 0; +#endif } void ovs_ct_exit(struct net *net) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) + ovs_ct_limit_exit(net, ovs_net); +#endif + if (ovs_net->xt_label) nf_connlabels_put(net); } diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 399dfdd2c4f97..900dadd70974a 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -17,10 +17,11 @@ #include "flow.h" struct ovs_conntrack_info; +struct ovs_ct_limit_info; enum ovs_key_attr; #if IS_ENABLED(CONFIG_NF_CONNTRACK) -void ovs_ct_init(struct net *); +int ovs_ct_init(struct net *); void ovs_ct_exit(struct net *); bool ovs_ct_verify(struct net *, enum ovs_key_attr attr); int ovs_ct_copy_action(struct net *, const struct nlattr *, @@ -44,7 +45,7 @@ void ovs_ct_free_action(const struct nlattr *a); #else #include <linux/errno.h> -static inline void ovs_ct_init(struct net *net) { } +static inline int ovs_ct_init(struct net *net) { return 0; } static inline void ovs_ct_exit(struct net *net) { } @@ -104,4 +105,8 @@ static inline void ovs_ct_free_action(const struct nlattr *a) { } #define CT_SUPPORTED_MASK 0 #endif /* CONFIG_NF_CONNTRACK */ + +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) +extern struct genl_family dp_ct_limit_genl_family; +#endif #endif /* ovs_conntrack.h */ diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 015e24e08909f..a61818e943969 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2288,6 +2288,9 @@ static struct genl_family * const dp_genl_families[] = { &dp_flow_genl_family, &dp_packet_genl_family, &dp_meter_genl_family, +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) + &dp_ct_limit_genl_family, +#endif }; static void dp_unregister_genl(int n_families) @@ -2323,8 +2326,7 @@ static int __net_init ovs_init_net(struct net *net) INIT_LIST_HEAD(&ovs_net->dps); INIT_WORK(&ovs_net->dp_notify_work, ovs_dp_notify_wq); - ovs_ct_init(net); - return 0; + return ovs_ct_init(net); } static void __net_exit list_vports_from_net(struct net *net, struct net *dnet, @@ -2469,3 +2471,4 @@ MODULE_ALIAS_GENL_FAMILY(OVS_VPORT_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_FLOW_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_PACKET_FAMILY); MODULE_ALIAS_GENL_FAMILY(OVS_METER_FAMILY); +MODULE_ALIAS_GENL_FAMILY(OVS_CT_LIMIT_FAMILY); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 523d65526766d..c9eb267c6f7e1 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -144,6 +144,9 @@ struct dp_upcall_info { struct ovs_net { struct list_head dps; struct work_struct dp_notify_work; +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) + struct ovs_ct_limit_info *ct_limit_info; +#endif /* Module reference for configuring conntrack. */ bool xt_label; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 674390b1f0847..54ce66f684828 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -209,7 +209,7 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *, static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); -static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb); +static u16 packet_pick_tx_queue(struct sk_buff *skb); struct packet_skb_cb { union { @@ -243,40 +243,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po); static int packet_direct_xmit(struct sk_buff *skb) { - struct net_device *dev = skb->dev; - struct sk_buff *orig_skb = skb; - struct netdev_queue *txq; - int ret = NETDEV_TX_BUSY; - bool again = false; - - if (unlikely(!netif_running(dev) || - !netif_carrier_ok(dev))) - goto drop; - - skb = validate_xmit_skb_list(skb, dev, &again); - if (skb != orig_skb) - goto drop; - - packet_pick_tx_queue(dev, skb); - txq = skb_get_tx_queue(dev, skb); - - local_bh_disable(); - - HARD_TX_LOCK(dev, txq, smp_processor_id()); - if (!netif_xmit_frozen_or_drv_stopped(txq)) - ret = netdev_start_xmit(skb, dev, txq, false); - HARD_TX_UNLOCK(dev, txq); - - local_bh_enable(); - - if (!dev_xmit_complete(ret)) - kfree_skb(skb); - - return ret; -drop: - atomic_long_inc(&dev->tx_dropped); - kfree_skb_list(skb); - return NET_XMIT_DROP; + return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } static struct net_device *packet_cached_dev_get(struct packet_sock *po) @@ -313,8 +280,9 @@ static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) return (u16) raw_smp_processor_id() % dev->real_num_tx_queues; } -static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) +static u16 packet_pick_tx_queue(struct sk_buff *skb) { + struct net_device *dev = skb->dev; const struct net_device_ops *ops = dev->netdev_ops; u16 queue_index; @@ -326,7 +294,7 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) queue_index = __packet_pick_tx_queue(dev, skb); } - skb_set_queue_mapping(skb, queue_index); + return queue_index; } /* __register_prot_hook must be invoked through register_prot_hook @@ -4281,7 +4249,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; if (po->tp_version >= TPACKET_V3 && req->tp_block_size <= - BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv)) + BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + sizeof(struct tpacket3_hdr)) goto out; if (unlikely(req->tp_frame_size < po->tp_hdrlen + po->tp_reserve)) diff --git a/net/qrtr/Kconfig b/net/qrtr/Kconfig index 326fd97444f5b..1944834d225cf 100644 --- a/net/qrtr/Kconfig +++ b/net/qrtr/Kconfig @@ -21,4 +21,11 @@ config QRTR_SMD Say Y here to support SMD based ipcrouter channels. SMD is the most common transport for IPC Router. +config QRTR_TUN + tristate "TUN device for Qualcomm IPC Router" + ---help--- + Say Y here to expose a character device that allows user space to + implement endpoints of QRTR, for purpose of tunneling data to other + hosts or testing purposes. + endif # QRTR diff --git a/net/qrtr/Makefile b/net/qrtr/Makefile index ab09e40f7c74b..be012bfd3e525 100644 --- a/net/qrtr/Makefile +++ b/net/qrtr/Makefile @@ -2,3 +2,5 @@ obj-$(CONFIG_QRTR) := qrtr.o obj-$(CONFIG_QRTR_SMD) += qrtr-smd.o qrtr-smd-y := smd.o +obj-$(CONFIG_QRTR_TUN) += qrtr-tun.o +qrtr-tun-y := tun.o diff --git a/net/qrtr/tun.c b/net/qrtr/tun.c new file mode 100644 index 0000000000000..ccff1e544c218 --- /dev/null +++ b/net/qrtr/tun.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Linaro Ltd */ + +#include <linux/miscdevice.h> +#include <linux/module.h> +#include <linux/poll.h> +#include <linux/skbuff.h> +#include <linux/uaccess.h> + +#include "qrtr.h" + +struct qrtr_tun { + struct qrtr_endpoint ep; + + struct sk_buff_head queue; + wait_queue_head_t readq; +}; + +static int qrtr_tun_send(struct qrtr_endpoint *ep, struct sk_buff *skb) +{ + struct qrtr_tun *tun = container_of(ep, struct qrtr_tun, ep); + + skb_queue_tail(&tun->queue, skb); + + /* wake up any blocking processes, waiting for new data */ + wake_up_interruptible(&tun->readq); + + return 0; +} + +static int qrtr_tun_open(struct inode *inode, struct file *filp) +{ + struct qrtr_tun *tun; + + tun = kzalloc(sizeof(*tun), GFP_KERNEL); + if (!tun) + return -ENOMEM; + + skb_queue_head_init(&tun->queue); + init_waitqueue_head(&tun->readq); + + tun->ep.xmit = qrtr_tun_send; + + filp->private_data = tun; + + return qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); +} + +static ssize_t qrtr_tun_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct file *filp = iocb->ki_filp; + struct qrtr_tun *tun = filp->private_data; + struct sk_buff *skb; + int count; + + while (!(skb = skb_dequeue(&tun->queue))) { + if (filp->f_flags & O_NONBLOCK) + return -EAGAIN; + + /* Wait until we get data or the endpoint goes away */ + if (wait_event_interruptible(tun->readq, + !skb_queue_empty(&tun->queue))) + return -ERESTARTSYS; + } + + count = min_t(size_t, iov_iter_count(to), skb->len); + if (copy_to_iter(skb->data, count, to) != count) + count = -EFAULT; + + kfree_skb(skb); + + return count; +} + +static ssize_t qrtr_tun_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *filp = iocb->ki_filp; + struct qrtr_tun *tun = filp->private_data; + size_t len = iov_iter_count(from); + ssize_t ret; + void *kbuf; + + kbuf = kzalloc(len, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + if (!copy_from_iter_full(kbuf, len, from)) + return -EFAULT; + + ret = qrtr_endpoint_post(&tun->ep, kbuf, len); + + return ret < 0 ? ret : len; +} + +static __poll_t qrtr_tun_poll(struct file *filp, poll_table *wait) +{ + struct qrtr_tun *tun = filp->private_data; + __poll_t mask = 0; + + poll_wait(filp, &tun->readq, wait); + + if (!skb_queue_empty(&tun->queue)) + mask |= EPOLLIN | EPOLLRDNORM; + + return mask; +} + +static int qrtr_tun_release(struct inode *inode, struct file *filp) +{ + struct qrtr_tun *tun = filp->private_data; + struct sk_buff *skb; + + qrtr_endpoint_unregister(&tun->ep); + + /* Discard all SKBs */ + while (!skb_queue_empty(&tun->queue)) { + skb = skb_dequeue(&tun->queue); + kfree_skb(skb); + } + + kfree(tun); + + return 0; +} + +static const struct file_operations qrtr_tun_ops = { + .owner = THIS_MODULE, + .open = qrtr_tun_open, + .poll = qrtr_tun_poll, + .read_iter = qrtr_tun_read_iter, + .write_iter = qrtr_tun_write_iter, + .release = qrtr_tun_release, +}; + +static struct miscdevice qrtr_tun_miscdev = { + MISC_DYNAMIC_MINOR, + "qrtr-tun", + &qrtr_tun_ops, +}; + +static int __init qrtr_tun_init(void) +{ + int ret; + + ret = misc_register(&qrtr_tun_miscdev); + if (ret) + pr_err("failed to register Qualcomm IPC Router tun device\n"); + + return ret; +} + +static void __exit qrtr_tun_exit(void) +{ + misc_deregister(&qrtr_tun_miscdev); +} + +module_init(qrtr_tun_init); +module_exit(qrtr_tun_exit); + +MODULE_DESCRIPTION("Qualcomm IPC Router TUN device"); +MODULE_LICENSE("GPL v2"); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 59d0eb9602758..a7a4e6ff9be29 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -178,9 +178,10 @@ static void rfkill_led_trigger_unregister(struct rfkill *rfkill) } static struct led_trigger rfkill_any_led_trigger; -static struct work_struct rfkill_any_work; +static struct led_trigger rfkill_none_led_trigger; +static struct work_struct rfkill_global_led_trigger_work; -static void rfkill_any_led_trigger_worker(struct work_struct *work) +static void rfkill_global_led_trigger_worker(struct work_struct *work) { enum led_brightness brightness = LED_OFF; struct rfkill *rfkill; @@ -195,30 +196,43 @@ static void rfkill_any_led_trigger_worker(struct work_struct *work) mutex_unlock(&rfkill_global_mutex); led_trigger_event(&rfkill_any_led_trigger, brightness); + led_trigger_event(&rfkill_none_led_trigger, + brightness == LED_OFF ? LED_FULL : LED_OFF); } -static void rfkill_any_led_trigger_event(void) +static void rfkill_global_led_trigger_event(void) { - schedule_work(&rfkill_any_work); + schedule_work(&rfkill_global_led_trigger_work); } -static void rfkill_any_led_trigger_activate(struct led_classdev *led_cdev) +static int rfkill_global_led_trigger_register(void) { - rfkill_any_led_trigger_event(); -} + int ret; + + INIT_WORK(&rfkill_global_led_trigger_work, + rfkill_global_led_trigger_worker); -static int rfkill_any_led_trigger_register(void) -{ - INIT_WORK(&rfkill_any_work, rfkill_any_led_trigger_worker); rfkill_any_led_trigger.name = "rfkill-any"; - rfkill_any_led_trigger.activate = rfkill_any_led_trigger_activate; - return led_trigger_register(&rfkill_any_led_trigger); + ret = led_trigger_register(&rfkill_any_led_trigger); + if (ret) + return ret; + + rfkill_none_led_trigger.name = "rfkill-none"; + ret = led_trigger_register(&rfkill_none_led_trigger); + if (ret) + led_trigger_unregister(&rfkill_any_led_trigger); + else + /* Delay activation until all global triggers are registered */ + rfkill_global_led_trigger_event(); + + return ret; } -static void rfkill_any_led_trigger_unregister(void) +static void rfkill_global_led_trigger_unregister(void) { + led_trigger_unregister(&rfkill_none_led_trigger); led_trigger_unregister(&rfkill_any_led_trigger); - cancel_work_sync(&rfkill_any_work); + cancel_work_sync(&rfkill_global_led_trigger_work); } #else static void rfkill_led_trigger_event(struct rfkill *rfkill) @@ -234,16 +248,16 @@ static inline void rfkill_led_trigger_unregister(struct rfkill *rfkill) { } -static void rfkill_any_led_trigger_event(void) +static void rfkill_global_led_trigger_event(void) { } -static int rfkill_any_led_trigger_register(void) +static int rfkill_global_led_trigger_register(void) { return 0; } -static void rfkill_any_led_trigger_unregister(void) +static void rfkill_global_led_trigger_unregister(void) { } #endif /* CONFIG_RFKILL_LEDS */ @@ -354,7 +368,7 @@ static void rfkill_set_block(struct rfkill *rfkill, bool blocked) spin_unlock_irqrestore(&rfkill->lock, flags); rfkill_led_trigger_event(rfkill); - rfkill_any_led_trigger_event(); + rfkill_global_led_trigger_event(); if (prev != curr) rfkill_event(rfkill); @@ -535,7 +549,7 @@ bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked) spin_unlock_irqrestore(&rfkill->lock, flags); rfkill_led_trigger_event(rfkill); - rfkill_any_led_trigger_event(); + rfkill_global_led_trigger_event(); if (rfkill->registered && prev != blocked) schedule_work(&rfkill->uevent_work); @@ -579,7 +593,7 @@ bool rfkill_set_sw_state(struct rfkill *rfkill, bool blocked) schedule_work(&rfkill->uevent_work); rfkill_led_trigger_event(rfkill); - rfkill_any_led_trigger_event(); + rfkill_global_led_trigger_event(); return blocked; } @@ -629,7 +643,7 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw) schedule_work(&rfkill->uevent_work); rfkill_led_trigger_event(rfkill); - rfkill_any_led_trigger_event(); + rfkill_global_led_trigger_event(); } } EXPORT_SYMBOL(rfkill_set_states); @@ -1046,7 +1060,7 @@ int __must_check rfkill_register(struct rfkill *rfkill) #endif } - rfkill_any_led_trigger_event(); + rfkill_global_led_trigger_event(); rfkill_send_events(rfkill, RFKILL_OP_ADD); mutex_unlock(&rfkill_global_mutex); @@ -1079,7 +1093,7 @@ void rfkill_unregister(struct rfkill *rfkill) mutex_lock(&rfkill_global_mutex); rfkill_send_events(rfkill, RFKILL_OP_DEL); list_del_init(&rfkill->node); - rfkill_any_led_trigger_event(); + rfkill_global_led_trigger_event(); mutex_unlock(&rfkill_global_mutex); rfkill_led_trigger_unregister(rfkill); @@ -1332,7 +1346,7 @@ static int __init rfkill_init(void) if (error) goto error_misc; - error = rfkill_any_led_trigger_register(); + error = rfkill_global_led_trigger_register(); if (error) goto error_led_trigger; @@ -1346,7 +1360,7 @@ static int __init rfkill_init(void) #ifdef CONFIG_RFKILL_INPUT error_input: - rfkill_any_led_trigger_unregister(); + rfkill_global_led_trigger_unregister(); #endif error_led_trigger: misc_deregister(&rfkill_miscdev); @@ -1362,7 +1376,7 @@ static void __exit rfkill_exit(void) #ifdef CONFIG_RFKILL_INPUT rfkill_handler_exit(); #endif - rfkill_any_led_trigger_unregister(); + rfkill_global_led_trigger_unregister(); misc_deregister(&rfkill_miscdev); class_unregister(&rfkill_class); } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 29923ec2189cb..5fb7d3254d9e2 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -477,6 +477,7 @@ enum rxrpc_call_flag { RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ + RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ }; /* @@ -624,6 +625,7 @@ struct rxrpc_call { */ rxrpc_seq_t rx_top; /* Highest Rx slot allocated. */ rxrpc_seq_t rx_expect_next; /* Expected next packet sequence number */ + rxrpc_serial_t rx_serial; /* Highest serial received for this call */ u8 rx_winsize; /* Size of Rx window */ u8 tx_winsize; /* Maximum size of Tx window */ bool tx_phase; /* T if transmission phase, F if receive phase */ diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 6e0d788b4dc43..20210418904bf 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -392,7 +392,13 @@ recheck_state: /* Process events */ if (test_and_clear_bit(RXRPC_CALL_EV_EXPIRED, &call->events)) { - rxrpc_abort_call("EXP", call, 0, RX_USER_ABORT, -ETIME); + if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && + (int)call->conn->hi_serial - (int)call->rx_serial > 0) { + trace_rxrpc_call_reset(call); + rxrpc_abort_call("EXP", call, 0, RX_USER_ABORT, -ECONNRESET); + } else { + rxrpc_abort_call("EXP", call, 0, RX_USER_ABORT, -ETIME); + } set_bit(RXRPC_CALL_EV_ABORT, &call->events); goto recheck_state; } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 1350f1be8037b..8229a52c2acd7 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -70,7 +70,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, iov[2].iov_len = sizeof(ack_info); pkt.whdr.epoch = htonl(conn->proto.epoch); - pkt.whdr.cid = htonl(conn->proto.cid); + pkt.whdr.cid = htonl(conn->proto.cid | channel); pkt.whdr.callNumber = htonl(call_id); pkt.whdr.seq = 0; pkt.whdr.type = chan->last_type; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index b5fd6381313d0..608d078a4981f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1278,8 +1278,14 @@ void rxrpc_data_ready(struct sock *udp_sk) call = NULL; } - if (call && sp->hdr.serviceId != call->service_id) - call->service_id = sp->hdr.serviceId; + if (call) { + if (sp->hdr.serviceId != call->service_id) + call->service_id = sp->hdr.serviceId; + if ((int)sp->hdr.serial - (int)call->rx_serial > 0) + call->rx_serial = sp->hdr.serial; + if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) + set_bit(RXRPC_CALL_RX_HEARD, &call->flags); + } } else { skew = 0; call = NULL; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 72251241665ad..3f4cf930f809b 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -77,9 +77,9 @@ static void free_tcf(struct tc_action *p) static void tcf_idr_remove(struct tcf_idrinfo *idrinfo, struct tc_action *p) { - spin_lock_bh(&idrinfo->lock); + spin_lock(&idrinfo->lock); idr_remove(&idrinfo->action_idr, p->tcfa_index); - spin_unlock_bh(&idrinfo->lock); + spin_unlock(&idrinfo->lock); gen_kill_estimator(&p->tcfa_rate_est); free_tcf(p); } @@ -156,7 +156,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, struct tc_action *p; unsigned long id = 1; - spin_lock_bh(&idrinfo->lock); + spin_lock(&idrinfo->lock); s_i = cb->args[0]; @@ -191,7 +191,7 @@ done: if (index >= 0) cb->args[0] = index + 1; - spin_unlock_bh(&idrinfo->lock); + spin_unlock(&idrinfo->lock); if (n_i) { if (act_flags & TCA_FLAG_LARGE_DUMP_ON) cb->args[1] = n_i; @@ -261,9 +261,9 @@ static struct tc_action *tcf_idr_lookup(u32 index, struct tcf_idrinfo *idrinfo) { struct tc_action *p = NULL; - spin_lock_bh(&idrinfo->lock); + spin_lock(&idrinfo->lock); p = idr_find(&idrinfo->action_idr, index); - spin_unlock_bh(&idrinfo->lock); + spin_unlock(&idrinfo->lock); return p; } @@ -323,7 +323,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, } spin_lock_init(&p->tcfa_lock); idr_preload(GFP_KERNEL); - spin_lock_bh(&idrinfo->lock); + spin_lock(&idrinfo->lock); /* user doesn't specify an index */ if (!index) { index = 1; @@ -331,7 +331,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, } else { err = idr_alloc_u32(idr, NULL, &index, index, GFP_ATOMIC); } - spin_unlock_bh(&idrinfo->lock); + spin_unlock(&idrinfo->lock); idr_preload_end(); if (err) goto err3; @@ -369,9 +369,9 @@ void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a) { struct tcf_idrinfo *idrinfo = tn->idrinfo; - spin_lock_bh(&idrinfo->lock); + spin_lock(&idrinfo->lock); idr_replace(&idrinfo->action_idr, a, a->tcfa_index); - spin_unlock_bh(&idrinfo->lock); + spin_unlock(&idrinfo->lock); } EXPORT_SYMBOL(tcf_idr_insert); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 7e28b2ce14376..526a8e491626e 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -648,6 +648,11 @@ static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static size_t tcf_csum_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_csum)); +} + static struct tc_action_ops act_csum_ops = { .kind = "csum", .type = TCA_ACT_CSUM, @@ -658,6 +663,7 @@ static struct tc_action_ops act_csum_ops = { .cleanup = tcf_csum_cleanup, .walk = tcf_csum_walker, .lookup = tcf_csum_search, + .get_fill_size = tcf_csum_get_fill_size, .size = sizeof(struct tcf_csum), }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index a57e112d9b3ee..cdc3c87c53e62 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -103,9 +103,10 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) } EXPORT_SYMBOL(unregister_tcf_proto_ops); -bool tcf_queue_work(struct work_struct *work) +bool tcf_queue_work(struct rcu_work *rwork, work_func_t func) { - return queue_work(tc_filter_wq, work); + INIT_RCU_WORK(rwork, func); + return queue_rcu_work(tc_filter_wq, rwork); } EXPORT_SYMBOL(tcf_queue_work); @@ -436,6 +437,78 @@ static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index) return idr_find(&tn->idr, block_index); } +/* Find tcf block. + * Set q, parent, cl when appropriate. + */ + +static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, + u32 *parent, unsigned long *cl, + int ifindex, u32 block_index, + struct netlink_ext_ack *extack) +{ + struct tcf_block *block; + + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { + block = tcf_block_lookup(net, block_index); + if (!block) { + NL_SET_ERR_MSG(extack, "Block of given index was not found"); + return ERR_PTR(-EINVAL); + } + } else { + const struct Qdisc_class_ops *cops; + struct net_device *dev; + + /* Find link */ + dev = __dev_get_by_index(net, ifindex); + if (!dev) + return ERR_PTR(-ENODEV); + + /* Find qdisc */ + if (!*parent) { + *q = dev->qdisc; + *parent = (*q)->handle; + } else { + *q = qdisc_lookup(dev, TC_H_MAJ(*parent)); + if (!*q) { + NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); + return ERR_PTR(-EINVAL); + } + } + + /* Is it classful? */ + cops = (*q)->ops->cl_ops; + if (!cops) { + NL_SET_ERR_MSG(extack, "Qdisc not classful"); + return ERR_PTR(-EINVAL); + } + + if (!cops->tcf_block) { + NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); + return ERR_PTR(-EOPNOTSUPP); + } + + /* Do we search for filter, attached to class? */ + if (TC_H_MIN(*parent)) { + *cl = cops->find(*q, *parent); + if (*cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); + return ERR_PTR(-ENOENT); + } + } + + /* And the last stroke */ + block = cops->tcf_block(*q, *cl, extack); + if (!block) + return ERR_PTR(-EINVAL); + if (tcf_block_shared(block)) { + NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters"); + return ERR_PTR(-EOPNOTSUPP); + } + } + + return block; +} + static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block) { return list_first_entry(&block->chain_list, struct tcf_chain, list); @@ -983,9 +1056,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, q, parent, 0, event, false); } -/* Add/change/delete/get a filter node */ - -static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, +static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); @@ -1006,8 +1077,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, int err; int tp_created; - if ((n->nlmsg_type != RTM_GETTFILTER) && - !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; replay: @@ -1025,24 +1095,13 @@ replay: cl = 0; if (prio == 0) { - switch (n->nlmsg_type) { - case RTM_DELTFILTER: - if (protocol || t->tcm_handle || tca[TCA_KIND]) { - NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set"); - return -ENOENT; - } - break; - case RTM_NEWTFILTER: - /* If no priority is provided by the user, - * we allocate one. - */ - if (n->nlmsg_flags & NLM_F_CREATE) { - prio = TC_H_MAKE(0x80000000U, 0U); - prio_allocate = true; - break; - } - /* fall-through */ - default: + /* If no priority is provided by the user, + * we allocate one. + */ + if (n->nlmsg_flags & NLM_F_CREATE) { + prio = TC_H_MAKE(0x80000000U, 0U); + prio_allocate = true; + } else { NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero"); return -ENOENT; } @@ -1050,66 +1109,11 @@ replay: /* Find head of filter chain. */ - if (t->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) { - block = tcf_block_lookup(net, t->tcm_block_index); - if (!block) { - NL_SET_ERR_MSG(extack, "Block of given index was not found"); - err = -EINVAL; - goto errout; - } - } else { - const struct Qdisc_class_ops *cops; - struct net_device *dev; - - /* Find link */ - dev = __dev_get_by_index(net, t->tcm_ifindex); - if (!dev) - return -ENODEV; - - /* Find qdisc */ - if (!parent) { - q = dev->qdisc; - parent = q->handle; - } else { - q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent)); - if (!q) { - NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); - return -EINVAL; - } - } - - /* Is it classful? */ - cops = q->ops->cl_ops; - if (!cops) { - NL_SET_ERR_MSG(extack, "Qdisc not classful"); - return -EINVAL; - } - - if (!cops->tcf_block) { - NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); - return -EOPNOTSUPP; - } - - /* Do we search for filter, attached to class? */ - if (TC_H_MIN(parent)) { - cl = cops->find(q, parent); - if (cl == 0) { - NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); - return -ENOENT; - } - } - - /* And the last stroke */ - block = cops->tcf_block(q, cl, extack); - if (!block) { - err = -EINVAL; - goto errout; - } - if (tcf_block_shared(block)) { - NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters"); - err = -EOPNOTSUPP; - goto errout; - } + block = tcf_block_find(net, &q, &parent, &cl, + t->tcm_ifindex, t->tcm_block_index, extack); + if (IS_ERR(block)) { + err = PTR_ERR(block); + goto errout; } chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; @@ -1118,19 +1122,10 @@ replay: err = -EINVAL; goto errout; } - chain = tcf_chain_get(block, chain_index, - n->nlmsg_type == RTM_NEWTFILTER); + chain = tcf_chain_get(block, chain_index, true); if (!chain) { NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); - err = n->nlmsg_type == RTM_NEWTFILTER ? -ENOMEM : -EINVAL; - goto errout; - } - - if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { - tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); - tcf_chain_flush(chain); - err = 0; + err = -ENOMEM; goto errout; } @@ -1151,8 +1146,7 @@ replay: goto errout; } - if (n->nlmsg_type != RTM_NEWTFILTER || - !(n->nlmsg_flags & NLM_F_CREATE)) { + if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter"); err = -ENOENT; goto errout; @@ -1177,56 +1171,15 @@ replay: fh = tp->ops->get(tp, t->tcm_handle); if (!fh) { - if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { - tcf_chain_tp_remove(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_DELTFILTER, false); - tcf_proto_destroy(tp, extack); - err = 0; - goto errout; - } - - if (n->nlmsg_type != RTM_NEWTFILTER || - !(n->nlmsg_flags & NLM_F_CREATE)) { + if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter"); err = -ENOENT; goto errout; } - } else { - bool last; - - switch (n->nlmsg_type) { - case RTM_NEWTFILTER: - if (n->nlmsg_flags & NLM_F_EXCL) { - if (tp_created) - tcf_proto_destroy(tp, NULL); - NL_SET_ERR_MSG(extack, "Filter already exists"); - err = -EEXIST; - goto errout; - } - break; - case RTM_DELTFILTER: - err = tfilter_del_notify(net, skb, n, tp, block, - q, parent, fh, false, &last, - extack); - if (err) - goto errout; - if (last) { - tcf_chain_tp_remove(chain, &chain_info, tp); - tcf_proto_destroy(tp, extack); - } - goto errout; - case RTM_GETTFILTER: - err = tfilter_notify(net, skb, n, tp, block, q, parent, - fh, RTM_NEWTFILTER, true); - if (err < 0) - NL_SET_ERR_MSG(extack, "Failed to send filter notify message"); - goto errout; - default: - NL_SET_ERR_MSG(extack, "Invalid netlink message type"); - err = -EINVAL; - goto errout; - } + } else if (n->nlmsg_flags & NLM_F_EXCL) { + NL_SET_ERR_MSG(extack, "Filter already exists"); + err = -EEXIST; + goto errout; } err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, @@ -1251,6 +1204,202 @@ errout: return err; } +static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; + struct tcmsg *t; + u32 protocol; + u32 prio; + u32 parent; + u32 chain_index; + struct Qdisc *q = NULL; + struct tcf_chain_info chain_info; + struct tcf_chain *chain = NULL; + struct tcf_block *block; + struct tcf_proto *tp = NULL; + unsigned long cl = 0; + void *fh = NULL; + int err; + + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack); + if (err < 0) + return err; + + t = nlmsg_data(n); + protocol = TC_H_MIN(t->tcm_info); + prio = TC_H_MAJ(t->tcm_info); + parent = t->tcm_parent; + + if (prio == 0 && (protocol || t->tcm_handle || tca[TCA_KIND])) { + NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set"); + return -ENOENT; + } + + /* Find head of filter chain. */ + + block = tcf_block_find(net, &q, &parent, &cl, + t->tcm_ifindex, t->tcm_block_index, extack); + if (IS_ERR(block)) { + err = PTR_ERR(block); + goto errout; + } + + chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + if (chain_index > TC_ACT_EXT_VAL_MASK) { + NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); + err = -EINVAL; + goto errout; + } + chain = tcf_chain_get(block, chain_index, false); + if (!chain) { + NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); + err = -EINVAL; + goto errout; + } + + if (prio == 0) { + tfilter_notify_chain(net, skb, block, q, parent, n, + chain, RTM_DELTFILTER); + tcf_chain_flush(chain); + err = 0; + goto errout; + } + + tp = tcf_chain_tp_find(chain, &chain_info, protocol, + prio, false); + if (!tp || IS_ERR(tp)) { + NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); + err = tp ? PTR_ERR(tp) : -ENOENT; + goto errout; + } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { + NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); + err = -EINVAL; + goto errout; + } + + fh = tp->ops->get(tp, t->tcm_handle); + + if (!fh) { + if (t->tcm_handle == 0) { + tcf_chain_tp_remove(chain, &chain_info, tp); + tfilter_notify(net, skb, n, tp, block, q, parent, fh, + RTM_DELTFILTER, false); + tcf_proto_destroy(tp, extack); + err = 0; + } else { + NL_SET_ERR_MSG(extack, "Specified filter handle not found"); + err = -ENOENT; + } + } else { + bool last; + + err = tfilter_del_notify(net, skb, n, tp, block, + q, parent, fh, false, &last, + extack); + if (err) + goto errout; + if (last) { + tcf_chain_tp_remove(chain, &chain_info, tp); + tcf_proto_destroy(tp, extack); + } + } + +errout: + if (chain) + tcf_chain_put(chain); + return err; +} + +static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; + struct tcmsg *t; + u32 protocol; + u32 prio; + u32 parent; + u32 chain_index; + struct Qdisc *q = NULL; + struct tcf_chain_info chain_info; + struct tcf_chain *chain = NULL; + struct tcf_block *block; + struct tcf_proto *tp = NULL; + unsigned long cl = 0; + void *fh = NULL; + int err; + + err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack); + if (err < 0) + return err; + + t = nlmsg_data(n); + protocol = TC_H_MIN(t->tcm_info); + prio = TC_H_MAJ(t->tcm_info); + parent = t->tcm_parent; + + if (prio == 0) { + NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero"); + return -ENOENT; + } + + /* Find head of filter chain. */ + + block = tcf_block_find(net, &q, &parent, &cl, + t->tcm_ifindex, t->tcm_block_index, extack); + if (IS_ERR(block)) { + err = PTR_ERR(block); + goto errout; + } + + chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + if (chain_index > TC_ACT_EXT_VAL_MASK) { + NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); + err = -EINVAL; + goto errout; + } + chain = tcf_chain_get(block, chain_index, false); + if (!chain) { + NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); + err = -EINVAL; + goto errout; + } + + tp = tcf_chain_tp_find(chain, &chain_info, protocol, + prio, false); + if (!tp || IS_ERR(tp)) { + NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); + err = tp ? PTR_ERR(tp) : -ENOENT; + goto errout; + } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { + NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); + err = -EINVAL; + goto errout; + } + + fh = tp->ops->get(tp, t->tcm_handle); + + if (!fh) { + NL_SET_ERR_MSG(extack, "Specified filter handle not found"); + err = -ENOENT; + } else { + err = tfilter_notify(net, skb, n, tp, block, q, parent, + fh, RTM_NEWTFILTER, true); + if (err < 0) + NL_SET_ERR_MSG(extack, "Failed to send filter notify message"); + } + +errout: + if (chain) + tcf_chain_put(chain); + return err; +} + struct tcf_dump_args { struct tcf_walker w; struct sk_buff *skb; @@ -1633,9 +1782,9 @@ static int __init tc_filter_init(void) if (err) goto err_register_pernet_subsys; - rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter, + rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter, tc_dump_tfilter, 0); return 0; diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 6b7ab3512f5bb..95367f37098de 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -35,10 +35,7 @@ struct basic_filter { struct tcf_result res; struct tcf_proto *tp; struct list_head link; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; }; static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -97,21 +94,14 @@ static void __basic_delete_filter(struct basic_filter *f) static void basic_delete_filter_work(struct work_struct *work) { - struct basic_filter *f = container_of(work, struct basic_filter, work); - + struct basic_filter *f = container_of(to_rcu_work(work), + struct basic_filter, + rwork); rtnl_lock(); __basic_delete_filter(f); rtnl_unlock(); } -static void basic_delete_filter(struct rcu_head *head) -{ - struct basic_filter *f = container_of(head, struct basic_filter, rcu); - - INIT_WORK(&f->work, basic_delete_filter_work); - tcf_queue_work(&f->work); -} - static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct basic_head *head = rtnl_dereference(tp->root); @@ -122,7 +112,7 @@ static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) tcf_unbind_filter(tp, &f->res); idr_remove(&head->handle_idr, f->handle); if (tcf_exts_get_net(&f->exts)) - call_rcu(&f->rcu, basic_delete_filter); + tcf_queue_work(&f->rwork, basic_delete_filter_work); else __basic_delete_filter(f); } @@ -140,7 +130,7 @@ static int basic_delete(struct tcf_proto *tp, void *arg, bool *last, tcf_unbind_filter(tp, &f->res); idr_remove(&head->handle_idr, f->handle); tcf_exts_get_net(&f->exts); - call_rcu(&f->rcu, basic_delete_filter); + tcf_queue_work(&f->rwork, basic_delete_filter_work); *last = list_empty(&head->flist); return 0; } @@ -234,7 +224,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, list_replace_rcu(&fold->link, &fnew->link); tcf_unbind_filter(tp, &fold->res); tcf_exts_get_net(&fold->exts); - call_rcu(&fold->rcu, basic_delete_filter); + tcf_queue_work(&fold->rwork, basic_delete_filter_work); } else { list_add_rcu(&fnew->link, &head->flist); } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index b07c1fa8bc0dd..1aa7f6511065a 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -49,10 +49,7 @@ struct cls_bpf_prog { struct sock_filter *bpf_ops; const char *bpf_name; struct tcf_proto *tp; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; }; static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { @@ -275,21 +272,14 @@ static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog) static void cls_bpf_delete_prog_work(struct work_struct *work) { - struct cls_bpf_prog *prog = container_of(work, struct cls_bpf_prog, work); - + struct cls_bpf_prog *prog = container_of(to_rcu_work(work), + struct cls_bpf_prog, + rwork); rtnl_lock(); __cls_bpf_delete_prog(prog); rtnl_unlock(); } -static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu) -{ - struct cls_bpf_prog *prog = container_of(rcu, struct cls_bpf_prog, rcu); - - INIT_WORK(&prog->work, cls_bpf_delete_prog_work); - tcf_queue_work(&prog->work); -} - static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog, struct netlink_ext_ack *extack) { @@ -300,7 +290,7 @@ static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog, list_del_rcu(&prog->link); tcf_unbind_filter(tp, &prog->res); if (tcf_exts_get_net(&prog->exts)) - call_rcu(&prog->rcu, cls_bpf_delete_prog_rcu); + tcf_queue_work(&prog->rwork, cls_bpf_delete_prog_work); else __cls_bpf_delete_prog(prog); } @@ -526,7 +516,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, list_replace_rcu(&oldprog->link, &prog->link); tcf_unbind_filter(tp, &oldprog->res); tcf_exts_get_net(&oldprog->exts); - call_rcu(&oldprog->rcu, cls_bpf_delete_prog_rcu); + tcf_queue_work(&oldprog->rwork, cls_bpf_delete_prog_work); } else { list_add_rcu(&prog->link, &head->plist); } diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 762da5c0cf5ea..3bc01bdde1659 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -23,10 +23,7 @@ struct cls_cgroup_head { struct tcf_exts exts; struct tcf_ematch_tree ematches; struct tcf_proto *tp; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; }; static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -70,24 +67,14 @@ static void __cls_cgroup_destroy(struct cls_cgroup_head *head) static void cls_cgroup_destroy_work(struct work_struct *work) { - struct cls_cgroup_head *head = container_of(work, + struct cls_cgroup_head *head = container_of(to_rcu_work(work), struct cls_cgroup_head, - work); + rwork); rtnl_lock(); __cls_cgroup_destroy(head); rtnl_unlock(); } -static void cls_cgroup_destroy_rcu(struct rcu_head *root) -{ - struct cls_cgroup_head *head = container_of(root, - struct cls_cgroup_head, - rcu); - - INIT_WORK(&head->work, cls_cgroup_destroy_work); - tcf_queue_work(&head->work); -} - static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -134,7 +121,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, rcu_assign_pointer(tp->root, new); if (head) { tcf_exts_get_net(&head->exts); - call_rcu(&head->rcu, cls_cgroup_destroy_rcu); + tcf_queue_work(&head->rwork, cls_cgroup_destroy_work); } return 0; errout: @@ -151,7 +138,7 @@ static void cls_cgroup_destroy(struct tcf_proto *tp, /* Head can still be NULL due to cls_cgroup_init(). */ if (head) { if (tcf_exts_get_net(&head->exts)) - call_rcu(&head->rcu, cls_cgroup_destroy_rcu); + tcf_queue_work(&head->rwork, cls_cgroup_destroy_work); else __cls_cgroup_destroy(head); } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index cd5fe383afddd..2bb043cd436b3 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -57,10 +57,7 @@ struct flow_filter { u32 divisor; u32 baseclass; u32 hashrnd; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; }; static inline u32 addr_fold(void *addr) @@ -383,21 +380,14 @@ static void __flow_destroy_filter(struct flow_filter *f) static void flow_destroy_filter_work(struct work_struct *work) { - struct flow_filter *f = container_of(work, struct flow_filter, work); - + struct flow_filter *f = container_of(to_rcu_work(work), + struct flow_filter, + rwork); rtnl_lock(); __flow_destroy_filter(f); rtnl_unlock(); } -static void flow_destroy_filter(struct rcu_head *head) -{ - struct flow_filter *f = container_of(head, struct flow_filter, rcu); - - INIT_WORK(&f->work, flow_destroy_filter_work); - tcf_queue_work(&f->work); -} - static int flow_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -563,7 +553,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, if (fold) { tcf_exts_get_net(&fold->exts); - call_rcu(&fold->rcu, flow_destroy_filter); + tcf_queue_work(&fold->rwork, flow_destroy_filter_work); } return 0; @@ -583,7 +573,7 @@ static int flow_delete(struct tcf_proto *tp, void *arg, bool *last, list_del_rcu(&f->list); tcf_exts_get_net(&f->exts); - call_rcu(&f->rcu, flow_destroy_filter); + tcf_queue_work(&f->rwork, flow_destroy_filter_work); *last = list_empty(&head->filters); return 0; } @@ -608,7 +598,7 @@ static void flow_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) list_for_each_entry_safe(f, next, &head->filters, list) { list_del_rcu(&f->list); if (tcf_exts_get_net(&f->exts)) - call_rcu(&f->rcu, flow_destroy_filter); + tcf_queue_work(&f->rwork, flow_destroy_filter_work); else __flow_destroy_filter(f); } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index c79f6e71512e5..2b5be42a9f1ca 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -61,24 +61,24 @@ struct fl_flow_mask_range { struct fl_flow_mask { struct fl_flow_key key; struct fl_flow_mask_range range; - struct rcu_head rcu; + struct rhash_head ht_node; + struct rhashtable ht; + struct rhashtable_params filter_ht_params; + struct flow_dissector dissector; + struct list_head filters; + struct rcu_head rcu; + struct list_head list; }; struct cls_fl_head { struct rhashtable ht; - struct fl_flow_mask mask; - struct flow_dissector dissector; - bool mask_assigned; - struct list_head filters; - struct rhashtable_params ht_params; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct list_head masks; + struct rcu_work rwork; struct idr handle_idr; }; struct cls_fl_filter { + struct fl_flow_mask *mask; struct rhash_head ht_node; struct fl_flow_key mkey; struct tcf_exts exts; @@ -87,13 +87,17 @@ struct cls_fl_filter { struct list_head list; u32 handle; u32 flags; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; struct net_device *hw_dev; }; +static const struct rhashtable_params mask_ht_params = { + .key_offset = offsetof(struct fl_flow_mask, key), + .key_len = sizeof(struct fl_flow_key), + .head_offset = offsetof(struct fl_flow_mask, ht_node), + .automatic_shrinking = true, +}; + static unsigned short int fl_mask_range(const struct fl_flow_mask *mask) { return mask->range.end - mask->range.start; @@ -103,13 +107,19 @@ static void fl_mask_update_range(struct fl_flow_mask *mask) { const u8 *bytes = (const u8 *) &mask->key; size_t size = sizeof(mask->key); - size_t i, first = 0, last = size - 1; + size_t i, first = 0, last; - for (i = 0; i < sizeof(mask->key); i++) { + for (i = 0; i < size; i++) { + if (bytes[i]) { + first = i; + break; + } + } + last = first; + for (i = size - 1; i != first; i--) { if (bytes[i]) { - if (!first && i) - first = i; last = i; + break; } } mask->range.start = rounddown(first, sizeof(long)); @@ -140,12 +150,11 @@ static void fl_clear_masked_range(struct fl_flow_key *key, memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask)); } -static struct cls_fl_filter *fl_lookup(struct cls_fl_head *head, +static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask, struct fl_flow_key *mkey) { - return rhashtable_lookup_fast(&head->ht, - fl_key_get_start(mkey, &head->mask), - head->ht_params); + return rhashtable_lookup_fast(&mask->ht, fl_key_get_start(mkey, mask), + mask->filter_ht_params); } static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -153,28 +162,28 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, { struct cls_fl_head *head = rcu_dereference_bh(tp->root); struct cls_fl_filter *f; + struct fl_flow_mask *mask; struct fl_flow_key skb_key; struct fl_flow_key skb_mkey; - if (!atomic_read(&head->ht.nelems)) - return -1; - - fl_clear_masked_range(&skb_key, &head->mask); + list_for_each_entry_rcu(mask, &head->masks, list) { + fl_clear_masked_range(&skb_key, mask); - skb_key.indev_ifindex = skb->skb_iif; - /* skb_flow_dissect() does not set n_proto in case an unknown protocol, - * so do it rather here. - */ - skb_key.basic.n_proto = skb->protocol; - skb_flow_dissect_tunnel_info(skb, &head->dissector, &skb_key); - skb_flow_dissect(skb, &head->dissector, &skb_key, 0); + skb_key.indev_ifindex = skb->skb_iif; + /* skb_flow_dissect() does not set n_proto in case an unknown + * protocol, so do it rather here. + */ + skb_key.basic.n_proto = skb->protocol; + skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); + skb_flow_dissect(skb, &mask->dissector, &skb_key, 0); - fl_set_masked_key(&skb_mkey, &skb_key, &head->mask); + fl_set_masked_key(&skb_mkey, &skb_key, mask); - f = fl_lookup(head, &skb_mkey); - if (f && !tc_skip_sw(f->flags)) { - *res = f->res; - return tcf_exts_exec(skb, &f->exts, res); + f = fl_lookup(mask, &skb_mkey); + if (f && !tc_skip_sw(f->flags)) { + *res = f->res; + return tcf_exts_exec(skb, &f->exts, res); + } } return -1; } @@ -187,11 +196,28 @@ static int fl_init(struct tcf_proto *tp) if (!head) return -ENOBUFS; - INIT_LIST_HEAD_RCU(&head->filters); + INIT_LIST_HEAD_RCU(&head->masks); rcu_assign_pointer(tp->root, head); idr_init(&head->handle_idr); - return 0; + return rhashtable_init(&head->ht, &mask_ht_params); +} + +static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask, + bool async) +{ + if (!list_empty(&mask->filters)) + return false; + + rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params); + rhashtable_destroy(&mask->ht); + list_del_rcu(&mask->list); + if (async) + kfree_rcu(mask, rcu); + else + kfree(mask); + + return true; } static void __fl_destroy_filter(struct cls_fl_filter *f) @@ -203,21 +229,14 @@ static void __fl_destroy_filter(struct cls_fl_filter *f) static void fl_destroy_filter_work(struct work_struct *work) { - struct cls_fl_filter *f = container_of(work, struct cls_fl_filter, work); + struct cls_fl_filter *f = container_of(to_rcu_work(work), + struct cls_fl_filter, rwork); rtnl_lock(); __fl_destroy_filter(f); rtnl_unlock(); } -static void fl_destroy_filter(struct rcu_head *head) -{ - struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu); - - INIT_WORK(&f->work, fl_destroy_filter_work); - tcf_queue_work(&f->work); -} - static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f, struct netlink_ext_ack *extack) { @@ -234,8 +253,6 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f, } static int fl_hw_replace_filter(struct tcf_proto *tp, - struct flow_dissector *dissector, - struct fl_flow_key *mask, struct cls_fl_filter *f, struct netlink_ext_ack *extack) { @@ -247,8 +264,8 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = TC_CLSFLOWER_REPLACE; cls_flower.cookie = (unsigned long) f; - cls_flower.dissector = dissector; - cls_flower.mask = mask; + cls_flower.dissector = &f->mask->dissector; + cls_flower.mask = &f->mask->key; cls_flower.key = &f->mkey; cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; @@ -283,51 +300,54 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) &cls_flower, false); } -static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, +static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); + bool async = tcf_exts_get_net(&f->exts); + bool last; idr_remove(&head->handle_idr, f->handle); list_del_rcu(&f->list); + last = fl_mask_put(head, f->mask, async); if (!tc_skip_hw(f->flags)) fl_hw_destroy_filter(tp, f, extack); tcf_unbind_filter(tp, &f->res); - if (tcf_exts_get_net(&f->exts)) - call_rcu(&f->rcu, fl_destroy_filter); + if (async) + tcf_queue_work(&f->rwork, fl_destroy_filter_work); else __fl_destroy_filter(f); + + return last; } static void fl_destroy_sleepable(struct work_struct *work) { - struct cls_fl_head *head = container_of(work, struct cls_fl_head, - work); - if (head->mask_assigned) - rhashtable_destroy(&head->ht); + struct cls_fl_head *head = container_of(to_rcu_work(work), + struct cls_fl_head, + rwork); + + rhashtable_destroy(&head->ht); kfree(head); module_put(THIS_MODULE); } -static void fl_destroy_rcu(struct rcu_head *rcu) -{ - struct cls_fl_head *head = container_of(rcu, struct cls_fl_head, rcu); - - INIT_WORK(&head->work, fl_destroy_sleepable); - schedule_work(&head->work); -} - static void fl_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); + struct fl_flow_mask *mask, *next_mask; struct cls_fl_filter *f, *next; - list_for_each_entry_safe(f, next, &head->filters, list) - __fl_delete(tp, f, extack); + list_for_each_entry_safe(mask, next_mask, &head->masks, list) { + list_for_each_entry_safe(f, next, &mask->filters, list) { + if (__fl_delete(tp, f, extack)) + break; + } + } idr_destroy(&head->handle_idr); __module_get(THIS_MODULE); - call_rcu(&head->rcu, fl_destroy_rcu); + tcf_queue_work(&head->rwork, fl_destroy_sleepable); } static void *fl_get(struct tcf_proto *tp, u32 handle) @@ -715,14 +735,14 @@ static int fl_set_key(struct net *net, struct nlattr **tb, return ret; } -static bool fl_mask_eq(struct fl_flow_mask *mask1, - struct fl_flow_mask *mask2) +static void fl_mask_copy(struct fl_flow_mask *dst, + struct fl_flow_mask *src) { - const long *lmask1 = fl_key_get_start(&mask1->key, mask1); - const long *lmask2 = fl_key_get_start(&mask2->key, mask2); + const void *psrc = fl_key_get_start(&src->key, src); + void *pdst = fl_key_get_start(&dst->key, src); - return !memcmp(&mask1->range, &mask2->range, sizeof(mask1->range)) && - !memcmp(lmask1, lmask2, fl_mask_range(mask1)); + memcpy(pdst, psrc, fl_mask_range(src)); + dst->range = src->range; } static const struct rhashtable_params fl_ht_params = { @@ -731,14 +751,13 @@ static const struct rhashtable_params fl_ht_params = { .automatic_shrinking = true, }; -static int fl_init_hashtable(struct cls_fl_head *head, - struct fl_flow_mask *mask) +static int fl_init_mask_hashtable(struct fl_flow_mask *mask) { - head->ht_params = fl_ht_params; - head->ht_params.key_len = fl_mask_range(mask); - head->ht_params.key_offset += mask->range.start; + mask->filter_ht_params = fl_ht_params; + mask->filter_ht_params.key_len = fl_mask_range(mask); + mask->filter_ht_params.key_offset += mask->range.start; - return rhashtable_init(&head->ht, &head->ht_params); + return rhashtable_init(&mask->ht, &mask->filter_ht_params); } #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) @@ -761,8 +780,7 @@ static int fl_init_hashtable(struct cls_fl_head *head, FL_KEY_SET(keys, cnt, id, member); \ } while(0); -static void fl_init_dissector(struct cls_fl_head *head, - struct fl_flow_mask *mask) +static void fl_init_dissector(struct fl_flow_mask *mask) { struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX]; size_t cnt = 0; @@ -802,31 +820,66 @@ static void fl_init_dissector(struct cls_fl_head *head, FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp); - skb_flow_dissector_init(&head->dissector, keys, cnt); + skb_flow_dissector_init(&mask->dissector, keys, cnt); +} + +static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head, + struct fl_flow_mask *mask) +{ + struct fl_flow_mask *newmask; + int err; + + newmask = kzalloc(sizeof(*newmask), GFP_KERNEL); + if (!newmask) + return ERR_PTR(-ENOMEM); + + fl_mask_copy(newmask, mask); + + err = fl_init_mask_hashtable(newmask); + if (err) + goto errout_free; + + fl_init_dissector(newmask); + + INIT_LIST_HEAD_RCU(&newmask->filters); + + err = rhashtable_insert_fast(&head->ht, &newmask->ht_node, + mask_ht_params); + if (err) + goto errout_destroy; + + list_add_tail_rcu(&newmask->list, &head->masks); + + return newmask; + +errout_destroy: + rhashtable_destroy(&newmask->ht); +errout_free: + kfree(newmask); + + return ERR_PTR(err); } static int fl_check_assign_mask(struct cls_fl_head *head, + struct cls_fl_filter *fnew, + struct cls_fl_filter *fold, struct fl_flow_mask *mask) { - int err; + struct fl_flow_mask *newmask; - if (head->mask_assigned) { - if (!fl_mask_eq(&head->mask, mask)) + fnew->mask = rhashtable_lookup_fast(&head->ht, mask, mask_ht_params); + if (!fnew->mask) { + if (fold) return -EINVAL; - else - return 0; - } - /* Mask is not assigned yet. So assign it and init hashtable - * according to that. - */ - err = fl_init_hashtable(head, mask); - if (err) - return err; - memcpy(&head->mask, mask, sizeof(head->mask)); - head->mask_assigned = true; + newmask = fl_create_new_mask(head, mask); + if (IS_ERR(newmask)) + return PTR_ERR(newmask); - fl_init_dissector(head, mask); + fnew->mask = newmask; + } else if (fold && fold->mask != fnew->mask) { + return -EINVAL; + } return 0; } @@ -924,30 +977,26 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err) goto errout_idr; - err = fl_check_assign_mask(head, &mask); + err = fl_check_assign_mask(head, fnew, fold, &mask); if (err) goto errout_idr; if (!tc_skip_sw(fnew->flags)) { - if (!fold && fl_lookup(head, &fnew->mkey)) { + if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) { err = -EEXIST; - goto errout_idr; + goto errout_mask; } - err = rhashtable_insert_fast(&head->ht, &fnew->ht_node, - head->ht_params); + err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); if (err) - goto errout_idr; + goto errout_mask; } if (!tc_skip_hw(fnew->flags)) { - err = fl_hw_replace_filter(tp, - &head->dissector, - &mask.key, - fnew, - extack); + err = fl_hw_replace_filter(tp, fnew, extack); if (err) - goto errout_idr; + goto errout_mask; } if (!tc_in_hw(fnew->flags)) @@ -955,8 +1004,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (fold) { if (!tc_skip_sw(fold->flags)) - rhashtable_remove_fast(&head->ht, &fold->ht_node, - head->ht_params); + rhashtable_remove_fast(&fold->mask->ht, + &fold->ht_node, + fold->mask->filter_ht_params); if (!tc_skip_hw(fold->flags)) fl_hw_destroy_filter(tp, fold, NULL); } @@ -968,14 +1018,17 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, list_replace_rcu(&fold->list, &fnew->list); tcf_unbind_filter(tp, &fold->res); tcf_exts_get_net(&fold->exts); - call_rcu(&fold->rcu, fl_destroy_filter); + tcf_queue_work(&fold->rwork, fl_destroy_filter_work); } else { - list_add_tail_rcu(&fnew->list, &head->filters); + list_add_tail_rcu(&fnew->list, &fnew->mask->filters); } kfree(tb); return 0; +errout_mask: + fl_mask_put(head, fnew->mask, false); + errout_idr: if (!fold) idr_remove(&head->handle_idr, fnew->handle); @@ -994,10 +1047,10 @@ static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, struct cls_fl_filter *f = arg; if (!tc_skip_sw(f->flags)) - rhashtable_remove_fast(&head->ht, &f->ht_node, - head->ht_params); + rhashtable_remove_fast(&f->mask->ht, &f->ht_node, + f->mask->filter_ht_params); __fl_delete(tp, f, extack); - *last = list_empty(&head->filters); + *last = list_empty(&head->masks); return 0; } @@ -1005,16 +1058,19 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f; - - list_for_each_entry_rcu(f, &head->filters, list) { - if (arg->count < arg->skip) - goto skip; - if (arg->fn(tp, f, arg) < 0) { - arg->stop = 1; - break; - } + struct fl_flow_mask *mask; + + list_for_each_entry_rcu(mask, &head->masks, list) { + list_for_each_entry_rcu(f, &mask->filters, list) { + if (arg->count < arg->skip) + goto skip; + if (arg->fn(tp, f, arg) < 0) { + arg->stop = 1; + break; + } skip: - arg->count++; + arg->count++; + } } } @@ -1150,7 +1206,6 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask) static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { - struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f = fh; struct nlattr *nest; struct fl_flow_key *key, *mask; @@ -1169,7 +1224,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, goto nla_put_failure; key = &f->key; - mask = &head->mask.key; + mask = &f->mask->key; if (mask->indev_ifindex) { struct net_device *dev; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 8b207723fbc20..29eeeaf3ea440 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -47,10 +47,7 @@ struct fw_filter { #endif /* CONFIG_NET_CLS_IND */ struct tcf_exts exts; struct tcf_proto *tp; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; }; static u32 fw_hash(u32 handle) @@ -134,21 +131,14 @@ static void __fw_delete_filter(struct fw_filter *f) static void fw_delete_filter_work(struct work_struct *work) { - struct fw_filter *f = container_of(work, struct fw_filter, work); - + struct fw_filter *f = container_of(to_rcu_work(work), + struct fw_filter, + rwork); rtnl_lock(); __fw_delete_filter(f); rtnl_unlock(); } -static void fw_delete_filter(struct rcu_head *head) -{ - struct fw_filter *f = container_of(head, struct fw_filter, rcu); - - INIT_WORK(&f->work, fw_delete_filter_work); - tcf_queue_work(&f->work); -} - static void fw_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); @@ -164,7 +154,7 @@ static void fw_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) rtnl_dereference(f->next)); tcf_unbind_filter(tp, &f->res); if (tcf_exts_get_net(&f->exts)) - call_rcu(&f->rcu, fw_delete_filter); + tcf_queue_work(&f->rwork, fw_delete_filter_work); else __fw_delete_filter(f); } @@ -193,7 +183,7 @@ static int fw_delete(struct tcf_proto *tp, void *arg, bool *last, RCU_INIT_POINTER(*fp, rtnl_dereference(f->next)); tcf_unbind_filter(tp, &f->res); tcf_exts_get_net(&f->exts); - call_rcu(&f->rcu, fw_delete_filter); + tcf_queue_work(&f->rwork, fw_delete_filter_work); ret = 0; break; } @@ -316,7 +306,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, rcu_assign_pointer(*fp, fnew); tcf_unbind_filter(tp, &f->res); tcf_exts_get_net(&f->exts); - call_rcu(&f->rcu, fw_delete_filter); + tcf_queue_work(&f->rwork, fw_delete_filter_work); *arg = fnew; return err; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 2ba721a590a72..47b207ef77620 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -21,10 +21,7 @@ struct cls_mall_head { struct tcf_result res; u32 handle; u32 flags; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; }; static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -53,22 +50,14 @@ static void __mall_destroy(struct cls_mall_head *head) static void mall_destroy_work(struct work_struct *work) { - struct cls_mall_head *head = container_of(work, struct cls_mall_head, - work); + struct cls_mall_head *head = container_of(to_rcu_work(work), + struct cls_mall_head, + rwork); rtnl_lock(); __mall_destroy(head); rtnl_unlock(); } -static void mall_destroy_rcu(struct rcu_head *rcu) -{ - struct cls_mall_head *head = container_of(rcu, struct cls_mall_head, - rcu); - - INIT_WORK(&head->work, mall_destroy_work); - tcf_queue_work(&head->work); -} - static void mall_destroy_hw_filter(struct tcf_proto *tp, struct cls_mall_head *head, unsigned long cookie, @@ -126,7 +115,7 @@ static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) mall_destroy_hw_filter(tp, head, (unsigned long) head, extack); if (tcf_exts_get_net(&head->exts)) - call_rcu(&head->rcu, mall_destroy_rcu); + tcf_queue_work(&head->rwork, mall_destroy_work); else __mall_destroy(head); } diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 21a03a8ee0296..0404aa5fa7cbb 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -57,10 +57,7 @@ struct route4_filter { u32 handle; struct route4_bucket *bkt; struct tcf_proto *tp; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; }; #define ROUTE4_FAILURE ((struct route4_filter *)(-1L)) @@ -266,19 +263,17 @@ static void __route4_delete_filter(struct route4_filter *f) static void route4_delete_filter_work(struct work_struct *work) { - struct route4_filter *f = container_of(work, struct route4_filter, work); - + struct route4_filter *f = container_of(to_rcu_work(work), + struct route4_filter, + rwork); rtnl_lock(); __route4_delete_filter(f); rtnl_unlock(); } -static void route4_delete_filter(struct rcu_head *head) +static void route4_queue_work(struct route4_filter *f) { - struct route4_filter *f = container_of(head, struct route4_filter, rcu); - - INIT_WORK(&f->work, route4_delete_filter_work); - tcf_queue_work(&f->work); + tcf_queue_work(&f->rwork, route4_delete_filter_work); } static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) @@ -304,7 +299,7 @@ static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) RCU_INIT_POINTER(b->ht[h2], next); tcf_unbind_filter(tp, &f->res); if (tcf_exts_get_net(&f->exts)) - call_rcu(&f->rcu, route4_delete_filter); + route4_queue_work(f); else __route4_delete_filter(f); } @@ -349,7 +344,7 @@ static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, /* Delete it */ tcf_unbind_filter(tp, &f->res); tcf_exts_get_net(&f->exts); - call_rcu(&f->rcu, route4_delete_filter); + tcf_queue_work(&f->rwork, route4_delete_filter_work); /* Strip RTNL protected tree */ for (i = 0; i <= 32; i++) { @@ -554,7 +549,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (fold) { tcf_unbind_filter(tp, &fold->res); tcf_exts_get_net(&fold->exts); - call_rcu(&fold->rcu, route4_delete_filter); + tcf_queue_work(&fold->rwork, route4_delete_filter_work); } return 0; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 4f1297657c270..e9ccf7daea7d8 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -97,10 +97,7 @@ struct rsvp_filter { u32 handle; struct rsvp_session *sess; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; }; static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) @@ -294,21 +291,14 @@ static void __rsvp_delete_filter(struct rsvp_filter *f) static void rsvp_delete_filter_work(struct work_struct *work) { - struct rsvp_filter *f = container_of(work, struct rsvp_filter, work); - + struct rsvp_filter *f = container_of(to_rcu_work(work), + struct rsvp_filter, + rwork); rtnl_lock(); __rsvp_delete_filter(f); rtnl_unlock(); } -static void rsvp_delete_filter_rcu(struct rcu_head *head) -{ - struct rsvp_filter *f = container_of(head, struct rsvp_filter, rcu); - - INIT_WORK(&f->work, rsvp_delete_filter_work); - tcf_queue_work(&f->work); -} - static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) { tcf_unbind_filter(tp, &f->res); @@ -317,7 +307,7 @@ static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) * in cleanup() callback */ if (tcf_exts_get_net(&f->exts)) - call_rcu(&f->rcu, rsvp_delete_filter_rcu); + tcf_queue_work(&f->rwork, rsvp_delete_filter_work); else __rsvp_delete_filter(f); } diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index b49cc990a0002..32f4bbd82f35a 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -28,20 +28,14 @@ struct tcindex_filter_result { struct tcf_exts exts; struct tcf_result res; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; }; struct tcindex_filter { u16 key; struct tcindex_filter_result result; struct tcindex_filter __rcu *next; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; }; @@ -152,21 +146,14 @@ static void tcindex_destroy_rexts_work(struct work_struct *work) { struct tcindex_filter_result *r; - r = container_of(work, struct tcindex_filter_result, work); + r = container_of(to_rcu_work(work), + struct tcindex_filter_result, + rwork); rtnl_lock(); __tcindex_destroy_rexts(r); rtnl_unlock(); } -static void tcindex_destroy_rexts(struct rcu_head *head) -{ - struct tcindex_filter_result *r; - - r = container_of(head, struct tcindex_filter_result, rcu); - INIT_WORK(&r->work, tcindex_destroy_rexts_work); - tcf_queue_work(&r->work); -} - static void __tcindex_destroy_fexts(struct tcindex_filter *f) { tcf_exts_destroy(&f->result.exts); @@ -176,23 +163,15 @@ static void __tcindex_destroy_fexts(struct tcindex_filter *f) static void tcindex_destroy_fexts_work(struct work_struct *work) { - struct tcindex_filter *f = container_of(work, struct tcindex_filter, - work); + struct tcindex_filter *f = container_of(to_rcu_work(work), + struct tcindex_filter, + rwork); rtnl_lock(); __tcindex_destroy_fexts(f); rtnl_unlock(); } -static void tcindex_destroy_fexts(struct rcu_head *head) -{ - struct tcindex_filter *f = container_of(head, struct tcindex_filter, - rcu); - - INIT_WORK(&f->work, tcindex_destroy_fexts_work); - tcf_queue_work(&f->work); -} - static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last, struct netlink_ext_ack *extack) { @@ -228,12 +207,12 @@ found: */ if (f) { if (tcf_exts_get_net(&f->result.exts)) - call_rcu(&f->rcu, tcindex_destroy_fexts); + tcf_queue_work(&f->rwork, tcindex_destroy_fexts_work); else __tcindex_destroy_fexts(f); } else { if (tcf_exts_get_net(&r->exts)) - call_rcu(&r->rcu, tcindex_destroy_rexts); + tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work); else __tcindex_destroy_rexts(r); } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index bac47b5d18fdb..fb861f90fde66 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -68,10 +68,7 @@ struct tc_u_knode { u32 __percpu *pcpu_success; #endif struct tcf_proto *tp; - union { - struct work_struct work; - struct rcu_head rcu; - }; + struct rcu_work rwork; /* The 'sel' field MUST be the last field in structure to allow for * tc_u32_keys allocated at end of structure. */ @@ -436,21 +433,14 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, */ static void u32_delete_key_work(struct work_struct *work) { - struct tc_u_knode *key = container_of(work, struct tc_u_knode, work); - + struct tc_u_knode *key = container_of(to_rcu_work(work), + struct tc_u_knode, + rwork); rtnl_lock(); u32_destroy_key(key->tp, key, false); rtnl_unlock(); } -static void u32_delete_key_rcu(struct rcu_head *rcu) -{ - struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu); - - INIT_WORK(&key->work, u32_delete_key_work); - tcf_queue_work(&key->work); -} - /* u32_delete_key_freepf_rcu is the rcu callback variant * that free's the entire structure including the statistics * percpu variables. Only use this if the key is not a copy @@ -460,21 +450,14 @@ static void u32_delete_key_rcu(struct rcu_head *rcu) */ static void u32_delete_key_freepf_work(struct work_struct *work) { - struct tc_u_knode *key = container_of(work, struct tc_u_knode, work); - + struct tc_u_knode *key = container_of(to_rcu_work(work), + struct tc_u_knode, + rwork); rtnl_lock(); u32_destroy_key(key->tp, key, true); rtnl_unlock(); } -static void u32_delete_key_freepf_rcu(struct rcu_head *rcu) -{ - struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu); - - INIT_WORK(&key->work, u32_delete_key_freepf_work); - tcf_queue_work(&key->work); -} - static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) { struct tc_u_knode __rcu **kp; @@ -491,7 +474,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key) tcf_unbind_filter(tp, &key->res); idr_remove(&ht->handle_idr, key->handle); tcf_exts_get_net(&key->exts); - call_rcu(&key->rcu, u32_delete_key_freepf_rcu); + tcf_queue_work(&key->rwork, u32_delete_key_freepf_work); return 0; } } @@ -611,7 +594,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, u32_remove_hw_knode(tp, n, extack); idr_remove(&ht->handle_idr, n->handle); if (tcf_exts_get_net(&n->exts)) - call_rcu(&n->rcu, u32_delete_key_freepf_rcu); + tcf_queue_work(&n->rwork, u32_delete_key_freepf_work); else u32_destroy_key(n->tp, n, true); } @@ -995,7 +978,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, u32_replace_knode(tp, tp_c, new); tcf_unbind_filter(tp, &n->res); tcf_exts_get_net(&n->exts); - call_rcu(&n->rcu, u32_delete_key_rcu); + tcf_queue_work(&n->rwork, u32_delete_key_work); return 0; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 39c144b6ff987..69078c82963ef 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -346,9 +346,6 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, return false; } - if (ret && netif_xmit_frozen_or_stopped(txq)) - return false; - return true; } @@ -373,33 +370,24 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, */ static inline bool qdisc_restart(struct Qdisc *q, int *packets) { - bool more, validate, nolock = q->flags & TCQ_F_NOLOCK; spinlock_t *root_lock = NULL; struct netdev_queue *txq; struct net_device *dev; struct sk_buff *skb; + bool validate; /* Dequeue packet */ - if (nolock && test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) - return false; - skb = dequeue_skb(q, &validate, packets); - if (unlikely(!skb)) { - if (nolock) - clear_bit(__QDISC_STATE_RUNNING, &q->state); + if (unlikely(!skb)) return false; - } - if (!nolock) + if (!(q->flags & TCQ_F_NOLOCK)) root_lock = qdisc_lock(q); dev = qdisc_dev(q); txq = skb_get_tx_queue(dev, skb); - more = sch_direct_xmit(skb, q, dev, txq, root_lock, validate); - if (nolock) - clear_bit(__QDISC_STATE_RUNNING, &q->state); - return more; + return sch_direct_xmit(skb, q, dev, txq, root_lock, validate); } void __qdisc_run(struct Qdisc *q) @@ -665,7 +653,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) if (__skb_array_empty(q)) continue; - skb = skb_array_consume_bh(q); + skb = __skb_array_consume(q); } if (likely(skb)) { qdisc_qstats_cpu_backlog_dec(qdisc, skb); @@ -706,7 +694,7 @@ static void pfifo_fast_reset(struct Qdisc *qdisc) if (!q->ring.queue) continue; - while ((skb = skb_array_consume_bh(q)) != NULL) + while ((skb = __skb_array_consume(q)) != NULL) kfree_skb(skb); } @@ -867,6 +855,11 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, lockdep_set_class(&sch->busylock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); + /* seqlock has the same scope of busylock, for NOLOCK qdisc */ + spin_lock_init(&sch->seqlock); + lockdep_set_class(&sch->busylock, + dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); + seqcount_init(&sch->running); lockdep_set_class(&sch->running, dev->qdisc_running_key ?: &qdisc_running_key); @@ -1106,6 +1099,10 @@ static void dev_deactivate_queue(struct net_device *dev, qdisc = rtnl_dereference(dev_queue->qdisc); if (qdisc) { + bool nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); spin_lock_bh(qdisc_lock(qdisc)); if (!(qdisc->flags & TCQ_F_BUILTIN)) @@ -1115,6 +1112,8 @@ static void dev_deactivate_queue(struct net_device *dev, qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) + spin_unlock_bh(&qdisc->seqlock); } } @@ -1131,17 +1130,13 @@ static bool some_qdisc_is_busy(struct net_device *dev) dev_queue = netdev_get_tx_queue(dev, i); q = dev_queue->qdisc_sleeping; - if (q->flags & TCQ_F_NOLOCK) { - val = test_bit(__QDISC_STATE_SCHED, &q->state); - } else { - root_lock = qdisc_lock(q); - spin_lock_bh(root_lock); + root_lock = qdisc_lock(q); + spin_lock_bh(root_lock); - val = (qdisc_is_running(q) || - test_bit(__QDISC_STATE_SCHED, &q->state)); + val = (qdisc_is_running(q) || + test_bit(__QDISC_STATE_SCHED, &q->state)); - spin_unlock_bh(root_lock); - } + spin_unlock_bh(root_lock); if (val) return true; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index f062a18e9162a..d6b8ae4ed7a3a 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -16,6 +16,7 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <net/netlink.h> +#include <net/pkt_cls.h> #include <net/pkt_sched.h> #include <net/sch_generic.h> @@ -23,12 +24,44 @@ struct mq_sched { struct Qdisc **qdiscs; }; +static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_mq_qopt_offload opt = { + .command = cmd, + .handle = sch->handle, + }; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt); +} + +static void mq_offload_stats(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_mq_qopt_offload opt = { + .command = TC_MQ_STATS, + .handle = sch->handle, + .stats = { + .bstats = &sch->bstats, + .qstats = &sch->qstats, + }, + }; + + if (tc_can_offload(dev) && dev->netdev_ops->ndo_setup_tc) + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt); +} + static void mq_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct mq_sched *priv = qdisc_priv(sch); unsigned int ntx; + mq_offload(sch, TC_MQ_DESTROY); + if (!priv->qdiscs) return; for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) @@ -70,6 +103,8 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt, } sch->flags |= TCQ_F_MQROOT; + + mq_offload(sch, TC_MQ_CREATE); return 0; } @@ -127,6 +162,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; sch->bstats.packets += qdisc->bstats.packets; + sch->qstats.qlen += qdisc->qstats.qlen; sch->qstats.backlog += qdisc->qstats.backlog; sch->qstats.drops += qdisc->qstats.drops; sch->qstats.requeues += qdisc->qstats.requeues; @@ -135,6 +171,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) spin_unlock_bh(qdisc_lock(qdisc)); } + mq_offload_stats(sch); return 0; } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index a47179da24e61..5d5a16204d505 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -652,33 +652,20 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, */ peer->param_flags = asoc->param_flags; - sctp_transport_route(peer, NULL, sp); - /* Initialize the pmtu of the transport. */ - if (peer->param_flags & SPP_PMTUD_DISABLE) { - if (asoc->pathmtu) - peer->pathmtu = asoc->pathmtu; - else - peer->pathmtu = SCTP_DEFAULT_MAXSEGMENT; - } + sctp_transport_route(peer, NULL, sp); /* If this is the first transport addr on this association, * initialize the association PMTU to the peer's PMTU. * If not and the current association PMTU is higher than the new * peer's PMTU, reset the association PMTU to the new peer's PMTU. */ - if (asoc->pathmtu) - asoc->pathmtu = min_t(int, peer->pathmtu, asoc->pathmtu); - else - asoc->pathmtu = peer->pathmtu; - - pr_debug("%s: association:%p PMTU set to %d\n", __func__, asoc, - asoc->pathmtu); + sctp_assoc_set_pmtu(asoc, asoc->pathmtu ? + min_t(int, peer->pathmtu, asoc->pathmtu) : + peer->pathmtu); peer->pmtu_pending = 0; - asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu); - /* The asoc->peer.port might not be meaningful yet, but * initialize the packet structure anyway. */ @@ -988,31 +975,6 @@ out: return match; } -/* Is this the association we are looking for? */ -struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc, - struct net *net, - const union sctp_addr *laddr, - const union sctp_addr *paddr) -{ - struct sctp_transport *transport; - - if ((htons(asoc->base.bind_addr.port) == laddr->v4.sin_port) && - (htons(asoc->peer.port) == paddr->v4.sin_port) && - net_eq(sock_net(asoc->base.sk), net)) { - transport = sctp_assoc_lookup_paddr(asoc, paddr); - if (!transport) - goto out; - - if (sctp_bind_addr_match(&asoc->base.bind_addr, laddr, - sctp_sk(asoc->base.sk))) - goto out; - } - transport = NULL; - -out: - return transport; -} - /* Do delayed input processing. This is scheduled by sctp_rcv(). */ static void sctp_assoc_bh_rcv(struct work_struct *work) { @@ -1434,6 +1396,31 @@ sctp_assoc_choose_alter_transport(struct sctp_association *asoc, } } +void sctp_assoc_update_frag_point(struct sctp_association *asoc) +{ + int frag = sctp_mtu_payload(sctp_sk(asoc->base.sk), asoc->pathmtu, + sctp_datachk_len(&asoc->stream)); + + if (asoc->user_frag) + frag = min_t(int, frag, asoc->user_frag); + + frag = min_t(int, frag, SCTP_MAX_CHUNK_LEN - + sctp_datachk_len(&asoc->stream)); + + asoc->frag_point = SCTP_TRUNC4(frag); +} + +void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu) +{ + if (asoc->pathmtu != pmtu) { + asoc->pathmtu = pmtu; + sctp_assoc_update_frag_point(asoc); + } + + pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc, + asoc->pathmtu, asoc->frag_point); +} + /* Update the association's pmtu and frag_point by going through all the * transports. This routine is called when a transport's PMTU has changed. */ @@ -1446,24 +1433,16 @@ void sctp_assoc_sync_pmtu(struct sctp_association *asoc) return; /* Get the lowest pmtu of all the transports. */ - list_for_each_entry(t, &asoc->peer.transport_addr_list, - transports) { + list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (t->pmtu_pending && t->dst) { - sctp_transport_update_pmtu( - t, SCTP_TRUNC4(dst_mtu(t->dst))); + sctp_transport_update_pmtu(t, sctp_dst_mtu(t->dst)); t->pmtu_pending = 0; } if (!pmtu || (t->pathmtu < pmtu)) pmtu = t->pathmtu; } - if (pmtu) { - asoc->pathmtu = pmtu; - asoc->frag_point = sctp_frag_point(asoc, pmtu); - } - - pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc, - asoc->pathmtu, asoc->frag_point); + sctp_assoc_set_pmtu(asoc, pmtu); } /* Should we send a SACK to update our peer? */ diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index be296d633e951..79daa98208c39 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -172,8 +172,6 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, struct list_head *pos, *temp; struct sctp_chunk *chunk; struct sctp_datamsg *msg; - struct sctp_sock *sp; - struct sctp_af *af; int err; msg = sctp_datamsg_new(GFP_KERNEL); @@ -192,12 +190,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, /* This is the biggest possible DATA chunk that can fit into * the packet */ - sp = sctp_sk(asoc->base.sk); - af = sp->pf->af; - max_data = asoc->pathmtu - af->net_header_len - - sizeof(struct sctphdr) - sctp_datachk_len(&asoc->stream) - - af->ip_options_len(asoc->base.sk); - max_data = SCTP_TRUNC4(max_data); + max_data = asoc->frag_point; /* If the the peer requested that we authenticate DATA chunks * we need to account for bundling of the AUTH chunks along with @@ -222,9 +215,6 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, } } - /* Check what's our max considering the above */ - max_data = min_t(size_t, max_data, asoc->frag_point); - /* Set first_len and then account for possible bundles on first frag */ first_len = max_data; diff --git a/net/sctp/output.c b/net/sctp/output.c index 690d8557bb7bf..e672dee302c70 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -90,8 +90,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, { struct sctp_transport *tp = packet->transport; struct sctp_association *asoc = tp->asoc; + struct sctp_sock *sp = NULL; struct sock *sk; - size_t overhead = sizeof(struct ipv6hdr) + sizeof(struct sctphdr); pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag); packet->vtag = vtag; @@ -102,28 +102,20 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, /* set packet max_size with pathmtu, then calculate overhead */ packet->max_size = tp->pathmtu; + if (asoc) { - struct sctp_sock *sp = sctp_sk(asoc->base.sk); - struct sctp_af *af = sp->pf->af; - - overhead = af->net_header_len + - af->ip_options_len(asoc->base.sk); - overhead += sizeof(struct sctphdr); - packet->overhead = overhead; - packet->size = overhead; - } else { - packet->overhead = overhead; - packet->size = overhead; - return; + sk = asoc->base.sk; + sp = sctp_sk(sk); } + packet->overhead = sctp_mtu_payload(sp, 0, 0); + packet->size = packet->overhead; + + if (!asoc) + return; /* update dst or transport pathmtu if in need */ - sk = asoc->base.sk; if (!sctp_transport_dst_check(tp)) { - sctp_transport_route(tp, NULL, sctp_sk(sk)); - if (asoc->param_flags & SPP_PMTUD_ENABLE) - sctp_assoc_sync_pmtu(asoc); - } else if (!sctp_transport_pmtu_check(tp)) { + sctp_transport_route(tp, NULL, sp); if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index f211b3db6a354..d68aa33485a94 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -601,14 +601,14 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, /* * Transmit DATA chunks on the retransmit queue. Upon return from - * sctp_outq_flush_rtx() the packet 'pkt' may contain chunks which + * __sctp_outq_flush_rtx() the packet 'pkt' may contain chunks which * need to be transmitted by the caller. * We assume that pkt->transport has already been set. * * The return value is a normal kernel error return value. */ -static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, - int rtx_timeout, int *start_timer) +static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, + int rtx_timeout, int *start_timer, gfp_t gfp) { struct sctp_transport *transport = pkt->transport; struct sctp_chunk *chunk, *chunk1; @@ -684,12 +684,12 @@ redo: * control chunks are already freed so there * is nothing we can do. */ - sctp_packet_transmit(pkt, GFP_ATOMIC); + sctp_packet_transmit(pkt, gfp); goto redo; } /* Send this packet. */ - error = sctp_packet_transmit(pkt, GFP_ATOMIC); + error = sctp_packet_transmit(pkt, gfp); /* If we are retransmitting, we should only * send a single packet. @@ -705,7 +705,7 @@ redo: case SCTP_XMIT_RWND_FULL: /* Send this packet. */ - error = sctp_packet_transmit(pkt, GFP_ATOMIC); + error = sctp_packet_transmit(pkt, gfp); /* Stop sending DATA as there is no more room * at the receiver. @@ -715,7 +715,7 @@ redo: case SCTP_XMIT_DELAY: /* Send this packet. */ - error = sctp_packet_transmit(pkt, GFP_ATOMIC); + error = sctp_packet_transmit(pkt, gfp); /* Stop sending DATA because of nagle delay. */ done = 1; @@ -776,68 +776,43 @@ void sctp_outq_uncork(struct sctp_outq *q, gfp_t gfp) sctp_outq_flush(q, 0, gfp); } - -/* - * Try to flush an outqueue. - * - * Description: Send everything in q which we legally can, subject to - * congestion limitations. - * * Note: This function can be called from multiple contexts so appropriate - * locking concerns must be made. Today we use the sock lock to protect - * this function. - */ -static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) +static int sctp_packet_singleton(struct sctp_transport *transport, + struct sctp_chunk *chunk, gfp_t gfp) { - struct sctp_packet *packet; + const struct sctp_association *asoc = transport->asoc; + const __u16 sport = asoc->base.bind_addr.port; + const __u16 dport = asoc->peer.port; + const __u32 vtag = asoc->peer.i.init_tag; struct sctp_packet singleton; - struct sctp_association *asoc = q->asoc; - __u16 sport = asoc->base.bind_addr.port; - __u16 dport = asoc->peer.port; - __u32 vtag = asoc->peer.i.init_tag; - struct sctp_transport *transport = NULL; - struct sctp_transport *new_transport; - struct sctp_chunk *chunk, *tmp; - enum sctp_xmit status; - int error = 0; - int start_timer = 0; - int one_packet = 0; + sctp_packet_init(&singleton, transport, sport, dport); + sctp_packet_config(&singleton, vtag, 0); + sctp_packet_append_chunk(&singleton, chunk); + return sctp_packet_transmit(&singleton, gfp); +} + +/* Struct to hold the context during sctp outq flush */ +struct sctp_flush_ctx { + struct sctp_outq *q; + /* Current transport being used. It's NOT the same as curr active one */ + struct sctp_transport *transport; /* These transports have chunks to send. */ struct list_head transport_list; - struct list_head *ltransport; - - INIT_LIST_HEAD(&transport_list); - packet = NULL; - - /* - * 6.10 Bundling - * ... - * When bundling control chunks with DATA chunks, an - * endpoint MUST place control chunks first in the outbound - * SCTP packet. The transmitter MUST transmit DATA chunks - * within a SCTP packet in increasing order of TSN. - * ... - */ - - list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { - /* RFC 5061, 5.3 - * F1) This means that until such time as the ASCONF - * containing the add is acknowledged, the sender MUST - * NOT use the new IP address as a source for ANY SCTP - * packet except on carrying an ASCONF Chunk. - */ - if (asoc->src_out_of_asoc_ok && - chunk->chunk_hdr->type != SCTP_CID_ASCONF) - continue; - - list_del_init(&chunk->list); + struct sctp_association *asoc; + /* Packet on the current transport above */ + struct sctp_packet *packet; + gfp_t gfp; +}; - /* Pick the right transport to use. */ - new_transport = chunk->transport; +/* transport: current transport */ +static void sctp_outq_select_transport(struct sctp_flush_ctx *ctx, + struct sctp_chunk *chunk) +{ + struct sctp_transport *new_transport = chunk->transport; - if (!new_transport) { - /* - * If we have a prior transport pointer, see if + if (!new_transport) { + if (!sctp_chunk_is_data(chunk)) { + /* If we have a prior transport pointer, see if * the destination address of the chunk * matches the destination address of the * current transport. If not a match, then @@ -846,22 +821,26 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) * after processing ASCONFs, we may have new * transports created. */ - if (transport && - sctp_cmp_addr_exact(&chunk->dest, - &transport->ipaddr)) - new_transport = transport; + if (ctx->transport && sctp_cmp_addr_exact(&chunk->dest, + &ctx->transport->ipaddr)) + new_transport = ctx->transport; else - new_transport = sctp_assoc_lookup_paddr(asoc, - &chunk->dest); + new_transport = sctp_assoc_lookup_paddr(ctx->asoc, + &chunk->dest); + } - /* if we still don't have a new transport, then - * use the current active path. - */ - if (!new_transport) - new_transport = asoc->peer.active_path; - } else if ((new_transport->state == SCTP_INACTIVE) || - (new_transport->state == SCTP_UNCONFIRMED) || - (new_transport->state == SCTP_PF)) { + /* if we still don't have a new transport, then + * use the current active path. + */ + if (!new_transport) + new_transport = ctx->asoc->peer.active_path; + } else { + __u8 type; + + switch (new_transport->state) { + case SCTP_INACTIVE: + case SCTP_UNCONFIRMED: + case SCTP_PF: /* If the chunk is Heartbeat or Heartbeat Ack, * send it to chunk->transport, even if it's * inactive. @@ -875,29 +854,64 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) * * ASCONF_ACKs also must be sent to the source. */ - if (chunk->chunk_hdr->type != SCTP_CID_HEARTBEAT && - chunk->chunk_hdr->type != SCTP_CID_HEARTBEAT_ACK && - chunk->chunk_hdr->type != SCTP_CID_ASCONF_ACK) - new_transport = asoc->peer.active_path; + type = chunk->chunk_hdr->type; + if (type != SCTP_CID_HEARTBEAT && + type != SCTP_CID_HEARTBEAT_ACK && + type != SCTP_CID_ASCONF_ACK) + new_transport = ctx->asoc->peer.active_path; + break; + default: + break; } + } + + /* Are we switching transports? Take care of transport locks. */ + if (new_transport != ctx->transport) { + ctx->transport = new_transport; + ctx->packet = &ctx->transport->packet; - /* Are we switching transports? - * Take care of transport locks. + if (list_empty(&ctx->transport->send_ready)) + list_add_tail(&ctx->transport->send_ready, + &ctx->transport_list); + + sctp_packet_config(ctx->packet, + ctx->asoc->peer.i.init_tag, + ctx->asoc->peer.ecn_capable); + /* We've switched transports, so apply the + * Burst limit to the new transport. */ - if (new_transport != transport) { - transport = new_transport; - if (list_empty(&transport->send_ready)) { - list_add_tail(&transport->send_ready, - &transport_list); - } - packet = &transport->packet; - sctp_packet_config(packet, vtag, - asoc->peer.ecn_capable); - } + sctp_transport_burst_limited(ctx->transport); + } +} + +static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) +{ + struct sctp_chunk *chunk, *tmp; + enum sctp_xmit status; + int one_packet, error; + + list_for_each_entry_safe(chunk, tmp, &ctx->q->control_chunk_list, list) { + one_packet = 0; + + /* RFC 5061, 5.3 + * F1) This means that until such time as the ASCONF + * containing the add is acknowledged, the sender MUST + * NOT use the new IP address as a source for ANY SCTP + * packet except on carrying an ASCONF Chunk. + */ + if (ctx->asoc->src_out_of_asoc_ok && + chunk->chunk_hdr->type != SCTP_CID_ASCONF) + continue; + + list_del_init(&chunk->list); + + /* Pick the right transport to use. Should always be true for + * the first chunk as we don't have a transport by then. + */ + sctp_outq_select_transport(ctx, chunk); switch (chunk->chunk_hdr->type) { - /* - * 6.10 Bundling + /* 6.10 Bundling * ... * An endpoint MUST NOT bundle INIT, INIT ACK or SHUTDOWN * COMPLETE with any other chunks. [Send them immediately.] @@ -905,20 +919,19 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: case SCTP_CID_SHUTDOWN_COMPLETE: - sctp_packet_init(&singleton, transport, sport, dport); - sctp_packet_config(&singleton, vtag, 0); - sctp_packet_append_chunk(&singleton, chunk); - error = sctp_packet_transmit(&singleton, gfp); + error = sctp_packet_singleton(ctx->transport, chunk, + ctx->gfp); if (error < 0) { - asoc->base.sk->sk_err = -error; + ctx->asoc->base.sk->sk_err = -error; return; } break; case SCTP_CID_ABORT: if (sctp_test_T_bit(chunk)) - packet->vtag = asoc->c.my_vtag; + ctx->packet->vtag = ctx->asoc->c.my_vtag; /* fallthru */ + /* The following chunks are "response" chunks, i.e. * they are generated in response to something we * received. If we are sending these, then we can @@ -942,27 +955,27 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) case SCTP_CID_FWD_TSN: case SCTP_CID_I_FWD_TSN: case SCTP_CID_RECONF: - status = sctp_packet_transmit_chunk(packet, chunk, - one_packet, gfp); - if (status != SCTP_XMIT_OK) { + status = sctp_packet_transmit_chunk(ctx->packet, chunk, + one_packet, ctx->gfp); + if (status != SCTP_XMIT_OK) { /* put the chunk back */ - list_add(&chunk->list, &q->control_chunk_list); + list_add(&chunk->list, &ctx->q->control_chunk_list); break; } - asoc->stats.octrlchunks++; + ctx->asoc->stats.octrlchunks++; /* PR-SCTP C5) If a FORWARD TSN is sent, the * sender MUST assure that at least one T3-rtx * timer is running. */ if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN || chunk->chunk_hdr->type == SCTP_CID_I_FWD_TSN) { - sctp_transport_reset_t3_rtx(transport); - transport->last_time_sent = jiffies; + sctp_transport_reset_t3_rtx(ctx->transport); + ctx->transport->last_time_sent = jiffies; } - if (chunk == asoc->strreset_chunk) - sctp_transport_reset_reconf_timer(transport); + if (chunk == ctx->asoc->strreset_chunk) + sctp_transport_reset_reconf_timer(ctx->transport); break; @@ -971,232 +984,186 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) BUG(); } } +} - if (q->asoc->src_out_of_asoc_ok) - goto sctp_flush_out; +/* Returns false if new data shouldn't be sent */ +static bool sctp_outq_flush_rtx(struct sctp_flush_ctx *ctx, + int rtx_timeout) +{ + int error, start_timer = 0; + + if (ctx->asoc->peer.retran_path->state == SCTP_UNCONFIRMED) + return false; + + if (ctx->transport != ctx->asoc->peer.retran_path) { + /* Switch transports & prepare the packet. */ + ctx->transport = ctx->asoc->peer.retran_path; + ctx->packet = &ctx->transport->packet; + + if (list_empty(&ctx->transport->send_ready)) + list_add_tail(&ctx->transport->send_ready, + &ctx->transport_list); + + sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag, + ctx->asoc->peer.ecn_capable); + } + + error = __sctp_outq_flush_rtx(ctx->q, ctx->packet, rtx_timeout, + &start_timer, ctx->gfp); + if (error < 0) + ctx->asoc->base.sk->sk_err = -error; + + if (start_timer) { + sctp_transport_reset_t3_rtx(ctx->transport); + ctx->transport->last_time_sent = jiffies; + } + + /* This can happen on COOKIE-ECHO resend. Only + * one chunk can get bundled with a COOKIE-ECHO. + */ + if (ctx->packet->has_cookie_echo) + return false; + + /* Don't send new data if there is still data + * waiting to retransmit. + */ + if (!list_empty(&ctx->q->retransmit)) + return false; + + return true; +} + +static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, + int rtx_timeout) +{ + struct sctp_chunk *chunk; + enum sctp_xmit status; /* Is it OK to send data chunks? */ - switch (asoc->state) { + switch (ctx->asoc->state) { case SCTP_STATE_COOKIE_ECHOED: /* Only allow bundling when this packet has a COOKIE-ECHO * chunk. */ - if (!packet || !packet->has_cookie_echo) - break; + if (!ctx->packet || !ctx->packet->has_cookie_echo) + return; /* fallthru */ case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: - /* - * RFC 2960 6.1 Transmission of DATA Chunks - * - * C) When the time comes for the sender to transmit, - * before sending new DATA chunks, the sender MUST - * first transmit any outstanding DATA chunks which - * are marked for retransmission (limited by the - * current cwnd). - */ - if (!list_empty(&q->retransmit)) { - if (asoc->peer.retran_path->state == SCTP_UNCONFIRMED) - goto sctp_flush_out; - if (transport == asoc->peer.retran_path) - goto retran; - - /* Switch transports & prepare the packet. */ - - transport = asoc->peer.retran_path; + break; - if (list_empty(&transport->send_ready)) { - list_add_tail(&transport->send_ready, - &transport_list); - } + default: + /* Do nothing. */ + return; + } - packet = &transport->packet; - sctp_packet_config(packet, vtag, - asoc->peer.ecn_capable); - retran: - error = sctp_outq_flush_rtx(q, packet, - rtx_timeout, &start_timer); - if (error < 0) - asoc->base.sk->sk_err = -error; + /* RFC 2960 6.1 Transmission of DATA Chunks + * + * C) When the time comes for the sender to transmit, + * before sending new DATA chunks, the sender MUST + * first transmit any outstanding DATA chunks which + * are marked for retransmission (limited by the + * current cwnd). + */ + if (!list_empty(&ctx->q->retransmit) && + !sctp_outq_flush_rtx(ctx, rtx_timeout)) + return; - if (start_timer) { - sctp_transport_reset_t3_rtx(transport); - transport->last_time_sent = jiffies; - } + /* Apply Max.Burst limitation to the current transport in + * case it will be used for new data. We are going to + * rest it before we return, but we want to apply the limit + * to the currently queued data. + */ + if (ctx->transport) + sctp_transport_burst_limited(ctx->transport); - /* This can happen on COOKIE-ECHO resend. Only - * one chunk can get bundled with a COOKIE-ECHO. - */ - if (packet->has_cookie_echo) - goto sctp_flush_out; + /* Finally, transmit new packets. */ + while ((chunk = sctp_outq_dequeue_data(ctx->q)) != NULL) { + __u32 sid = ntohs(chunk->subh.data_hdr->stream); - /* Don't send new data if there is still data - * waiting to retransmit. - */ - if (!list_empty(&q->retransmit)) - goto sctp_flush_out; + /* Has this chunk expired? */ + if (sctp_chunk_abandoned(chunk)) { + sctp_sched_dequeue_done(ctx->q, chunk); + sctp_chunk_fail(chunk, 0); + sctp_chunk_free(chunk); + continue; } - /* Apply Max.Burst limitation to the current transport in - * case it will be used for new data. We are going to - * rest it before we return, but we want to apply the limit - * to the currently queued data. - */ - if (transport) - sctp_transport_burst_limited(transport); - - /* Finally, transmit new packets. */ - while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { - __u32 sid = ntohs(chunk->subh.data_hdr->stream); - - /* Has this chunk expired? */ - if (sctp_chunk_abandoned(chunk)) { - sctp_sched_dequeue_done(q, chunk); - sctp_chunk_fail(chunk, 0); - sctp_chunk_free(chunk); - continue; - } + if (ctx->asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) { + sctp_outq_head_data(ctx->q, chunk); + break; + } - if (asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) { - sctp_outq_head_data(q, chunk); - goto sctp_flush_out; - } + sctp_outq_select_transport(ctx, chunk); - /* If there is a specified transport, use it. - * Otherwise, we want to use the active path. + pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p skb->users:%d\n", + __func__, ctx->q, chunk, chunk && chunk->chunk_hdr ? + sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : + "illegal chunk", ntohl(chunk->subh.data_hdr->tsn), + chunk->skb ? chunk->skb->head : NULL, chunk->skb ? + refcount_read(&chunk->skb->users) : -1); + + /* Add the chunk to the packet. */ + status = sctp_packet_transmit_chunk(ctx->packet, chunk, 0, + ctx->gfp); + if (status != SCTP_XMIT_OK) { + /* We could not append this chunk, so put + * the chunk back on the output queue. */ - new_transport = chunk->transport; - if (!new_transport || - ((new_transport->state == SCTP_INACTIVE) || - (new_transport->state == SCTP_UNCONFIRMED) || - (new_transport->state == SCTP_PF))) - new_transport = asoc->peer.active_path; - if (new_transport->state == SCTP_UNCONFIRMED) { - WARN_ONCE(1, "Attempt to send packet on unconfirmed path."); - sctp_sched_dequeue_done(q, chunk); - sctp_chunk_fail(chunk, 0); - sctp_chunk_free(chunk); - continue; - } - - /* Change packets if necessary. */ - if (new_transport != transport) { - transport = new_transport; + pr_debug("%s: could not transmit tsn:0x%x, status:%d\n", + __func__, ntohl(chunk->subh.data_hdr->tsn), + status); - /* Schedule to have this transport's - * packet flushed. - */ - if (list_empty(&transport->send_ready)) { - list_add_tail(&transport->send_ready, - &transport_list); - } - - packet = &transport->packet; - sctp_packet_config(packet, vtag, - asoc->peer.ecn_capable); - /* We've switched transports, so apply the - * Burst limit to the new transport. - */ - sctp_transport_burst_limited(transport); - } - - pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p " - "skb->users:%d\n", - __func__, q, chunk, chunk && chunk->chunk_hdr ? - sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : - "illegal chunk", ntohl(chunk->subh.data_hdr->tsn), - chunk->skb ? chunk->skb->head : NULL, chunk->skb ? - refcount_read(&chunk->skb->users) : -1); - - /* Add the chunk to the packet. */ - status = sctp_packet_transmit_chunk(packet, chunk, 0, gfp); - - switch (status) { - case SCTP_XMIT_PMTU_FULL: - case SCTP_XMIT_RWND_FULL: - case SCTP_XMIT_DELAY: - /* We could not append this chunk, so put - * the chunk back on the output queue. - */ - pr_debug("%s: could not transmit tsn:0x%x, status:%d\n", - __func__, ntohl(chunk->subh.data_hdr->tsn), - status); - - sctp_outq_head_data(q, chunk); - goto sctp_flush_out; - - case SCTP_XMIT_OK: - /* The sender is in the SHUTDOWN-PENDING state, - * The sender MAY set the I-bit in the DATA - * chunk header. - */ - if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING) - chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM; - if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) - asoc->stats.ouodchunks++; - else - asoc->stats.oodchunks++; - - /* Only now it's safe to consider this - * chunk as sent, sched-wise. - */ - sctp_sched_dequeue_done(q, chunk); - - break; + sctp_outq_head_data(ctx->q, chunk); + break; + } - default: - BUG(); - } + /* The sender is in the SHUTDOWN-PENDING state, + * The sender MAY set the I-bit in the DATA + * chunk header. + */ + if (ctx->asoc->state == SCTP_STATE_SHUTDOWN_PENDING) + chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM; + if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) + ctx->asoc->stats.ouodchunks++; + else + ctx->asoc->stats.oodchunks++; - /* BUG: We assume that the sctp_packet_transmit() - * call below will succeed all the time and add the - * chunk to the transmitted list and restart the - * timers. - * It is possible that the call can fail under OOM - * conditions. - * - * Is this really a problem? Won't this behave - * like a lost TSN? - */ - list_add_tail(&chunk->transmitted_list, - &transport->transmitted); + /* Only now it's safe to consider this + * chunk as sent, sched-wise. + */ + sctp_sched_dequeue_done(ctx->q, chunk); - sctp_transport_reset_t3_rtx(transport); - transport->last_time_sent = jiffies; + list_add_tail(&chunk->transmitted_list, + &ctx->transport->transmitted); - /* Only let one DATA chunk get bundled with a - * COOKIE-ECHO chunk. - */ - if (packet->has_cookie_echo) - goto sctp_flush_out; - } - break; + sctp_transport_reset_t3_rtx(ctx->transport); + ctx->transport->last_time_sent = jiffies; - default: - /* Do nothing. */ - break; + /* Only let one DATA chunk get bundled with a + * COOKIE-ECHO chunk. + */ + if (ctx->packet->has_cookie_echo) + break; } +} -sctp_flush_out: +static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx) +{ + struct list_head *ltransport; + struct sctp_packet *packet; + struct sctp_transport *t; + int error = 0; - /* Before returning, examine all the transports touched in - * this call. Right now, we bluntly force clear all the - * transports. Things might change after we implement Nagle. - * But such an examination is still required. - * - * --xguo - */ - while ((ltransport = sctp_list_dequeue(&transport_list)) != NULL) { - struct sctp_transport *t = list_entry(ltransport, - struct sctp_transport, - send_ready); + while ((ltransport = sctp_list_dequeue(&ctx->transport_list)) != NULL) { + t = list_entry(ltransport, struct sctp_transport, send_ready); packet = &t->packet; if (!sctp_packet_empty(packet)) { - error = sctp_packet_transmit(packet, gfp); + error = sctp_packet_transmit(packet, ctx->gfp); if (error < 0) - asoc->base.sk->sk_err = -error; + ctx->q->asoc->base.sk->sk_err = -error; } /* Clear the burst limited state, if any */ @@ -1204,6 +1171,47 @@ sctp_flush_out: } } +/* Try to flush an outqueue. + * + * Description: Send everything in q which we legally can, subject to + * congestion limitations. + * * Note: This function can be called from multiple contexts so appropriate + * locking concerns must be made. Today we use the sock lock to protect + * this function. + */ + +static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) +{ + struct sctp_flush_ctx ctx = { + .q = q, + .transport = NULL, + .transport_list = LIST_HEAD_INIT(ctx.transport_list), + .asoc = q->asoc, + .packet = NULL, + .gfp = gfp, + }; + + /* 6.10 Bundling + * ... + * When bundling control chunks with DATA chunks, an + * endpoint MUST place control chunks first in the outbound + * SCTP packet. The transmitter MUST transmit DATA chunks + * within a SCTP packet in increasing order of TSN. + * ... + */ + + sctp_outq_flush_ctrl(&ctx); + + if (q->asoc->src_out_of_asoc_ok) + goto sctp_flush_out; + + sctp_outq_flush_data(&ctx, rtx_timeout); + +sctp_flush_out: + + sctp_outq_flush_transports(&ctx); +} + /* Update unack_data based on the incoming SACK chunk */ static void sctp_sack_update_unack_data(struct sctp_association *assoc, struct sctp_sackhdr *sack) @@ -1457,7 +1465,7 @@ static void sctp_check_transmitted(struct sctp_outq *q, * the outstanding bytes for this chunk, so only * count bytes associated with a transport. */ - if (transport) { + if (transport && !tchunk->tsn_gap_acked) { /* If this chunk is being used for RTT * measurement, calculate the RTT and update * the RTO using this value. @@ -1469,14 +1477,34 @@ static void sctp_check_transmitted(struct sctp_outq *q, * first instance of the packet or a later * instance). */ - if (!tchunk->tsn_gap_acked && - !sctp_chunk_retransmitted(tchunk) && + if (!sctp_chunk_retransmitted(tchunk) && tchunk->rtt_in_progress) { tchunk->rtt_in_progress = 0; rtt = jiffies - tchunk->sent_at; sctp_transport_update_rto(transport, rtt); } + + if (TSN_lte(tsn, sack_ctsn)) { + /* + * SFR-CACC algorithm: + * 2) If the SACK contains gap acks + * and the flag CHANGEOVER_ACTIVE is + * set the receiver of the SACK MUST + * take the following action: + * + * B) For each TSN t being acked that + * has not been acked in any SACK so + * far, set cacc_saw_newack to 1 for + * the destination that the TSN was + * sent to. + */ + if (sack->num_gap_ack_blocks && + q->asoc->peer.primary_path->cacc. + changeover_active) + transport->cacc.cacc_saw_newack + = 1; + } } /* If the chunk hasn't been marked as ACKED, @@ -1508,28 +1536,6 @@ static void sctp_check_transmitted(struct sctp_outq *q, restart_timer = 1; forward_progress = true; - if (!tchunk->tsn_gap_acked) { - /* - * SFR-CACC algorithm: - * 2) If the SACK contains gap acks - * and the flag CHANGEOVER_ACTIVE is - * set the receiver of the SACK MUST - * take the following action: - * - * B) For each TSN t being acked that - * has not been acked in any SACK so - * far, set cacc_saw_newack to 1 for - * the destination that the TSN was - * sent to. - */ - if (transport && - sack->num_gap_ack_blocks && - q->asoc->peer.primary_path->cacc. - changeover_active) - transport->cacc.cacc_saw_newack - = 1; - } - list_add_tail(&tchunk->transmitted_list, &q->sacked); } else { @@ -1756,7 +1762,7 @@ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn) if (TSN_lte(tsn, ctsn)) goto pass; - /* 3.3.4 Selective Acknowledgement (SACK) (3): + /* 3.3.4 Selective Acknowledgment (SACK) (3): * * Gap Ack Blocks: * These fields contain the Gap Ack Blocks. They are repeated diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index e62addb60434a..4a4fd19712552 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -81,8 +81,6 @@ static int sctp_process_param(struct sctp_association *asoc, gfp_t gfp); static void *sctp_addto_param(struct sctp_chunk *chunk, int len, const void *data); -static void *sctp_addto_chunk_fixed(struct sctp_chunk *, int len, - const void *data); /* Control chunk destructor */ static void sctp_control_release_owner(struct sk_buff *skb) @@ -154,12 +152,11 @@ static const struct sctp_paramhdr prsctp_param = { cpu_to_be16(sizeof(struct sctp_paramhdr)), }; -/* A helper to initialize an op error inside a - * provided chunk, as most cause codes will be embedded inside an - * abort chunk. +/* A helper to initialize an op error inside a provided chunk, as most + * cause codes will be embedded inside an abort chunk. */ -void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, - size_t paylen) +int sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, + size_t paylen) { struct sctp_errhdr err; __u16 len; @@ -167,33 +164,16 @@ void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, /* Cause code constants are now defined in network order. */ err.cause = cause_code; len = sizeof(err) + paylen; - err.length = htons(len); - chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(err), &err); -} - -/* A helper to initialize an op error inside a - * provided chunk, as most cause codes will be embedded inside an - * abort chunk. Differs from sctp_init_cause in that it won't oops - * if there isn't enough space in the op error chunk - */ -static int sctp_init_cause_fixed(struct sctp_chunk *chunk, __be16 cause_code, - size_t paylen) -{ - struct sctp_errhdr err; - __u16 len; - - /* Cause code constants are now defined in network order. */ - err.cause = cause_code; - len = sizeof(err) + paylen; - err.length = htons(len); + err.length = htons(len); if (skb_tailroom(chunk->skb) < len) return -ENOSPC; - chunk->subh.err_hdr = sctp_addto_chunk_fixed(chunk, sizeof(err), &err); + chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(err), &err); return 0; } + /* 3.3.2 Initiation (INIT) (1) * * This chunk is used to initiate a SCTP association between two @@ -779,10 +759,9 @@ struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc, * association. This reports on which TSN's we've seen to date, * including duplicates and gaps. */ -struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) +struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc) { struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; - struct sctp_association *aptr = (struct sctp_association *)asoc; struct sctp_gap_ack_block gabs[SCTP_MAX_GABS]; __u16 num_gabs, num_dup_tsns; struct sctp_transport *trans; @@ -857,7 +836,7 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) /* Add the duplicate TSN information. */ if (num_dup_tsns) { - aptr->stats.idupchunks += num_dup_tsns; + asoc->stats.idupchunks += num_dup_tsns; sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns, sctp_tsnmap_get_dups(map)); } @@ -869,11 +848,11 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) * association so no transport will match after a wrap event like this, * Until the next sack */ - if (++aptr->peer.sack_generation == 0) { + if (++asoc->peer.sack_generation == 0) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) trans->sack_generation = 0; - aptr->peer.sack_generation = 1; + asoc->peer.sack_generation = 1; } nodata: return retval; @@ -1258,20 +1237,26 @@ nodata: return retval; } -/* Create an Operation Error chunk of a fixed size, - * specifically, max(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - * This is a helper function to allocate an error chunk for - * for those invalid parameter codes in which we may not want - * to report all the errors, if the incoming chunk is large +/* Create an Operation Error chunk of a fixed size, specifically, + * min(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - overheads. + * This is a helper function to allocate an error chunk for for those + * invalid parameter codes in which we may not want to report all the + * errors, if the incoming chunk is large. If it can't fit in a single + * packet, we ignore it. */ -static inline struct sctp_chunk *sctp_make_op_error_fixed( +static inline struct sctp_chunk *sctp_make_op_error_limited( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { - size_t size = asoc ? asoc->pathmtu : 0; + size_t size = SCTP_DEFAULT_MAXSEGMENT; + struct sctp_sock *sp = NULL; - if (!size) - size = SCTP_DEFAULT_MAXSEGMENT; + if (asoc) { + size = min_t(size_t, size, asoc->pathmtu); + sp = sctp_sk(asoc->base.sk); + } + + size = sctp_mtu_payload(sp, size, sizeof(struct sctp_errhdr)); return sctp_make_op_error_space(asoc, chunk, size); } @@ -1523,18 +1508,6 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) return target; } -/* Append bytes to the end of a chunk. Returns NULL if there isn't sufficient - * space in the chunk - */ -static void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk, - int len, const void *data) -{ - if (skb_tailroom(chunk->skb) >= len) - return sctp_addto_chunk(chunk, len, data); - else - return NULL; -} - /* Append bytes from user space to the end of a chunk. Will panic if * chunk is not big enough. * Returns a kernel err value. @@ -1829,6 +1802,9 @@ no_hmac: kt = ktime_get_real(); if (!asoc && ktime_before(bear_cookie->expiration, kt)) { + suseconds_t usecs = ktime_to_us(ktime_sub(kt, bear_cookie->expiration)); + __be32 n = htonl(usecs); + /* * Section 3.3.10.3 Stale Cookie Error (3) * @@ -1837,17 +1813,12 @@ no_hmac: * Stale Cookie Error: Indicates the receipt of a valid State * Cookie that has expired. */ - len = ntohs(chunk->chunk_hdr->length); - *errp = sctp_make_op_error_space(asoc, chunk, len); - if (*errp) { - suseconds_t usecs = ktime_to_us(ktime_sub(kt, bear_cookie->expiration)); - __be32 n = htonl(usecs); - - sctp_init_cause(*errp, SCTP_ERROR_STALE_COOKIE, - sizeof(n)); - sctp_addto_chunk(*errp, sizeof(n), &n); + *errp = sctp_make_op_error(asoc, chunk, + SCTP_ERROR_STALE_COOKIE, &n, + sizeof(n), 0); + if (*errp) *error = -SCTP_IERROR_STALE_COOKIE; - } else + else *error = -SCTP_IERROR_NOMEM; goto fail; @@ -1998,12 +1969,8 @@ static int sctp_process_hn_param(const struct sctp_association *asoc, if (*errp) sctp_chunk_free(*errp); - *errp = sctp_make_op_error_space(asoc, chunk, len); - - if (*errp) { - sctp_init_cause(*errp, SCTP_ERROR_DNS_FAILED, len); - sctp_addto_chunk(*errp, len, param.v); - } + *errp = sctp_make_op_error(asoc, chunk, SCTP_ERROR_DNS_FAILED, + param.v, len, 0); /* Stop processing this chunk. */ return 0; @@ -2128,23 +2095,23 @@ static enum sctp_ierror sctp_process_unk_param( /* Make an ERROR chunk, preparing enough room for * returning multiple unknown parameters. */ - if (NULL == *errp) - *errp = sctp_make_op_error_fixed(asoc, chunk); - - if (*errp) { - if (!sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM, - SCTP_PAD4(ntohs(param.p->length)))) - sctp_addto_chunk_fixed(*errp, - SCTP_PAD4(ntohs(param.p->length)), - param.v); - } else { - /* If there is no memory for generating the ERROR - * report as specified, an ABORT will be triggered - * to the peer and the association won't be - * established. - */ - retval = SCTP_IERROR_NOMEM; + if (!*errp) { + *errp = sctp_make_op_error_limited(asoc, chunk); + if (!*errp) { + /* If there is no memory for generating the + * ERROR report as specified, an ABORT will be + * triggered to the peer and the association + * won't be established. + */ + retval = SCTP_IERROR_NOMEM; + break; + } } + + if (!sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM, + ntohs(param.p->length))) + sctp_addto_chunk(*errp, ntohs(param.p->length), + param.v); break; default: break; @@ -2220,10 +2187,10 @@ static enum sctp_ierror sctp_verify_param(struct net *net, * MUST be aborted. The ABORT chunk SHOULD contain the error * cause 'Protocol Violation'. */ - if (SCTP_AUTH_RANDOM_LENGTH != - ntohs(param.p->length) - sizeof(struct sctp_paramhdr)) { + if (SCTP_AUTH_RANDOM_LENGTH != ntohs(param.p->length) - + sizeof(struct sctp_paramhdr)) { sctp_process_inv_paramlength(asoc, param.p, - chunk, err_chunk); + chunk, err_chunk); retval = SCTP_IERROR_ABORT; } break; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index bf747094d26bf..d20f7addee19e 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -644,16 +644,15 @@ static int sctp_send_asconf_add_ip(struct sock *sk, list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { - /* Clear the source and route cache */ - sctp_transport_dst_release(trans); trans->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); trans->ssthresh = asoc->peer.i.a_rwnd; trans->rto = asoc->rto_initial; sctp_max_rto(asoc, trans); trans->rtt = trans->srtt = trans->rttvar = 0; + /* Clear the source and route cache */ sctp_transport_route(trans, NULL, - sctp_sk(asoc->base.sk)); + sctp_sk(asoc->base.sk)); } } retval = sctp_send_asconf(asoc, chunk); @@ -896,7 +895,6 @@ skip_mkasconf: */ list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { - sctp_transport_dst_release(transport); sctp_transport_route(transport, NULL, sctp_sk(asoc->base.sk)); } @@ -1894,6 +1892,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo) { struct sock *sk = asoc->base.sk; + struct sctp_sock *sp = sctp_sk(sk); struct net *net = sock_net(sk); struct sctp_datamsg *datamsg; bool wait_connect = false; @@ -1912,13 +1911,16 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, goto err; } - if (sctp_sk(sk)->disable_fragments && msg_len > asoc->frag_point) { + if (sp->disable_fragments && msg_len > asoc->frag_point) { err = -EMSGSIZE; goto err; } - if (asoc->pmtu_pending) - sctp_assoc_pending_pmtu(asoc); + if (asoc->pmtu_pending) { + if (sp->param_flags & SPP_PMTUD_ENABLE) + sctp_assoc_sync_pmtu(asoc); + asoc->pmtu_pending = 0; + } if (sctp_wspace(asoc) < msg_len) sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); @@ -1935,7 +1937,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, if (err) goto err; - if (sctp_sk(sk)->strm_interleave) { + if (sp->strm_interleave) { timeo = sock_sndtimeo(sk, 0); err = sctp_wait_for_connect(asoc, &timeo); if (err) @@ -2538,7 +2540,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, trans->pathmtu = params->spp_pathmtu; sctp_assoc_sync_pmtu(asoc); } else if (asoc) { - asoc->pathmtu = params->spp_pathmtu; + sctp_assoc_set_pmtu(asoc, params->spp_pathmtu); } else { sp->pathmtu = params->spp_pathmtu; } @@ -3208,7 +3210,6 @@ static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, unsign static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); - struct sctp_af *af = sp->pf->af; struct sctp_assoc_value params; struct sctp_association *asoc; int val; @@ -3230,30 +3231,24 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned return -EINVAL; } + asoc = sctp_id2assoc(sk, params.assoc_id); + if (val) { int min_len, max_len; + __u16 datasize = asoc ? sctp_datachk_len(&asoc->stream) : + sizeof(struct sctp_data_chunk); - min_len = SCTP_DEFAULT_MINSEGMENT - af->net_header_len; - min_len -= af->ip_options_len(sk); - min_len -= sizeof(struct sctphdr) + - sizeof(struct sctp_data_chunk); - - max_len = SCTP_MAX_CHUNK_LEN - sizeof(struct sctp_data_chunk); + min_len = sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT, + datasize); + max_len = SCTP_MAX_CHUNK_LEN - datasize; if (val < min_len || val > max_len) return -EINVAL; } - asoc = sctp_id2assoc(sk, params.assoc_id); if (asoc) { - if (val == 0) { - val = asoc->pathmtu - af->net_header_len; - val -= af->ip_options_len(sk); - val -= sizeof(struct sctphdr) + - sctp_datachk_len(&asoc->stream); - } asoc->user_frag = val; - asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu); + sctp_assoc_update_frag_point(asoc); } else { if (params.assoc_id && sctp_style(sk, UDP)) return -EINVAL; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 47f82bd794d91..445b7ef61677c 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -242,9 +242,18 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) &transport->fl, sk); } - if (transport->dst) { - transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst)); - } else + if (transport->param_flags & SPP_PMTUD_DISABLE) { + struct sctp_association *asoc = transport->asoc; + + if (!transport->pathmtu && asoc && asoc->pathmtu) + transport->pathmtu = asoc->pathmtu; + if (transport->pathmtu) + return; + } + + if (transport->dst) + transport->pathmtu = sctp_dst_mtu(transport->dst); + else transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } @@ -290,6 +299,7 @@ void sctp_transport_route(struct sctp_transport *transport, struct sctp_association *asoc = transport->asoc; struct sctp_af *af = transport->af_specific; + sctp_transport_dst_release(transport); af->get_dst(transport, saddr, &transport->fl, sctp_opt2sk(opt)); if (saddr) @@ -297,21 +307,14 @@ void sctp_transport_route(struct sctp_transport *transport, else af->get_saddr(opt, transport, &transport->fl); - if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) { - return; - } - if (transport->dst) { - transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst)); + sctp_transport_pmtu(transport, sctp_opt2sk(opt)); - /* Initialize sk->sk_rcv_saddr, if the transport is the - * association's active path for getsockname(). - */ - if (asoc && (!asoc->peer.primary_path || - (transport == asoc->peer.active_path))) - opt->pf->to_sk_saddr(&transport->saddr, - asoc->base.sk); - } else - transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; + /* Initialize sk->sk_rcv_saddr, if the transport is the + * association's active path for getsockname(). + */ + if (transport->dst && asoc && + (!asoc->peer.primary_path || transport == asoc->peer.active_path)) + opt->pf->to_sk_saddr(&transport->saddr, asoc->base.sk); } /* Hold a reference to a transport. */ @@ -634,7 +637,7 @@ unsigned long sctp_transport_timeout(struct sctp_transport *trans) trans->state != SCTP_PF) timeout += trans->hbinterval; - return timeout; + return max_t(unsigned long, timeout, HZ / 5); } /* Reset transport variables to their initial values */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 544bab42f925a..973b4471b532b 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -8,8 +8,6 @@ * * Initial restrictions: * - support for alternate links postponed - * - partial support for non-blocking sockets only - * - support for urgent data postponed * * Copyright IBM Corp. 2016, 2018 * @@ -29,6 +27,7 @@ #include <net/sock.h> #include <net/tcp.h> #include <net/smc.h> +#include <asm/ioctls.h> #include "smc.h" #include "smc_clc.h" @@ -45,11 +44,6 @@ static DEFINE_MUTEX(smc_create_lgr_pending); /* serialize link group * creation */ -struct smc_lgr_list smc_lgr_list = { /* established link groups */ - .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock), - .list = LIST_HEAD_INIT(smc_lgr_list.list), -}; - static void smc_tcp_listen_work(struct work_struct *); static void smc_set_keepalive(struct sock *sk, int val) @@ -192,8 +186,10 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_protocol = protocol; smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); + INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work); INIT_LIST_HEAD(&smc->accept_q); spin_lock_init(&smc->accept_q_lock); + spin_lock_init(&smc->conn.send_lock); sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); @@ -292,19 +288,28 @@ static void smc_copy_sock_settings_to_smc(struct smc_sock *smc) smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC); } -/* register a new rmb */ -static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc) +/* register a new rmb, optionally send confirm_rkey msg to register with peer */ +static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc, + bool conf_rkey) { /* register memory region for new rmb */ if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) { rmb_desc->regerr = 1; return -EFAULT; } + if (!conf_rkey) + return 0; + /* exchange confirm_rkey msg with peer */ + if (smc_llc_do_confirm_rkey(link, rmb_desc)) { + rmb_desc->regerr = 1; + return -EFAULT; + } return 0; } static int smc_clnt_conf_first_link(struct smc_sock *smc) { + struct net *net = sock_net(smc->clcsock->sk); struct smc_link_group *lgr = smc->conn.lgr; struct smc_link *link; int rest; @@ -332,7 +337,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) smc_wr_remember_qp_attr(link); - if (smc_reg_rmb(link, smc->conn.rmb_desc)) + if (smc_reg_rmb(link, smc->conn.rmb_desc, false)) return SMC_CLC_DECL_INTERR; /* send CONFIRM LINK response over RoCE fabric */ @@ -362,7 +367,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) if (rc < 0) return SMC_CLC_DECL_TCL; - link->state = SMC_LNK_ACTIVE; + smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time); return 0; } @@ -370,10 +375,13 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) static void smc_conn_save_peer_info(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *clc) { - smc->conn.peer_conn_idx = clc->conn_idx; + int bufsize = smc_uncompress_bufsize(clc->rmbe_size); + + smc->conn.peer_rmbe_idx = clc->rmbe_idx; smc->conn.local_tx_ctrl.token = ntohl(clc->rmbe_alert_token); - smc->conn.peer_rmbe_size = smc_uncompress_bufsize(clc->rmbe_size); + smc->conn.peer_rmbe_size = bufsize; atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); + smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1); } static void smc_link_save_peer_info(struct smc_link *link, @@ -386,160 +394,186 @@ static void smc_link_save_peer_info(struct smc_link *link, link->peer_mtu = clc->qp_mtu; } -/* setup for RDMA connection of client */ -static int smc_connect_rdma(struct smc_sock *smc) +/* fall back during connect */ +static int smc_connect_fallback(struct smc_sock *smc) { - struct smc_clc_msg_accept_confirm aclc; - int local_contact = SMC_FIRST_CONTACT; - struct smc_ib_device *smcibdev; - struct smc_link *link; - u8 srv_first_contact; - int reason_code = 0; - int rc = 0; - u8 ibport; + smc->use_fallback = true; + smc_copy_sock_settings_to_clc(smc); + if (smc->sk.sk_state == SMC_INIT) + smc->sk.sk_state = SMC_ACTIVE; + return 0; +} - sock_hold(&smc->sk); /* sock put in passive closing */ +/* decline and fall back during connect */ +static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) +{ + int rc; - if (!tcp_sk(smc->clcsock->sk)->syn_smc) { - /* peer has not signalled SMC-capability */ - smc->use_fallback = true; - goto out_connected; + if (reason_code < 0) /* error, fallback is not possible */ + return reason_code; + if (reason_code != SMC_CLC_DECL_REPLY) { + rc = smc_clc_send_decline(smc, reason_code); + if (rc < 0) + return rc; } + return smc_connect_fallback(smc); +} - /* IPSec connections opt out of SMC-R optimizations */ - if (using_ipsec(smc)) { - reason_code = SMC_CLC_DECL_IPSEC; - goto decline_rdma; - } +/* abort connecting */ +static int smc_connect_abort(struct smc_sock *smc, int reason_code, + int local_contact) +{ + if (local_contact == SMC_FIRST_CONTACT) + smc_lgr_forget(smc->conn.lgr); + mutex_unlock(&smc_create_lgr_pending); + smc_conn_free(&smc->conn); + if (reason_code < 0 && smc->sk.sk_state == SMC_INIT) + sock_put(&smc->sk); /* passive closing */ + return reason_code; +} + +/* check if there is a rdma device available for this connection. */ +/* called for connect and listen */ +static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev, + u8 *ibport) +{ + int reason_code = 0; /* PNET table look up: search active ib_device and port * within same PNETID that also contains the ethernet device * used for the internal TCP socket */ - smc_pnet_find_roce_resource(smc->clcsock->sk, &smcibdev, &ibport); - if (!smcibdev) { + smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport); + if (!(*ibdev)) reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */ - goto decline_rdma; - } + + return reason_code; +} + +/* CLC handshake during connect */ +static int smc_connect_clc(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *aclc, + struct smc_ib_device *ibdev, u8 ibport) +{ + int rc = 0; /* do inband token exchange */ - reason_code = smc_clc_send_proposal(smc, smcibdev, ibport); - if (reason_code < 0) { - rc = reason_code; - goto out_err; - } - if (reason_code > 0) /* configuration error */ - goto decline_rdma; + rc = smc_clc_send_proposal(smc, ibdev, ibport); + if (rc) + return rc; /* receive SMC Accept CLC message */ - reason_code = smc_clc_wait_msg(smc, &aclc, sizeof(aclc), - SMC_CLC_ACCEPT); - if (reason_code < 0) { - rc = reason_code; - goto out_err; - } - if (reason_code > 0) - goto decline_rdma; + return smc_clc_wait_msg(smc, aclc, sizeof(*aclc), SMC_CLC_ACCEPT); +} + +/* setup for RDMA connection of client */ +static int smc_connect_rdma(struct smc_sock *smc, + struct smc_clc_msg_accept_confirm *aclc, + struct smc_ib_device *ibdev, u8 ibport) +{ + int local_contact = SMC_FIRST_CONTACT; + struct smc_link *link; + int reason_code = 0; - srv_first_contact = aclc.hdr.flag; mutex_lock(&smc_create_lgr_pending); - local_contact = smc_conn_create(smc, smcibdev, ibport, &aclc.lcl, - srv_first_contact); + local_contact = smc_conn_create(smc, ibdev, ibport, &aclc->lcl, + aclc->hdr.flag); if (local_contact < 0) { - rc = local_contact; - if (rc == -ENOMEM) + if (local_contact == -ENOMEM) reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/ - else if (rc == -ENOLINK) + else if (local_contact == -ENOLINK) reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */ - goto decline_rdma_unlock; + else + reason_code = SMC_CLC_DECL_INTERR; /* other error */ + return smc_connect_abort(smc, reason_code, 0); } link = &smc->conn.lgr->lnk[SMC_SINGLE_LINK]; - smc_conn_save_peer_info(smc, &aclc); + smc_conn_save_peer_info(smc, aclc); /* create send buffer and rmb */ - rc = smc_buf_create(smc); - if (rc) { - reason_code = SMC_CLC_DECL_MEM; - goto decline_rdma_unlock; - } + if (smc_buf_create(smc)) + return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact); if (local_contact == SMC_FIRST_CONTACT) - smc_link_save_peer_info(link, &aclc); + smc_link_save_peer_info(link, aclc); - rc = smc_rmb_rtoken_handling(&smc->conn, &aclc); - if (rc) { - reason_code = SMC_CLC_DECL_INTERR; - goto decline_rdma_unlock; - } + if (smc_rmb_rtoken_handling(&smc->conn, aclc)) + return smc_connect_abort(smc, SMC_CLC_DECL_INTERR, + local_contact); smc_close_init(smc); smc_rx_init(smc); if (local_contact == SMC_FIRST_CONTACT) { - rc = smc_ib_ready_link(link); - if (rc) { - reason_code = SMC_CLC_DECL_INTERR; - goto decline_rdma_unlock; - } + if (smc_ib_ready_link(link)) + return smc_connect_abort(smc, SMC_CLC_DECL_INTERR, + local_contact); } else { - if (!smc->conn.rmb_desc->reused) { - if (smc_reg_rmb(link, smc->conn.rmb_desc)) { - reason_code = SMC_CLC_DECL_INTERR; - goto decline_rdma_unlock; - } - } + if (!smc->conn.rmb_desc->reused && + smc_reg_rmb(link, smc->conn.rmb_desc, true)) + return smc_connect_abort(smc, SMC_CLC_DECL_INTERR, + local_contact); } smc_rmb_sync_sg_for_device(&smc->conn); - rc = smc_clc_send_confirm(smc); - if (rc) - goto out_err_unlock; + reason_code = smc_clc_send_confirm(smc); + if (reason_code) + return smc_connect_abort(smc, reason_code, local_contact); + + smc_tx_init(smc); if (local_contact == SMC_FIRST_CONTACT) { /* QP confirmation over RoCE fabric */ reason_code = smc_clnt_conf_first_link(smc); - if (reason_code < 0) { - rc = reason_code; - goto out_err_unlock; - } - if (reason_code > 0) - goto decline_rdma_unlock; + if (reason_code) + return smc_connect_abort(smc, reason_code, + local_contact); } - mutex_unlock(&smc_create_lgr_pending); - smc_tx_init(smc); -out_connected: smc_copy_sock_settings_to_clc(smc); if (smc->sk.sk_state == SMC_INIT) smc->sk.sk_state = SMC_ACTIVE; - return rc ? rc : local_contact; + return 0; +} -decline_rdma_unlock: - if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(smc->conn.lgr); - mutex_unlock(&smc_create_lgr_pending); - smc_conn_free(&smc->conn); -decline_rdma: - /* RDMA setup failed, switch back to TCP */ - smc->use_fallback = true; - if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) { - rc = smc_clc_send_decline(smc, reason_code); - if (rc < 0) - goto out_err; - } - goto out_connected; +/* perform steps before actually connecting */ +static int __smc_connect(struct smc_sock *smc) +{ + struct smc_clc_msg_accept_confirm aclc; + struct smc_ib_device *ibdev; + int rc = 0; + u8 ibport; -out_err_unlock: - if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(smc->conn.lgr); - mutex_unlock(&smc_create_lgr_pending); - smc_conn_free(&smc->conn); -out_err: - if (smc->sk.sk_state == SMC_INIT) - sock_put(&smc->sk); /* passive closing */ - return rc; + sock_hold(&smc->sk); /* sock put in passive closing */ + + if (smc->use_fallback) + return smc_connect_fallback(smc); + + /* if peer has not signalled SMC-capability, fall back */ + if (!tcp_sk(smc->clcsock->sk)->syn_smc) + return smc_connect_fallback(smc); + + /* IPSec connections opt out of SMC-R optimizations */ + if (using_ipsec(smc)) + return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC); + + /* check if a RDMA device is available; if not, fall back */ + if (smc_check_rdma(smc, &ibdev, &ibport)) + return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR); + + /* perform CLC handshake */ + rc = smc_connect_clc(smc, &aclc, ibdev, ibport); + if (rc) + return smc_connect_decline_fallback(smc, rc); + + /* connect using rdma */ + rc = smc_connect_rdma(smc, &aclc, ibdev, ibport); + if (rc) + return smc_connect_decline_fallback(smc, rc); + + return 0; } static int smc_connect(struct socket *sock, struct sockaddr *addr, @@ -575,8 +609,7 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, if (rc) goto out; - /* setup RDMA connection */ - rc = smc_connect_rdma(smc); + rc = __smc_connect(smc); if (rc < 0) goto out; else @@ -716,6 +749,7 @@ void smc_close_non_accepted(struct sock *sk) static int smc_serv_conf_first_link(struct smc_sock *smc) { + struct net *net = sock_net(smc->clcsock->sk); struct smc_link_group *lgr = smc->conn.lgr; struct smc_link *link; int rest; @@ -723,7 +757,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc) link = &lgr->lnk[SMC_SINGLE_LINK]; - if (smc_reg_rmb(link, smc->conn.rmb_desc)) + if (smc_reg_rmb(link, smc->conn.rmb_desc, false)) return SMC_CLC_DECL_INTERR; /* send CONFIRM LINK request to client over the RoCE fabric */ @@ -768,184 +802,244 @@ static int smc_serv_conf_first_link(struct smc_sock *smc) return rc; } - link->state = SMC_LNK_ACTIVE; + smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time); return 0; } -/* setup for RDMA connection of server */ -static void smc_listen_work(struct work_struct *work) +/* listen worker: finish */ +static void smc_listen_out(struct smc_sock *new_smc) { - struct smc_sock *new_smc = container_of(work, struct smc_sock, - smc_listen_work); - struct smc_clc_msg_proposal_prefix *pclc_prfx; - struct socket *newclcsock = new_smc->clcsock; struct smc_sock *lsmc = new_smc->listen_smc; - struct smc_clc_msg_accept_confirm cclc; - int local_contact = SMC_REUSE_CONTACT; struct sock *newsmcsk = &new_smc->sk; - struct smc_clc_msg_proposal *pclc; - struct smc_ib_device *smcibdev; - u8 buf[SMC_CLC_MAX_LEN]; - struct smc_link *link; - int reason_code = 0; - int rc = 0; - u8 ibport; - /* check if peer is smc capable */ - if (!tcp_sk(newclcsock->sk)->syn_smc) { - new_smc->use_fallback = true; - goto out_connected; + lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); + if (lsmc->sk.sk_state == SMC_LISTEN) { + smc_accept_enqueue(&lsmc->sk, newsmcsk); + } else { /* no longer listening */ + smc_close_non_accepted(newsmcsk); } + release_sock(&lsmc->sk); - /* do inband token exchange - - *wait for and receive SMC Proposal CLC message - */ - reason_code = smc_clc_wait_msg(new_smc, &buf, sizeof(buf), - SMC_CLC_PROPOSAL); - if (reason_code < 0) - goto out_err; - if (reason_code > 0) - goto decline_rdma; + /* Wake up accept */ + lsmc->sk.sk_data_ready(&lsmc->sk); + sock_put(&lsmc->sk); /* sock_hold in smc_tcp_listen_work */ +} - /* IPSec connections opt out of SMC-R optimizations */ - if (using_ipsec(new_smc)) { - reason_code = SMC_CLC_DECL_IPSEC; - goto decline_rdma; - } +/* listen worker: finish in state connected */ +static void smc_listen_out_connected(struct smc_sock *new_smc) +{ + struct sock *newsmcsk = &new_smc->sk; - /* PNET table look up: search active ib_device and port - * within same PNETID that also contains the ethernet device - * used for the internal TCP socket - */ - smc_pnet_find_roce_resource(newclcsock->sk, &smcibdev, &ibport); - if (!smcibdev) { - reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */ - goto decline_rdma; + sk_refcnt_debug_inc(newsmcsk); + if (newsmcsk->sk_state == SMC_INIT) + newsmcsk->sk_state = SMC_ACTIVE; + + smc_listen_out(new_smc); +} + +/* listen worker: finish in error state */ +static void smc_listen_out_err(struct smc_sock *new_smc) +{ + struct sock *newsmcsk = &new_smc->sk; + + if (newsmcsk->sk_state == SMC_INIT) + sock_put(&new_smc->sk); /* passive closing */ + newsmcsk->sk_state = SMC_CLOSED; + smc_conn_free(&new_smc->conn); + + smc_listen_out(new_smc); +} + +/* listen worker: decline and fall back if possible */ +static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, + int local_contact) +{ + /* RDMA setup failed, switch back to TCP */ + if (local_contact == SMC_FIRST_CONTACT) + smc_lgr_forget(new_smc->conn.lgr); + if (reason_code < 0) { /* error, no fallback possible */ + smc_listen_out_err(new_smc); + return; + } + smc_conn_free(&new_smc->conn); + new_smc->use_fallback = true; + if (reason_code && reason_code != SMC_CLC_DECL_REPLY) { + if (smc_clc_send_decline(new_smc, reason_code) < 0) { + smc_listen_out_err(new_smc); + return; + } } + smc_listen_out_connected(new_smc); +} + +/* listen worker: check prefixes */ +static int smc_listen_rdma_check(struct smc_sock *new_smc, + struct smc_clc_msg_proposal *pclc) +{ + struct smc_clc_msg_proposal_prefix *pclc_prfx; + struct socket *newclcsock = new_smc->clcsock; - pclc = (struct smc_clc_msg_proposal *)&buf; pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (smc_clc_prfx_match(newclcsock, pclc_prfx)) + return SMC_CLC_DECL_CNFERR; - rc = smc_clc_prfx_match(newclcsock, pclc_prfx); - if (rc) { - reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */ - goto decline_rdma; - } + return 0; +} +/* listen worker: initialize connection and buffers */ +static int smc_listen_rdma_init(struct smc_sock *new_smc, + struct smc_clc_msg_proposal *pclc, + struct smc_ib_device *ibdev, u8 ibport, + int *local_contact) +{ /* allocate connection / link group */ - mutex_lock(&smc_create_lgr_pending); - local_contact = smc_conn_create(new_smc, smcibdev, ibport, &pclc->lcl, - 0); - if (local_contact < 0) { - rc = local_contact; - if (rc == -ENOMEM) - reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/ - goto decline_rdma_unlock; + *local_contact = smc_conn_create(new_smc, ibdev, ibport, &pclc->lcl, 0); + if (*local_contact < 0) { + if (*local_contact == -ENOMEM) + return SMC_CLC_DECL_MEM;/* insufficient memory*/ + return SMC_CLC_DECL_INTERR; /* other error */ } - link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK]; /* create send buffer and rmb */ - rc = smc_buf_create(new_smc); - if (rc) { - reason_code = SMC_CLC_DECL_MEM; - goto decline_rdma_unlock; - } + if (smc_buf_create(new_smc)) + return SMC_CLC_DECL_MEM; - smc_close_init(new_smc); - smc_rx_init(new_smc); + return 0; +} + +/* listen worker: register buffers */ +static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact) +{ + struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK]; if (local_contact != SMC_FIRST_CONTACT) { if (!new_smc->conn.rmb_desc->reused) { - if (smc_reg_rmb(link, new_smc->conn.rmb_desc)) { - reason_code = SMC_CLC_DECL_INTERR; - goto decline_rdma_unlock; - } + if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true)) + return SMC_CLC_DECL_INTERR; } } smc_rmb_sync_sg_for_device(&new_smc->conn); - rc = smc_clc_send_accept(new_smc, local_contact); - if (rc) - goto out_err_unlock; + return 0; +} + +/* listen worker: finish RDMA setup */ +static void smc_listen_rdma_finish(struct smc_sock *new_smc, + struct smc_clc_msg_accept_confirm *cclc, + int local_contact) +{ + struct smc_link *link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK]; + int reason_code = 0; - /* receive SMC Confirm CLC message */ - reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc), - SMC_CLC_CONFIRM); - if (reason_code < 0) - goto out_err_unlock; - if (reason_code > 0) - goto decline_rdma_unlock; - smc_conn_save_peer_info(new_smc, &cclc); if (local_contact == SMC_FIRST_CONTACT) - smc_link_save_peer_info(link, &cclc); + smc_link_save_peer_info(link, cclc); - rc = smc_rmb_rtoken_handling(&new_smc->conn, &cclc); - if (rc) { + if (smc_rmb_rtoken_handling(&new_smc->conn, cclc)) { reason_code = SMC_CLC_DECL_INTERR; - goto decline_rdma_unlock; + goto decline; } if (local_contact == SMC_FIRST_CONTACT) { - rc = smc_ib_ready_link(link); - if (rc) { + if (smc_ib_ready_link(link)) { reason_code = SMC_CLC_DECL_INTERR; - goto decline_rdma_unlock; + goto decline; } /* QP confirmation over RoCE fabric */ reason_code = smc_serv_conf_first_link(new_smc); - if (reason_code < 0) - /* peer is not aware of a problem */ - goto out_err_unlock; - if (reason_code > 0) - goto decline_rdma_unlock; + if (reason_code) + goto decline; } + return; - smc_tx_init(new_smc); +decline: mutex_unlock(&smc_create_lgr_pending); + smc_listen_decline(new_smc, reason_code, local_contact); +} -out_connected: - sk_refcnt_debug_inc(newsmcsk); - if (newsmcsk->sk_state == SMC_INIT) - newsmcsk->sk_state = SMC_ACTIVE; -enqueue: - lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); - if (lsmc->sk.sk_state == SMC_LISTEN) { - smc_accept_enqueue(&lsmc->sk, newsmcsk); - } else { /* no longer listening */ - smc_close_non_accepted(newsmcsk); +/* setup for RDMA connection of server */ +static void smc_listen_work(struct work_struct *work) +{ + struct smc_sock *new_smc = container_of(work, struct smc_sock, + smc_listen_work); + struct socket *newclcsock = new_smc->clcsock; + struct smc_clc_msg_accept_confirm cclc; + struct smc_clc_msg_proposal *pclc; + struct smc_ib_device *ibdev; + u8 buf[SMC_CLC_MAX_LEN]; + int local_contact = 0; + int reason_code = 0; + int rc = 0; + u8 ibport; + + if (new_smc->use_fallback) { + smc_listen_out_connected(new_smc); + return; } - release_sock(&lsmc->sk); - /* Wake up accept */ - lsmc->sk.sk_data_ready(&lsmc->sk); - sock_put(&lsmc->sk); /* sock_hold in smc_tcp_listen_work */ - return; + /* check if peer is smc capable */ + if (!tcp_sk(newclcsock->sk)->syn_smc) { + new_smc->use_fallback = true; + smc_listen_out_connected(new_smc); + return; + } -decline_rdma_unlock: - if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); - mutex_unlock(&smc_create_lgr_pending); -decline_rdma: - /* RDMA setup failed, switch back to TCP */ - smc_conn_free(&new_smc->conn); - new_smc->use_fallback = true; - if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) { - if (smc_clc_send_decline(new_smc, reason_code) < 0) - goto out_err; + /* do inband token exchange - + * wait for and receive SMC Proposal CLC message + */ + pclc = (struct smc_clc_msg_proposal *)&buf; + reason_code = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN, + SMC_CLC_PROPOSAL); + if (reason_code) { + smc_listen_decline(new_smc, reason_code, 0); + return; } - goto out_connected; -out_err_unlock: - if (local_contact == SMC_FIRST_CONTACT) - smc_lgr_forget(new_smc->conn.lgr); + /* IPSec connections opt out of SMC-R optimizations */ + if (using_ipsec(new_smc)) { + smc_listen_decline(new_smc, SMC_CLC_DECL_IPSEC, 0); + return; + } + + mutex_lock(&smc_create_lgr_pending); + smc_close_init(new_smc); + smc_rx_init(new_smc); + smc_tx_init(new_smc); + + /* check if RDMA is available */ + if (smc_check_rdma(new_smc, &ibdev, &ibport) || + smc_listen_rdma_check(new_smc, pclc) || + smc_listen_rdma_init(new_smc, pclc, ibdev, ibport, + &local_contact) || + smc_listen_rdma_reg(new_smc, local_contact)) { + /* SMC not supported, decline */ + mutex_unlock(&smc_create_lgr_pending); + smc_listen_decline(new_smc, SMC_CLC_DECL_CNFERR, local_contact); + return; + } + + /* send SMC Accept CLC message */ + rc = smc_clc_send_accept(new_smc, local_contact); + if (rc) { + mutex_unlock(&smc_create_lgr_pending); + smc_listen_decline(new_smc, rc, local_contact); + return; + } + + /* receive SMC Confirm CLC message */ + reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc), + SMC_CLC_CONFIRM); + if (reason_code) { + mutex_unlock(&smc_create_lgr_pending); + smc_listen_decline(new_smc, reason_code, local_contact); + return; + } + + /* finish worker */ + smc_listen_rdma_finish(new_smc, &cclc, local_contact); + smc_conn_save_peer_info(new_smc, &cclc); mutex_unlock(&smc_create_lgr_pending); -out_err: - if (newsmcsk->sk_state == SMC_INIT) - sock_put(&new_smc->sk); /* passive closing */ - newsmcsk->sk_state = SMC_CLOSED; - smc_conn_free(&new_smc->conn); - goto enqueue; /* queue new sock with sk_err set */ + smc_listen_out_connected(new_smc); } static void smc_tcp_listen_work(struct work_struct *work) @@ -965,7 +1059,7 @@ static void smc_tcp_listen_work(struct work_struct *work) continue; new_smc->listen_smc = lsmc; - new_smc->use_fallback = false; /* assume rdma capability first*/ + new_smc->use_fallback = lsmc->use_fallback; sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); @@ -1001,7 +1095,8 @@ static int smc_listen(struct socket *sock, int backlog) * them to the clc socket -- copy smc socket options to clc socket */ smc_copy_sock_settings_to_clc(smc); - tcp_sk(smc->clcsock->sk)->syn_smc = 1; + if (!smc->use_fallback) + tcp_sk(smc->clcsock->sk)->syn_smc = 1; rc = kernel_listen(smc->clcsock, backlog); if (rc) @@ -1034,6 +1129,7 @@ static int smc_accept(struct socket *sock, struct socket *new_sock, if (lsmc->sk.sk_state != SMC_LISTEN) { rc = -EINVAL; + release_sock(sk); goto out; } @@ -1061,9 +1157,29 @@ static int smc_accept(struct socket *sock, struct socket *new_sock, if (!rc) rc = sock_error(nsk); + release_sock(sk); + if (rc) + goto out; + + if (lsmc->sockopt_defer_accept && !(flags & O_NONBLOCK)) { + /* wait till data arrives on the socket */ + timeo = msecs_to_jiffies(lsmc->sockopt_defer_accept * + MSEC_PER_SEC); + if (smc_sk(nsk)->use_fallback) { + struct sock *clcsk = smc_sk(nsk)->clcsock->sk; + + lock_sock(clcsk); + if (skb_queue_empty(&clcsk->sk_receive_queue)) + sk_wait_data(clcsk, &timeo, NULL); + release_sock(clcsk); + } else if (!atomic_read(&smc_sk(nsk)->conn.bytes_to_rcv)) { + lock_sock(nsk); + smc_rx_wait(smc_sk(nsk), &timeo, smc_rx_data_available); + release_sock(nsk); + } + } out: - release_sock(sk); sock_put(sk); /* sock_hold above */ return rc; } @@ -1094,6 +1210,16 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) (sk->sk_state != SMC_APPCLOSEWAIT1) && (sk->sk_state != SMC_INIT)) goto out; + + if (msg->msg_flags & MSG_FASTOPEN) { + if (sk->sk_state == SMC_INIT) { + smc->use_fallback = true; + } else { + rc = -EINVAL; + goto out; + } + } + if (smc->use_fallback) rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len); else @@ -1122,10 +1248,12 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } - if (smc->use_fallback) + if (smc->use_fallback) { rc = smc->clcsock->ops->recvmsg(smc->clcsock, msg, len, flags); - else - rc = smc_rx_recvmsg(smc, msg, len, flags); + } else { + msg->msg_namelen = 0; + rc = smc_rx_recvmsg(smc, msg, NULL, len, flags); + } out: release_sock(sk); @@ -1172,7 +1300,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, if (sk->sk_state == SMC_INIT && mask & EPOLLOUT && smc->clcsock->sk->sk_state != TCP_CLOSE) { - rc = smc_connect_rdma(smc); + rc = __smc_connect(smc); if (rc < 0) mask |= EPOLLERR; /* success cases including fallback */ @@ -1208,6 +1336,8 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, if (sk->sk_state == SMC_APPCLOSEWAIT1) mask |= EPOLLIN; } + if (smc->conn.urg_state == SMC_URG_VALID) + mask |= EPOLLPRI; } release_sock(sk); @@ -1273,14 +1403,64 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; struct smc_sock *smc; + int val, rc; smc = smc_sk(sk); /* generic setsockopts reaching us here always apply to the * CLC socket */ - return smc->clcsock->ops->setsockopt(smc->clcsock, level, optname, - optval, optlen); + rc = smc->clcsock->ops->setsockopt(smc->clcsock, level, optname, + optval, optlen); + if (smc->clcsock->sk->sk_err) { + sk->sk_err = smc->clcsock->sk->sk_err; + sk->sk_error_report(sk); + } + if (rc) + return rc; + + if (optlen < sizeof(int)) + return -EINVAL; + get_user(val, (int __user *)optval); + + lock_sock(sk); + switch (optname) { + case TCP_ULP: + case TCP_FASTOPEN: + case TCP_FASTOPEN_CONNECT: + case TCP_FASTOPEN_KEY: + case TCP_FASTOPEN_NO_COOKIE: + /* option not supported by SMC */ + if (sk->sk_state == SMC_INIT) { + smc->use_fallback = true; + } else { + if (!smc->use_fallback) + rc = -EINVAL; + } + break; + case TCP_NODELAY: + if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (val && !smc->use_fallback) + mod_delayed_work(system_wq, &smc->conn.tx_work, + 0); + } + break; + case TCP_CORK: + if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (!val && !smc->use_fallback) + mod_delayed_work(system_wq, &smc->conn.tx_work, + 0); + } + break; + case TCP_DEFER_ACCEPT: + smc->sockopt_defer_accept = val; + break; + default: + break; + } + release_sock(sk); + + return rc; } static int smc_getsockopt(struct socket *sock, int level, int optname, @@ -1297,13 +1477,71 @@ static int smc_getsockopt(struct socket *sock, int level, int optname, static int smc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { + union smc_host_cursor cons, urg; + struct smc_connection *conn; struct smc_sock *smc; + int answ; smc = smc_sk(sock->sk); - if (smc->use_fallback) + conn = &smc->conn; + if (smc->use_fallback) { + if (!smc->clcsock) + return -EBADF; return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg); - else - return sock_no_ioctl(sock, cmd, arg); + } + switch (cmd) { + case SIOCINQ: /* same as FIONREAD */ + if (smc->sk.sk_state == SMC_LISTEN) + return -EINVAL; + if (smc->sk.sk_state == SMC_INIT || + smc->sk.sk_state == SMC_CLOSED) + answ = 0; + else + answ = atomic_read(&smc->conn.bytes_to_rcv); + break; + case SIOCOUTQ: + /* output queue size (not send + not acked) */ + if (smc->sk.sk_state == SMC_LISTEN) + return -EINVAL; + if (smc->sk.sk_state == SMC_INIT || + smc->sk.sk_state == SMC_CLOSED) + answ = 0; + else + answ = smc->conn.sndbuf_desc->len - + atomic_read(&smc->conn.sndbuf_space); + break; + case SIOCOUTQNSD: + /* output queue size (not send only) */ + if (smc->sk.sk_state == SMC_LISTEN) + return -EINVAL; + if (smc->sk.sk_state == SMC_INIT || + smc->sk.sk_state == SMC_CLOSED) + answ = 0; + else + answ = smc_tx_prepared_sends(&smc->conn); + break; + case SIOCATMARK: + if (smc->sk.sk_state == SMC_LISTEN) + return -EINVAL; + if (smc->sk.sk_state == SMC_INIT || + smc->sk.sk_state == SMC_CLOSED) { + answ = 0; + } else { + smc_curs_write(&cons, + smc_curs_read(&conn->local_tx_ctrl.cons, conn), + conn); + smc_curs_write(&urg, + smc_curs_read(&conn->urg_curs, conn), + conn); + answ = smc_curs_diff(conn->rmb_desc->len, + &cons, &urg) == 1; + } + break; + default: + return -ENOIOCTLCMD; + } + + return put_user(answ, (int __user *)arg); } static ssize_t smc_sendpage(struct socket *sock, struct page *page, @@ -1330,9 +1568,15 @@ out: return rc; } +/* Map the affected portions of the rmbe into an spd, note the number of bytes + * to splice in conn->splice_pending, and press 'go'. Delays consumer cursor + * updates till whenever a respective page has been fully processed. + * Note that subsequent recv() calls have to wait till all splice() processing + * completed. + */ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, - unsigned int flags) + unsigned int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -1340,16 +1584,34 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, smc = smc_sk(sk); lock_sock(sk); - if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_CLOSED)) + + if (sk->sk_state == SMC_INIT || + sk->sk_state == SMC_LISTEN || + sk->sk_state == SMC_CLOSED) + goto out; + + if (sk->sk_state == SMC_PEERFINCLOSEWAIT) { + rc = 0; goto out; + } + if (smc->use_fallback) { rc = smc->clcsock->ops->splice_read(smc->clcsock, ppos, pipe, len, flags); } else { - rc = -EOPNOTSUPP; + if (*ppos) { + rc = -ESPIPE; + goto out; + } + if (flags & SPLICE_F_NONBLOCK) + flags = MSG_DONTWAIT; + else + flags = 0; + rc = smc_rx_recvmsg(smc, NULL, pipe, len, flags); } out: release_sock(sk); + return rc; } @@ -1482,18 +1744,7 @@ out_pnet: static void __exit smc_exit(void) { - struct smc_link_group *lgr, *lg; - LIST_HEAD(lgr_freeing_list); - - spin_lock_bh(&smc_lgr_list.lock); - if (!list_empty(&smc_lgr_list.list)) - list_splice_init(&smc_lgr_list.list, &lgr_freeing_list); - spin_unlock_bh(&smc_lgr_list.lock); - list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) { - list_del_init(&lgr->list); - cancel_delayed_work_sync(&lgr->free_work); - smc_lgr_free(lgr); /* free link group */ - } + smc_core_exit(); static_branch_disable(&tcp_have_smc); smc_ib_unregister_client(); sock_unregister(PF_SMC); diff --git a/net/smc/smc.h b/net/smc/smc.h index e4829a2f46baf..51ae1f10d81aa 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -114,11 +114,17 @@ struct smc_host_cdc_msg { /* Connection Data Control message */ u8 reserved[18]; } __aligned(8); +enum smc_urg_state { + SMC_URG_VALID, /* data present */ + SMC_URG_NOTYET, /* data pending */ + SMC_URG_READ /* data was already read */ +}; + struct smc_connection { struct rb_node alert_node; struct smc_link_group *lgr; /* link group of connection */ u32 alert_token_local; /* unique conn. id */ - u8 peer_conn_idx; /* from tcp handshake */ + u8 peer_rmbe_idx; /* from tcp handshake */ int peer_rmbe_size; /* size of peer rx buffer */ atomic_t peer_rmbe_space;/* remaining free bytes in peer * rmbe @@ -126,9 +132,7 @@ struct smc_connection { int rtoken_idx; /* idx to peer RMB rkey/addr */ struct smc_buf_desc *sndbuf_desc; /* send buffer descriptor */ - int sndbuf_size; /* sndbuf size <== sock wmem */ struct smc_buf_desc *rmb_desc; /* RMBE descriptor */ - int rmbe_size; /* RMBE size <== sock rmem */ int rmbe_size_short;/* compressed notation */ int rmbe_update_limit; /* lower limit for consumer @@ -153,6 +157,7 @@ struct smc_connection { u16 tx_cdc_seq; /* sequence # for CDC send */ spinlock_t send_lock; /* protect wr_sends */ struct delayed_work tx_work; /* retry of smc_cdc_msg_send */ + u32 tx_off; /* base offset in peer rmb */ struct smc_host_cdc_msg local_rx_ctrl; /* filled during event_handl. * .prod cf. TCP rcv_nxt @@ -161,9 +166,21 @@ struct smc_connection { union smc_host_cursor rx_curs_confirmed; /* confirmed to peer * source of snd_una ? */ + union smc_host_cursor urg_curs; /* points at urgent byte */ + enum smc_urg_state urg_state; + bool urg_tx_pend; /* urgent data staged */ + bool urg_rx_skip_pend; + /* indicate urgent oob data + * read, but previous regular + * data still pending + */ + char urg_rx_byte; /* urgent byte */ atomic_t bytes_to_rcv; /* arrived data, * not yet received */ + atomic_t splice_pending; /* number of spliced bytes + * pending processing + */ #ifndef KERNEL_HAS_ATOMIC64 spinlock_t acurs_lock; /* protect cursors */ #endif @@ -180,6 +197,10 @@ struct smc_sock { /* smc sock container */ struct list_head accept_q; /* sockets to be accepted */ spinlock_t accept_q_lock; /* protects accept_q */ bool use_fallback; /* fallback to tcp */ + int sockopt_defer_accept; + /* sockopt TCP_DEFER_ACCEPT + * value + */ u8 wait_close_tx_prepared : 1; /* shutdown wr or close * started, waiting for unsent @@ -214,41 +235,6 @@ static inline u32 ntoh24(u8 *net) return be32_to_cpu(t); } -#define SMC_BUF_MIN_SIZE 16384 /* minimum size of an RMB */ - -#define SMC_RMBE_SIZES 16 /* number of distinct sizes for an RMBE */ -/* theoretically, the RFC states that largest size would be 512K, - * i.e. compressed 5 and thus 6 sizes (0..5), despite - * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15) - */ - -/* convert the RMB size into the compressed notation - minimum 16K. - * In contrast to plain ilog2, this rounds towards the next power of 2, - * so the socket application gets at least its desired sndbuf / rcvbuf size. - */ -static inline u8 smc_compress_bufsize(int size) -{ - u8 compressed; - - if (size <= SMC_BUF_MIN_SIZE) - return 0; - - size = (size - 1) >> 14; - compressed = ilog2(size) + 1; - if (compressed >= SMC_RMBE_SIZES) - compressed = SMC_RMBE_SIZES - 1; - return compressed; -} - -/* convert the RMB size from compressed notation into integer */ -static inline int smc_uncompress_bufsize(u8 compressed) -{ - u32 size; - - size = 0x00000001 << (((int)compressed) + 14); - return (int)size; -} - #ifdef CONFIG_XFRM static inline bool using_ipsec(struct smc_sock *smc) { @@ -262,12 +248,6 @@ static inline bool using_ipsec(struct smc_sock *smc) } #endif -struct smc_clc_msg_local; - -void smc_conn_free(struct smc_connection *conn); -int smc_conn_create(struct smc_sock *smc, - struct smc_ib_device *smcibdev, u8 ibport, - struct smc_clc_msg_local *lcl, int srv_first_contact); struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock); void smc_close_non_accepted(struct sock *sk); diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index b42395d24cba5..a7e8d63fc8aeb 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -44,13 +44,13 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, smc = container_of(cdcpend->conn, struct smc_sock, conn); bh_lock_sock(&smc->sk); if (!wc_status) { - diff = smc_curs_diff(cdcpend->conn->sndbuf_size, + diff = smc_curs_diff(cdcpend->conn->sndbuf_desc->len, &cdcpend->conn->tx_curs_fin, &cdcpend->cursor); /* sndbuf_space is decreased in smc_sendmsg */ smp_mb__before_atomic(); atomic_add(diff, &cdcpend->conn->sndbuf_space); - /* guarantee 0 <= sndbuf_space <= sndbuf_size */ + /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */ smp_mb__after_atomic(); smc_curs_write(&cdcpend->conn->tx_curs_fin, smc_curs_read(&cdcpend->cursor, cdcpend->conn), @@ -82,7 +82,7 @@ static inline void smc_cdc_add_pending_send(struct smc_connection *conn, sizeof(struct smc_cdc_msg) > SMC_WR_BUF_SIZE, "must increase SMC_WR_BUF_SIZE to at least sizeof(struct smc_cdc_msg)"); BUILD_BUG_ON_MSG( - offsetof(struct smc_cdc_msg, reserved) > SMC_WR_TX_SIZE, + sizeof(struct smc_cdc_msg) != SMC_WR_TX_SIZE, "must adapt SMC_WR_TX_SIZE to sizeof(struct smc_cdc_msg); if not all smc_wr upper layer protocols use the same message size any more, must start to set link->wr_tx_sges[i].length on each individual smc_wr_tx_send()"); BUILD_BUG_ON_MSG( sizeof(struct smc_cdc_tx_pend) > SMC_WR_TX_PEND_PRIV_SIZE, @@ -164,20 +164,35 @@ static inline bool smc_cdc_before(u16 seq1, u16 seq2) return (s16)(seq1 - seq2) < 0; } +static void smc_cdc_handle_urg_data_arrival(struct smc_sock *smc, + int *diff_prod) +{ + struct smc_connection *conn = &smc->conn; + char *base; + + /* new data included urgent business */ + smc_curs_write(&conn->urg_curs, + smc_curs_read(&conn->local_rx_ctrl.prod, conn), + conn); + conn->urg_state = SMC_URG_VALID; + if (!sock_flag(&smc->sk, SOCK_URGINLINE)) + /* we'll skip the urgent byte, so don't account for it */ + (*diff_prod)--; + base = (char *)conn->rmb_desc->cpu_addr; + if (conn->urg_curs.count) + conn->urg_rx_byte = *(base + conn->urg_curs.count - 1); + else + conn->urg_rx_byte = *(base + conn->rmb_desc->len - 1); + sk_send_sigurg(&smc->sk); +} + static void smc_cdc_msg_recv_action(struct smc_sock *smc, - struct smc_link *link, struct smc_cdc_msg *cdc) { union smc_host_cursor cons_old, prod_old; struct smc_connection *conn = &smc->conn; int diff_cons, diff_prod; - if (!cdc->prod_flags.failover_validation) { - if (smc_cdc_before(ntohs(cdc->seqno), - conn->local_rx_ctrl.seqno)) - /* received seqno is old */ - return; - } smc_curs_write(&prod_old, smc_curs_read(&conn->local_rx_ctrl.prod, conn), conn); @@ -198,18 +213,28 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, smp_mb__after_atomic(); } - diff_prod = smc_curs_diff(conn->rmbe_size, &prod_old, + diff_prod = smc_curs_diff(conn->rmb_desc->len, &prod_old, &conn->local_rx_ctrl.prod); if (diff_prod) { + if (conn->local_rx_ctrl.prod_flags.urg_data_present) + smc_cdc_handle_urg_data_arrival(smc, &diff_prod); /* bytes_to_rcv is decreased in smc_recvmsg */ smp_mb__before_atomic(); atomic_add(diff_prod, &conn->bytes_to_rcv); - /* guarantee 0 <= bytes_to_rcv <= rmbe_size */ + /* guarantee 0 <= bytes_to_rcv <= rmb_desc->len */ smp_mb__after_atomic(); smc->sk.sk_data_ready(&smc->sk); - } else if ((conn->local_rx_ctrl.prod_flags.write_blocked) || - (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req)) { - smc->sk.sk_data_ready(&smc->sk); + } else { + if (conn->local_rx_ctrl.prod_flags.write_blocked || + conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || + conn->local_rx_ctrl.prod_flags.urg_data_pending) { + if (conn->local_rx_ctrl.prod_flags.urg_data_pending) + conn->urg_state = SMC_URG_NOTYET; + /* force immediate tx of current consumer cursor, but + * under send_lock to guarantee arrival in seqno-order + */ + smc_tx_sndbuf_nonempty(conn); + } } /* piggy backed tx info */ @@ -219,6 +244,12 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, /* trigger socket release if connection closed */ smc_close_wake_tx_prepared(smc); } + if (diff_cons && conn->urg_tx_pend && + atomic_read(&conn->peer_rmbe_space) == conn->peer_rmbe_size) { + /* urg data confirmed by peer, indicate we're ready for more */ + conn->urg_tx_pend = false; + smc->sk.sk_write_space(&smc->sk); + } if (conn->local_rx_ctrl.conn_state_flags.peer_conn_abort) { smc->sk.sk_err = ECONNRESET; @@ -236,26 +267,11 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, } /* called under tasklet context */ -static inline void smc_cdc_msg_recv(struct smc_cdc_msg *cdc, - struct smc_link *link, u64 wr_id) +static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc) { - struct smc_link_group *lgr = container_of(link, struct smc_link_group, - lnk[SMC_SINGLE_LINK]); - struct smc_connection *connection; - struct smc_sock *smc; - - /* lookup connection */ - read_lock_bh(&lgr->conns_lock); - connection = smc_lgr_find_conn(ntohl(cdc->token), lgr); - if (!connection) { - read_unlock_bh(&lgr->conns_lock); - return; - } - smc = container_of(connection, struct smc_sock, conn); sock_hold(&smc->sk); - read_unlock_bh(&lgr->conns_lock); bh_lock_sock(&smc->sk); - smc_cdc_msg_recv_action(smc, link, cdc); + smc_cdc_msg_recv_action(smc, cdc); bh_unlock_sock(&smc->sk); sock_put(&smc->sk); /* no free sk in softirq-context */ } @@ -266,12 +282,31 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf) { struct smc_link *link = (struct smc_link *)wc->qp->qp_context; struct smc_cdc_msg *cdc = buf; + struct smc_connection *conn; + struct smc_link_group *lgr; + struct smc_sock *smc; if (wc->byte_len < offsetof(struct smc_cdc_msg, reserved)) return; /* short message */ if (cdc->len != SMC_WR_TX_SIZE) return; /* invalid message */ - smc_cdc_msg_recv(cdc, link, wc->wr_id); + + /* lookup connection */ + lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]); + read_lock_bh(&lgr->conns_lock); + conn = smc_lgr_find_conn(ntohl(cdc->token), lgr); + read_unlock_bh(&lgr->conns_lock); + if (!conn) + return; + smc = container_of(conn, struct smc_sock, conn); + + if (!cdc->prod_flags.failover_validation) { + if (smc_cdc_before(ntohs(cdc->seqno), + conn->local_rx_ctrl.seqno)) + /* received seqno is old */ + return; + } + smc_cdc_msg_recv(smc, cdc); } static struct smc_wr_rx_handler smc_cdc_rx_handlers[] = { diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index ab240b37ad114..f60082fee5b87 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -48,7 +48,7 @@ struct smc_cdc_msg { struct smc_cdc_producer_flags prod_flags; struct smc_cdc_conn_state_flags conn_state_flags; u8 reserved[18]; -} __aligned(8); +} __packed; /* format defined in RFC7609 */ static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn) { @@ -146,6 +146,19 @@ static inline int smc_curs_diff(unsigned int size, return max_t(int, 0, (new->count - old->count)); } +/* calculate cursor difference between old and new - returns negative + * value in case old > new + */ +static inline int smc_curs_comp(unsigned int size, + union smc_host_cursor *old, + union smc_host_cursor *new) +{ + if (old->wrap > new->wrap || + (old->wrap == new->wrap && old->count > new->count)) + return -smc_curs_diff(size, new, old); + return smc_curs_diff(size, old, new); +} + static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer, union smc_host_cursor *local, struct smc_connection *conn) diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 3a988c22f627f..717449b1da0b7 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -316,7 +316,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, if (clcm->type == SMC_CLC_DECLINE) { reason_code = SMC_CLC_DECL_REPLY; if (((struct smc_clc_msg_decline *)buf)->hdr.flag) { - smc->conn.lgr->sync_err = true; + smc->conn.lgr->sync_err = 1; smc_lgr_terminate(smc->conn.lgr); } } @@ -442,7 +442,7 @@ int smc_clc_send_confirm(struct smc_sock *smc) hton24(cclc.qpn, link->roce_qp->qp_num); cclc.rmb_rkey = htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); - cclc.conn_idx = 1; /* for now: 1 RMB = 1 RMBE */ + cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */ cclc.rmbe_alert_token = htonl(conn->alert_token_local); cclc.qp_mtu = min(link->path_mtu, link->peer_mtu); cclc.rmbe_size = conn->rmbe_size_short; @@ -494,7 +494,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact) hton24(aclc.qpn, link->roce_qp->qp_num); aclc.rmb_rkey = htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); - aclc.conn_idx = 1; /* as long as 1 RMB = 1 RMBE */ + aclc.rmbe_idx = 1; /* as long as 1 RMB = 1 RMBE */ aclc.rmbe_alert_token = htonl(conn->alert_token_local); aclc.qp_mtu = link->path_mtu; aclc.rmbe_size = conn->rmbe_size_short, diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 63bf1dc2c1f97..41ff9ea96139c 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -97,7 +97,7 @@ struct smc_clc_msg_accept_confirm { /* clc accept / confirm message */ struct smc_clc_msg_local lcl; u8 qpn[3]; /* QP number */ __be32 rmb_rkey; /* RMB rkey */ - u8 conn_idx; /* Connection index, which RMBE in RMB */ + u8 rmbe_idx; /* Index of RMBE in RMB */ __be32 rmbe_alert_token;/* unique connection id */ #if defined(__BIG_ENDIAN_BITFIELD) u8 rmbe_size : 4, /* RMBE buf size (compressed notation) */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index d4bd01bb44e17..add82b0266f30 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -28,12 +28,16 @@ #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) -#define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10) +#define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10 * HZ) -static u32 smc_lgr_num; /* unique link group number */ +static struct smc_lgr_list smc_lgr_list = { /* established link groups */ + .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock), + .list = LIST_HEAD_INIT(smc_lgr_list.list), + .num = 0, +}; -static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk, - bool is_rmb); +static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, + struct smc_buf_desc *buf_desc); static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) { @@ -148,8 +152,11 @@ static void smc_lgr_free_work(struct work_struct *work) list_del_init(&lgr->list); /* remove from smc_lgr_list */ free: spin_unlock_bh(&smc_lgr_list.lock); - if (!delayed_work_pending(&lgr->free_work)) + if (!delayed_work_pending(&lgr->free_work)) { + if (lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE) + smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); smc_lgr_free(lgr); + } } /* create a new SMC link group */ @@ -169,7 +176,7 @@ static int smc_lgr_create(struct smc_sock *smc, goto out; } lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; - lgr->sync_err = false; + lgr->sync_err = 0; memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN); lgr->vlan_id = vlan_id; rwlock_init(&lgr->sndbufs_lock); @@ -178,8 +185,8 @@ static int smc_lgr_create(struct smc_sock *smc, INIT_LIST_HEAD(&lgr->sndbufs[i]); INIT_LIST_HEAD(&lgr->rmbs[i]); } - smc_lgr_num += SMC_LGR_NUM_INCR; - memcpy(&lgr->id, (u8 *)&smc_lgr_num, SMC_LGR_ID_SIZE); + smc_lgr_list.num += SMC_LGR_NUM_INCR; + memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE); INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work); lgr->conns_all = RB_ROOT; @@ -194,9 +201,12 @@ static int smc_lgr_create(struct smc_sock *smc, smc_ib_setup_per_ibdev(smcibdev); get_random_bytes(rndvec, sizeof(rndvec)); lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16); - rc = smc_wr_alloc_link_mem(lnk); + rc = smc_llc_link_init(lnk); if (rc) goto free_lgr; + rc = smc_wr_alloc_link_mem(lnk); + if (rc) + goto clear_llc_lnk; rc = smc_ib_create_protection_domain(lnk); if (rc) goto free_link_mem; @@ -206,10 +216,6 @@ static int smc_lgr_create(struct smc_sock *smc, rc = smc_wr_create_link(lnk); if (rc) goto destroy_qp; - init_completion(&lnk->llc_confirm); - init_completion(&lnk->llc_confirm_resp); - init_completion(&lnk->llc_add); - init_completion(&lnk->llc_add_resp); smc->conn.lgr = lgr; rwlock_init(&lgr->conns_lock); @@ -224,6 +230,8 @@ dealloc_pd: smc_ib_dealloc_protection_domain(lnk); free_link_mem: smc_wr_free_link_mem(lnk); +clear_llc_lnk: + smc_llc_link_clear(lnk); free_lgr: kfree(lgr); out: @@ -232,26 +240,21 @@ out: static void smc_buf_unuse(struct smc_connection *conn) { - if (conn->sndbuf_desc) { + if (conn->sndbuf_desc) conn->sndbuf_desc->used = 0; - conn->sndbuf_size = 0; - } if (conn->rmb_desc) { if (!conn->rmb_desc->regerr) { conn->rmb_desc->reused = 1; conn->rmb_desc->used = 0; - conn->rmbe_size = 0; } else { /* buf registration failed, reuse not possible */ struct smc_link_group *lgr = conn->lgr; - struct smc_link *lnk; write_lock_bh(&lgr->rmbs_lock); list_del(&conn->rmb_desc->list); write_unlock_bh(&lgr->rmbs_lock); - lnk = &lgr->lnk[SMC_SINGLE_LINK]; - smc_buf_free(conn->rmb_desc, lnk, true); + smc_buf_free(lgr, true, conn->rmb_desc); } } } @@ -269,6 +272,7 @@ void smc_conn_free(struct smc_connection *conn) static void smc_link_clear(struct smc_link *lnk) { lnk->peer_qpn = 0; + smc_llc_link_clear(lnk); smc_ib_modify_qp_reset(lnk); smc_wr_free_link(lnk); smc_ib_destroy_queue_pair(lnk); @@ -276,9 +280,11 @@ static void smc_link_clear(struct smc_link *lnk) smc_wr_free_link_mem(lnk); } -static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk, - bool is_rmb) +static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, + struct smc_buf_desc *buf_desc) { + struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK]; + if (is_rmb) { if (buf_desc->mr_rx[SMC_SINGLE_LINK]) smc_ib_put_memory_region( @@ -290,14 +296,13 @@ static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk, DMA_TO_DEVICE); } sg_free_table(&buf_desc->sgt[SMC_SINGLE_LINK]); - if (buf_desc->cpu_addr) - free_pages((unsigned long)buf_desc->cpu_addr, buf_desc->order); + if (buf_desc->pages) + __free_pages(buf_desc->pages, buf_desc->order); kfree(buf_desc); } static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb) { - struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK]; struct smc_buf_desc *buf_desc, *bf_desc; struct list_head *buf_list; int i; @@ -310,7 +315,7 @@ static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb) list_for_each_entry_safe(buf_desc, bf_desc, buf_list, list) { list_del(&buf_desc->list); - smc_buf_free(buf_desc, lnk, is_rmb); + smc_buf_free(lgr, is_rmb, buf_desc); } } } @@ -341,13 +346,18 @@ void smc_lgr_forget(struct smc_link_group *lgr) } /* terminate linkgroup abnormally */ -void smc_lgr_terminate(struct smc_link_group *lgr) +static void __smc_lgr_terminate(struct smc_link_group *lgr) { struct smc_connection *conn; struct smc_sock *smc; struct rb_node *node; - smc_lgr_forget(lgr); + if (lgr->terminating) + return; /* lgr already terminating */ + lgr->terminating = 1; + if (!list_empty(&lgr->list)) /* forget lgr */ + list_del_init(&lgr->list); + smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); write_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); @@ -368,13 +378,35 @@ void smc_lgr_terminate(struct smc_link_group *lgr) smc_lgr_schedule_free_work(lgr); } +void smc_lgr_terminate(struct smc_link_group *lgr) +{ + spin_lock_bh(&smc_lgr_list.lock); + __smc_lgr_terminate(lgr); + spin_unlock_bh(&smc_lgr_list.lock); +} + +/* Called when IB port is terminated */ +void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport) +{ + struct smc_link_group *lgr, *l; + + spin_lock_bh(&smc_lgr_list.lock); + list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) { + if (lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev && + lgr->lnk[SMC_SINGLE_LINK].ibport == ibport) + __smc_lgr_terminate(lgr); + } + spin_unlock_bh(&smc_lgr_list.lock); +} + /* Determine vlan of internal TCP socket. * @vlan_id: address to store the determined vlan id into */ static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id) { struct dst_entry *dst = sk_dst_get(clcsock->sk); - int rc = 0; + struct net_device *ndev; + int i, nest_lvl, rc = 0; *vlan_id = 0; if (!dst) { @@ -386,8 +418,27 @@ static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id) goto out_rel; } - if (is_vlan_dev(dst->dev)) - *vlan_id = vlan_dev_vlan_id(dst->dev); + ndev = dst->dev; + if (is_vlan_dev(ndev)) { + *vlan_id = vlan_dev_vlan_id(ndev); + goto out_rel; + } + + rtnl_lock(); + nest_lvl = dev_get_nest_level(ndev); + for (i = 0; i < nest_lvl; i++) { + struct list_head *lower = &ndev->adj_list.lower; + + if (list_empty(lower)) + break; + lower = lower->next; + ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); + if (is_vlan_dev(ndev)) { + *vlan_id = vlan_dev_vlan_id(ndev); + break; + } + } + rtnl_unlock(); out_rel: dst_release(dst); @@ -432,10 +483,10 @@ int smc_conn_create(struct smc_sock *smc, struct smc_clc_msg_local *lcl, int srv_first_contact) { struct smc_connection *conn = &smc->conn; + int local_contact = SMC_FIRST_CONTACT; struct smc_link_group *lgr; unsigned short vlan_id; enum smc_lgr_role role; - int local_contact = SMC_FIRST_CONTACT; int rc = 0; role = smc->listen_smc ? SMC_SERV : SMC_CLNT; @@ -493,6 +544,7 @@ create: } conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; + conn->urg_state = SMC_URG_READ; #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); #endif @@ -501,14 +553,39 @@ out: return rc ? rc : local_contact; } +/* convert the RMB size into the compressed notation - minimum 16K. + * In contrast to plain ilog2, this rounds towards the next power of 2, + * so the socket application gets at least its desired sndbuf / rcvbuf size. + */ +static u8 smc_compress_bufsize(int size) +{ + u8 compressed; + + if (size <= SMC_BUF_MIN_SIZE) + return 0; + + size = (size - 1) >> 14; + compressed = ilog2(size) + 1; + if (compressed >= SMC_RMBE_SIZES) + compressed = SMC_RMBE_SIZES - 1; + return compressed; +} + +/* convert the RMB size from compressed notation into integer */ +int smc_uncompress_bufsize(u8 compressed) +{ + u32 size; + + size = 0x00000001 << (((int)compressed) + 14); + return (int)size; +} + /* try to reuse a sndbuf or rmb description slot for a certain * buffer size; if not available, return NULL */ -static inline -struct smc_buf_desc *smc_buf_get_slot(struct smc_link_group *lgr, - int compressed_bufsize, - rwlock_t *lock, - struct list_head *buf_list) +static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, + rwlock_t *lock, + struct list_head *buf_list) { struct smc_buf_desc *buf_slot; @@ -544,23 +621,23 @@ static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr, if (!buf_desc) return ERR_PTR(-ENOMEM); - buf_desc->cpu_addr = - (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | - __GFP_NOMEMALLOC | - __GFP_NORETRY | __GFP_ZERO, - get_order(bufsize)); - if (!buf_desc->cpu_addr) { + buf_desc->order = get_order(bufsize); + buf_desc->pages = alloc_pages(GFP_KERNEL | __GFP_NOWARN | + __GFP_NOMEMALLOC | __GFP_COMP | + __GFP_NORETRY | __GFP_ZERO, + buf_desc->order); + if (!buf_desc->pages) { kfree(buf_desc); return ERR_PTR(-EAGAIN); } - buf_desc->order = get_order(bufsize); + buf_desc->cpu_addr = (void *)page_address(buf_desc->pages); /* build the sg table from the pages */ lnk = &lgr->lnk[SMC_SINGLE_LINK]; rc = sg_alloc_table(&buf_desc->sgt[SMC_SINGLE_LINK], 1, GFP_KERNEL); if (rc) { - smc_buf_free(buf_desc, lnk, is_rmb); + smc_buf_free(lgr, is_rmb, buf_desc); return ERR_PTR(rc); } sg_set_buf(buf_desc->sgt[SMC_SINGLE_LINK].sgl, @@ -571,7 +648,7 @@ static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr, is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE); /* SMC protocol depends on mapping to one DMA address only */ if (rc != 1) { - smc_buf_free(buf_desc, lnk, is_rmb); + smc_buf_free(lgr, is_rmb, buf_desc); return ERR_PTR(-EAGAIN); } @@ -582,19 +659,20 @@ static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr, IB_ACCESS_LOCAL_WRITE, buf_desc); if (rc) { - smc_buf_free(buf_desc, lnk, is_rmb); + smc_buf_free(lgr, is_rmb, buf_desc); return ERR_PTR(rc); } } + buf_desc->len = bufsize; return buf_desc; } static int __smc_buf_create(struct smc_sock *smc, bool is_rmb) { + struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM); struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; - struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM); struct list_head *buf_list; int bufsize, bufsize_short; int sk_buf_size; @@ -622,7 +700,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_rmb) continue; /* check for reusable slot in the link group */ - buf_desc = smc_buf_get_slot(lgr, bufsize_short, lock, buf_list); + buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); if (buf_desc) { memset(buf_desc->cpu_addr, 0, bufsize); break; /* found reusable slot */ @@ -646,14 +724,12 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_rmb) if (is_rmb) { conn->rmb_desc = buf_desc; - conn->rmbe_size = bufsize; conn->rmbe_size_short = bufsize_short; smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize); } else { conn->sndbuf_desc = buf_desc; - conn->sndbuf_size = bufsize; smc->sk.sk_sndbuf = bufsize * 2; atomic_set(&conn->sndbuf_space, bufsize); } @@ -709,8 +785,7 @@ int smc_buf_create(struct smc_sock *smc) /* create rmb */ rc = __smc_buf_create(smc, true); if (rc) - smc_buf_free(smc->conn.sndbuf_desc, - &smc->conn.lgr->lnk[SMC_SINGLE_LINK], false); + smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); return rc; } @@ -777,3 +852,21 @@ int smc_rmb_rtoken_handling(struct smc_connection *conn, return conn->rtoken_idx; return 0; } + +/* Called (from smc_exit) when module is removed */ +void smc_core_exit(void) +{ + struct smc_link_group *lgr, *lg; + LIST_HEAD(lgr_freeing_list); + + spin_lock_bh(&smc_lgr_list.lock); + if (!list_empty(&smc_lgr_list.list)) + list_splice_init(&smc_lgr_list.list, &lgr_freeing_list); + spin_unlock_bh(&smc_lgr_list.lock); + list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) { + list_del_init(&lgr->list); + smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); + cancel_delayed_work_sync(&lgr->free_work); + smc_lgr_free(lgr); /* free link group */ + } +} diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 5dfcb15d529f8..93cb3523bf509 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -23,10 +23,9 @@ struct smc_lgr_list { /* list of link group definition */ struct list_head list; spinlock_t lock; /* protects list of link groups */ + u32 num; /* unique link group number */ }; -extern struct smc_lgr_list smc_lgr_list; /* list of link groups */ - enum smc_lgr_role { /* possible roles of a link group */ SMC_CLNT, /* client */ SMC_SERV /* server */ @@ -79,6 +78,7 @@ struct smc_link { dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */ u64 wr_rx_id; /* seq # of last recv WR */ u32 wr_rx_cnt; /* number of WR recv buffers */ + unsigned long wr_rx_tstamp; /* jiffies when last buf rx */ struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ @@ -95,12 +95,18 @@ struct smc_link { u8 link_id; /* unique # within link group */ enum smc_link_state state; /* state of link */ + struct workqueue_struct *llc_wq; /* single thread work queue */ struct completion llc_confirm; /* wait for rx of conf link */ struct completion llc_confirm_resp; /* wait 4 rx of cnf lnk rsp */ int llc_confirm_rc; /* rc from confirm link msg */ int llc_confirm_resp_rc; /* rc from conf_resp msg */ struct completion llc_add; /* wait for rx of add link */ struct completion llc_add_resp; /* wait for rx of add link rsp*/ + struct delayed_work llc_testlink_wrk; /* testlink worker */ + struct completion llc_testlink_resp; /* wait for rx of testlink */ + int llc_testlink_time; /* testlink interval */ + struct completion llc_confirm_rkey; /* wait 4 rx of cnf rkey */ + int llc_confirm_rkey_rc; /* rc from cnf rkey msg */ }; /* For now we just allow one parallel link per link group. The SMC protocol @@ -116,6 +122,8 @@ struct smc_link { struct smc_buf_desc { struct list_head list; void *cpu_addr; /* virtual address of buffer */ + struct page *pages; + int len; /* length of buffer */ struct sg_table sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */ struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX]; /* for rmb only: memory region @@ -133,6 +141,12 @@ struct smc_rtoken { /* address/key of remote RMB */ }; #define SMC_LGR_ID_SIZE 4 +#define SMC_BUF_MIN_SIZE 16384 /* minimum size of an RMB */ +#define SMC_RMBE_SIZES 16 /* number of distinct RMBE sizes */ +/* theoretically, the RFC states that largest size would be 512K, + * i.e. compressed 5 and thus 6 sizes (0..5), despite + * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15) + */ struct smc_link_group { struct list_head list; @@ -158,7 +172,8 @@ struct smc_link_group { u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ - bool sync_err; /* lgr no longer fits to peer */ + u8 sync_err : 1; /* lgr no longer fits to peer */ + u8 terminating : 1;/* lgr is terminating */ }; /* Find the connection associated with the given alert token in the link group. @@ -196,11 +211,14 @@ static inline struct smc_connection *smc_lgr_find_conn( struct smc_sock; struct smc_clc_msg_accept_confirm; +struct smc_clc_msg_local; void smc_lgr_free(struct smc_link_group *lgr); void smc_lgr_forget(struct smc_link_group *lgr); void smc_lgr_terminate(struct smc_link_group *lgr); +void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); int smc_buf_create(struct smc_sock *smc); +int smc_uncompress_bufsize(u8 compressed); int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_clc_msg_accept_confirm *clc); int smc_rtoken_add(struct smc_link_group *lgr, __be64 nw_vaddr, __be32 nw_rkey); @@ -209,4 +227,9 @@ void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn); void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn); void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn); void smc_rmb_sync_sg_for_device(struct smc_connection *conn); +void smc_conn_free(struct smc_connection *conn); +int smc_conn_create(struct smc_sock *smc, + struct smc_ib_device *smcibdev, u8 ibport, + struct smc_clc_msg_local *lcl, int srv_first_contact); +void smc_core_exit(void); #endif diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 427b91c1c964f..839354402215a 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -38,17 +38,27 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk) { struct smc_sock *smc = smc_sk(sk); - r->diag_family = sk->sk_family; if (!smc->clcsock) return; r->id.idiag_sport = htons(smc->clcsock->sk->sk_num); r->id.idiag_dport = smc->clcsock->sk->sk_dport; r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if; sock_diag_save_cookie(sk, r->id.idiag_cookie); - memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); - memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); - r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr; - r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr; + if (sk->sk_protocol == SMCPROTO_SMC) { + r->diag_family = PF_INET; + memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); + memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); + r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr; + r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (sk->sk_protocol == SMCPROTO_SMC6) { + r->diag_family = PF_INET6; + memcpy(&r->id.idiag_src, &smc->clcsock->sk->sk_v6_rcv_saddr, + sizeof(smc->clcsock->sk->sk_v6_rcv_saddr)); + memcpy(&r->id.idiag_dst, &smc->clcsock->sk->sk_v6_daddr, + sizeof(smc->clcsock->sk->sk_v6_daddr)); +#endif + } } static int smc_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, @@ -91,8 +101,9 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, struct smc_connection *conn = &smc->conn; struct smc_diag_conninfo cinfo = { .token = conn->alert_token_local, - .sndbuf_size = conn->sndbuf_size, - .rmbe_size = conn->rmbe_size, + .sndbuf_size = conn->sndbuf_desc ? + conn->sndbuf_desc->len : 0, + .rmbe_size = conn->rmb_desc ? conn->rmb_desc->len : 0, .peer_rmbe_size = conn->peer_rmbe_size, .rx_prod.wrap = conn->local_rx_ctrl.prod.wrap, @@ -153,7 +164,8 @@ errout: return -EMSGSIZE; } -static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb, + struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nlattr *bc = NULL; @@ -161,8 +173,8 @@ static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) struct sock *sk; int rc = 0; - read_lock(&smc_proto.h.smc_hash->lock); - head = &smc_proto.h.smc_hash->ht; + read_lock(&prot->h.smc_hash->lock); + head = &prot->h.smc_hash->ht; if (hlist_empty(head)) goto out; @@ -175,7 +187,17 @@ static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) } out: - read_unlock(&smc_proto.h.smc_hash->lock); + read_unlock(&prot->h.smc_hash->lock); + return rc; +} + +static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int rc = 0; + + rc = smc_diag_dump_proto(&smc_proto, skb, cb); + if (!rc) + rc = smc_diag_dump_proto(&smc_proto6, skb, cb); return rc; } diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 26df554f7588d..0eed7ab9f28b5 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -143,17 +143,6 @@ out: return rc; } -static void smc_ib_port_terminate(struct smc_ib_device *smcibdev, u8 ibport) -{ - struct smc_link_group *lgr, *l; - - list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) { - if (lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev && - lgr->lnk[SMC_SINGLE_LINK].ibport == ibport) - smc_lgr_terminate(lgr); - } -} - /* process context wrapper for might_sleep smc_ib_remember_port_attr */ static void smc_ib_port_event_work(struct work_struct *work) { @@ -165,7 +154,7 @@ static void smc_ib_port_event_work(struct work_struct *work) smc_ib_remember_port_attr(smcibdev, port_idx + 1); clear_bit(port_idx, &smcibdev->port_event_mask); if (!smc_ib_port_active(smcibdev, port_idx + 1)) - smc_ib_port_terminate(smcibdev, port_idx + 1); + smc_port_terminate(smcibdev, port_idx + 1); } } diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index ea4b21981b4bd..5800a6b43d830 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -214,12 +214,11 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[], return rc; } -/* send ADD LINK request or response */ -int smc_llc_send_add_link(struct smc_link *link, u8 mac[], - union ib_gid *gid, - enum smc_llc_reqresp reqresp) +/* send LLC confirm rkey request */ +static int smc_llc_send_confirm_rkey(struct smc_link *link, + struct smc_buf_desc *rmb_desc) { - struct smc_llc_msg_add_link *addllc; + struct smc_llc_msg_confirm_rkey *rkeyllc; struct smc_wr_tx_pend_priv *pend; struct smc_wr_buf *wr_buf; int rc; @@ -227,7 +226,25 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], rc = smc_llc_add_pending_send(link, &wr_buf, &pend); if (rc) return rc; - addllc = (struct smc_llc_msg_add_link *)wr_buf; + rkeyllc = (struct smc_llc_msg_confirm_rkey *)wr_buf; + memset(rkeyllc, 0, sizeof(*rkeyllc)); + rkeyllc->hd.common.type = SMC_LLC_CONFIRM_RKEY; + rkeyllc->hd.length = sizeof(struct smc_llc_msg_confirm_rkey); + rkeyllc->rtoken[0].rmb_key = + htonl(rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey); + rkeyllc->rtoken[0].rmb_vaddr = cpu_to_be64( + (u64)sg_dma_address(rmb_desc->sgt[SMC_SINGLE_LINK].sgl)); + /* send llc message */ + rc = smc_wr_tx_send(link, pend); + return rc; +} + +/* prepare an add link message */ +static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc, + struct smc_link *link, u8 mac[], + union ib_gid *gid, + enum smc_llc_reqresp reqresp) +{ memset(addllc, 0, sizeof(*addllc)); addllc->hd.common.type = SMC_LLC_ADD_LINK; addllc->hd.length = sizeof(struct smc_llc_msg_add_link); @@ -239,16 +256,14 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], } memcpy(addllc->sender_mac, mac, ETH_ALEN); memcpy(addllc->sender_gid, gid, SMC_GID_SIZE); - /* send llc message */ - rc = smc_wr_tx_send(link, pend); - return rc; } -/* send DELETE LINK request or response */ -int smc_llc_send_delete_link(struct smc_link *link, - enum smc_llc_reqresp reqresp) +/* send ADD LINK request or response */ +int smc_llc_send_add_link(struct smc_link *link, u8 mac[], + union ib_gid *gid, + enum smc_llc_reqresp reqresp) { - struct smc_llc_msg_del_link *delllc; + struct smc_llc_msg_add_link *addllc; struct smc_wr_tx_pend_priv *pend; struct smc_wr_buf *wr_buf; int rc; @@ -256,7 +271,18 @@ int smc_llc_send_delete_link(struct smc_link *link, rc = smc_llc_add_pending_send(link, &wr_buf, &pend); if (rc) return rc; - delllc = (struct smc_llc_msg_del_link *)wr_buf; + addllc = (struct smc_llc_msg_add_link *)wr_buf; + smc_llc_prep_add_link(addllc, link, mac, gid, reqresp); + /* send llc message */ + rc = smc_wr_tx_send(link, pend); + return rc; +} + +/* prepare a delete link message */ +static void smc_llc_prep_delete_link(struct smc_llc_msg_del_link *delllc, + struct smc_link *link, + enum smc_llc_reqresp reqresp) +{ memset(delllc, 0, sizeof(*delllc)); delllc->hd.common.type = SMC_LLC_DELETE_LINK; delllc->hd.length = sizeof(struct smc_llc_msg_add_link); @@ -266,14 +292,29 @@ int smc_llc_send_delete_link(struct smc_link *link, delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ALL; delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY; delllc->link_num = link->link_id; +} + +/* send DELETE LINK request or response */ +int smc_llc_send_delete_link(struct smc_link *link, + enum smc_llc_reqresp reqresp) +{ + struct smc_llc_msg_del_link *delllc; + struct smc_wr_tx_pend_priv *pend; + struct smc_wr_buf *wr_buf; + int rc; + + rc = smc_llc_add_pending_send(link, &wr_buf, &pend); + if (rc) + return rc; + delllc = (struct smc_llc_msg_del_link *)wr_buf; + smc_llc_prep_delete_link(delllc, link, reqresp); /* send llc message */ rc = smc_wr_tx_send(link, pend); return rc; } -/* send LLC test link request or response */ -int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16], - enum smc_llc_reqresp reqresp) +/* send LLC test link request */ +static int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16]) { struct smc_llc_msg_test_link *testllc; struct smc_wr_tx_pend_priv *pend; @@ -287,28 +328,52 @@ int smc_llc_send_test_link(struct smc_link *link, u8 user_data[16], memset(testllc, 0, sizeof(*testllc)); testllc->hd.common.type = SMC_LLC_TEST_LINK; testllc->hd.length = sizeof(struct smc_llc_msg_test_link); - if (reqresp == SMC_LLC_RESP) - testllc->hd.flags |= SMC_LLC_FLAG_RESP; memcpy(testllc->user_data, user_data, sizeof(testllc->user_data)); /* send llc message */ rc = smc_wr_tx_send(link, pend); return rc; } -/* send a prepared message */ -static int smc_llc_send_message(struct smc_link *link, void *llcbuf, int llclen) +struct smc_llc_send_work { + struct work_struct work; + struct smc_link *link; + int llclen; + union smc_llc_msg llcbuf; +}; + +/* worker that sends a prepared message */ +static void smc_llc_send_message_work(struct work_struct *work) { + struct smc_llc_send_work *llcwrk = container_of(work, + struct smc_llc_send_work, work); struct smc_wr_tx_pend_priv *pend; struct smc_wr_buf *wr_buf; int rc; - rc = smc_llc_add_pending_send(link, &wr_buf, &pend); + if (llcwrk->link->state == SMC_LNK_INACTIVE) + goto out; + rc = smc_llc_add_pending_send(llcwrk->link, &wr_buf, &pend); if (rc) - return rc; - memcpy(wr_buf, llcbuf, llclen); - /* send llc message */ - rc = smc_wr_tx_send(link, pend); - return rc; + goto out; + memcpy(wr_buf, &llcwrk->llcbuf, llcwrk->llclen); + smc_wr_tx_send(llcwrk->link, pend); +out: + kfree(llcwrk); +} + +/* copy llcbuf and schedule an llc send on link */ +static int smc_llc_send_message(struct smc_link *link, void *llcbuf, int llclen) +{ + struct smc_llc_send_work *wrk = kmalloc(sizeof(*wrk), GFP_ATOMIC); + + if (!wrk) + return -ENOMEM; + INIT_WORK(&wrk->work, smc_llc_send_message_work); + wrk->link = link; + wrk->llclen = llclen; + memcpy(&wrk->llcbuf, llcbuf, llclen); + queue_work(link->llc_wq, &wrk->work); + return 0; } /********************************* receive ***********************************/ @@ -359,17 +424,18 @@ static void smc_llc_rx_add_link(struct smc_link *link, } if (lgr->role == SMC_SERV) { - smc_llc_send_add_link(link, + smc_llc_prep_add_link(llc, link, link->smcibdev->mac[link->ibport - 1], &link->smcibdev->gid[link->ibport - 1], SMC_LLC_REQ); } else { - smc_llc_send_add_link(link, + smc_llc_prep_add_link(llc, link, link->smcibdev->mac[link->ibport - 1], &link->smcibdev->gid[link->ibport - 1], SMC_LLC_RESP); } + smc_llc_send_message(link, llc, sizeof(*llc)); } } @@ -385,9 +451,11 @@ static void smc_llc_rx_delete_link(struct smc_link *link, } else { if (lgr->role == SMC_SERV) { smc_lgr_forget(lgr); - smc_llc_send_delete_link(link, SMC_LLC_REQ); + smc_llc_prep_delete_link(llc, link, SMC_LLC_REQ); + smc_llc_send_message(link, llc, sizeof(*llc)); } else { - smc_llc_send_delete_link(link, SMC_LLC_RESP); + smc_llc_prep_delete_link(llc, link, SMC_LLC_RESP); + smc_llc_send_message(link, llc, sizeof(*llc)); smc_lgr_terminate(lgr); } } @@ -397,9 +465,11 @@ static void smc_llc_rx_test_link(struct smc_link *link, struct smc_llc_msg_test_link *llc) { if (llc->hd.flags & SMC_LLC_FLAG_RESP) { - /* unused as long as we don't send this type of msg */ + if (link->state == SMC_LNK_ACTIVE) + complete(&link->llc_testlink_resp); } else { - smc_llc_send_test_link(link, llc->user_data, SMC_LLC_RESP); + llc->hd.flags |= SMC_LLC_FLAG_RESP; + smc_llc_send_message(link, llc, sizeof(*llc)); } } @@ -412,7 +482,9 @@ static void smc_llc_rx_confirm_rkey(struct smc_link *link, lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]); if (llc->hd.flags & SMC_LLC_FLAG_RESP) { - /* unused as long as we don't send this type of msg */ + link->llc_confirm_rkey_rc = llc->hd.flags & + SMC_LLC_FLAG_RKEY_NEG; + complete(&link->llc_confirm_rkey); } else { rc = smc_rtoken_add(lgr, llc->rtoken[0].rmb_vaddr, @@ -423,7 +495,7 @@ static void smc_llc_rx_confirm_rkey(struct smc_link *link, llc->hd.flags |= SMC_LLC_FLAG_RESP; if (rc < 0) llc->hd.flags |= SMC_LLC_FLAG_RKEY_NEG; - smc_llc_send_message(link, (void *)llc, sizeof(*llc)); + smc_llc_send_message(link, llc, sizeof(*llc)); } } @@ -435,7 +507,7 @@ static void smc_llc_rx_confirm_rkey_cont(struct smc_link *link, } else { /* ignore rtokens for other links, we have only one link */ llc->hd.flags |= SMC_LLC_FLAG_RESP; - smc_llc_send_message(link, (void *)llc, sizeof(*llc)); + smc_llc_send_message(link, llc, sizeof(*llc)); } } @@ -463,7 +535,7 @@ static void smc_llc_rx_delete_rkey(struct smc_link *link, } llc->hd.flags |= SMC_LLC_FLAG_RESP; - smc_llc_send_message(link, (void *)llc, sizeof(*llc)); + smc_llc_send_message(link, llc, sizeof(*llc)); } } @@ -476,6 +548,8 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf) return; /* short message */ if (llc->raw.hdr.length != sizeof(*llc)) return; /* invalid message */ + if (link->state == SMC_LNK_INACTIVE) + return; /* link not active, drop msg */ switch (llc->raw.hdr.common.type) { case SMC_LLC_TEST_LINK: @@ -502,6 +576,100 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf) } } +/***************************** worker, utils *********************************/ + +static void smc_llc_testlink_work(struct work_struct *work) +{ + struct smc_link *link = container_of(to_delayed_work(work), + struct smc_link, llc_testlink_wrk); + unsigned long next_interval; + struct smc_link_group *lgr; + unsigned long expire_time; + u8 user_data[16] = { 0 }; + int rc; + + lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]); + if (link->state != SMC_LNK_ACTIVE) + return; /* don't reschedule worker */ + expire_time = link->wr_rx_tstamp + link->llc_testlink_time; + if (time_is_after_jiffies(expire_time)) { + next_interval = expire_time - jiffies; + goto out; + } + reinit_completion(&link->llc_testlink_resp); + smc_llc_send_test_link(link, user_data); + /* receive TEST LINK response over RoCE fabric */ + rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp, + SMC_LLC_WAIT_TIME); + if (rc <= 0) { + smc_lgr_terminate(lgr); + return; + } + next_interval = link->llc_testlink_time; +out: + queue_delayed_work(link->llc_wq, &link->llc_testlink_wrk, + next_interval); +} + +int smc_llc_link_init(struct smc_link *link) +{ + struct smc_link_group *lgr = container_of(link, struct smc_link_group, + lnk[SMC_SINGLE_LINK]); + link->llc_wq = alloc_ordered_workqueue("llc_wq-%x:%x)", WQ_MEM_RECLAIM, + *((u32 *)lgr->id), + link->link_id); + if (!link->llc_wq) + return -ENOMEM; + init_completion(&link->llc_confirm); + init_completion(&link->llc_confirm_resp); + init_completion(&link->llc_add); + init_completion(&link->llc_add_resp); + init_completion(&link->llc_confirm_rkey); + init_completion(&link->llc_testlink_resp); + INIT_DELAYED_WORK(&link->llc_testlink_wrk, smc_llc_testlink_work); + return 0; +} + +void smc_llc_link_active(struct smc_link *link, int testlink_time) +{ + link->state = SMC_LNK_ACTIVE; + if (testlink_time) { + link->llc_testlink_time = testlink_time * HZ; + queue_delayed_work(link->llc_wq, &link->llc_testlink_wrk, + link->llc_testlink_time); + } +} + +/* called in tasklet context */ +void smc_llc_link_inactive(struct smc_link *link) +{ + link->state = SMC_LNK_INACTIVE; + cancel_delayed_work(&link->llc_testlink_wrk); +} + +/* called in worker context */ +void smc_llc_link_clear(struct smc_link *link) +{ + flush_workqueue(link->llc_wq); + destroy_workqueue(link->llc_wq); +} + +/* register a new rtoken at the remote peer */ +int smc_llc_do_confirm_rkey(struct smc_link *link, + struct smc_buf_desc *rmb_desc) +{ + int rc; + + reinit_completion(&link->llc_confirm_rkey); + smc_llc_send_confirm_rkey(link, rmb_desc); + /* receive CONFIRM RKEY response from server over RoCE fabric */ + rc = wait_for_completion_interruptible_timeout(&link->llc_confirm_rkey, + SMC_LLC_WAIT_TIME); + if (rc <= 0 || link->llc_confirm_rkey_rc) + return -EFAULT; + return 0; +} + /***************************** init, exit, misc ******************************/ static struct smc_wr_rx_handler smc_llc_rx_handlers[] = { diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h index e4a7d5e234d5d..65c8645e96a14 100644 --- a/net/smc/smc_llc.h +++ b/net/smc/smc_llc.h @@ -42,8 +42,12 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], union ib_gid *gid, enum smc_llc_reqresp reqresp); int smc_llc_send_delete_link(struct smc_link *link, enum smc_llc_reqresp reqresp); -int smc_llc_send_test_link(struct smc_link *lnk, u8 user_data[16], - enum smc_llc_reqresp reqresp); +int smc_llc_link_init(struct smc_link *link); +void smc_llc_link_active(struct smc_link *link, int testlink_time); +void smc_llc_link_inactive(struct smc_link *link); +void smc_llc_link_clear(struct smc_link *link); +int smc_llc_do_confirm_rkey(struct smc_link *link, + struct smc_buf_desc *rmb_desc); int smc_llc_init(void) __init; #endif /* SMC_LLC_H */ diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index eff4e0d0bb310..3d77b383cccd9 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -22,11 +22,10 @@ #include "smc_tx.h" /* smc_tx_consumer_update() */ #include "smc_rx.h" -/* callback implementation for sk.sk_data_ready() - * to wakeup rcvbuf consumers that blocked with smc_rx_wait_data(). +/* callback implementation to wakeup consumers blocked with smc_rx_wait(). * indirectly called by smc_cdc_msg_recv_action(). */ -static void smc_rx_data_ready(struct sock *sk) +static void smc_rx_wake_up(struct sock *sk) { struct socket_wq *wq; @@ -44,28 +43,180 @@ static void smc_rx_data_ready(struct sock *sk) rcu_read_unlock(); } +/* Update consumer cursor + * @conn connection to update + * @cons consumer cursor + * @len number of Bytes consumed + * Returns: + * 1 if we should end our receive, 0 otherwise + */ +static int smc_rx_update_consumer(struct smc_sock *smc, + union smc_host_cursor cons, size_t len) +{ + struct smc_connection *conn = &smc->conn; + struct sock *sk = &smc->sk; + bool force = false; + int diff, rc = 0; + + smc_curs_add(conn->rmb_desc->len, &cons, len); + + /* did we process urgent data? */ + if (conn->urg_state == SMC_URG_VALID || conn->urg_rx_skip_pend) { + diff = smc_curs_comp(conn->rmb_desc->len, &cons, + &conn->urg_curs); + if (sock_flag(sk, SOCK_URGINLINE)) { + if (diff == 0) { + force = true; + rc = 1; + conn->urg_state = SMC_URG_READ; + } + } else { + if (diff == 1) { + /* skip urgent byte */ + force = true; + smc_curs_add(conn->rmb_desc->len, &cons, 1); + conn->urg_rx_skip_pend = false; + } else if (diff < -1) + /* we read past urgent byte */ + conn->urg_state = SMC_URG_READ; + } + } + + smc_curs_write(&conn->local_tx_ctrl.cons, smc_curs_read(&cons, conn), + conn); + + /* send consumer cursor update if required */ + /* similar to advertising new TCP rcv_wnd if required */ + smc_tx_consumer_update(conn, force); + + return rc; +} + +static void smc_rx_update_cons(struct smc_sock *smc, size_t len) +{ + struct smc_connection *conn = &smc->conn; + union smc_host_cursor cons; + + smc_curs_write(&cons, smc_curs_read(&conn->local_tx_ctrl.cons, conn), + conn); + smc_rx_update_consumer(smc, cons, len); +} + +struct smc_spd_priv { + struct smc_sock *smc; + size_t len; +}; + +static void smc_rx_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + struct smc_spd_priv *priv = (struct smc_spd_priv *)buf->private; + struct smc_sock *smc = priv->smc; + struct smc_connection *conn; + struct sock *sk = &smc->sk; + + if (sk->sk_state == SMC_CLOSED || + sk->sk_state == SMC_PEERFINCLOSEWAIT || + sk->sk_state == SMC_APPFINCLOSEWAIT) + goto out; + conn = &smc->conn; + lock_sock(sk); + smc_rx_update_cons(smc, priv->len); + release_sock(sk); + if (atomic_sub_and_test(priv->len, &conn->splice_pending)) + smc_rx_wake_up(sk); +out: + kfree(priv); + put_page(buf->page); + sock_put(sk); +} + +static int smc_rx_pipe_buf_nosteal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + return 1; +} + +static const struct pipe_buf_operations smc_pipe_ops = { + .can_merge = 0, + .confirm = generic_pipe_buf_confirm, + .release = smc_rx_pipe_buf_release, + .steal = smc_rx_pipe_buf_nosteal, + .get = generic_pipe_buf_get +}; + +static void smc_rx_spd_release(struct splice_pipe_desc *spd, + unsigned int i) +{ + put_page(spd->pages[i]); +} + +static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, + struct smc_sock *smc) +{ + struct splice_pipe_desc spd; + struct partial_page partial; + struct smc_spd_priv *priv; + struct page *page; + int bytes; + + page = virt_to_page(smc->conn.rmb_desc->cpu_addr); + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + priv->len = len; + priv->smc = smc; + partial.offset = src - (char *)smc->conn.rmb_desc->cpu_addr; + partial.len = len; + partial.private = (unsigned long)priv; + + spd.nr_pages_max = 1; + spd.nr_pages = 1; + spd.pages = &page; + spd.partial = &partial; + spd.ops = &smc_pipe_ops; + spd.spd_release = smc_rx_spd_release; + + bytes = splice_to_pipe(pipe, &spd); + if (bytes > 0) { + sock_hold(&smc->sk); + get_page(smc->conn.rmb_desc->pages); + atomic_add(bytes, &smc->conn.splice_pending); + } + + return bytes; +} + +static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn) +{ + return atomic_read(&conn->bytes_to_rcv) && + !atomic_read(&conn->splice_pending); +} + /* blocks rcvbuf consumer until >=len bytes available or timeout or interrupted * @smc smc socket * @timeo pointer to max seconds to wait, pointer to value 0 for no timeout + * @fcrit add'l criterion to evaluate as function pointer * Returns: * 1 if at least 1 byte available in rcvbuf or if socket error/shutdown. * 0 otherwise (nothing in rcvbuf nor timeout, e.g. interrupted). */ -static int smc_rx_wait_data(struct smc_sock *smc, long *timeo) +int smc_rx_wait(struct smc_sock *smc, long *timeo, + int (*fcrit)(struct smc_connection *conn)) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; int rc; - if (atomic_read(&conn->bytes_to_rcv)) + if (fcrit(conn)) return 1; sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); add_wait_queue(sk_sleep(sk), &wait); rc = sk_wait_event(sk, timeo, sk->sk_err || sk->sk_shutdown & RCV_SHUTDOWN || - atomic_read(&conn->bytes_to_rcv) || + fcrit(conn) || smc_cdc_rxed_any_close_or_senddone(conn), &wait); remove_wait_queue(sk_sleep(sk), &wait); @@ -73,65 +224,115 @@ static int smc_rx_wait_data(struct smc_sock *smc, long *timeo) return rc; } -/* rcvbuf consumer: main API called by socket layer. - * called under sk lock. +static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len, + int flags) +{ + struct smc_connection *conn = &smc->conn; + union smc_host_cursor cons; + struct sock *sk = &smc->sk; + int rc = 0; + + if (sock_flag(sk, SOCK_URGINLINE) || + !(conn->urg_state == SMC_URG_VALID) || + conn->urg_state == SMC_URG_READ) + return -EINVAL; + + if (conn->urg_state == SMC_URG_VALID) { + if (!(flags & MSG_PEEK)) + smc->conn.urg_state = SMC_URG_READ; + msg->msg_flags |= MSG_OOB; + if (len > 0) { + if (!(flags & MSG_TRUNC)) + rc = memcpy_to_msg(msg, &conn->urg_rx_byte, 1); + len = 1; + smc_curs_write(&cons, + smc_curs_read(&conn->local_tx_ctrl.cons, + conn), + conn); + if (smc_curs_diff(conn->rmb_desc->len, &cons, + &conn->urg_curs) > 1) + conn->urg_rx_skip_pend = true; + /* Urgent Byte was already accounted for, but trigger + * skipping the urgent byte in non-inline case + */ + if (!(flags & MSG_PEEK)) + smc_rx_update_consumer(smc, cons, 0); + } else { + msg->msg_flags |= MSG_TRUNC; + } + + return rc ? -EFAULT : len; + } + + if (sk->sk_state == SMC_CLOSED || sk->sk_shutdown & RCV_SHUTDOWN) + return 0; + + return -EAGAIN; +} + +/* smc_rx_recvmsg - receive data from RMBE + * @msg: copy data to receive buffer + * @pipe: copy data to pipe if set - indicates splice() call + * + * rcvbuf consumer: main API called by socket layer. + * Called under sk lock. */ -int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len, - int flags) +int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, + struct pipe_inode_info *pipe, size_t len, int flags) { size_t copylen, read_done = 0, read_remaining = len; size_t chunk_len, chunk_off, chunk_len_sum; struct smc_connection *conn = &smc->conn; + int (*func)(struct smc_connection *conn); union smc_host_cursor cons; int readable, chunk; char *rcvbuf_base; struct sock *sk; + int splbytes; long timeo; int target; /* Read at least these many bytes */ int rc; if (unlikely(flags & MSG_ERRQUEUE)) return -EINVAL; /* future work for sk.sk_family == AF_SMC */ - if (flags & MSG_OOB) - return -EINVAL; /* future work */ sk = &smc->sk; if (sk->sk_state == SMC_LISTEN) return -ENOTCONN; + if (flags & MSG_OOB) + return smc_rx_recv_urg(smc, msg, len, flags); timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - msg->msg_namelen = 0; /* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */ rcvbuf_base = conn->rmb_desc->cpu_addr; do { /* while (read_remaining) */ - if (read_done >= target) + if (read_done >= target || (pipe && read_done)) break; if (atomic_read(&conn->bytes_to_rcv)) goto copy; + else if (conn->urg_state == SMC_URG_VALID) + /* we received a single urgent Byte - skip */ + smc_rx_update_cons(smc, 0); + + if (sk->sk_shutdown & RCV_SHUTDOWN || + smc_cdc_rxed_any_close_or_senddone(conn) || + conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) + break; if (read_done) { if (sk->sk_err || sk->sk_state == SMC_CLOSED || - sk->sk_shutdown & RCV_SHUTDOWN || !timeo || - signal_pending(current) || - smc_cdc_rxed_any_close_or_senddone(conn) || - conn->local_tx_ctrl.conn_state_flags. - peer_conn_abort) + signal_pending(current)) break; } else { if (sk->sk_err) { read_done = sock_error(sk); break; } - if (sk->sk_shutdown & RCV_SHUTDOWN || - smc_cdc_rxed_any_close_or_senddone(conn) || - conn->local_tx_ctrl.conn_state_flags. - peer_conn_abort) - break; if (sk->sk_state == SMC_CLOSED) { if (!sock_flag(sk, SOCK_DONE)) { /* This occurs when user tries to read @@ -150,32 +351,56 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len, return -EAGAIN; } - if (!atomic_read(&conn->bytes_to_rcv)) { - smc_rx_wait_data(smc, &timeo); + if (!smc_rx_data_available(conn)) { + smc_rx_wait(smc, &timeo, smc_rx_data_available); continue; } copy: /* initialize variables for 1st iteration of subsequent loop */ - /* could be just 1 byte, even after smc_rx_wait_data above */ + /* could be just 1 byte, even after waiting on data above */ readable = atomic_read(&conn->bytes_to_rcv); - /* not more than what user space asked for */ - copylen = min_t(size_t, read_remaining, readable); + splbytes = atomic_read(&conn->splice_pending); + if (!readable || (msg && splbytes)) { + if (splbytes) + func = smc_rx_data_available_and_no_splice_pend; + else + func = smc_rx_data_available; + smc_rx_wait(smc, &timeo, func); + continue; + } + smc_curs_write(&cons, smc_curs_read(&conn->local_tx_ctrl.cons, conn), conn); + /* subsequent splice() calls pick up where previous left */ + if (splbytes) + smc_curs_add(conn->rmb_desc->len, &cons, splbytes); + if (conn->urg_state == SMC_URG_VALID && + sock_flag(&smc->sk, SOCK_URGINLINE) && + readable > 1) + readable--; /* always stop at urgent Byte */ + /* not more than what user space asked for */ + copylen = min_t(size_t, read_remaining, readable); /* determine chunks where to read from rcvbuf */ /* either unwrapped case, or 1st chunk of wrapped case */ - chunk_len = min_t(size_t, - copylen, conn->rmbe_size - cons.count); + chunk_len = min_t(size_t, copylen, conn->rmb_desc->len - + cons.count); chunk_len_sum = chunk_len; chunk_off = cons.count; smc_rmb_sync_sg_for_cpu(conn); for (chunk = 0; chunk < 2; chunk++) { if (!(flags & MSG_TRUNC)) { - rc = memcpy_to_msg(msg, rcvbuf_base + chunk_off, - chunk_len); - if (rc) { + if (msg) { + rc = memcpy_to_msg(msg, rcvbuf_base + + chunk_off, + chunk_len); + } else { + rc = smc_rx_splice(pipe, rcvbuf_base + + chunk_off, chunk_len, + smc); + } + if (rc < 0) { if (!read_done) read_done = -EFAULT; smc_rmb_sync_sg_for_device(conn); @@ -196,18 +421,13 @@ copy: /* update cursors */ if (!(flags & MSG_PEEK)) { - smc_curs_add(conn->rmbe_size, &cons, copylen); /* increased in recv tasklet smc_cdc_msg_rcv() */ smp_mb__before_atomic(); atomic_sub(copylen, &conn->bytes_to_rcv); - /* guarantee 0 <= bytes_to_rcv <= rmbe_size */ + /* guarantee 0 <= bytes_to_rcv <= rmb_desc->len */ smp_mb__after_atomic(); - smc_curs_write(&conn->local_tx_ctrl.cons, - smc_curs_read(&cons, conn), - conn); - /* send consumer cursor update if required */ - /* similar to advertising new TCP rcv_wnd if required */ - smc_tx_consumer_update(conn); + if (msg && smc_rx_update_consumer(smc, cons, copylen)) + goto out; } } while (read_remaining); out: @@ -217,5 +437,7 @@ out: /* Initialize receive properties on connection establishment. NB: not __init! */ void smc_rx_init(struct smc_sock *smc) { - smc->sk.sk_data_ready = smc_rx_data_ready; + smc->sk.sk_data_ready = smc_rx_wake_up; + atomic_set(&smc->conn.splice_pending, 0); + smc->conn.urg_state = SMC_URG_READ; } diff --git a/net/smc/smc_rx.h b/net/smc/smc_rx.h index 3a32b59bf06c5..db823c97d824e 100644 --- a/net/smc/smc_rx.h +++ b/net/smc/smc_rx.h @@ -18,7 +18,14 @@ #include "smc.h" void smc_rx_init(struct smc_sock *smc); -int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len, - int flags); + +int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, + struct pipe_inode_info *pipe, size_t len, int flags); +int smc_rx_wait(struct smc_sock *smc, long *timeo, + int (*fcrit)(struct smc_connection *conn)); +static inline int smc_rx_data_available(struct smc_connection *conn) +{ + return atomic_read(&conn->bytes_to_rcv); +} #endif /* SMC_RX_H */ diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 72f004c9c9b13..cee6664007524 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -19,6 +19,7 @@ #include <linux/sched/signal.h> #include <net/sock.h> +#include <net/tcp.h> #include "smc.h" #include "smc_wr.h" @@ -26,11 +27,12 @@ #include "smc_tx.h" #define SMC_TX_WORK_DELAY HZ +#define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */ /***************************** sndbuf producer *******************************/ /* callback implementation for sk.sk_write_space() - * to wakeup sndbuf producers that blocked with smc_tx_wait_memory(). + * to wakeup sndbuf producers that blocked with smc_tx_wait(). * called under sk_socket lock. */ static void smc_tx_write_space(struct sock *sk) @@ -54,7 +56,7 @@ static void smc_tx_write_space(struct sock *sk) } } -/* Wakeup sndbuf producers that blocked with smc_tx_wait_memory(). +/* Wakeup sndbuf producers that blocked with smc_tx_wait(). * Cf. tcp_data_snd_check()=>tcp_check_space()=>tcp_new_space(). */ void smc_tx_sndbuf_nonfull(struct smc_sock *smc) @@ -64,8 +66,10 @@ void smc_tx_sndbuf_nonfull(struct smc_sock *smc) smc->sk.sk_write_space(&smc->sk); } -/* blocks sndbuf producer until at least one byte of free space available */ -static int smc_tx_wait_memory(struct smc_sock *smc, int flags) +/* blocks sndbuf producer until at least one byte of free space available + * or urgent Byte was consumed + */ +static int smc_tx_wait(struct smc_sock *smc, int flags) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct smc_connection *conn = &smc->conn; @@ -101,20 +105,28 @@ static int smc_tx_wait_memory(struct smc_sock *smc, int flags) break; } sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (atomic_read(&conn->sndbuf_space)) - break; /* at least 1 byte of free space available */ + if (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend) + break; /* at least 1 byte of free & no urgent data */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk_wait_event(sk, &timeo, sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN) || smc_cdc_rxed_any_close(conn) || - atomic_read(&conn->sndbuf_space), + (atomic_read(&conn->sndbuf_space) && + !conn->urg_tx_pend), &wait); } remove_wait_queue(sk_sleep(sk), &wait); return rc; } +static bool smc_tx_is_corked(struct smc_sock *smc) +{ + struct tcp_sock *tp = tcp_sk(smc->clcsock->sk); + + return (tp->nonagle & TCP_NAGLE_CORK) ? true : false; +} + /* sndbuf producer: main API called by socket layer. * called under sock lock. */ @@ -148,8 +160,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) if (smc_cdc_rxed_any_close(conn)) return send_done ?: -ECONNRESET; - if (!atomic_read(&conn->sndbuf_space)) { - rc = smc_tx_wait_memory(smc, msg->msg_flags); + if (msg->msg_flags & MSG_OOB) + conn->local_tx_ctrl.prod_flags.urg_data_pending = 1; + + if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) { + rc = smc_tx_wait(smc, msg->msg_flags); if (rc) { if (send_done) return send_done; @@ -159,7 +174,7 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) } /* initialize variables for 1st iteration of subsequent loop */ - /* could be just 1 byte, even after smc_tx_wait_memory above */ + /* could be just 1 byte, even after smc_tx_wait above */ writespace = atomic_read(&conn->sndbuf_space); /* not more than what user space asked for */ copylen = min_t(size_t, send_remaining, writespace); @@ -171,8 +186,8 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) tx_cnt_prep = prep.count; /* determine chunks where to write into sndbuf */ /* either unwrapped case, or 1st chunk of wrapped case */ - chunk_len = min_t(size_t, - copylen, conn->sndbuf_size - tx_cnt_prep); + chunk_len = min_t(size_t, copylen, conn->sndbuf_desc->len - + tx_cnt_prep); chunk_len_sum = chunk_len; chunk_off = tx_cnt_prep; smc_sndbuf_sync_sg_for_cpu(conn); @@ -197,19 +212,30 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) } smc_sndbuf_sync_sg_for_device(conn); /* update cursors */ - smc_curs_add(conn->sndbuf_size, &prep, copylen); + smc_curs_add(conn->sndbuf_desc->len, &prep, copylen); smc_curs_write(&conn->tx_curs_prep, smc_curs_read(&prep, conn), conn); /* increased in send tasklet smc_cdc_tx_handler() */ smp_mb__before_atomic(); atomic_sub(copylen, &conn->sndbuf_space); - /* guarantee 0 <= sndbuf_space <= sndbuf_size */ + /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */ smp_mb__after_atomic(); /* since we just produced more new data into sndbuf, * trigger sndbuf consumer: RDMA write into peer RMBE and CDC */ - smc_tx_sndbuf_nonempty(conn); + if ((msg->msg_flags & MSG_OOB) && !send_remaining) + conn->urg_tx_pend = true; + if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) && + (atomic_read(&conn->sndbuf_space) > + (conn->sndbuf_desc->len >> 1))) + /* for a corked socket defer the RDMA writes if there + * is still sufficient sndbuf_space available + */ + schedule_delayed_work(&conn->tx_work, + SMC_TX_CORK_DELAY); + else + smc_tx_sndbuf_nonempty(conn); } /* while (msg_data_left(msg)) */ return send_done; @@ -243,7 +269,7 @@ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, rdma_wr.remote_addr = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr + /* RMBE within RMB */ - ((conn->peer_conn_idx - 1) * conn->peer_rmbe_size) + + conn->tx_off + /* offset within RMBE */ peer_rmbe_offset; rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; @@ -268,7 +294,7 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn, atomic_sub(len, &conn->peer_rmbe_space); /* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */ smp_mb__after_atomic(); - smc_curs_add(conn->sndbuf_size, sent, len); + smc_curs_add(conn->sndbuf_desc->len, sent, len); } /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit; @@ -281,6 +307,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) union smc_host_cursor sent, prep, prod, cons; struct ib_sge sges[SMC_IB_MAX_SEND_SGE]; struct smc_link_group *lgr = conn->lgr; + struct smc_cdc_producer_flags *pflags; int to_send, rmbespace; struct smc_link *link; dma_addr_t dma_addr; @@ -291,7 +318,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) smc_curs_write(&sent, smc_curs_read(&conn->tx_curs_sent, conn), conn); smc_curs_write(&prep, smc_curs_read(&conn->tx_curs_prep, conn), conn); /* cf. wmem_alloc - (snd_max - snd_una) */ - to_send = smc_curs_diff(conn->sndbuf_size, &sent, &prep); + to_send = smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep); if (to_send <= 0) return 0; @@ -308,7 +335,8 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) conn); /* if usable snd_wnd closes ask peer to advertise once it opens again */ - conn->local_tx_ctrl.prod_flags.write_blocked = (to_send >= rmbespace); + pflags = &conn->local_tx_ctrl.prod_flags; + pflags->write_blocked = (to_send >= rmbespace); /* cf. usable snd_wnd */ len = min(to_send, rmbespace); @@ -333,12 +361,12 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) dst_len_sum = dst_len; src_off = sent.count; /* dst_len determines the maximum src_len */ - if (sent.count + dst_len <= conn->sndbuf_size) { + if (sent.count + dst_len <= conn->sndbuf_desc->len) { /* unwrapped src case: single chunk of entire dst_len */ src_len = dst_len; } else { /* wrapped src case: 2 chunks of sum dst_len; start with 1st: */ - src_len = conn->sndbuf_size - sent.count; + src_len = conn->sndbuf_desc->len - sent.count; } src_len_sum = src_len; dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl); @@ -350,8 +378,8 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) sges[srcchunk].lkey = link->roce_pd->local_dma_lkey; num_sges++; src_off += src_len; - if (src_off >= conn->sndbuf_size) - src_off -= conn->sndbuf_size; + if (src_off >= conn->sndbuf_desc->len) + src_off -= conn->sndbuf_desc->len; /* modulo in send ring */ if (src_len_sum == dst_len) break; /* either on 1st or 2nd iteration */ @@ -369,10 +397,12 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) dst_len = len - dst_len; /* remainder */ dst_len_sum += dst_len; src_len = min_t(int, - dst_len, conn->sndbuf_size - sent.count); + dst_len, conn->sndbuf_desc->len - sent.count); src_len_sum = src_len; } + if (conn->urg_tx_pend && len == to_send) + pflags->urg_data_present = 1; smc_tx_advance_cursors(conn, &prod, &sent, len); /* update connection's cursors with advanced local cursors */ smc_curs_write(&conn->local_tx_ctrl.prod, @@ -392,6 +422,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) */ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) { + struct smc_cdc_producer_flags *pflags; struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; int rc; @@ -409,20 +440,27 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) } rc = 0; if (conn->alert_token_local) /* connection healthy */ - schedule_delayed_work(&conn->tx_work, - SMC_TX_WORK_DELAY); + mod_delayed_work(system_wq, &conn->tx_work, + SMC_TX_WORK_DELAY); } goto out_unlock; } - rc = smc_tx_rdma_writes(conn); - if (rc) { - smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], - (struct smc_wr_tx_pend_priv *)pend); - goto out_unlock; + if (!conn->local_tx_ctrl.prod_flags.urg_data_present) { + rc = smc_tx_rdma_writes(conn); + if (rc) { + smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], + (struct smc_wr_tx_pend_priv *)pend); + goto out_unlock; + } } rc = smc_cdc_msg_send(conn, wr_buf, pend); + pflags = &conn->local_tx_ctrl.prod_flags; + if (!rc && pflags->urg_data_present) { + pflags->urg_data_pending = 0; + pflags->urg_data_present = 0; + } out_unlock: spin_unlock_bh(&conn->send_lock); @@ -432,7 +470,7 @@ out_unlock: /* Wakeup sndbuf consumers from process context * since there is more data to transmit */ -static void smc_tx_work(struct work_struct *work) +void smc_tx_work(struct work_struct *work) { struct smc_connection *conn = container_of(to_delayed_work(work), struct smc_connection, @@ -455,7 +493,7 @@ out: release_sock(&smc->sk); } -void smc_tx_consumer_update(struct smc_connection *conn) +void smc_tx_consumer_update(struct smc_connection *conn, bool force) { union smc_host_cursor cfed, cons; int to_confirm; @@ -466,11 +504,12 @@ void smc_tx_consumer_update(struct smc_connection *conn) smc_curs_write(&cfed, smc_curs_read(&conn->rx_curs_confirmed, conn), conn); - to_confirm = smc_curs_diff(conn->rmbe_size, &cfed, &cons); + to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons); if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || + force || ((to_confirm > conn->rmbe_update_limit) && - ((to_confirm > (conn->rmbe_size / 2)) || + ((to_confirm > (conn->rmb_desc->len / 2)) || conn->local_rx_ctrl.prod_flags.write_blocked))) { if ((smc_cdc_get_slot_and_msg_send(conn) < 0) && conn->alert_token_local) { /* connection healthy */ @@ -494,6 +533,4 @@ void smc_tx_consumer_update(struct smc_connection *conn) void smc_tx_init(struct smc_sock *smc) { smc->sk.sk_write_space = smc_tx_write_space; - INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work); - spin_lock_init(&smc->conn.send_lock); } diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h index 78255964fa4dc..9d2238909fa08 100644 --- a/net/smc/smc_tx.h +++ b/net/smc/smc_tx.h @@ -24,13 +24,14 @@ static inline int smc_tx_prepared_sends(struct smc_connection *conn) smc_curs_write(&sent, smc_curs_read(&conn->tx_curs_sent, conn), conn); smc_curs_write(&prep, smc_curs_read(&conn->tx_curs_prep, conn), conn); - return smc_curs_diff(conn->sndbuf_size, &sent, &prep); + return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep); } +void smc_tx_work(struct work_struct *work); void smc_tx_init(struct smc_sock *smc); int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len); int smc_tx_sndbuf_nonempty(struct smc_connection *conn); void smc_tx_sndbuf_nonfull(struct smc_sock *smc); -void smc_tx_consumer_update(struct smc_connection *conn); +void smc_tx_consumer_update(struct smc_connection *conn, bool force); #endif /* SMC_TX_H */ diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 1b8af23e6e2b9..cc7c1bb60fe87 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -376,6 +376,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num) for (i = 0; i < num; i++) { link = wc[i].qp->qp_context; if (wc[i].status == IB_WC_SUCCESS) { + link->wr_rx_tstamp = jiffies; smc_wr_rx_demultiplex(&wc[i]); smc_wr_rx_post(link); /* refill WR RX */ } else { diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 092bebc700483..1a96951835999 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -512,6 +512,19 @@ int strp_init(struct strparser *strp, struct sock *sk, } EXPORT_SYMBOL_GPL(strp_init); +/* Sock process lock held (lock_sock) */ +void __strp_unpause(struct strparser *strp) +{ + strp->paused = 0; + + if (strp->need_bytes) { + if (strp_peek_len(strp) < strp->need_bytes) + return; + } + strp_read_sock(strp); +} +EXPORT_SYMBOL_GPL(__strp_unpause); + void strp_unpause(struct strparser *strp) { strp->paused = 0; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index f7d47c89d6581..2dfb492a7c943 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -697,6 +697,9 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->window)) goto prop_msg_full; + if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, bearer->mtu)) + goto prop_msg_full; nla_nest_end(msg->skb, prop); @@ -979,12 +982,23 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) if (props[TIPC_NLA_PROP_TOL]) { b->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]); - tipc_node_apply_tolerance(net, b); + tipc_node_apply_property(net, b, TIPC_NLA_PROP_TOL); } if (props[TIPC_NLA_PROP_PRIO]) b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) b->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + if (props[TIPC_NLA_PROP_MTU]) { + if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) + return -EINVAL; +#ifdef CONFIG_TIPC_MEDIA_UDP + if (tipc_udp_mtu_bad(nla_get_u32 + (props[TIPC_NLA_PROP_MTU]))) + return -EINVAL; + b->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); + tipc_node_apply_property(net, b, TIPC_NLA_PROP_MTU); +#endif + } } return 0; @@ -1029,6 +1043,9 @@ static int __tipc_nl_add_media(struct tipc_nl_msg *msg, goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->window)) goto prop_msg_full; + if (media->type_id == TIPC_MEDIA_TYPE_UDP) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, media->mtu)) + goto prop_msg_full; nla_nest_end(msg->skb, prop); nla_nest_end(msg->skb, attrs); @@ -1158,6 +1175,16 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) m->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) m->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + if (props[TIPC_NLA_PROP_MTU]) { + if (m->type_id != TIPC_MEDIA_TYPE_UDP) + return -EINVAL; +#ifdef CONFIG_TIPC_MEDIA_UDP + if (tipc_udp_mtu_bad(nla_get_u32 + (props[TIPC_NLA_PROP_MTU]))) + return -EINVAL; + m->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); +#endif + } } return 0; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 6efcee63a3819..394290cbbb1de 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -94,6 +94,8 @@ struct tipc_bearer; * @priority: default link (and bearer) priority * @tolerance: default time (in ms) before declaring link failure * @window: default window (in packets) before declaring link congestion + * @mtu: max packet size bearer can support for media type not dependent on + * underlying device MTU * @type_id: TIPC media identifier * @hwaddr_len: TIPC media address len * @name: media name @@ -118,6 +120,7 @@ struct tipc_media { u32 priority; u32 tolerance; u32 window; + u32 mtu; u32 type_id; u32 hwaddr_len; char name[TIPC_MAX_MEDIA_NAME]; diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index dd1c4fa2eb78a..bebe88cae07be 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -136,12 +136,12 @@ static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd) } /** - * tipc_service_find_range - find service range matching a service instance + * tipc_service_first_range - find first service range in tree matching instance * * Very time-critical, so binary search through range rb tree */ -static struct service_range *tipc_service_find_range(struct tipc_service *sc, - u32 instance) +static struct service_range *tipc_service_first_range(struct tipc_service *sc, + u32 instance) { struct rb_node *n = sc->ranges.rb_node; struct service_range *sr; @@ -158,6 +158,30 @@ static struct service_range *tipc_service_find_range(struct tipc_service *sc, return NULL; } +/* tipc_service_find_range - find service range matching publication parameters + */ +static struct service_range *tipc_service_find_range(struct tipc_service *sc, + u32 lower, u32 upper) +{ + struct rb_node *n = sc->ranges.rb_node; + struct service_range *sr; + + sr = tipc_service_first_range(sc, lower); + if (!sr) + return NULL; + + /* Look for exact match */ + for (n = &sr->tree_node; n; n = rb_next(n)) { + sr = container_of(n, struct service_range, tree_node); + if (sr->upper == upper) + break; + } + if (!n || sr->lower != lower || sr->upper != upper) + return NULL; + + return sr; +} + static struct service_range *tipc_service_create_range(struct tipc_service *sc, u32 lower, u32 upper) { @@ -238,54 +262,19 @@ err: /** * tipc_service_remove_publ - remove a publication from a service */ -static struct publication *tipc_service_remove_publ(struct net *net, - struct tipc_service *sc, - u32 lower, u32 upper, - u32 node, u32 key, - struct service_range **rng) +static struct publication *tipc_service_remove_publ(struct service_range *sr, + u32 node, u32 key) { - struct tipc_subscription *sub, *tmp; - struct service_range *sr; struct publication *p; - bool found = false; - bool last = false; - struct rb_node *n; - - sr = tipc_service_find_range(sc, lower); - if (!sr) - return NULL; - /* Find exact matching service range */ - for (n = &sr->tree_node; n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper == upper) - break; - } - if (!n || sr->lower != lower || sr->upper != upper) - return NULL; - - /* Find publication, if it exists */ list_for_each_entry(p, &sr->all_publ, all_publ) { if (p->key != key || (node && node != p->node)) continue; - found = true; - break; + list_del(&p->all_publ); + list_del(&p->local_publ); + return p; } - if (!found) - return NULL; - - list_del(&p->all_publ); - list_del(&p->local_publ); - if (list_empty(&sr->all_publ)) - last = true; - - /* Notify any waiting subscriptions */ - list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { - tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_WITHDRAWN, - p->port, p->node, p->scope, last); - } - *rng = sr; - return p; + return NULL; } /** @@ -376,17 +365,31 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, u32 node, u32 key) { struct tipc_service *sc = tipc_service_find(net, type); + struct tipc_subscription *sub, *tmp; struct service_range *sr = NULL; struct publication *p = NULL; + bool last; if (!sc) return NULL; spin_lock_bh(&sc->lock); - p = tipc_service_remove_publ(net, sc, lower, upper, node, key, &sr); + sr = tipc_service_find_range(sc, lower, upper); + if (!sr) + goto exit; + p = tipc_service_remove_publ(sr, node, key); + if (!p) + goto exit; + + /* Notify any waiting subscriptions */ + last = list_empty(&sr->all_publ); + list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { + tipc_sub_report_overlap(sub, lower, upper, TIPC_WITHDRAWN, + p->port, node, p->scope, last); + } /* Remove service range item if this was its last publication */ - if (sr && list_empty(&sr->all_publ)) { + if (list_empty(&sr->all_publ)) { rb_erase(&sr->tree_node, &sc->ranges); kfree(sr); } @@ -396,6 +399,7 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, hlist_del_init_rcu(&sc->service_list); kfree_rcu(sc, rcu); } +exit: spin_unlock_bh(&sc->lock); return p; } @@ -437,7 +441,7 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode) goto not_found; spin_lock_bh(&sc->lock); - sr = tipc_service_find_range(sc, instance); + sr = tipc_service_first_range(sc, instance); if (unlikely(!sr)) goto no_match; @@ -484,7 +488,7 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope, spin_lock_bh(&sc->lock); - sr = tipc_service_find_range(sc, instance); + sr = tipc_service_first_range(sc, instance); if (!sr) goto no_match; @@ -756,8 +760,7 @@ static void tipc_service_delete(struct net *net, struct tipc_service *sc) spin_lock_bh(&sc->lock); rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) { list_for_each_entry_safe(p, tmp, &sr->all_publ, all_publ) { - tipc_service_remove_publ(net, sc, p->lower, p->upper, - p->node, p->key, &sr); + tipc_service_remove_publ(sr, p->node, p->key); kfree_rcu(p, rcu); } rb_erase(&sr->tree_node, &sc->ranges); diff --git a/net/tipc/node.c b/net/tipc/node.c index f29549de9245f..6a44eb812baf4 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -195,6 +195,27 @@ int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel) return mtu; } +bool tipc_node_get_id(struct net *net, u32 addr, u8 *id) +{ + u8 *own_id = tipc_own_id(net); + struct tipc_node *n; + + if (!own_id) + return true; + + if (addr == tipc_own_addr(net)) { + memcpy(id, own_id, TIPC_NODEID_LEN); + return true; + } + n = tipc_node_find(net, addr); + if (!n) + return false; + + memcpy(id, &n->peer_id, TIPC_NODEID_LEN); + tipc_node_put(n); + return true; +} + u16 tipc_node_get_capabilities(struct net *net, u32 addr) { struct tipc_node *n; @@ -1681,7 +1702,8 @@ discard: kfree_skb(skb); } -void tipc_node_apply_tolerance(struct net *net, struct tipc_bearer *b) +void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, + int prop) { struct tipc_net *tn = tipc_net(net); int bearer_id = b->identity; @@ -1696,8 +1718,13 @@ void tipc_node_apply_tolerance(struct net *net, struct tipc_bearer *b) list_for_each_entry_rcu(n, &tn->node_list, list) { tipc_node_write_lock(n); e = &n->links[bearer_id]; - if (e->link) - tipc_link_set_tolerance(e->link, b->tolerance, &xmitq); + if (e->link) { + if (prop == TIPC_NLA_PROP_TOL) + tipc_link_set_tolerance(e->link, b->tolerance, + &xmitq); + else if (prop == TIPC_NLA_PROP_MTU) + tipc_link_set_mtu(e->link, b->mtu); + } tipc_node_write_unlock(n); tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr); } diff --git a/net/tipc/node.h b/net/tipc/node.h index f24b83500df15..846c8f240872f 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -60,6 +60,7 @@ enum { #define INVALID_BEARER_ID -1 void tipc_node_stop(struct net *net); +bool tipc_node_get_id(struct net *net, u32 addr, u8 *id); u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr); void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128, struct tipc_bearer *bearer, @@ -67,7 +68,7 @@ void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128, struct tipc_media_addr *maddr, bool *respond, bool *dupl_addr); void tipc_node_delete_links(struct net *net, int bearer_id); -void tipc_node_apply_tolerance(struct net *net, struct tipc_bearer *b); +void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, int prop); int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, char *linkname, size_t len); int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3bb45042e8334..14a5d055717d2 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2970,7 +2970,8 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { - struct sock *sk = sock->sk; + struct net *net = sock_net(sock->sk); + struct tipc_sioc_nodeid_req nr = {0}; struct tipc_sioc_ln_req lnr; void __user *argp = (void __user *)arg; @@ -2978,7 +2979,7 @@ static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCGETLINKNAME: if (copy_from_user(&lnr, argp, sizeof(lnr))) return -EFAULT; - if (!tipc_node_get_linkname(sock_net(sk), + if (!tipc_node_get_linkname(net, lnr.bearer_id & 0xffff, lnr.peer, lnr.linkname, TIPC_MAX_LINK_NAME)) { if (copy_to_user(argp, &lnr, sizeof(lnr))) @@ -2986,6 +2987,14 @@ static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return 0; } return -EADDRNOTAVAIL; + case SIOCGETNODEID: + if (copy_from_user(&nr, argp, sizeof(nr))) + return -EFAULT; + if (!tipc_node_get_id(net, nr.peer, nr.node_id)) + return -EADDRNOTAVAIL; + if (copy_to_user(argp, &nr, sizeof(nr))) + return -EFAULT; + return 0; default: return -ENOIOCTLCMD; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index e7d91f5d5caed..9783101bc4a9a 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -713,8 +713,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, err = -EINVAL; goto err; } - b->mtu = dev->mtu - sizeof(struct iphdr) - - sizeof(struct udphdr); + b->mtu = b->media->mtu; #if IS_ENABLED(CONFIG_IPV6) } else if (local.proto == htons(ETH_P_IPV6)) { udp_conf.family = AF_INET6; @@ -803,6 +802,7 @@ struct tipc_media udp_media_info = { .priority = TIPC_DEF_LINK_PRI, .tolerance = TIPC_DEF_LINK_TOL, .window = TIPC_DEF_LINK_WIN, + .mtu = TIPC_DEF_LINK_UDP_MTU, .type_id = TIPC_MEDIA_TYPE_UDP, .hwaddr_len = 0, .name = "udp" diff --git a/net/tipc/udp_media.h b/net/tipc/udp_media.h index 281bbae877264..e7455cc73e16c 100644 --- a/net/tipc/udp_media.h +++ b/net/tipc/udp_media.h @@ -38,9 +38,23 @@ #ifndef _TIPC_UDP_MEDIA_H #define _TIPC_UDP_MEDIA_H +#include <linux/ip.h> +#include <linux/udp.h> + int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr); int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b); int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb); +/* check if configured MTU is too low for tipc headers */ +static inline bool tipc_udp_mtu_bad(u32 mtu) +{ + if (mtu >= (TIPC_MIN_BEARER_MTU + sizeof(struct iphdr) + + sizeof(struct udphdr))) + return false; + + pr_warn("MTU too low for tipc bearer\n"); + return true; +} + #endif #endif diff --git a/net/tls/Kconfig b/net/tls/Kconfig index 89b8745a986f0..73f05ece53d0c 100644 --- a/net/tls/Kconfig +++ b/net/tls/Kconfig @@ -14,3 +14,13 @@ config TLS encryption handling of the TLS protocol to be done in-kernel. If unsure, say N. + +config TLS_DEVICE + bool "Transport Layer Security HW offload" + depends on TLS + select SOCK_VALIDATE_XMIT + default n + help + Enable kernel support for HW offload of the TLS protocol. + + If unsure, say N. diff --git a/net/tls/Makefile b/net/tls/Makefile index a930fd1c4f7b8..4d6b728a67d0c 100644 --- a/net/tls/Makefile +++ b/net/tls/Makefile @@ -5,3 +5,5 @@ obj-$(CONFIG_TLS) += tls.o tls-y := tls_main.o tls_sw.o + +tls-$(CONFIG_TLS_DEVICE) += tls_device.o tls_device_fallback.o diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c new file mode 100644 index 0000000000000..a7a8f8e20ff30 --- /dev/null +++ b/net/tls/tls_device.c @@ -0,0 +1,766 @@ +/* Copyright (c) 2018, Mellanox Technologies All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - 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. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <crypto/aead.h> +#include <linux/highmem.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <net/dst.h> +#include <net/inet_connection_sock.h> +#include <net/tcp.h> +#include <net/tls.h> + +/* device_offload_lock is used to synchronize tls_dev_add + * against NETDEV_DOWN notifications. + */ +static DECLARE_RWSEM(device_offload_lock); + +static void tls_device_gc_task(struct work_struct *work); + +static DECLARE_WORK(tls_device_gc_work, tls_device_gc_task); +static LIST_HEAD(tls_device_gc_list); +static LIST_HEAD(tls_device_list); +static DEFINE_SPINLOCK(tls_device_lock); + +static void tls_device_free_ctx(struct tls_context *ctx) +{ + struct tls_offload_context *offload_ctx = tls_offload_ctx(ctx); + + kfree(offload_ctx); + kfree(ctx); +} + +static void tls_device_gc_task(struct work_struct *work) +{ + struct tls_context *ctx, *tmp; + unsigned long flags; + LIST_HEAD(gc_list); + + spin_lock_irqsave(&tls_device_lock, flags); + list_splice_init(&tls_device_gc_list, &gc_list); + spin_unlock_irqrestore(&tls_device_lock, flags); + + list_for_each_entry_safe(ctx, tmp, &gc_list, list) { + struct net_device *netdev = ctx->netdev; + + if (netdev) { + netdev->tlsdev_ops->tls_dev_del(netdev, ctx, + TLS_OFFLOAD_CTX_DIR_TX); + dev_put(netdev); + } + + list_del(&ctx->list); + tls_device_free_ctx(ctx); + } +} + +static void tls_device_queue_ctx_destruction(struct tls_context *ctx) +{ + unsigned long flags; + + spin_lock_irqsave(&tls_device_lock, flags); + list_move_tail(&ctx->list, &tls_device_gc_list); + + /* schedule_work inside the spinlock + * to make sure tls_device_down waits for that work. + */ + schedule_work(&tls_device_gc_work); + + spin_unlock_irqrestore(&tls_device_lock, flags); +} + +/* We assume that the socket is already connected */ +static struct net_device *get_netdev_for_sock(struct sock *sk) +{ + struct dst_entry *dst = sk_dst_get(sk); + struct net_device *netdev = NULL; + + if (likely(dst)) { + netdev = dst->dev; + dev_hold(netdev); + } + + dst_release(dst); + + return netdev; +} + +static void destroy_record(struct tls_record_info *record) +{ + int nr_frags = record->num_frags; + skb_frag_t *frag; + + while (nr_frags-- > 0) { + frag = &record->frags[nr_frags]; + __skb_frag_unref(frag); + } + kfree(record); +} + +static void delete_all_records(struct tls_offload_context *offload_ctx) +{ + struct tls_record_info *info, *temp; + + list_for_each_entry_safe(info, temp, &offload_ctx->records_list, list) { + list_del(&info->list); + destroy_record(info); + } + + offload_ctx->retransmit_hint = NULL; +} + +static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_record_info *info, *temp; + struct tls_offload_context *ctx; + u64 deleted_records = 0; + unsigned long flags; + + if (!tls_ctx) + return; + + ctx = tls_offload_ctx(tls_ctx); + + spin_lock_irqsave(&ctx->lock, flags); + info = ctx->retransmit_hint; + if (info && !before(acked_seq, info->end_seq)) { + ctx->retransmit_hint = NULL; + list_del(&info->list); + destroy_record(info); + deleted_records++; + } + + list_for_each_entry_safe(info, temp, &ctx->records_list, list) { + if (before(acked_seq, info->end_seq)) + break; + list_del(&info->list); + + destroy_record(info); + deleted_records++; + } + + ctx->unacked_record_sn += deleted_records; + spin_unlock_irqrestore(&ctx->lock, flags); +} + +/* At this point, there should be no references on this + * socket and no in-flight SKBs associated with this + * socket, so it is safe to free all the resources. + */ +void tls_device_sk_destruct(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + + if (ctx->open_record) + destroy_record(ctx->open_record); + + delete_all_records(ctx); + crypto_free_aead(ctx->aead_send); + ctx->sk_destruct(sk); + clean_acked_data_disable(inet_csk(sk)); + + if (refcount_dec_and_test(&tls_ctx->refcount)) + tls_device_queue_ctx_destruction(tls_ctx); +} +EXPORT_SYMBOL(tls_device_sk_destruct); + +static void tls_append_frag(struct tls_record_info *record, + struct page_frag *pfrag, + int size) +{ + skb_frag_t *frag; + + frag = &record->frags[record->num_frags - 1]; + if (frag->page.p == pfrag->page && + frag->page_offset + frag->size == pfrag->offset) { + frag->size += size; + } else { + ++frag; + frag->page.p = pfrag->page; + frag->page_offset = pfrag->offset; + frag->size = size; + ++record->num_frags; + get_page(pfrag->page); + } + + pfrag->offset += size; + record->len += size; +} + +static int tls_push_record(struct sock *sk, + struct tls_context *ctx, + struct tls_offload_context *offload_ctx, + struct tls_record_info *record, + struct page_frag *pfrag, + int flags, + unsigned char record_type) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct page_frag dummy_tag_frag; + skb_frag_t *frag; + int i; + + /* fill prepend */ + frag = &record->frags[0]; + tls_fill_prepend(ctx, + skb_frag_address(frag), + record->len - ctx->tx.prepend_size, + record_type); + + /* HW doesn't care about the data in the tag, because it fills it. */ + dummy_tag_frag.page = skb_frag_page(frag); + dummy_tag_frag.offset = 0; + + tls_append_frag(record, &dummy_tag_frag, ctx->tx.tag_size); + record->end_seq = tp->write_seq + record->len; + spin_lock_irq(&offload_ctx->lock); + list_add_tail(&record->list, &offload_ctx->records_list); + spin_unlock_irq(&offload_ctx->lock); + offload_ctx->open_record = NULL; + set_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); + tls_advance_record_sn(sk, &ctx->tx); + + for (i = 0; i < record->num_frags; i++) { + frag = &record->frags[i]; + sg_unmark_end(&offload_ctx->sg_tx_data[i]); + sg_set_page(&offload_ctx->sg_tx_data[i], skb_frag_page(frag), + frag->size, frag->page_offset); + sk_mem_charge(sk, frag->size); + get_page(skb_frag_page(frag)); + } + sg_mark_end(&offload_ctx->sg_tx_data[record->num_frags - 1]); + + /* all ready, send */ + return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); +} + +static int tls_create_new_record(struct tls_offload_context *offload_ctx, + struct page_frag *pfrag, + size_t prepend_size) +{ + struct tls_record_info *record; + skb_frag_t *frag; + + record = kmalloc(sizeof(*record), GFP_KERNEL); + if (!record) + return -ENOMEM; + + frag = &record->frags[0]; + __skb_frag_set_page(frag, pfrag->page); + frag->page_offset = pfrag->offset; + skb_frag_size_set(frag, prepend_size); + + get_page(pfrag->page); + pfrag->offset += prepend_size; + + record->num_frags = 1; + record->len = prepend_size; + offload_ctx->open_record = record; + return 0; +} + +static int tls_do_allocation(struct sock *sk, + struct tls_offload_context *offload_ctx, + struct page_frag *pfrag, + size_t prepend_size) +{ + int ret; + + if (!offload_ctx->open_record) { + if (unlikely(!skb_page_frag_refill(prepend_size, pfrag, + sk->sk_allocation))) { + sk->sk_prot->enter_memory_pressure(sk); + sk_stream_moderate_sndbuf(sk); + return -ENOMEM; + } + + ret = tls_create_new_record(offload_ctx, pfrag, prepend_size); + if (ret) + return ret; + + if (pfrag->size > pfrag->offset) + return 0; + } + + if (!sk_page_frag_refill(sk, pfrag)) + return -ENOMEM; + + return 0; +} + +static int tls_push_data(struct sock *sk, + struct iov_iter *msg_iter, + size_t size, int flags, + unsigned char record_type) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST; + int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE); + struct tls_record_info *record = ctx->open_record; + struct page_frag *pfrag; + size_t orig_size = size; + u32 max_open_record_len; + int copy, rc = 0; + bool done = false; + long timeo; + + if (flags & + ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST)) + return -ENOTSUPP; + + if (sk->sk_err) + return -sk->sk_err; + + timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + rc = tls_complete_pending_work(sk, tls_ctx, flags, &timeo); + if (rc < 0) + return rc; + + pfrag = sk_page_frag(sk); + + /* TLS_HEADER_SIZE is not counted as part of the TLS record, and + * we need to leave room for an authentication tag. + */ + max_open_record_len = TLS_MAX_PAYLOAD_SIZE + + tls_ctx->tx.prepend_size; + do { + rc = tls_do_allocation(sk, ctx, pfrag, + tls_ctx->tx.prepend_size); + if (rc) { + rc = sk_stream_wait_memory(sk, &timeo); + if (!rc) + continue; + + record = ctx->open_record; + if (!record) + break; +handle_error: + if (record_type != TLS_RECORD_TYPE_DATA) { + /* avoid sending partial + * record with type != + * application_data + */ + size = orig_size; + destroy_record(record); + ctx->open_record = NULL; + } else if (record->len > tls_ctx->tx.prepend_size) { + goto last_record; + } + + break; + } + + record = ctx->open_record; + copy = min_t(size_t, size, (pfrag->size - pfrag->offset)); + copy = min_t(size_t, copy, (max_open_record_len - record->len)); + + if (copy_from_iter_nocache(page_address(pfrag->page) + + pfrag->offset, + copy, msg_iter) != copy) { + rc = -EFAULT; + goto handle_error; + } + tls_append_frag(record, pfrag, copy); + + size -= copy; + if (!size) { +last_record: + tls_push_record_flags = flags; + if (more) { + tls_ctx->pending_open_record_frags = + record->num_frags; + break; + } + + done = true; + } + + if (done || record->len >= max_open_record_len || + (record->num_frags >= MAX_SKB_FRAGS - 1)) { + rc = tls_push_record(sk, + tls_ctx, + ctx, + record, + pfrag, + tls_push_record_flags, + record_type); + if (rc < 0) + break; + } + } while (!done); + + if (orig_size - size > 0) + rc = orig_size - size; + + return rc; +} + +int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + unsigned char record_type = TLS_RECORD_TYPE_DATA; + int rc; + + lock_sock(sk); + + if (unlikely(msg->msg_controllen)) { + rc = tls_proccess_cmsg(sk, msg, &record_type); + if (rc) + goto out; + } + + rc = tls_push_data(sk, &msg->msg_iter, size, + msg->msg_flags, record_type); + +out: + release_sock(sk); + return rc; +} + +int tls_device_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags) +{ + struct iov_iter msg_iter; + char *kaddr = kmap(page); + struct kvec iov; + int rc; + + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + + lock_sock(sk); + + if (flags & MSG_OOB) { + rc = -ENOTSUPP; + goto out; + } + + iov.iov_base = kaddr + offset; + iov.iov_len = size; + iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, &iov, 1, size); + rc = tls_push_data(sk, &msg_iter, size, + flags, TLS_RECORD_TYPE_DATA); + kunmap(page); + +out: + release_sock(sk); + return rc; +} + +struct tls_record_info *tls_get_record(struct tls_offload_context *context, + u32 seq, u64 *p_record_sn) +{ + u64 record_sn = context->hint_record_sn; + struct tls_record_info *info; + + info = context->retransmit_hint; + if (!info || + before(seq, info->end_seq - info->len)) { + /* if retransmit_hint is irrelevant start + * from the beggining of the list + */ + info = list_first_entry(&context->records_list, + struct tls_record_info, list); + record_sn = context->unacked_record_sn; + } + + list_for_each_entry_from(info, &context->records_list, list) { + if (before(seq, info->end_seq)) { + if (!context->retransmit_hint || + after(info->end_seq, + context->retransmit_hint->end_seq)) { + context->hint_record_sn = record_sn; + context->retransmit_hint = info; + } + *p_record_sn = record_sn; + return info; + } + record_sn++; + } + + return NULL; +} +EXPORT_SYMBOL(tls_get_record); + +static int tls_device_push_pending_record(struct sock *sk, int flags) +{ + struct iov_iter msg_iter; + + iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); + return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA); +} + +int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) +{ + u16 nonce_size, tag_size, iv_size, rec_seq_size; + struct tls_record_info *start_marker_record; + struct tls_offload_context *offload_ctx; + struct tls_crypto_info *crypto_info; + struct net_device *netdev; + char *iv, *rec_seq; + struct sk_buff *skb; + int rc = -EINVAL; + __be64 rcd_sn; + + if (!ctx) + goto out; + + if (ctx->priv_ctx_tx) { + rc = -EEXIST; + goto out; + } + + start_marker_record = kmalloc(sizeof(*start_marker_record), GFP_KERNEL); + if (!start_marker_record) { + rc = -ENOMEM; + goto out; + } + + offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE, GFP_KERNEL); + if (!offload_ctx) { + rc = -ENOMEM; + goto free_marker_record; + } + + crypto_info = &ctx->crypto_send; + switch (crypto_info->cipher_type) { + case TLS_CIPHER_AES_GCM_128: + nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; + tag_size = TLS_CIPHER_AES_GCM_128_TAG_SIZE; + iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; + iv = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->iv; + rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE; + rec_seq = + ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq; + break; + default: + rc = -EINVAL; + goto free_offload_ctx; + } + + ctx->tx.prepend_size = TLS_HEADER_SIZE + nonce_size; + ctx->tx.tag_size = tag_size; + ctx->tx.overhead_size = ctx->tx.prepend_size + ctx->tx.tag_size; + ctx->tx.iv_size = iv_size; + ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + GFP_KERNEL); + if (!ctx->tx.iv) { + rc = -ENOMEM; + goto free_offload_ctx; + } + + memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); + + ctx->tx.rec_seq_size = rec_seq_size; + ctx->tx.rec_seq = kmalloc(rec_seq_size, GFP_KERNEL); + if (!ctx->tx.rec_seq) { + rc = -ENOMEM; + goto free_iv; + } + memcpy(ctx->tx.rec_seq, rec_seq, rec_seq_size); + + rc = tls_sw_fallback_init(sk, offload_ctx, crypto_info); + if (rc) + goto free_rec_seq; + + /* start at rec_seq - 1 to account for the start marker record */ + memcpy(&rcd_sn, ctx->tx.rec_seq, sizeof(rcd_sn)); + offload_ctx->unacked_record_sn = be64_to_cpu(rcd_sn) - 1; + + start_marker_record->end_seq = tcp_sk(sk)->write_seq; + start_marker_record->len = 0; + start_marker_record->num_frags = 0; + + INIT_LIST_HEAD(&offload_ctx->records_list); + list_add_tail(&start_marker_record->list, &offload_ctx->records_list); + spin_lock_init(&offload_ctx->lock); + sg_init_table(offload_ctx->sg_tx_data, + ARRAY_SIZE(offload_ctx->sg_tx_data)); + + clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked); + ctx->push_pending_record = tls_device_push_pending_record; + offload_ctx->sk_destruct = sk->sk_destruct; + + /* TLS offload is greatly simplified if we don't send + * SKBs where only part of the payload needs to be encrypted. + * So mark the last skb in the write queue as end of record. + */ + skb = tcp_write_queue_tail(sk); + if (skb) + TCP_SKB_CB(skb)->eor = 1; + + refcount_set(&ctx->refcount, 1); + + /* We support starting offload on multiple sockets + * concurrently, so we only need a read lock here. + * This lock must precede get_netdev_for_sock to prevent races between + * NETDEV_DOWN and setsockopt. + */ + down_read(&device_offload_lock); + netdev = get_netdev_for_sock(sk); + if (!netdev) { + pr_err_ratelimited("%s: netdev not found\n", __func__); + rc = -EINVAL; + goto release_lock; + } + + if (!(netdev->features & NETIF_F_HW_TLS_TX)) { + rc = -ENOTSUPP; + goto release_netdev; + } + + /* Avoid offloading if the device is down + * We don't want to offload new flows after + * the NETDEV_DOWN event + */ + if (!(netdev->flags & IFF_UP)) { + rc = -EINVAL; + goto release_netdev; + } + + ctx->priv_ctx_tx = offload_ctx; + rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX, + &ctx->crypto_send, + tcp_sk(sk)->write_seq); + if (rc) + goto release_netdev; + + ctx->netdev = netdev; + + spin_lock_irq(&tls_device_lock); + list_add_tail(&ctx->list, &tls_device_list); + spin_unlock_irq(&tls_device_lock); + + sk->sk_validate_xmit_skb = tls_validate_xmit_skb; + /* following this assignment tls_is_sk_tx_device_offloaded + * will return true and the context might be accessed + * by the netdev's xmit function. + */ + smp_store_release(&sk->sk_destruct, + &tls_device_sk_destruct); + up_read(&device_offload_lock); + goto out; + +release_netdev: + dev_put(netdev); +release_lock: + up_read(&device_offload_lock); + clean_acked_data_disable(inet_csk(sk)); + crypto_free_aead(offload_ctx->aead_send); +free_rec_seq: + kfree(ctx->tx.rec_seq); +free_iv: + kfree(ctx->tx.iv); +free_offload_ctx: + kfree(offload_ctx); + ctx->priv_ctx_tx = NULL; +free_marker_record: + kfree(start_marker_record); +out: + return rc; +} + +static int tls_device_down(struct net_device *netdev) +{ + struct tls_context *ctx, *tmp; + unsigned long flags; + LIST_HEAD(list); + + /* Request a write lock to block new offload attempts */ + down_write(&device_offload_lock); + + spin_lock_irqsave(&tls_device_lock, flags); + list_for_each_entry_safe(ctx, tmp, &tls_device_list, list) { + if (ctx->netdev != netdev || + !refcount_inc_not_zero(&ctx->refcount)) + continue; + + list_move(&ctx->list, &list); + } + spin_unlock_irqrestore(&tls_device_lock, flags); + + list_for_each_entry_safe(ctx, tmp, &list, list) { + netdev->tlsdev_ops->tls_dev_del(netdev, ctx, + TLS_OFFLOAD_CTX_DIR_TX); + ctx->netdev = NULL; + dev_put(netdev); + list_del_init(&ctx->list); + + if (refcount_dec_and_test(&ctx->refcount)) + tls_device_free_ctx(ctx); + } + + up_write(&device_offload_lock); + + flush_work(&tls_device_gc_work); + + return NOTIFY_DONE; +} + +static int tls_dev_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (!(dev->features & NETIF_F_HW_TLS_TX)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_REGISTER: + case NETDEV_FEAT_CHANGE: + if (dev->tlsdev_ops && + dev->tlsdev_ops->tls_dev_add && + dev->tlsdev_ops->tls_dev_del) + return NOTIFY_DONE; + else + return NOTIFY_BAD; + case NETDEV_DOWN: + return tls_device_down(dev); + } + return NOTIFY_DONE; +} + +static struct notifier_block tls_dev_notifier = { + .notifier_call = tls_dev_event, +}; + +void __init tls_device_init(void) +{ + register_netdevice_notifier(&tls_dev_notifier); +} + +void __exit tls_device_cleanup(void) +{ + unregister_netdevice_notifier(&tls_dev_notifier); + flush_work(&tls_device_gc_work); +} diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c new file mode 100644 index 0000000000000..748914abdb604 --- /dev/null +++ b/net/tls/tls_device_fallback.c @@ -0,0 +1,450 @@ +/* Copyright (c) 2018, Mellanox Technologies All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - 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. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <net/tls.h> +#include <crypto/aead.h> +#include <crypto/scatterwalk.h> +#include <net/ip6_checksum.h> + +static void chain_to_walk(struct scatterlist *sg, struct scatter_walk *walk) +{ + struct scatterlist *src = walk->sg; + int diff = walk->offset - src->offset; + + sg_set_page(sg, sg_page(src), + src->length - diff, walk->offset); + + scatterwalk_crypto_chain(sg, sg_next(src), 0, 2); +} + +static int tls_enc_record(struct aead_request *aead_req, + struct crypto_aead *aead, char *aad, + char *iv, __be64 rcd_sn, + struct scatter_walk *in, + struct scatter_walk *out, int *in_len) +{ + unsigned char buf[TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE]; + struct scatterlist sg_in[3]; + struct scatterlist sg_out[3]; + u16 len; + int rc; + + len = min_t(int, *in_len, ARRAY_SIZE(buf)); + + scatterwalk_copychunks(buf, in, len, 0); + scatterwalk_copychunks(buf, out, len, 1); + + *in_len -= len; + if (!*in_len) + return 0; + + scatterwalk_pagedone(in, 0, 1); + scatterwalk_pagedone(out, 1, 1); + + len = buf[4] | (buf[3] << 8); + len -= TLS_CIPHER_AES_GCM_128_IV_SIZE; + + tls_make_aad(aad, len - TLS_CIPHER_AES_GCM_128_TAG_SIZE, + (char *)&rcd_sn, sizeof(rcd_sn), buf[0]); + + memcpy(iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, buf + TLS_HEADER_SIZE, + TLS_CIPHER_AES_GCM_128_IV_SIZE); + + sg_init_table(sg_in, ARRAY_SIZE(sg_in)); + sg_init_table(sg_out, ARRAY_SIZE(sg_out)); + sg_set_buf(sg_in, aad, TLS_AAD_SPACE_SIZE); + sg_set_buf(sg_out, aad, TLS_AAD_SPACE_SIZE); + chain_to_walk(sg_in + 1, in); + chain_to_walk(sg_out + 1, out); + + *in_len -= len; + if (*in_len < 0) { + *in_len += TLS_CIPHER_AES_GCM_128_TAG_SIZE; + /* the input buffer doesn't contain the entire record. + * trim len accordingly. The resulting authentication tag + * will contain garbage, but we don't care, so we won't + * include any of it in the output skb + * Note that we assume the output buffer length + * is larger then input buffer length + tag size + */ + if (*in_len < 0) + len += *in_len; + + *in_len = 0; + } + + if (*in_len) { + scatterwalk_copychunks(NULL, in, len, 2); + scatterwalk_pagedone(in, 0, 1); + scatterwalk_copychunks(NULL, out, len, 2); + scatterwalk_pagedone(out, 1, 1); + } + + len -= TLS_CIPHER_AES_GCM_128_TAG_SIZE; + aead_request_set_crypt(aead_req, sg_in, sg_out, len, iv); + + rc = crypto_aead_encrypt(aead_req); + + return rc; +} + +static void tls_init_aead_request(struct aead_request *aead_req, + struct crypto_aead *aead) +{ + aead_request_set_tfm(aead_req, aead); + aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); +} + +static struct aead_request *tls_alloc_aead_request(struct crypto_aead *aead, + gfp_t flags) +{ + unsigned int req_size = sizeof(struct aead_request) + + crypto_aead_reqsize(aead); + struct aead_request *aead_req; + + aead_req = kzalloc(req_size, flags); + if (aead_req) + tls_init_aead_request(aead_req, aead); + return aead_req; +} + +static int tls_enc_records(struct aead_request *aead_req, + struct crypto_aead *aead, struct scatterlist *sg_in, + struct scatterlist *sg_out, char *aad, char *iv, + u64 rcd_sn, int len) +{ + struct scatter_walk out, in; + int rc; + + scatterwalk_start(&in, sg_in); + scatterwalk_start(&out, sg_out); + + do { + rc = tls_enc_record(aead_req, aead, aad, iv, + cpu_to_be64(rcd_sn), &in, &out, &len); + rcd_sn++; + + } while (rc == 0 && len); + + scatterwalk_done(&in, 0, 0); + scatterwalk_done(&out, 1, 0); + + return rc; +} + +/* Can't use icsk->icsk_af_ops->send_check here because the ip addresses + * might have been changed by NAT. + */ +static void update_chksum(struct sk_buff *skb, int headln) +{ + struct tcphdr *th = tcp_hdr(skb); + int datalen = skb->len - headln; + const struct ipv6hdr *ipv6h; + const struct iphdr *iph; + + /* We only changed the payload so if we are using partial we don't + * need to update anything. + */ + if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) + return; + + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct tcphdr, check); + + if (skb->sk->sk_family == AF_INET6) { + ipv6h = ipv6_hdr(skb); + th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + datalen, IPPROTO_TCP, 0); + } else { + iph = ip_hdr(skb); + th->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, + IPPROTO_TCP, 0); + } +} + +static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln) +{ + skb_copy_header(nskb, skb); + + skb_put(nskb, skb->len); + memcpy(nskb->data, skb->data, headln); + update_chksum(nskb, headln); + + nskb->destructor = skb->destructor; + nskb->sk = skb->sk; + skb->destructor = NULL; + skb->sk = NULL; + refcount_add(nskb->truesize - skb->truesize, + &nskb->sk->sk_wmem_alloc); +} + +/* This function may be called after the user socket is already + * closed so make sure we don't use anything freed during + * tls_sk_proto_close here + */ + +static int fill_sg_in(struct scatterlist *sg_in, + struct sk_buff *skb, + struct tls_offload_context *ctx, + u64 *rcd_sn, + s32 *sync_size, + int *resync_sgs) +{ + int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); + int payload_len = skb->len - tcp_payload_offset; + u32 tcp_seq = ntohl(tcp_hdr(skb)->seq); + struct tls_record_info *record; + unsigned long flags; + int remaining; + int i; + + spin_lock_irqsave(&ctx->lock, flags); + record = tls_get_record(ctx, tcp_seq, rcd_sn); + if (!record) { + spin_unlock_irqrestore(&ctx->lock, flags); + WARN(1, "Record not found for seq %u\n", tcp_seq); + return -EINVAL; + } + + *sync_size = tcp_seq - tls_record_start_seq(record); + if (*sync_size < 0) { + int is_start_marker = tls_record_is_start_marker(record); + + spin_unlock_irqrestore(&ctx->lock, flags); + /* This should only occur if the relevant record was + * already acked. In that case it should be ok + * to drop the packet and avoid retransmission. + * + * There is a corner case where the packet contains + * both an acked and a non-acked record. + * We currently don't handle that case and rely + * on TCP to retranmit a packet that doesn't contain + * already acked payload. + */ + if (!is_start_marker) + *sync_size = 0; + return -EINVAL; + } + + remaining = *sync_size; + for (i = 0; remaining > 0; i++) { + skb_frag_t *frag = &record->frags[i]; + + __skb_frag_ref(frag); + sg_set_page(sg_in + i, skb_frag_page(frag), + skb_frag_size(frag), frag->page_offset); + + remaining -= skb_frag_size(frag); + + if (remaining < 0) + sg_in[i].length += remaining; + } + *resync_sgs = i; + + spin_unlock_irqrestore(&ctx->lock, flags); + if (skb_to_sgvec(skb, &sg_in[i], tcp_payload_offset, payload_len) < 0) + return -EINVAL; + + return 0; +} + +static void fill_sg_out(struct scatterlist sg_out[3], void *buf, + struct tls_context *tls_ctx, + struct sk_buff *nskb, + int tcp_payload_offset, + int payload_len, + int sync_size, + void *dummy_buf) +{ + sg_set_buf(&sg_out[0], dummy_buf, sync_size); + sg_set_buf(&sg_out[1], nskb->data + tcp_payload_offset, payload_len); + /* Add room for authentication tag produced by crypto */ + dummy_buf += sync_size; + sg_set_buf(&sg_out[2], dummy_buf, TLS_CIPHER_AES_GCM_128_TAG_SIZE); +} + +static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx, + struct scatterlist sg_out[3], + struct scatterlist *sg_in, + struct sk_buff *skb, + s32 sync_size, u64 rcd_sn) +{ + int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); + struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + int payload_len = skb->len - tcp_payload_offset; + void *buf, *iv, *aad, *dummy_buf; + struct aead_request *aead_req; + struct sk_buff *nskb = NULL; + int buf_len; + + aead_req = tls_alloc_aead_request(ctx->aead_send, GFP_ATOMIC); + if (!aead_req) + return NULL; + + buf_len = TLS_CIPHER_AES_GCM_128_SALT_SIZE + + TLS_CIPHER_AES_GCM_128_IV_SIZE + + TLS_AAD_SPACE_SIZE + + sync_size + + TLS_CIPHER_AES_GCM_128_TAG_SIZE; + buf = kmalloc(buf_len, GFP_ATOMIC); + if (!buf) + goto free_req; + + iv = buf; + memcpy(iv, tls_ctx->crypto_send_aes_gcm_128.salt, + TLS_CIPHER_AES_GCM_128_SALT_SIZE); + aad = buf + TLS_CIPHER_AES_GCM_128_SALT_SIZE + + TLS_CIPHER_AES_GCM_128_IV_SIZE; + dummy_buf = aad + TLS_AAD_SPACE_SIZE; + + nskb = alloc_skb(skb_headroom(skb) + skb->len, GFP_ATOMIC); + if (!nskb) + goto free_buf; + + skb_reserve(nskb, skb_headroom(skb)); + + fill_sg_out(sg_out, buf, tls_ctx, nskb, tcp_payload_offset, + payload_len, sync_size, dummy_buf); + + if (tls_enc_records(aead_req, ctx->aead_send, sg_in, sg_out, aad, iv, + rcd_sn, sync_size + payload_len) < 0) + goto free_nskb; + + complete_skb(nskb, skb, tcp_payload_offset); + + /* validate_xmit_skb_list assumes that if the skb wasn't segmented + * nskb->prev will point to the skb itself + */ + nskb->prev = nskb; + +free_buf: + kfree(buf); +free_req: + kfree(aead_req); + return nskb; +free_nskb: + kfree_skb(nskb); + nskb = NULL; + goto free_buf; +} + +static struct sk_buff *tls_sw_fallback(struct sock *sk, struct sk_buff *skb) +{ + int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + int payload_len = skb->len - tcp_payload_offset; + struct scatterlist *sg_in, sg_out[3]; + struct sk_buff *nskb = NULL; + int sg_in_max_elements; + int resync_sgs = 0; + s32 sync_size = 0; + u64 rcd_sn; + + /* worst case is: + * MAX_SKB_FRAGS in tls_record_info + * MAX_SKB_FRAGS + 1 in SKB head and frags. + */ + sg_in_max_elements = 2 * MAX_SKB_FRAGS + 1; + + if (!payload_len) + return skb; + + sg_in = kmalloc_array(sg_in_max_elements, sizeof(*sg_in), GFP_ATOMIC); + if (!sg_in) + goto free_orig; + + sg_init_table(sg_in, sg_in_max_elements); + sg_init_table(sg_out, ARRAY_SIZE(sg_out)); + + if (fill_sg_in(sg_in, skb, ctx, &rcd_sn, &sync_size, &resync_sgs)) { + /* bypass packets before kernel TLS socket option was set */ + if (sync_size < 0 && payload_len <= -sync_size) + nskb = skb_get(skb); + goto put_sg; + } + + nskb = tls_enc_skb(tls_ctx, sg_out, sg_in, skb, sync_size, rcd_sn); + +put_sg: + while (resync_sgs) + put_page(sg_page(&sg_in[--resync_sgs])); + kfree(sg_in); +free_orig: + kfree_skb(skb); + return nskb; +} + +struct sk_buff *tls_validate_xmit_skb(struct sock *sk, + struct net_device *dev, + struct sk_buff *skb) +{ + if (dev == tls_get_ctx(sk)->netdev) + return skb; + + return tls_sw_fallback(sk, skb); +} + +int tls_sw_fallback_init(struct sock *sk, + struct tls_offload_context *offload_ctx, + struct tls_crypto_info *crypto_info) +{ + const u8 *key; + int rc; + + offload_ctx->aead_send = + crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(offload_ctx->aead_send)) { + rc = PTR_ERR(offload_ctx->aead_send); + pr_err_ratelimited("crypto_alloc_aead failed rc=%d\n", rc); + offload_ctx->aead_send = NULL; + goto err_out; + } + + key = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->key; + + rc = crypto_aead_setkey(offload_ctx->aead_send, key, + TLS_CIPHER_AES_GCM_128_KEY_SIZE); + if (rc) + goto free_aead; + + rc = crypto_aead_setauthsize(offload_ctx->aead_send, + TLS_CIPHER_AES_GCM_128_TAG_SIZE); + if (rc) + goto free_aead; + + return 0; +free_aead: + crypto_free_aead(offload_ctx->aead_send); +err_out: + return rc; +} diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 20cd93be6236e..301f224304698 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -51,12 +51,12 @@ enum { TLSV6, TLS_NUM_PROTS, }; - enum { TLS_BASE, - TLS_SW_TX, - TLS_SW_RX, - TLS_SW_RXTX, + TLS_SW, +#ifdef CONFIG_TLS_DEVICE + TLS_HW, +#endif TLS_HW_RECORD, TLS_NUM_CONFIG, }; @@ -65,14 +65,14 @@ static struct proto *saved_tcpv6_prot; static DEFINE_MUTEX(tcpv6_prot_mutex); static LIST_HEAD(device_list); static DEFINE_MUTEX(device_mutex); -static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG]; +static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static struct proto_ops tls_sw_proto_ops; -static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx) +static void update_sk_prot(struct sock *sk, struct tls_context *ctx) { int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; - sk->sk_prot = &tls_prots[ip_ver][ctx->conf]; + sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf]; } int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -254,7 +254,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) lock_sock(sk); sk_proto_close = ctx->sk_proto_close; - if (ctx->conf == TLS_BASE || ctx->conf == TLS_HW_RECORD) { + if ((ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD) || + (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE)) { free_ctx = true; goto skip_tx_cleanup; } @@ -275,15 +276,26 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) } } - kfree(ctx->tx.rec_seq); - kfree(ctx->tx.iv); - kfree(ctx->rx.rec_seq); - kfree(ctx->rx.iv); + /* We need these for tls_sw_fallback handling of other packets */ + if (ctx->tx_conf == TLS_SW) { + kfree(ctx->tx.rec_seq); + kfree(ctx->tx.iv); + tls_sw_free_resources_tx(sk); + } - if (ctx->conf == TLS_SW_TX || - ctx->conf == TLS_SW_RX || - ctx->conf == TLS_SW_RXTX) { - tls_sw_free_resources(sk); + if (ctx->rx_conf == TLS_SW) { + kfree(ctx->rx.rec_seq); + kfree(ctx->rx.iv); + tls_sw_free_resources_rx(sk); + } + +#ifdef CONFIG_TLS_DEVICE + if (ctx->tx_conf != TLS_HW) { +#else + { +#endif + kfree(ctx); + ctx = NULL; } skip_tx_cleanup: @@ -446,25 +458,29 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, goto err_crypto_info; } - /* currently SW is default, we will have ethtool in future */ if (tx) { - rc = tls_set_sw_offload(sk, ctx, 1); - if (ctx->conf == TLS_SW_RX) - conf = TLS_SW_RXTX; - else - conf = TLS_SW_TX; +#ifdef CONFIG_TLS_DEVICE + rc = tls_set_device_offload(sk, ctx); + conf = TLS_HW; + if (rc) { +#else + { +#endif + rc = tls_set_sw_offload(sk, ctx, 1); + conf = TLS_SW; + } } else { rc = tls_set_sw_offload(sk, ctx, 0); - if (ctx->conf == TLS_SW_TX) - conf = TLS_SW_RXTX; - else - conf = TLS_SW_RX; + conf = TLS_SW; } if (rc) goto err_crypto_info; - ctx->conf = conf; + if (tx) + ctx->tx_conf = conf; + else + ctx->rx_conf = conf; update_sk_prot(sk, ctx); if (tx) { ctx->sk_write_space = sk->sk_write_space; @@ -540,7 +556,8 @@ static int tls_hw_prot(struct sock *sk) ctx->hash = sk->sk_prot->hash; ctx->unhash = sk->sk_prot->unhash; ctx->sk_proto_close = sk->sk_prot->close; - ctx->conf = TLS_HW_RECORD; + ctx->rx_conf = TLS_HW_RECORD; + ctx->tx_conf = TLS_HW_RECORD; update_sk_prot(sk, ctx); rc = 1; break; @@ -584,29 +601,40 @@ static int tls_hw_hash(struct sock *sk) return err; } -static void build_protos(struct proto *prot, struct proto *base) +static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], + struct proto *base) { - prot[TLS_BASE] = *base; - prot[TLS_BASE].setsockopt = tls_setsockopt; - prot[TLS_BASE].getsockopt = tls_getsockopt; - prot[TLS_BASE].close = tls_sk_proto_close; - - prot[TLS_SW_TX] = prot[TLS_BASE]; - prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; - prot[TLS_SW_TX].sendpage = tls_sw_sendpage; - - prot[TLS_SW_RX] = prot[TLS_BASE]; - prot[TLS_SW_RX].recvmsg = tls_sw_recvmsg; - prot[TLS_SW_RX].close = tls_sk_proto_close; - - prot[TLS_SW_RXTX] = prot[TLS_SW_TX]; - prot[TLS_SW_RXTX].recvmsg = tls_sw_recvmsg; - prot[TLS_SW_RXTX].close = tls_sk_proto_close; - - prot[TLS_HW_RECORD] = *base; - prot[TLS_HW_RECORD].hash = tls_hw_hash; - prot[TLS_HW_RECORD].unhash = tls_hw_unhash; - prot[TLS_HW_RECORD].close = tls_sk_proto_close; + prot[TLS_BASE][TLS_BASE] = *base; + prot[TLS_BASE][TLS_BASE].setsockopt = tls_setsockopt; + prot[TLS_BASE][TLS_BASE].getsockopt = tls_getsockopt; + prot[TLS_BASE][TLS_BASE].close = tls_sk_proto_close; + + prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; + prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg; + prot[TLS_SW][TLS_BASE].sendpage = tls_sw_sendpage; + + prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE]; + prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg; + prot[TLS_BASE][TLS_SW].close = tls_sk_proto_close; + + prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE]; + prot[TLS_SW][TLS_SW].recvmsg = tls_sw_recvmsg; + prot[TLS_SW][TLS_SW].close = tls_sk_proto_close; + +#ifdef CONFIG_TLS_DEVICE + prot[TLS_HW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; + prot[TLS_HW][TLS_BASE].sendmsg = tls_device_sendmsg; + prot[TLS_HW][TLS_BASE].sendpage = tls_device_sendpage; + + prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW]; + prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg; + prot[TLS_HW][TLS_SW].sendpage = tls_device_sendpage; +#endif + + prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base; + prot[TLS_HW_RECORD][TLS_HW_RECORD].hash = tls_hw_hash; + prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash = tls_hw_unhash; + prot[TLS_HW_RECORD][TLS_HW_RECORD].close = tls_sk_proto_close; } static int tls_init(struct sock *sk) @@ -637,7 +665,7 @@ static int tls_init(struct sock *sk) ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close; - /* Build IPv6 TLS whenever the address of tcpv6_prot changes */ + /* Build IPv6 TLS whenever the address of tcpv6 _prot changes */ if (ip_ver == TLSV6 && unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { mutex_lock(&tcpv6_prot_mutex); @@ -648,7 +676,8 @@ static int tls_init(struct sock *sk) mutex_unlock(&tcpv6_prot_mutex); } - ctx->conf = TLS_BASE; + ctx->tx_conf = TLS_BASE; + ctx->rx_conf = TLS_BASE; update_sk_prot(sk, ctx); out: return rc; @@ -686,6 +715,9 @@ static int __init tls_register(void) tls_sw_proto_ops.poll = tls_sw_poll; tls_sw_proto_ops.splice_read = tls_sw_splice_read; +#ifdef CONFIG_TLS_DEVICE + tls_device_init(); +#endif tcp_register_ulp(&tcp_tls_ulp_ops); return 0; @@ -694,6 +726,9 @@ static int __init tls_register(void) static void __exit tls_unregister(void) { tcp_unregister_ulp(&tcp_tls_ulp_ops); +#ifdef CONFIG_TLS_DEVICE + tls_device_cleanup(); +#endif } module_init(tls_register); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index e1c93ce74e0fe..8ca57d01b18f6 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -52,7 +52,7 @@ static int tls_do_decryption(struct sock *sk, gfp_t flags) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct strp_msg *rxm = strp_msg(skb); struct aead_request *aead_req; @@ -122,7 +122,7 @@ out: static void trim_both_sgl(struct sock *sk, int target_size) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); trim_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem, @@ -141,7 +141,7 @@ static void trim_both_sgl(struct sock *sk, int target_size) static int alloc_encrypted_sg(struct sock *sk, int len) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); int rc = 0; rc = sk_alloc_sg(sk, len, @@ -155,7 +155,7 @@ static int alloc_encrypted_sg(struct sock *sk, int len) static int alloc_plaintext_sg(struct sock *sk, int len) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); int rc = 0; rc = sk_alloc_sg(sk, len, ctx->sg_plaintext_data, 0, @@ -181,7 +181,7 @@ static void free_sg(struct sock *sk, struct scatterlist *sg, static void tls_free_both_sg(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); free_sg(sk, ctx->sg_encrypted_data, &ctx->sg_encrypted_num_elem, &ctx->sg_encrypted_size); @@ -191,7 +191,7 @@ static void tls_free_both_sg(struct sock *sk) } static int tls_do_encryption(struct tls_context *tls_ctx, - struct tls_sw_context *ctx, size_t data_len, + struct tls_sw_context_tx *ctx, size_t data_len, gfp_t flags) { unsigned int req_size = sizeof(struct aead_request) + @@ -227,7 +227,7 @@ static int tls_push_record(struct sock *sk, int flags, unsigned char record_type) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); int rc; sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1); @@ -339,7 +339,7 @@ static int memcopy_from_iter(struct sock *sk, struct iov_iter *from, int bytes) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct scatterlist *sg = ctx->sg_plaintext_data; int copy, i, rc = 0; @@ -367,7 +367,7 @@ out: int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); int ret = 0; int required_size; long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); @@ -522,7 +522,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); int ret = 0; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); bool eor; @@ -636,7 +636,7 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, long timeo, int *err) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct sk_buff *skb; DEFINE_WAIT_FUNC(wait, woken_wake_function); @@ -674,7 +674,7 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + MAX_IV_SIZE]; struct scatterlist sgin_arr[MAX_SKB_FRAGS + 2]; struct scatterlist *sgin = &sgin_arr[0]; @@ -692,8 +692,7 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, if (!sgout) { nsg = skb_cow_data(skb, 0, &unused) + 1; sgin = kmalloc_array(nsg, sizeof(*sgin), sk->sk_allocation); - if (!sgout) - sgout = sgin; + sgout = sgin; } sg_init_table(sgin, nsg); @@ -723,7 +722,7 @@ static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb, unsigned int len) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct strp_msg *rxm = strp_msg(skb); if (len < rxm->full_len) { @@ -736,7 +735,7 @@ static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb, /* Finished with message */ ctx->recv_pkt = NULL; kfree_skb(skb); - strp_unpause(&ctx->strp); + __strp_unpause(&ctx->strp); return true; } @@ -749,7 +748,7 @@ int tls_sw_recvmsg(struct sock *sk, int *addr_len) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); unsigned char control; struct strp_msg *rxm; struct sk_buff *skb; @@ -869,7 +868,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, size_t len, unsigned int flags) { struct tls_context *tls_ctx = tls_get_ctx(sock->sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct strp_msg *rxm = NULL; struct sock *sk = sock->sk; struct sk_buff *skb; @@ -922,7 +921,7 @@ unsigned int tls_sw_poll(struct file *file, struct socket *sock, unsigned int ret; struct sock *sk = sock->sk; struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); /* Grab POLLOUT and POLLHUP from the underlying socket */ ret = ctx->sk_poll(file, sock, wait); @@ -938,7 +937,7 @@ unsigned int tls_sw_poll(struct file *file, struct socket *sock, static int tls_read_size(struct strparser *strp, struct sk_buff *skb) { struct tls_context *tls_ctx = tls_get_ctx(strp->sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); char header[tls_ctx->rx.prepend_size]; struct strp_msg *rxm = strp_msg(skb); size_t cipher_overhead; @@ -987,7 +986,7 @@ read_failure: static void tls_queue(struct strparser *strp, struct sk_buff *skb) { struct tls_context *tls_ctx = tls_get_ctx(strp->sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct strp_msg *rxm; rxm = strp_msg(skb); @@ -1003,18 +1002,28 @@ static void tls_queue(struct strparser *strp, struct sk_buff *skb) static void tls_data_ready(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); strp_data_ready(&ctx->strp); } -void tls_sw_free_resources(struct sock *sk) +void tls_sw_free_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); if (ctx->aead_send) crypto_free_aead(ctx->aead_send); + tls_free_both_sg(sk); + + kfree(ctx); +} + +void tls_sw_free_resources_rx(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + if (ctx->aead_recv) { if (ctx->recv_pkt) { kfree_skb(ctx->recv_pkt); @@ -1030,10 +1039,7 @@ void tls_sw_free_resources(struct sock *sk) lock_sock(sk); } - tls_free_both_sg(sk); - kfree(ctx); - kfree(tls_ctx); } int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) @@ -1041,7 +1047,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; struct tls_crypto_info *crypto_info; struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; - struct tls_sw_context *sw_ctx; + struct tls_sw_context_tx *sw_ctx_tx = NULL; + struct tls_sw_context_rx *sw_ctx_rx = NULL; struct cipher_context *cctx; struct crypto_aead **aead; struct strp_callbacks cb; @@ -1054,27 +1061,32 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto out; } - if (!ctx->priv_ctx) { - sw_ctx = kzalloc(sizeof(*sw_ctx), GFP_KERNEL); - if (!sw_ctx) { + if (tx) { + sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL); + if (!sw_ctx_tx) { rc = -ENOMEM; goto out; } - crypto_init_wait(&sw_ctx->async_wait); + crypto_init_wait(&sw_ctx_tx->async_wait); + ctx->priv_ctx_tx = sw_ctx_tx; } else { - sw_ctx = ctx->priv_ctx; + sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL); + if (!sw_ctx_rx) { + rc = -ENOMEM; + goto out; + } + crypto_init_wait(&sw_ctx_rx->async_wait); + ctx->priv_ctx_rx = sw_ctx_rx; } - ctx->priv_ctx = (struct tls_offload_context *)sw_ctx; - if (tx) { crypto_info = &ctx->crypto_send; cctx = &ctx->tx; - aead = &sw_ctx->aead_send; + aead = &sw_ctx_tx->aead_send; } else { crypto_info = &ctx->crypto_recv; cctx = &ctx->rx; - aead = &sw_ctx->aead_recv; + aead = &sw_ctx_rx->aead_recv; } switch (crypto_info->cipher_type) { @@ -1121,22 +1133,24 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) } memcpy(cctx->rec_seq, rec_seq, rec_seq_size); - if (tx) { - sg_init_table(sw_ctx->sg_encrypted_data, - ARRAY_SIZE(sw_ctx->sg_encrypted_data)); - sg_init_table(sw_ctx->sg_plaintext_data, - ARRAY_SIZE(sw_ctx->sg_plaintext_data)); - - sg_init_table(sw_ctx->sg_aead_in, 2); - sg_set_buf(&sw_ctx->sg_aead_in[0], sw_ctx->aad_space, - sizeof(sw_ctx->aad_space)); - sg_unmark_end(&sw_ctx->sg_aead_in[1]); - sg_chain(sw_ctx->sg_aead_in, 2, sw_ctx->sg_plaintext_data); - sg_init_table(sw_ctx->sg_aead_out, 2); - sg_set_buf(&sw_ctx->sg_aead_out[0], sw_ctx->aad_space, - sizeof(sw_ctx->aad_space)); - sg_unmark_end(&sw_ctx->sg_aead_out[1]); - sg_chain(sw_ctx->sg_aead_out, 2, sw_ctx->sg_encrypted_data); + if (sw_ctx_tx) { + sg_init_table(sw_ctx_tx->sg_encrypted_data, + ARRAY_SIZE(sw_ctx_tx->sg_encrypted_data)); + sg_init_table(sw_ctx_tx->sg_plaintext_data, + ARRAY_SIZE(sw_ctx_tx->sg_plaintext_data)); + + sg_init_table(sw_ctx_tx->sg_aead_in, 2); + sg_set_buf(&sw_ctx_tx->sg_aead_in[0], sw_ctx_tx->aad_space, + sizeof(sw_ctx_tx->aad_space)); + sg_unmark_end(&sw_ctx_tx->sg_aead_in[1]); + sg_chain(sw_ctx_tx->sg_aead_in, 2, + sw_ctx_tx->sg_plaintext_data); + sg_init_table(sw_ctx_tx->sg_aead_out, 2); + sg_set_buf(&sw_ctx_tx->sg_aead_out[0], sw_ctx_tx->aad_space, + sizeof(sw_ctx_tx->aad_space)); + sg_unmark_end(&sw_ctx_tx->sg_aead_out[1]); + sg_chain(sw_ctx_tx->sg_aead_out, 2, + sw_ctx_tx->sg_encrypted_data); } if (!*aead) { @@ -1161,22 +1175,22 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (rc) goto free_aead; - if (!tx) { + if (sw_ctx_rx) { /* Set up strparser */ memset(&cb, 0, sizeof(cb)); cb.rcv_msg = tls_queue; cb.parse_msg = tls_read_size; - strp_init(&sw_ctx->strp, sk, &cb); + strp_init(&sw_ctx_rx->strp, sk, &cb); write_lock_bh(&sk->sk_callback_lock); - sw_ctx->saved_data_ready = sk->sk_data_ready; + sw_ctx_rx->saved_data_ready = sk->sk_data_ready; sk->sk_data_ready = tls_data_ready; write_unlock_bh(&sk->sk_callback_lock); - sw_ctx->sk_poll = sk->sk_socket->ops->poll; + sw_ctx_rx->sk_poll = sk->sk_socket->ops->poll; - strp_check_rcv(&sw_ctx->strp); + strp_check_rcv(&sw_ctx_rx->strp); } goto out; @@ -1188,11 +1202,16 @@ free_rec_seq: kfree(cctx->rec_seq); cctx->rec_seq = NULL; free_iv: - kfree(ctx->tx.iv); - ctx->tx.iv = NULL; + kfree(cctx->iv); + cctx->iv = NULL; free_priv: - kfree(ctx->priv_ctx); - ctx->priv_ctx = NULL; + if (tx) { + kfree(ctx->priv_ctx_tx); + ctx->priv_ctx_tx = NULL; + } else { + kfree(ctx->priv_ctx_rx); + ctx->priv_ctx_rx = NULL; + } out: return rc; } diff --git a/net/wireless/core.c b/net/wireless/core.c index c0fd8a85e7f72..5fe35aafdd9cf 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -725,6 +725,10 @@ int wiphy_register(struct wiphy *wiphy) (!rdev->ops->set_pmk || !rdev->ops->del_pmk))) return -EINVAL; + if (WARN_ON(!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_FW_ROAM) && + rdev->ops->update_connect_params)) + return -EINVAL; + if (wiphy->addresses) memcpy(wiphy->perm_addr, wiphy->addresses[0].addr, ETH_ALEN); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 7c5135a92d764..07514ca011b2f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4,6 +4,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation */ #include <linux/if.h> @@ -423,6 +424,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_PMK] = { .type = NLA_BINARY, .len = PMK_MAX_LEN }, [NL80211_ATTR_SCHED_SCAN_MULTI] = { .type = NLA_FLAG }, [NL80211_ATTR_EXTERNAL_AUTH_SUPPORT] = { .type = NLA_FLAG }, + + [NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 }, + [NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 }, + [NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 }, }; /* policy for the key attributes */ @@ -645,7 +650,43 @@ static inline void *nl80211hdr_put(struct sk_buff *skb, u32 portid, u32 seq, return genlmsg_put(skb, portid, seq, &nl80211_fam, flags, cmd); } -static int nl80211_msg_put_channel(struct sk_buff *msg, +static int nl80211_msg_put_wmm_rules(struct sk_buff *msg, + const struct ieee80211_reg_rule *rule) +{ + int j; + struct nlattr *nl_wmm_rules = + nla_nest_start(msg, NL80211_FREQUENCY_ATTR_WMM); + + if (!nl_wmm_rules) + goto nla_put_failure; + + for (j = 0; j < IEEE80211_NUM_ACS; j++) { + struct nlattr *nl_wmm_rule = nla_nest_start(msg, j); + + if (!nl_wmm_rule) + goto nla_put_failure; + + if (nla_put_u16(msg, NL80211_WMMR_CW_MIN, + rule->wmm_rule->client[j].cw_min) || + nla_put_u16(msg, NL80211_WMMR_CW_MAX, + rule->wmm_rule->client[j].cw_max) || + nla_put_u8(msg, NL80211_WMMR_AIFSN, + rule->wmm_rule->client[j].aifsn) || + nla_put_u8(msg, NL80211_WMMR_TXOP, + rule->wmm_rule->client[j].cot)) + goto nla_put_failure; + + nla_nest_end(msg, nl_wmm_rule); + } + nla_nest_end(msg, nl_wmm_rules); + + return 0; + +nla_put_failure: + return -ENOBUFS; +} + +static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, struct ieee80211_channel *chan, bool large) { @@ -721,12 +762,55 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, DBM_TO_MBM(chan->max_power))) goto nla_put_failure; + if (large) { + const struct ieee80211_reg_rule *rule = + freq_reg_info(wiphy, chan->center_freq); + + if (!IS_ERR(rule) && rule->wmm_rule) { + if (nl80211_msg_put_wmm_rules(msg, rule)) + goto nla_put_failure; + } + } + return 0; nla_put_failure: return -ENOBUFS; } +static bool nl80211_put_txq_stats(struct sk_buff *msg, + struct cfg80211_txq_stats *txqstats, + int attrtype) +{ + struct nlattr *txqattr; + +#define PUT_TXQVAL_U32(attr, memb) do { \ + if (txqstats->filled & BIT(NL80211_TXQ_STATS_ ## attr) && \ + nla_put_u32(msg, NL80211_TXQ_STATS_ ## attr, txqstats->memb)) \ + return false; \ + } while (0) + + txqattr = nla_nest_start(msg, attrtype); + if (!txqattr) + return false; + + PUT_TXQVAL_U32(BACKLOG_BYTES, backlog_bytes); + PUT_TXQVAL_U32(BACKLOG_PACKETS, backlog_packets); + PUT_TXQVAL_U32(FLOWS, flows); + PUT_TXQVAL_U32(DROPS, drops); + PUT_TXQVAL_U32(ECN_MARKS, ecn_marks); + PUT_TXQVAL_U32(OVERLIMIT, overlimit); + PUT_TXQVAL_U32(OVERMEMORY, overmemory); + PUT_TXQVAL_U32(COLLISIONS, collisions); + PUT_TXQVAL_U32(TX_BYTES, tx_bytes); + PUT_TXQVAL_U32(TX_PACKETS, tx_packets); + PUT_TXQVAL_U32(MAX_FLOWS, max_flows); + nla_nest_end(msg, txqattr); + +#undef PUT_TXQVAL_U32 + return true; +} + /* netlink command implementations */ struct key_parse { @@ -1631,7 +1715,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, chan = &sband->channels[i]; if (nl80211_msg_put_channel( - msg, chan, + msg, &rdev->wiphy, chan, state->split)) goto nla_put_failure; @@ -1926,6 +2010,28 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.nan_supported_bands)) goto nla_put_failure; + if (wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_TXQS)) { + struct cfg80211_txq_stats txqstats = {}; + int res; + + res = rdev_get_txq_stats(rdev, NULL, &txqstats); + if (!res && + !nl80211_put_txq_stats(msg, &txqstats, + NL80211_ATTR_TXQ_STATS)) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_ATTR_TXQ_LIMIT, + rdev->wiphy.txq_limit)) + goto nla_put_failure; + if (nla_put_u32(msg, NL80211_ATTR_TXQ_MEMORY_LIMIT, + rdev->wiphy.txq_memory_limit)) + goto nla_put_failure; + if (nla_put_u32(msg, NL80211_ATTR_TXQ_QUANTUM, + rdev->wiphy.txq_quantum)) + goto nla_put_failure; + } + /* done */ state->split_start = 0; break; @@ -2303,6 +2409,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) u8 retry_short = 0, retry_long = 0; u32 frag_threshold = 0, rts_threshold = 0; u8 coverage_class = 0; + u32 txq_limit = 0, txq_memory_limit = 0, txq_quantum = 0; ASSERT_RTNL(); @@ -2509,10 +2616,38 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) changed |= WIPHY_PARAM_DYN_ACK; } + if (info->attrs[NL80211_ATTR_TXQ_LIMIT]) { + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_TXQS)) + return -EOPNOTSUPP; + txq_limit = nla_get_u32( + info->attrs[NL80211_ATTR_TXQ_LIMIT]); + changed |= WIPHY_PARAM_TXQ_LIMIT; + } + + if (info->attrs[NL80211_ATTR_TXQ_MEMORY_LIMIT]) { + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_TXQS)) + return -EOPNOTSUPP; + txq_memory_limit = nla_get_u32( + info->attrs[NL80211_ATTR_TXQ_MEMORY_LIMIT]); + changed |= WIPHY_PARAM_TXQ_MEMORY_LIMIT; + } + + if (info->attrs[NL80211_ATTR_TXQ_QUANTUM]) { + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_TXQS)) + return -EOPNOTSUPP; + txq_quantum = nla_get_u32( + info->attrs[NL80211_ATTR_TXQ_QUANTUM]); + changed |= WIPHY_PARAM_TXQ_QUANTUM; + } + if (changed) { u8 old_retry_short, old_retry_long; u32 old_frag_threshold, old_rts_threshold; u8 old_coverage_class; + u32 old_txq_limit, old_txq_memory_limit, old_txq_quantum; if (!rdev->ops->set_wiphy_params) return -EOPNOTSUPP; @@ -2522,6 +2657,9 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) old_frag_threshold = rdev->wiphy.frag_threshold; old_rts_threshold = rdev->wiphy.rts_threshold; old_coverage_class = rdev->wiphy.coverage_class; + old_txq_limit = rdev->wiphy.txq_limit; + old_txq_memory_limit = rdev->wiphy.txq_memory_limit; + old_txq_quantum = rdev->wiphy.txq_quantum; if (changed & WIPHY_PARAM_RETRY_SHORT) rdev->wiphy.retry_short = retry_short; @@ -2533,6 +2671,12 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev->wiphy.rts_threshold = rts_threshold; if (changed & WIPHY_PARAM_COVERAGE_CLASS) rdev->wiphy.coverage_class = coverage_class; + if (changed & WIPHY_PARAM_TXQ_LIMIT) + rdev->wiphy.txq_limit = txq_limit; + if (changed & WIPHY_PARAM_TXQ_MEMORY_LIMIT) + rdev->wiphy.txq_memory_limit = txq_memory_limit; + if (changed & WIPHY_PARAM_TXQ_QUANTUM) + rdev->wiphy.txq_quantum = txq_quantum; result = rdev_set_wiphy_params(rdev, changed); if (result) { @@ -2541,6 +2685,9 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rdev->wiphy.frag_threshold = old_frag_threshold; rdev->wiphy.rts_threshold = old_rts_threshold; rdev->wiphy.coverage_class = old_coverage_class; + rdev->wiphy.txq_limit = old_txq_limit; + rdev->wiphy.txq_memory_limit = old_txq_memory_limit; + rdev->wiphy.txq_quantum = old_txq_quantum; return result; } } @@ -2662,6 +2809,16 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag } wdev_unlock(wdev); + if (rdev->ops->get_txq_stats) { + struct cfg80211_txq_stats txqstats = {}; + int ret = rdev_get_txq_stats(rdev, wdev, &txqstats); + + if (ret == 0 && + !nl80211_put_txq_stats(msg, &txqstats, + NL80211_ATTR_TXQ_STATS)) + goto nla_put_failure; + } + genlmsg_end(msg, hdr); return 0; @@ -4494,11 +4651,14 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO_U64(BEACON_RX, rx_beacon); PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8); PUT_SINFO(ACK_SIGNAL, ack_signal, u8); + if (wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT)) + PUT_SINFO(DATA_ACK_SIGNAL_AVG, avg_ack_signal, s8); #undef PUT_SINFO #undef PUT_SINFO_U64 - if (sinfo->filled & BIT(NL80211_STA_INFO_TID_STATS)) { + if (sinfo->pertid) { struct nlattr *tidsattr; int tid; @@ -4532,6 +4692,12 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_TIDVAL_U64(TX_MSDU_FAILED, tx_msdu_failed); #undef PUT_TIDVAL_U64 + if ((tidstats->filled & + BIT(NL80211_TID_STATS_TXQ_STATS)) && + !nl80211_put_txq_stats(msg, &tidstats->txq_stats, + NL80211_TID_STATS_TXQ_STATS)) + goto nla_put_failure; + nla_nest_end(msg, tidattr); } @@ -4545,10 +4711,12 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, sinfo->assoc_req_ies)) goto nla_put_failure; + cfg80211_sinfo_release_content(sinfo); genlmsg_end(msg, hdr); return 0; nla_put_failure: + cfg80211_sinfo_release_content(sinfo); genlmsg_cancel(msg, hdr); return -EMSGSIZE; } @@ -4630,8 +4798,10 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) return err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) + if (!msg) { + cfg80211_sinfo_release_content(&sinfo); return -ENOMEM; + } if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, info->snd_portid, info->snd_seq, 0, @@ -7930,7 +8100,15 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) wdev_lock(wdev); spin_lock_bh(&rdev->bss_lock); - cfg80211_bss_expire(rdev); + + /* + * dump_scan will be called multiple times to break up the scan results + * into multiple messages. It is unlikely that any more bss-es will be + * expired after the first call, so only call only call this on the + * first dump_scan invocation. + */ + if (start == 0) + cfg80211_bss_expire(rdev); cb->seq = rdev->bss_generation; @@ -8336,6 +8514,10 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) const u8 *bssid, *ssid; int err, ssid_len = 0; + if (dev->ieee80211_ptr->conn_owner_nlportid && + dev->ieee80211_ptr->conn_owner_nlportid != info->snd_portid) + return -EPERM; + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; @@ -8458,6 +8640,10 @@ static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) u16 reason_code; bool local_state_change; + if (dev->ieee80211_ptr->conn_owner_nlportid && + dev->ieee80211_ptr->conn_owner_nlportid != info->snd_portid) + return -EPERM; + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; @@ -8505,6 +8691,10 @@ static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) u16 reason_code; bool local_state_change; + if (dev->ieee80211_ptr->conn_owner_nlportid && + dev->ieee80211_ptr->conn_owner_nlportid != info->snd_portid) + return -EPERM; + if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; @@ -9251,6 +9441,8 @@ static int nl80211_update_connect_params(struct sk_buff *skb, struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; + bool fils_sk_offload; + u32 auth_type; u32 changed = 0; int ret; @@ -9265,6 +9457,56 @@ static int nl80211_update_connect_params(struct sk_buff *skb, changed |= UPDATE_ASSOC_IES; } + fils_sk_offload = wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_FILS_SK_OFFLOAD); + + /* + * when driver supports fils-sk offload all attributes must be + * provided. So the else covers "fils-sk-not-all" and + * "no-fils-sk-any". + */ + if (fils_sk_offload && + info->attrs[NL80211_ATTR_FILS_ERP_USERNAME] && + info->attrs[NL80211_ATTR_FILS_ERP_REALM] && + info->attrs[NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM] && + info->attrs[NL80211_ATTR_FILS_ERP_RRK]) { + connect.fils_erp_username = + nla_data(info->attrs[NL80211_ATTR_FILS_ERP_USERNAME]); + connect.fils_erp_username_len = + nla_len(info->attrs[NL80211_ATTR_FILS_ERP_USERNAME]); + connect.fils_erp_realm = + nla_data(info->attrs[NL80211_ATTR_FILS_ERP_REALM]); + connect.fils_erp_realm_len = + nla_len(info->attrs[NL80211_ATTR_FILS_ERP_REALM]); + connect.fils_erp_next_seq_num = + nla_get_u16( + info->attrs[NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM]); + connect.fils_erp_rrk = + nla_data(info->attrs[NL80211_ATTR_FILS_ERP_RRK]); + connect.fils_erp_rrk_len = + nla_len(info->attrs[NL80211_ATTR_FILS_ERP_RRK]); + changed |= UPDATE_FILS_ERP_INFO; + } else if (info->attrs[NL80211_ATTR_FILS_ERP_USERNAME] || + info->attrs[NL80211_ATTR_FILS_ERP_REALM] || + info->attrs[NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM] || + info->attrs[NL80211_ATTR_FILS_ERP_RRK]) { + return -EINVAL; + } + + if (info->attrs[NL80211_ATTR_AUTH_TYPE]) { + auth_type = nla_get_u32(info->attrs[NL80211_ATTR_AUTH_TYPE]); + if (!nl80211_valid_auth_type(rdev, auth_type, + NL80211_CMD_CONNECT)) + return -EINVAL; + + if (auth_type == NL80211_AUTHTYPE_FILS_SK && + fils_sk_offload && !(changed & UPDATE_FILS_ERP_INFO)) + return -EINVAL; + + connect.auth_type = auth_type; + changed |= UPDATE_AUTH_TYPE; + } + wdev_lock(dev->ieee80211_ptr); if (!wdev->current_bss) ret = -ENOLINK; @@ -9282,6 +9524,10 @@ static int nl80211_disconnect(struct sk_buff *skb, struct genl_info *info) u16 reason; int ret; + if (dev->ieee80211_ptr->conn_owner_nlportid && + dev->ieee80211_ptr->conn_owner_nlportid != info->snd_portid) + return -EPERM; + if (!info->attrs[NL80211_ATTR_REASON_CODE]) reason = WLAN_REASON_DEAUTH_LEAVING; else @@ -14028,8 +14274,8 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, void *hdr; msg = nlmsg_new(100 + cr->req_ie_len + cr->resp_ie_len + - cr->fils_kek_len + cr->pmk_len + - (cr->pmkid ? WLAN_PMKID_LEN : 0), gfp); + cr->fils.kek_len + cr->fils.pmk_len + + (cr->fils.pmkid ? WLAN_PMKID_LEN : 0), gfp); if (!msg) return; @@ -14055,17 +14301,17 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, (cr->resp_ie && nla_put(msg, NL80211_ATTR_RESP_IE, cr->resp_ie_len, cr->resp_ie)) || - (cr->update_erp_next_seq_num && + (cr->fils.update_erp_next_seq_num && nla_put_u16(msg, NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM, - cr->fils_erp_next_seq_num)) || + cr->fils.erp_next_seq_num)) || (cr->status == WLAN_STATUS_SUCCESS && - ((cr->fils_kek && - nla_put(msg, NL80211_ATTR_FILS_KEK, cr->fils_kek_len, - cr->fils_kek)) || - (cr->pmk && - nla_put(msg, NL80211_ATTR_PMK, cr->pmk_len, cr->pmk)) || - (cr->pmkid && - nla_put(msg, NL80211_ATTR_PMKID, WLAN_PMKID_LEN, cr->pmkid))))) + ((cr->fils.kek && + nla_put(msg, NL80211_ATTR_FILS_KEK, cr->fils.kek_len, + cr->fils.kek)) || + (cr->fils.pmk && + nla_put(msg, NL80211_ATTR_PMK, cr->fils.pmk_len, cr->fils.pmk)) || + (cr->fils.pmkid && + nla_put(msg, NL80211_ATTR_PMKID, WLAN_PMKID_LEN, cr->fils.pmkid))))) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -14086,7 +14332,9 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, void *hdr; const u8 *bssid = info->bss ? info->bss->bssid : info->bssid; - msg = nlmsg_new(100 + info->req_ie_len + info->resp_ie_len, gfp); + msg = nlmsg_new(100 + info->req_ie_len + info->resp_ie_len + + info->fils.kek_len + info->fils.pmk_len + + (info->fils.pmkid ? WLAN_PMKID_LEN : 0), gfp); if (!msg) return; @@ -14104,7 +14352,17 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, info->req_ie)) || (info->resp_ie && nla_put(msg, NL80211_ATTR_RESP_IE, info->resp_ie_len, - info->resp_ie))) + info->resp_ie)) || + (info->fils.update_erp_next_seq_num && + nla_put_u16(msg, NL80211_ATTR_FILS_ERP_NEXT_SEQ_NUM, + info->fils.erp_next_seq_num)) || + (info->fils.kek && + nla_put(msg, NL80211_ATTR_FILS_KEK, info->fils.kek_len, + info->fils.kek)) || + (info->fils.pmk && + nla_put(msg, NL80211_ATTR_PMK, info->fils.pmk_len, info->fils.pmk)) || + (info->fils.pmkid && + nla_put(msg, NL80211_ATTR_PMKID, WLAN_PMKID_LEN, info->fils.pmkid))) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -14321,7 +14579,8 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy, nl_freq = nla_nest_start(msg, NL80211_ATTR_FREQ_BEFORE); if (!nl_freq) goto nla_put_failure; - if (nl80211_msg_put_channel(msg, channel_before, false)) + + if (nl80211_msg_put_channel(msg, wiphy, channel_before, false)) goto nla_put_failure; nla_nest_end(msg, nl_freq); @@ -14329,7 +14588,8 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy, nl_freq = nla_nest_start(msg, NL80211_ATTR_FREQ_AFTER); if (!nl_freq) goto nla_put_failure; - if (nl80211_msg_put_channel(msg, channel_after, false)) + + if (nl80211_msg_put_channel(msg, wiphy, channel_after, false)) goto nla_put_failure; nla_nest_end(msg, nl_freq); @@ -14456,8 +14716,10 @@ void cfg80211_del_sta_sinfo(struct net_device *dev, const u8 *mac_addr, trace_cfg80211_del_sta(dev, mac_addr); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); - if (!msg) + if (!msg) { + cfg80211_sinfo_release_content(sinfo); return; + } if (nl80211_send_station(msg, NL80211_CMD_DEL_STATION, 0, 0, 0, rdev, dev, mac_addr, sinfo) < 0) { diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 87479a53411bd..364f5d67f05b3 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -586,6 +586,18 @@ rdev_set_multicast_to_unicast(struct cfg80211_registered_device *rdev, return ret; } +static inline int +rdev_get_txq_stats(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct cfg80211_txq_stats *txqstats) +{ + int ret; + trace_rdev_get_txq_stats(&rdev->wiphy, wdev); + ret = rdev->ops->get_txq_stats(&rdev->wiphy, wdev, txqstats); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + static inline void rdev_rfkill_poll(struct cfg80211_registered_device *rdev) { trace_rdev_rfkill_poll(&rdev->wiphy); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 5fcec5c94eb72..bbe6298e4bb9e 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1656,7 +1656,7 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator) case NL80211_REGDOM_SET_BY_DRIVER: return "driver"; case NL80211_REGDOM_SET_BY_COUNTRY_IE: - return "country IE"; + return "country element"; default: WARN_ON(1); return "bug"; @@ -2622,7 +2622,7 @@ reg_process_hint_country_ie(struct wiphy *wiphy, * This doesn't happen yet, not sure we * ever want to support it for this case. */ - WARN_ONCE(1, "Unexpected intersection for country IEs"); + WARN_ONCE(1, "Unexpected intersection for country elements"); return REG_REQ_IGNORE; } @@ -2772,6 +2772,21 @@ out_free: reg_free_request(reg_request); } +static void notify_self_managed_wiphys(struct regulatory_request *request) +{ + struct cfg80211_registered_device *rdev; + struct wiphy *wiphy; + + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + wiphy = &rdev->wiphy; + if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED && + request->initiator == NL80211_REGDOM_SET_BY_USER && + request->user_reg_hint_type == + NL80211_USER_REG_HINT_CELL_BASE) + reg_call_notifier(wiphy, request); + } +} + static bool reg_only_self_managed_wiphys(void) { struct cfg80211_registered_device *rdev; @@ -2823,6 +2838,7 @@ static void reg_process_pending_hints(void) spin_unlock(®_requests_lock); + notify_self_managed_wiphys(reg_request); if (reg_only_self_managed_wiphys()) { reg_free_request(reg_request); return; @@ -3387,7 +3403,7 @@ bool reg_supported_dfs_region(enum nl80211_dfs_regions dfs_region) case NL80211_DFS_JP: return true; default: - pr_debug("Ignoring uknown DFS master region: %d\n", dfs_region); + pr_debug("Ignoring unknown DFS master region: %d\n", dfs_region); return false; } } @@ -3702,17 +3718,26 @@ EXPORT_SYMBOL(regulatory_set_wiphy_regd_sync_rtnl); void wiphy_regulatory_register(struct wiphy *wiphy) { - struct regulatory_request *lr; + struct regulatory_request *lr = get_last_request(); - /* self-managed devices ignore external hints */ - if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) + /* self-managed devices ignore beacon hints and country IE */ + if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) { wiphy->regulatory_flags |= REGULATORY_DISABLE_BEACON_HINTS | REGULATORY_COUNTRY_IE_IGNORE; + /* + * The last request may have been received before this + * registration call. Call the driver notifier if + * initiator is USER and user type is CELL_BASE. + */ + if (lr->initiator == NL80211_REGDOM_SET_BY_USER && + lr->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE) + reg_call_notifier(wiphy, lr); + } + if (!reg_dev_ignore_cell_hint(wiphy)) reg_num_devs_support_basehint++; - lr = get_last_request(); wiphy_update_regulatory(wiphy, lr->initiator); wiphy_all_share_dfs_chan_state(wiphy); } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 5df6b33db7868..d536b07582f8c 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -803,8 +803,8 @@ void cfg80211_connect_done(struct net_device *dev, ev = kzalloc(sizeof(*ev) + (params->bssid ? ETH_ALEN : 0) + params->req_ie_len + params->resp_ie_len + - params->fils_kek_len + params->pmk_len + - (params->pmkid ? WLAN_PMKID_LEN : 0), gfp); + params->fils.kek_len + params->fils.pmk_len + + (params->fils.pmkid ? WLAN_PMKID_LEN : 0), gfp); if (!ev) { cfg80211_put_bss(wdev->wiphy, params->bss); return; @@ -831,27 +831,29 @@ void cfg80211_connect_done(struct net_device *dev, params->resp_ie_len); next += params->resp_ie_len; } - if (params->fils_kek_len) { - ev->cr.fils_kek = next; - ev->cr.fils_kek_len = params->fils_kek_len; - memcpy((void *)ev->cr.fils_kek, params->fils_kek, - params->fils_kek_len); - next += params->fils_kek_len; + if (params->fils.kek_len) { + ev->cr.fils.kek = next; + ev->cr.fils.kek_len = params->fils.kek_len; + memcpy((void *)ev->cr.fils.kek, params->fils.kek, + params->fils.kek_len); + next += params->fils.kek_len; } - if (params->pmk_len) { - ev->cr.pmk = next; - ev->cr.pmk_len = params->pmk_len; - memcpy((void *)ev->cr.pmk, params->pmk, params->pmk_len); - next += params->pmk_len; + if (params->fils.pmk_len) { + ev->cr.fils.pmk = next; + ev->cr.fils.pmk_len = params->fils.pmk_len; + memcpy((void *)ev->cr.fils.pmk, params->fils.pmk, + params->fils.pmk_len); + next += params->fils.pmk_len; } - if (params->pmkid) { - ev->cr.pmkid = next; - memcpy((void *)ev->cr.pmkid, params->pmkid, WLAN_PMKID_LEN); + if (params->fils.pmkid) { + ev->cr.fils.pmkid = next; + memcpy((void *)ev->cr.fils.pmkid, params->fils.pmkid, + WLAN_PMKID_LEN); next += WLAN_PMKID_LEN; } - ev->cr.update_erp_next_seq_num = params->update_erp_next_seq_num; - if (params->update_erp_next_seq_num) - ev->cr.fils_erp_next_seq_num = params->fils_erp_next_seq_num; + ev->cr.fils.update_erp_next_seq_num = params->fils.update_erp_next_seq_num; + if (params->fils.update_erp_next_seq_num) + ev->cr.fils.erp_next_seq_num = params->fils.erp_next_seq_num; if (params->bss) cfg80211_hold_bss(bss_from_pub(params->bss)); ev->cr.bss = params->bss; @@ -930,6 +932,7 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; + u8 *next; if (!info->bss) { info->bss = cfg80211_get_bss(wdev->wiphy, info->channel, @@ -942,19 +945,52 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, if (WARN_ON(!info->bss)) return; - ev = kzalloc(sizeof(*ev) + info->req_ie_len + info->resp_ie_len, gfp); + ev = kzalloc(sizeof(*ev) + info->req_ie_len + info->resp_ie_len + + info->fils.kek_len + info->fils.pmk_len + + (info->fils.pmkid ? WLAN_PMKID_LEN : 0), gfp); if (!ev) { cfg80211_put_bss(wdev->wiphy, info->bss); return; } ev->type = EVENT_ROAMED; - ev->rm.req_ie = ((u8 *)ev) + sizeof(*ev); - ev->rm.req_ie_len = info->req_ie_len; - memcpy((void *)ev->rm.req_ie, info->req_ie, info->req_ie_len); - ev->rm.resp_ie = ((u8 *)ev) + sizeof(*ev) + info->req_ie_len; - ev->rm.resp_ie_len = info->resp_ie_len; - memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); + next = ((u8 *)ev) + sizeof(*ev); + if (info->req_ie_len) { + ev->rm.req_ie = next; + ev->rm.req_ie_len = info->req_ie_len; + memcpy((void *)ev->rm.req_ie, info->req_ie, info->req_ie_len); + next += info->req_ie_len; + } + if (info->resp_ie_len) { + ev->rm.resp_ie = next; + ev->rm.resp_ie_len = info->resp_ie_len; + memcpy((void *)ev->rm.resp_ie, info->resp_ie, + info->resp_ie_len); + next += info->resp_ie_len; + } + if (info->fils.kek_len) { + ev->rm.fils.kek = next; + ev->rm.fils.kek_len = info->fils.kek_len; + memcpy((void *)ev->rm.fils.kek, info->fils.kek, + info->fils.kek_len); + next += info->fils.kek_len; + } + if (info->fils.pmk_len) { + ev->rm.fils.pmk = next; + ev->rm.fils.pmk_len = info->fils.pmk_len; + memcpy((void *)ev->rm.fils.pmk, info->fils.pmk, + info->fils.pmk_len); + next += info->fils.pmk_len; + } + if (info->fils.pmkid) { + ev->rm.fils.pmkid = next; + memcpy((void *)ev->rm.fils.pmkid, info->fils.pmkid, + WLAN_PMKID_LEN); + next += WLAN_PMKID_LEN; + } + ev->rm.fils.update_erp_next_seq_num = info->fils.update_erp_next_seq_num; + if (info->fils.update_erp_next_seq_num) + ev->rm.fils.erp_next_seq_num = info->fils.erp_next_seq_num; ev->rm.bss = info->bss; spin_lock_irqsave(&wdev->event_lock, flags); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 55fb279a51969..2b417a2fe63ff 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -3243,6 +3243,20 @@ TRACE_EVENT(rdev_set_multicast_to_unicast, WIPHY_PR_ARG, NETDEV_PR_ARG, BOOL_TO_STR(__entry->enabled)) ); + +TRACE_EVENT(rdev_get_txq_stats, + TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev), + TP_ARGS(wiphy, wdev), + TP_STRUCT__entry( + WIPHY_ENTRY + WDEV_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + WDEV_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT, WIPHY_PR_ARG, WDEV_PR_ARG) +); #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/wireless/util.c b/net/wireless/util.c index d112e9a893645..b5bb1c3099146 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1787,6 +1787,17 @@ bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, return false; } +int cfg80211_sinfo_alloc_tid_stats(struct station_info *sinfo, gfp_t gfp) +{ + sinfo->pertid = kcalloc(sizeof(*(sinfo->pertid)), + IEEE80211_NUM_TIDS + 1, gfp); + if (!sinfo->pertid) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL(cfg80211_sinfo_alloc_tid_stats); + /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ /* Ethernet-II snap header (RFC1042 for most EtherTypes) */ const unsigned char rfc1042_header[] __aligned(2) = diff --git a/net/xdp/Kconfig b/net/xdp/Kconfig new file mode 100644 index 0000000000000..90e4a7152854f --- /dev/null +++ b/net/xdp/Kconfig @@ -0,0 +1,7 @@ +config XDP_SOCKETS + bool "XDP sockets" + depends on BPF_SYSCALL + default n + help + XDP sockets allows a channel between XDP programs and + userspace applications. diff --git a/net/xdp/Makefile b/net/xdp/Makefile new file mode 100644 index 0000000000000..04f073146256e --- /dev/null +++ b/net/xdp/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o xsk_queue.o diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c new file mode 100644 index 0000000000000..7eb4948a38d23 --- /dev/null +++ b/net/xdp/xdp_umem.c @@ -0,0 +1,361 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XDP user-space packet buffer + * Copyright(c) 2018 Intel Corporation. + */ + +#include <linux/init.h> +#include <linux/sched/mm.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> +#include <linux/uaccess.h> +#include <linux/slab.h> +#include <linux/bpf.h> +#include <linux/mm.h> + +#include "xdp_umem.h" +#include "xsk_queue.h" + +#define XDP_UMEM_MIN_CHUNK_SIZE 2048 + +void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) +{ + unsigned long flags; + + spin_lock_irqsave(&umem->xsk_list_lock, flags); + list_add_rcu(&xs->list, &umem->xsk_list); + spin_unlock_irqrestore(&umem->xsk_list_lock, flags); +} + +void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) +{ + unsigned long flags; + + if (xs->dev) { + spin_lock_irqsave(&umem->xsk_list_lock, flags); + list_del_rcu(&xs->list); + spin_unlock_irqrestore(&umem->xsk_list_lock, flags); + + if (umem->zc) + synchronize_net(); + } +} + +int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, + u32 queue_id, u16 flags) +{ + bool force_zc, force_copy; + struct netdev_bpf bpf; + int err; + + force_zc = flags & XDP_ZEROCOPY; + force_copy = flags & XDP_COPY; + + if (force_zc && force_copy) + return -EINVAL; + + if (force_copy) + return 0; + + dev_hold(dev); + + if (dev->netdev_ops->ndo_bpf && dev->netdev_ops->ndo_xsk_async_xmit) { + bpf.command = XDP_QUERY_XSK_UMEM; + + rtnl_lock(); + err = dev->netdev_ops->ndo_bpf(dev, &bpf); + rtnl_unlock(); + + if (err) { + dev_put(dev); + return force_zc ? -ENOTSUPP : 0; + } + + bpf.command = XDP_SETUP_XSK_UMEM; + bpf.xsk.umem = umem; + bpf.xsk.queue_id = queue_id; + + rtnl_lock(); + err = dev->netdev_ops->ndo_bpf(dev, &bpf); + rtnl_unlock(); + + if (err) { + dev_put(dev); + return force_zc ? err : 0; /* fail or fallback */ + } + + umem->dev = dev; + umem->queue_id = queue_id; + umem->zc = true; + return 0; + } + + dev_put(dev); + return force_zc ? -ENOTSUPP : 0; /* fail or fallback */ +} + +static void xdp_umem_clear_dev(struct xdp_umem *umem) +{ + struct netdev_bpf bpf; + int err; + + if (umem->dev) { + bpf.command = XDP_SETUP_XSK_UMEM; + bpf.xsk.umem = NULL; + bpf.xsk.queue_id = umem->queue_id; + + rtnl_lock(); + err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf); + rtnl_unlock(); + + if (err) + WARN(1, "failed to disable umem!\n"); + + dev_put(umem->dev); + umem->dev = NULL; + } +} + +static void xdp_umem_unpin_pages(struct xdp_umem *umem) +{ + unsigned int i; + + for (i = 0; i < umem->npgs; i++) { + struct page *page = umem->pgs[i]; + + set_page_dirty_lock(page); + put_page(page); + } + + kfree(umem->pgs); + umem->pgs = NULL; +} + +static void xdp_umem_unaccount_pages(struct xdp_umem *umem) +{ + atomic_long_sub(umem->npgs, &umem->user->locked_vm); + free_uid(umem->user); +} + +static void xdp_umem_release(struct xdp_umem *umem) +{ + struct task_struct *task; + struct mm_struct *mm; + + xdp_umem_clear_dev(umem); + + if (umem->fq) { + xskq_destroy(umem->fq); + umem->fq = NULL; + } + + if (umem->cq) { + xskq_destroy(umem->cq); + umem->cq = NULL; + } + + xdp_umem_unpin_pages(umem); + + task = get_pid_task(umem->pid, PIDTYPE_PID); + put_pid(umem->pid); + if (!task) + goto out; + mm = get_task_mm(task); + put_task_struct(task); + if (!mm) + goto out; + + mmput(mm); + kfree(umem->pages); + umem->pages = NULL; + + xdp_umem_unaccount_pages(umem); +out: + kfree(umem); +} + +static void xdp_umem_release_deferred(struct work_struct *work) +{ + struct xdp_umem *umem = container_of(work, struct xdp_umem, work); + + xdp_umem_release(umem); +} + +void xdp_get_umem(struct xdp_umem *umem) +{ + refcount_inc(&umem->users); +} + +void xdp_put_umem(struct xdp_umem *umem) +{ + if (!umem) + return; + + if (refcount_dec_and_test(&umem->users)) { + INIT_WORK(&umem->work, xdp_umem_release_deferred); + schedule_work(&umem->work); + } +} + +static int xdp_umem_pin_pages(struct xdp_umem *umem) +{ + unsigned int gup_flags = FOLL_WRITE; + long npgs; + int err; + + umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL); + if (!umem->pgs) + return -ENOMEM; + + down_write(¤t->mm->mmap_sem); + npgs = get_user_pages(umem->address, umem->npgs, + gup_flags, &umem->pgs[0], NULL); + up_write(¤t->mm->mmap_sem); + + if (npgs != umem->npgs) { + if (npgs >= 0) { + umem->npgs = npgs; + err = -ENOMEM; + goto out_pin; + } + err = npgs; + goto out_pgs; + } + return 0; + +out_pin: + xdp_umem_unpin_pages(umem); +out_pgs: + kfree(umem->pgs); + umem->pgs = NULL; + return err; +} + +static int xdp_umem_account_pages(struct xdp_umem *umem) +{ + unsigned long lock_limit, new_npgs, old_npgs; + + if (capable(CAP_IPC_LOCK)) + return 0; + + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + umem->user = get_uid(current_user()); + + do { + old_npgs = atomic_long_read(&umem->user->locked_vm); + new_npgs = old_npgs + umem->npgs; + if (new_npgs > lock_limit) { + free_uid(umem->user); + umem->user = NULL; + return -ENOBUFS; + } + } while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs, + new_npgs) != old_npgs); + return 0; +} + +static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) +{ + u32 chunk_size = mr->chunk_size, headroom = mr->headroom; + unsigned int chunks, chunks_per_page; + u64 addr = mr->addr, size = mr->len; + int size_chk, err, i; + + if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { + /* Strictly speaking we could support this, if: + * - huge pages, or* + * - using an IOMMU, or + * - making sure the memory area is consecutive + * but for now, we simply say "computer says no". + */ + return -EINVAL; + } + + if (!is_power_of_2(chunk_size)) + return -EINVAL; + + if (!PAGE_ALIGNED(addr)) { + /* Memory area has to be page size aligned. For + * simplicity, this might change. + */ + return -EINVAL; + } + + if ((addr + size) < addr) + return -EINVAL; + + chunks = (unsigned int)div_u64(size, chunk_size); + if (chunks == 0) + return -EINVAL; + + chunks_per_page = PAGE_SIZE / chunk_size; + if (chunks < chunks_per_page || chunks % chunks_per_page) + return -EINVAL; + + headroom = ALIGN(headroom, 64); + + size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM; + if (size_chk < 0) + return -EINVAL; + + umem->pid = get_task_pid(current, PIDTYPE_PID); + umem->address = (unsigned long)addr; + umem->props.chunk_mask = ~((u64)chunk_size - 1); + umem->props.size = size; + umem->headroom = headroom; + umem->chunk_size_nohr = chunk_size - headroom; + umem->npgs = size / PAGE_SIZE; + umem->pgs = NULL; + umem->user = NULL; + INIT_LIST_HEAD(&umem->xsk_list); + spin_lock_init(&umem->xsk_list_lock); + + refcount_set(&umem->users, 1); + + err = xdp_umem_account_pages(umem); + if (err) + goto out; + + err = xdp_umem_pin_pages(umem); + if (err) + goto out_account; + + umem->pages = kcalloc(umem->npgs, sizeof(*umem->pages), GFP_KERNEL); + if (!umem->pages) { + err = -ENOMEM; + goto out_account; + } + + for (i = 0; i < umem->npgs; i++) + umem->pages[i].addr = page_address(umem->pgs[i]); + + return 0; + +out_account: + xdp_umem_unaccount_pages(umem); +out: + put_pid(umem->pid); + return err; +} + +struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) +{ + struct xdp_umem *umem; + int err; + + umem = kzalloc(sizeof(*umem), GFP_KERNEL); + if (!umem) + return ERR_PTR(-ENOMEM); + + err = xdp_umem_reg(umem, mr); + if (err) { + kfree(umem); + return ERR_PTR(err); + } + + return umem; +} + +bool xdp_umem_validate_queues(struct xdp_umem *umem) +{ + return umem->fq && umem->cq; +} diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h new file mode 100644 index 0000000000000..f11560334f884 --- /dev/null +++ b/net/xdp/xdp_umem.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* XDP user-space packet buffer + * Copyright(c) 2018 Intel Corporation. + */ + +#ifndef XDP_UMEM_H_ +#define XDP_UMEM_H_ + +#include <net/xdp_sock.h> + +static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) +{ + return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1)); +} + +static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) +{ + return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1)); +} + +int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, + u32 queue_id, u16 flags); +bool xdp_umem_validate_queues(struct xdp_umem *umem); +void xdp_get_umem(struct xdp_umem *umem); +void xdp_put_umem(struct xdp_umem *umem); +void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs); +void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs); +struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr); + +#endif /* XDP_UMEM_H_ */ diff --git a/net/xdp/xdp_umem_props.h b/net/xdp/xdp_umem_props.h new file mode 100644 index 0000000000000..40eab10dfc49d --- /dev/null +++ b/net/xdp/xdp_umem_props.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* XDP user-space packet buffer + * Copyright(c) 2018 Intel Corporation. + */ + +#ifndef XDP_UMEM_PROPS_H_ +#define XDP_UMEM_PROPS_H_ + +struct xdp_umem_props { + u64 chunk_mask; + u64 size; +}; + +#endif /* XDP_UMEM_PROPS_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c new file mode 100644 index 0000000000000..c6ed2454f7ce5 --- /dev/null +++ b/net/xdp/xsk.c @@ -0,0 +1,788 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XDP sockets + * + * AF_XDP sockets allows a channel between XDP programs and userspace + * applications. + * Copyright(c) 2018 Intel Corporation. + * + * Author(s): Björn Töpel <bjorn.topel@intel.com> + * Magnus Karlsson <magnus.karlsson@intel.com> + */ + +#define pr_fmt(fmt) "AF_XDP: %s: " fmt, __func__ + +#include <linux/if_xdp.h> +#include <linux/init.h> +#include <linux/sched/mm.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> +#include <linux/socket.h> +#include <linux/file.h> +#include <linux/uaccess.h> +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/rculist.h> +#include <net/xdp_sock.h> +#include <net/xdp.h> + +#include "xsk_queue.h" +#include "xdp_umem.h" + +#define TX_BATCH_SIZE 16 + +static struct xdp_sock *xdp_sk(struct sock *sk) +{ + return (struct xdp_sock *)sk; +} + +bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) +{ + return READ_ONCE(xs->rx) && READ_ONCE(xs->umem) && + READ_ONCE(xs->umem->fq); +} + +u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) +{ + return xskq_peek_addr(umem->fq, addr); +} +EXPORT_SYMBOL(xsk_umem_peek_addr); + +void xsk_umem_discard_addr(struct xdp_umem *umem) +{ + xskq_discard_addr(umem->fq); +} +EXPORT_SYMBOL(xsk_umem_discard_addr); + +static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) +{ + void *buffer; + u64 addr; + int err; + + if (!xskq_peek_addr(xs->umem->fq, &addr) || + len > xs->umem->chunk_size_nohr) { + xs->rx_dropped++; + return -ENOSPC; + } + + addr += xs->umem->headroom; + + buffer = xdp_umem_get_data(xs->umem, addr); + memcpy(buffer, xdp->data, len); + err = xskq_produce_batch_desc(xs->rx, addr, len); + if (!err) { + xskq_discard_addr(xs->umem->fq); + xdp_return_buff(xdp); + return 0; + } + + xs->rx_dropped++; + return err; +} + +static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) +{ + int err = xskq_produce_batch_desc(xs->rx, (u64)xdp->handle, len); + + if (err) { + xdp_return_buff(xdp); + xs->rx_dropped++; + } + + return err; +} + +int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +{ + u32 len; + + if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) + return -EINVAL; + + len = xdp->data_end - xdp->data; + + return (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) ? + __xsk_rcv_zc(xs, xdp, len) : __xsk_rcv(xs, xdp, len); +} + +void xsk_flush(struct xdp_sock *xs) +{ + xskq_produce_flush_desc(xs->rx); + xs->sk.sk_data_ready(&xs->sk); +} + +int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +{ + u32 len = xdp->data_end - xdp->data; + void *buffer; + u64 addr; + int err; + + if (!xskq_peek_addr(xs->umem->fq, &addr) || + len > xs->umem->chunk_size_nohr) { + xs->rx_dropped++; + return -ENOSPC; + } + + addr += xs->umem->headroom; + + buffer = xdp_umem_get_data(xs->umem, addr); + memcpy(buffer, xdp->data, len); + err = xskq_produce_batch_desc(xs->rx, addr, len); + if (!err) { + xskq_discard_addr(xs->umem->fq); + xsk_flush(xs); + return 0; + } + + xs->rx_dropped++; + return err; +} + +void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +{ + xskq_produce_flush_addr_n(umem->cq, nb_entries); +} +EXPORT_SYMBOL(xsk_umem_complete_tx); + +void xsk_umem_consume_tx_done(struct xdp_umem *umem) +{ + struct xdp_sock *xs; + + rcu_read_lock(); + list_for_each_entry_rcu(xs, &umem->xsk_list, list) { + xs->sk.sk_write_space(&xs->sk); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(xsk_umem_consume_tx_done); + +bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len) +{ + struct xdp_desc desc; + struct xdp_sock *xs; + + rcu_read_lock(); + list_for_each_entry_rcu(xs, &umem->xsk_list, list) { + if (!xskq_peek_desc(xs->tx, &desc)) + continue; + + if (xskq_produce_addr_lazy(umem->cq, desc.addr)) + goto out; + + *dma = xdp_umem_get_dma(umem, desc.addr); + *len = desc.len; + + xskq_discard_desc(xs->tx); + rcu_read_unlock(); + return true; + } + +out: + rcu_read_unlock(); + return false; +} +EXPORT_SYMBOL(xsk_umem_consume_tx); + +static int xsk_zc_xmit(struct sock *sk) +{ + struct xdp_sock *xs = xdp_sk(sk); + struct net_device *dev = xs->dev; + + return dev->netdev_ops->ndo_xsk_async_xmit(dev, xs->queue_id); +} + +static void xsk_destruct_skb(struct sk_buff *skb) +{ + u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg; + struct xdp_sock *xs = xdp_sk(skb->sk); + + WARN_ON_ONCE(xskq_produce_addr(xs->umem->cq, addr)); + + sock_wfree(skb); +} + +static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, + size_t total_len) +{ + u32 max_batch = TX_BATCH_SIZE; + struct xdp_sock *xs = xdp_sk(sk); + bool sent_frame = false; + struct xdp_desc desc; + struct sk_buff *skb; + int err = 0; + + if (unlikely(!xs->tx)) + return -ENOBUFS; + + mutex_lock(&xs->mutex); + + while (xskq_peek_desc(xs->tx, &desc)) { + char *buffer; + u64 addr; + u32 len; + + if (max_batch-- == 0) { + err = -EAGAIN; + goto out; + } + + if (xskq_reserve_addr(xs->umem->cq)) { + err = -EAGAIN; + goto out; + } + + len = desc.len; + if (unlikely(len > xs->dev->mtu)) { + err = -EMSGSIZE; + goto out; + } + + if (xs->queue_id >= xs->dev->real_num_tx_queues) { + err = -ENXIO; + goto out; + } + + skb = sock_alloc_send_skb(sk, len, 1, &err); + if (unlikely(!skb)) { + err = -EAGAIN; + goto out; + } + + skb_put(skb, len); + addr = desc.addr; + buffer = xdp_umem_get_data(xs->umem, addr); + err = skb_store_bits(skb, 0, buffer, len); + if (unlikely(err)) { + kfree_skb(skb); + goto out; + } + + skb->dev = xs->dev; + skb->priority = sk->sk_priority; + skb->mark = sk->sk_mark; + skb_shinfo(skb)->destructor_arg = (void *)(long)addr; + skb->destructor = xsk_destruct_skb; + + err = dev_direct_xmit(skb, xs->queue_id); + /* Ignore NET_XMIT_CN as packet might have been sent */ + if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) { + err = -EAGAIN; + /* SKB consumed by dev_direct_xmit() */ + goto out; + } + + sent_frame = true; + xskq_discard_desc(xs->tx); + } + +out: + if (sent_frame) + sk->sk_write_space(sk); + + mutex_unlock(&xs->mutex); + return err; +} + +static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) +{ + bool need_wait = !(m->msg_flags & MSG_DONTWAIT); + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + + if (unlikely(!xs->dev)) + return -ENXIO; + if (unlikely(!(xs->dev->flags & IFF_UP))) + return -ENETDOWN; + if (need_wait) + return -EOPNOTSUPP; + + return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len); +} + +static __poll_t xsk_poll_mask(struct socket *sock, __poll_t events) +{ + __poll_t mask = datagram_poll_mask(sock, events); + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + + if (xs->rx && !xskq_empty_desc(xs->rx)) + mask |= POLLIN | POLLRDNORM; + if (xs->tx && !xskq_full_desc(xs->tx)) + mask |= POLLOUT | POLLWRNORM; + + return mask; +} + +static int xsk_init_queue(u32 entries, struct xsk_queue **queue, + bool umem_queue) +{ + struct xsk_queue *q; + + if (entries == 0 || *queue || !is_power_of_2(entries)) + return -EINVAL; + + q = xskq_create(entries, umem_queue); + if (!q) + return -ENOMEM; + + /* Make sure queue is ready before it can be seen by others */ + smp_wmb(); + *queue = q; + return 0; +} + +static int xsk_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + struct net *net; + + if (!sk) + return 0; + + net = sock_net(sk); + + local_bh_disable(); + sock_prot_inuse_add(net, sk->sk_prot, -1); + local_bh_enable(); + + if (xs->dev) { + /* Wait for driver to stop using the xdp socket. */ + synchronize_net(); + dev_put(xs->dev); + xs->dev = NULL; + } + + sock_orphan(sk); + sock->sk = NULL; + + sk_refcnt_debug_release(sk); + sock_put(sk); + + return 0; +} + +static struct socket *xsk_lookup_xsk_from_fd(int fd) +{ + struct socket *sock; + int err; + + sock = sockfd_lookup(fd, &err); + if (!sock) + return ERR_PTR(-ENOTSOCK); + + if (sock->sk->sk_family != PF_XDP) { + sockfd_put(sock); + return ERR_PTR(-ENOPROTOOPT); + } + + return sock; +} + +static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +{ + struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr; + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + struct net_device *dev; + u32 flags, qid; + int err = 0; + + if (addr_len < sizeof(struct sockaddr_xdp)) + return -EINVAL; + if (sxdp->sxdp_family != AF_XDP) + return -EINVAL; + + mutex_lock(&xs->mutex); + if (xs->dev) { + err = -EBUSY; + goto out_release; + } + + dev = dev_get_by_index(sock_net(sk), sxdp->sxdp_ifindex); + if (!dev) { + err = -ENODEV; + goto out_release; + } + + if (!xs->rx && !xs->tx) { + err = -EINVAL; + goto out_unlock; + } + + qid = sxdp->sxdp_queue_id; + + if ((xs->rx && qid >= dev->real_num_rx_queues) || + (xs->tx && qid >= dev->real_num_tx_queues)) { + err = -EINVAL; + goto out_unlock; + } + + flags = sxdp->sxdp_flags; + + if (flags & XDP_SHARED_UMEM) { + struct xdp_sock *umem_xs; + struct socket *sock; + + if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY)) { + /* Cannot specify flags for shared sockets. */ + err = -EINVAL; + goto out_unlock; + } + + if (xs->umem) { + /* We have already our own. */ + err = -EINVAL; + goto out_unlock; + } + + sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd); + if (IS_ERR(sock)) { + err = PTR_ERR(sock); + goto out_unlock; + } + + umem_xs = xdp_sk(sock->sk); + if (!umem_xs->umem) { + /* No umem to inherit. */ + err = -EBADF; + sockfd_put(sock); + goto out_unlock; + } else if (umem_xs->dev != dev || umem_xs->queue_id != qid) { + err = -EINVAL; + sockfd_put(sock); + goto out_unlock; + } + + xdp_get_umem(umem_xs->umem); + xs->umem = umem_xs->umem; + sockfd_put(sock); + } else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) { + err = -EINVAL; + goto out_unlock; + } else { + /* This xsk has its own umem. */ + xskq_set_umem(xs->umem->fq, &xs->umem->props); + xskq_set_umem(xs->umem->cq, &xs->umem->props); + + err = xdp_umem_assign_dev(xs->umem, dev, qid, flags); + if (err) + goto out_unlock; + } + + xs->dev = dev; + xs->zc = xs->umem->zc; + xs->queue_id = qid; + xskq_set_umem(xs->rx, &xs->umem->props); + xskq_set_umem(xs->tx, &xs->umem->props); + xdp_add_sk_umem(xs->umem, xs); + +out_unlock: + if (err) + dev_put(dev); +out_release: + mutex_unlock(&xs->mutex); + return err; +} + +static int xsk_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + int err; + + if (level != SOL_XDP) + return -ENOPROTOOPT; + + switch (optname) { + case XDP_RX_RING: + case XDP_TX_RING: + { + struct xsk_queue **q; + int entries; + + if (optlen < sizeof(entries)) + return -EINVAL; + if (copy_from_user(&entries, optval, sizeof(entries))) + return -EFAULT; + + mutex_lock(&xs->mutex); + q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx; + err = xsk_init_queue(entries, q, false); + mutex_unlock(&xs->mutex); + return err; + } + case XDP_UMEM_REG: + { + struct xdp_umem_reg mr; + struct xdp_umem *umem; + + if (copy_from_user(&mr, optval, sizeof(mr))) + return -EFAULT; + + mutex_lock(&xs->mutex); + if (xs->umem) { + mutex_unlock(&xs->mutex); + return -EBUSY; + } + + umem = xdp_umem_create(&mr); + if (IS_ERR(umem)) { + mutex_unlock(&xs->mutex); + return PTR_ERR(umem); + } + + /* Make sure umem is ready before it can be seen by others */ + smp_wmb(); + xs->umem = umem; + mutex_unlock(&xs->mutex); + return 0; + } + case XDP_UMEM_FILL_RING: + case XDP_UMEM_COMPLETION_RING: + { + struct xsk_queue **q; + int entries; + + if (copy_from_user(&entries, optval, sizeof(entries))) + return -EFAULT; + + mutex_lock(&xs->mutex); + if (!xs->umem) { + mutex_unlock(&xs->mutex); + return -EINVAL; + } + + q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq : + &xs->umem->cq; + err = xsk_init_queue(entries, q, true); + mutex_unlock(&xs->mutex); + return err; + } + default: + break; + } + + return -ENOPROTOOPT; +} + +static int xsk_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + int len; + + if (level != SOL_XDP) + return -ENOPROTOOPT; + + if (get_user(len, optlen)) + return -EFAULT; + if (len < 0) + return -EINVAL; + + switch (optname) { + case XDP_STATISTICS: + { + struct xdp_statistics stats; + + if (len < sizeof(stats)) + return -EINVAL; + + mutex_lock(&xs->mutex); + stats.rx_dropped = xs->rx_dropped; + stats.rx_invalid_descs = xskq_nb_invalid_descs(xs->rx); + stats.tx_invalid_descs = xskq_nb_invalid_descs(xs->tx); + mutex_unlock(&xs->mutex); + + if (copy_to_user(optval, &stats, sizeof(stats))) + return -EFAULT; + if (put_user(sizeof(stats), optlen)) + return -EFAULT; + + return 0; + } + case XDP_MMAP_OFFSETS: + { + struct xdp_mmap_offsets off; + + if (len < sizeof(off)) + return -EINVAL; + + off.rx.producer = offsetof(struct xdp_rxtx_ring, ptrs.producer); + off.rx.consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer); + off.rx.desc = offsetof(struct xdp_rxtx_ring, desc); + off.tx.producer = offsetof(struct xdp_rxtx_ring, ptrs.producer); + off.tx.consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer); + off.tx.desc = offsetof(struct xdp_rxtx_ring, desc); + + off.fr.producer = offsetof(struct xdp_umem_ring, ptrs.producer); + off.fr.consumer = offsetof(struct xdp_umem_ring, ptrs.consumer); + off.fr.desc = offsetof(struct xdp_umem_ring, desc); + off.cr.producer = offsetof(struct xdp_umem_ring, ptrs.producer); + off.cr.consumer = offsetof(struct xdp_umem_ring, ptrs.consumer); + off.cr.desc = offsetof(struct xdp_umem_ring, desc); + + len = sizeof(off); + if (copy_to_user(optval, &off, len)) + return -EFAULT; + if (put_user(len, optlen)) + return -EFAULT; + + return 0; + } + default: + break; + } + + return -EOPNOTSUPP; +} + +static int xsk_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma) +{ + unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; + unsigned long size = vma->vm_end - vma->vm_start; + struct xdp_sock *xs = xdp_sk(sock->sk); + struct xsk_queue *q = NULL; + struct xdp_umem *umem; + unsigned long pfn; + struct page *qpg; + + if (offset == XDP_PGOFF_RX_RING) { + q = READ_ONCE(xs->rx); + } else if (offset == XDP_PGOFF_TX_RING) { + q = READ_ONCE(xs->tx); + } else { + umem = READ_ONCE(xs->umem); + if (!umem) + return -EINVAL; + + if (offset == XDP_UMEM_PGOFF_FILL_RING) + q = READ_ONCE(umem->fq); + else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) + q = READ_ONCE(umem->cq); + } + + if (!q) + return -EINVAL; + + qpg = virt_to_head_page(q->ring); + if (size > (PAGE_SIZE << compound_order(qpg))) + return -EINVAL; + + pfn = virt_to_phys(q->ring) >> PAGE_SHIFT; + return remap_pfn_range(vma, vma->vm_start, pfn, + size, vma->vm_page_prot); +} + +static struct proto xsk_proto = { + .name = "XDP", + .owner = THIS_MODULE, + .obj_size = sizeof(struct xdp_sock), +}; + +static const struct proto_ops xsk_proto_ops = { + .family = PF_XDP, + .owner = THIS_MODULE, + .release = xsk_release, + .bind = xsk_bind, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll_mask = xsk_poll_mask, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = xsk_setsockopt, + .getsockopt = xsk_getsockopt, + .sendmsg = xsk_sendmsg, + .recvmsg = sock_no_recvmsg, + .mmap = xsk_mmap, + .sendpage = sock_no_sendpage, +}; + +static void xsk_destruct(struct sock *sk) +{ + struct xdp_sock *xs = xdp_sk(sk); + + if (!sock_flag(sk, SOCK_DEAD)) + return; + + xskq_destroy(xs->rx); + xskq_destroy(xs->tx); + xdp_del_sk_umem(xs->umem, xs); + xdp_put_umem(xs->umem); + + sk_refcnt_debug_dec(sk); +} + +static int xsk_create(struct net *net, struct socket *sock, int protocol, + int kern) +{ + struct sock *sk; + struct xdp_sock *xs; + + if (!ns_capable(net->user_ns, CAP_NET_RAW)) + return -EPERM; + if (sock->type != SOCK_RAW) + return -ESOCKTNOSUPPORT; + + if (protocol) + return -EPROTONOSUPPORT; + + sock->state = SS_UNCONNECTED; + + sk = sk_alloc(net, PF_XDP, GFP_KERNEL, &xsk_proto, kern); + if (!sk) + return -ENOBUFS; + + sock->ops = &xsk_proto_ops; + + sock_init_data(sock, sk); + + sk->sk_family = PF_XDP; + + sk->sk_destruct = xsk_destruct; + sk_refcnt_debug_inc(sk); + + xs = xdp_sk(sk); + mutex_init(&xs->mutex); + + local_bh_disable(); + sock_prot_inuse_add(net, &xsk_proto, 1); + local_bh_enable(); + + return 0; +} + +static const struct net_proto_family xsk_family_ops = { + .family = PF_XDP, + .create = xsk_create, + .owner = THIS_MODULE, +}; + +static int __init xsk_init(void) +{ + int err; + + err = proto_register(&xsk_proto, 0 /* no slab */); + if (err) + goto out; + + err = sock_register(&xsk_family_ops); + if (err) + goto out_proto; + + return 0; + +out_proto: + proto_unregister(&xsk_proto); +out: + return err; +} + +fs_initcall(xsk_init); diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c new file mode 100644 index 0000000000000..6c32e92e98fcb --- /dev/null +++ b/net/xdp/xsk_queue.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XDP user-space ring structure + * Copyright(c) 2018 Intel Corporation. + */ + +#include <linux/slab.h> + +#include "xsk_queue.h" + +void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props) +{ + if (!q) + return; + + q->umem_props = *umem_props; +} + +static u32 xskq_umem_get_ring_size(struct xsk_queue *q) +{ + return sizeof(struct xdp_umem_ring) + q->nentries * sizeof(u64); +} + +static u32 xskq_rxtx_get_ring_size(struct xsk_queue *q) +{ + return sizeof(struct xdp_ring) + q->nentries * sizeof(struct xdp_desc); +} + +struct xsk_queue *xskq_create(u32 nentries, bool umem_queue) +{ + struct xsk_queue *q; + gfp_t gfp_flags; + size_t size; + + q = kzalloc(sizeof(*q), GFP_KERNEL); + if (!q) + return NULL; + + q->nentries = nentries; + q->ring_mask = nentries - 1; + + gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | + __GFP_COMP | __GFP_NORETRY; + size = umem_queue ? xskq_umem_get_ring_size(q) : + xskq_rxtx_get_ring_size(q); + + q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags, + get_order(size)); + if (!q->ring) { + kfree(q); + return NULL; + } + + return q; +} + +void xskq_destroy(struct xsk_queue *q) +{ + if (!q) + return; + + page_frag_free(q->ring); + kfree(q); +} diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h new file mode 100644 index 0000000000000..ef6a6f0ec9490 --- /dev/null +++ b/net/xdp/xsk_queue.h @@ -0,0 +1,265 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* XDP user-space ring structure + * Copyright(c) 2018 Intel Corporation. + */ + +#ifndef _LINUX_XSK_QUEUE_H +#define _LINUX_XSK_QUEUE_H + +#include <linux/types.h> +#include <linux/if_xdp.h> +#include <net/xdp_sock.h> + +#define RX_BATCH_SIZE 16 +#define LAZY_UPDATE_THRESHOLD 128 + +struct xdp_ring { + u32 producer ____cacheline_aligned_in_smp; + u32 consumer ____cacheline_aligned_in_smp; +}; + +/* Used for the RX and TX queues for packets */ +struct xdp_rxtx_ring { + struct xdp_ring ptrs; + struct xdp_desc desc[0] ____cacheline_aligned_in_smp; +}; + +/* Used for the fill and completion queues for buffers */ +struct xdp_umem_ring { + struct xdp_ring ptrs; + u64 desc[0] ____cacheline_aligned_in_smp; +}; + +struct xsk_queue { + struct xdp_umem_props umem_props; + u32 ring_mask; + u32 nentries; + u32 prod_head; + u32 prod_tail; + u32 cons_head; + u32 cons_tail; + struct xdp_ring *ring; + u64 invalid_descs; +}; + +/* Common functions operating for both RXTX and umem queues */ + +static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q) +{ + return q ? q->invalid_descs : 0; +} + +static inline u32 xskq_nb_avail(struct xsk_queue *q, u32 dcnt) +{ + u32 entries = q->prod_tail - q->cons_tail; + + if (entries == 0) { + /* Refresh the local pointer */ + q->prod_tail = READ_ONCE(q->ring->producer); + entries = q->prod_tail - q->cons_tail; + } + + return (entries > dcnt) ? dcnt : entries; +} + +static inline u32 xskq_nb_free_lazy(struct xsk_queue *q, u32 producer) +{ + return q->nentries - (producer - q->cons_tail); +} + +static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt) +{ + u32 free_entries = xskq_nb_free_lazy(q, producer); + + if (free_entries >= dcnt) + return free_entries; + + /* Refresh the local tail pointer */ + q->cons_tail = READ_ONCE(q->ring->consumer); + return q->nentries - (producer - q->cons_tail); +} + +/* UMEM queue */ + +static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr) +{ + if (addr >= q->umem_props.size) { + q->invalid_descs++; + return false; + } + + return true; +} + +static inline u64 *xskq_validate_addr(struct xsk_queue *q, u64 *addr) +{ + while (q->cons_tail != q->cons_head) { + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + unsigned int idx = q->cons_tail & q->ring_mask; + + *addr = READ_ONCE(ring->desc[idx]) & q->umem_props.chunk_mask; + if (xskq_is_valid_addr(q, *addr)) + return addr; + + q->cons_tail++; + } + + return NULL; +} + +static inline u64 *xskq_peek_addr(struct xsk_queue *q, u64 *addr) +{ + if (q->cons_tail == q->cons_head) { + WRITE_ONCE(q->ring->consumer, q->cons_tail); + q->cons_head = q->cons_tail + xskq_nb_avail(q, RX_BATCH_SIZE); + + /* Order consumer and data */ + smp_rmb(); + } + + return xskq_validate_addr(q, addr); +} + +static inline void xskq_discard_addr(struct xsk_queue *q) +{ + q->cons_tail++; +} + +static inline int xskq_produce_addr(struct xsk_queue *q, u64 addr) +{ + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + + if (xskq_nb_free(q, q->prod_tail, LAZY_UPDATE_THRESHOLD) == 0) + return -ENOSPC; + + ring->desc[q->prod_tail++ & q->ring_mask] = addr; + + /* Order producer and data */ + smp_wmb(); + + WRITE_ONCE(q->ring->producer, q->prod_tail); + return 0; +} + +static inline int xskq_produce_addr_lazy(struct xsk_queue *q, u64 addr) +{ + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + + if (xskq_nb_free(q, q->prod_head, LAZY_UPDATE_THRESHOLD) == 0) + return -ENOSPC; + + ring->desc[q->prod_head++ & q->ring_mask] = addr; + return 0; +} + +static inline void xskq_produce_flush_addr_n(struct xsk_queue *q, + u32 nb_entries) +{ + /* Order producer and data */ + smp_wmb(); + + q->prod_tail += nb_entries; + WRITE_ONCE(q->ring->producer, q->prod_tail); +} + +static inline int xskq_reserve_addr(struct xsk_queue *q) +{ + if (xskq_nb_free(q, q->prod_head, 1) == 0) + return -ENOSPC; + + q->prod_head++; + return 0; +} + +/* Rx/Tx queue */ + +static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d) +{ + if (!xskq_is_valid_addr(q, d->addr)) + return false; + + if (((d->addr + d->len) & q->umem_props.chunk_mask) != + (d->addr & q->umem_props.chunk_mask)) { + q->invalid_descs++; + return false; + } + + return true; +} + +static inline struct xdp_desc *xskq_validate_desc(struct xsk_queue *q, + struct xdp_desc *desc) +{ + while (q->cons_tail != q->cons_head) { + struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; + unsigned int idx = q->cons_tail & q->ring_mask; + + *desc = READ_ONCE(ring->desc[idx]); + if (xskq_is_valid_desc(q, desc)) + return desc; + + q->cons_tail++; + } + + return NULL; +} + +static inline struct xdp_desc *xskq_peek_desc(struct xsk_queue *q, + struct xdp_desc *desc) +{ + if (q->cons_tail == q->cons_head) { + WRITE_ONCE(q->ring->consumer, q->cons_tail); + q->cons_head = q->cons_tail + xskq_nb_avail(q, RX_BATCH_SIZE); + + /* Order consumer and data */ + smp_rmb(); + } + + return xskq_validate_desc(q, desc); +} + +static inline void xskq_discard_desc(struct xsk_queue *q) +{ + q->cons_tail++; +} + +static inline int xskq_produce_batch_desc(struct xsk_queue *q, + u64 addr, u32 len) +{ + struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; + unsigned int idx; + + if (xskq_nb_free(q, q->prod_head, 1) == 0) + return -ENOSPC; + + idx = (q->prod_head++) & q->ring_mask; + ring->desc[idx].addr = addr; + ring->desc[idx].len = len; + + return 0; +} + +static inline void xskq_produce_flush_desc(struct xsk_queue *q) +{ + /* Order producer and data */ + smp_wmb(); + + q->prod_tail = q->prod_head, + WRITE_ONCE(q->ring->producer, q->prod_tail); +} + +static inline bool xskq_full_desc(struct xsk_queue *q) +{ + return xskq_nb_avail(q, q->nentries) == q->nentries; +} + +static inline bool xskq_empty_desc(struct xsk_queue *q) +{ + return xskq_nb_free(q, q->prod_tail, 1) == q->nentries; +} + +void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props); +struct xsk_queue *xskq_create(u32 nentries, bool umem_queue); +void xskq_destroy(struct xsk_queue *q_ops); + +#endif /* _LINUX_XSK_QUEUE_H */ diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 6c177ae7a6d92..8308281f32530 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -42,6 +42,7 @@ static void xfrm_state_gc_task(struct work_struct *work); static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation); +static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); static HLIST_HEAD(xfrm_state_gc_list); @@ -451,7 +452,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) } xfrm_dev_state_free(x); security_xfrm_state_free(x); - kfree(x); + kmem_cache_free(xfrm_state_cache, x); } static void xfrm_state_gc_task(struct work_struct *work) @@ -563,7 +564,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) { struct xfrm_state *x; - x = kzalloc(sizeof(struct xfrm_state), GFP_ATOMIC); + x = kmem_cache_alloc(xfrm_state_cache, GFP_ATOMIC | __GFP_ZERO); if (x) { write_pnet(&x->xs_net, net); @@ -2313,6 +2314,10 @@ int __net_init xfrm_state_init(struct net *net) { unsigned int sz; + if (net_eq(net, &init_net)) + xfrm_state_cache = KMEM_CACHE(xfrm_state, + SLAB_HWCACHE_ALIGN | SLAB_PANIC); + INIT_LIST_HEAD(&net->xfrm.state_all); sz = sizeof(struct hlist_head) * 8; |