diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-06-30 15:51:09 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-06-30 15:51:09 -0700 |
| commit | dbe69e43372212527abf48609aba7fc39a6daa27 (patch) | |
| tree | 96cfafdf70f5325ceeac1054daf7deca339c9730 /net | |
| parent | a6eaf3850cb171c328a8b0db6d3c79286a1eba9d (diff) | |
| parent | b6df00789e2831fff7a2c65aa7164b2a4dcbe599 (diff) | |
Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core:
- BPF:
- add syscall program type and libbpf support for generating
instructions and bindings for in-kernel BPF loaders (BPF loaders
for BPF), this is a stepping stone for signed BPF programs
- infrastructure to migrate TCP child sockets from one listener to
another in the same reuseport group/map to improve flexibility
of service hand-off/restart
- add broadcast support to XDP redirect
- allow bypass of the lockless qdisc to improving performance (for
pktgen: +23% with one thread, +44% with 2 threads)
- add a simpler version of "DO_ONCE()" which does not require jump
labels, intended for slow-path usage
- virtio/vsock: introduce SOCK_SEQPACKET support
- add getsocketopt to retrieve netns cookie
- ip: treat lowest address of a IPv4 subnet as ordinary unicast
address allowing reclaiming of precious IPv4 addresses
- ipv6: use prandom_u32() for ID generation
- ip: add support for more flexible field selection for hashing
across multi-path routes (w/ offload to mlxsw)
- icmp: add support for extended RFC 8335 PROBE (ping)
- seg6: add support for SRv6 End.DT46 behavior
- mptcp:
- DSS checksum support (RFC 8684) to detect middlebox meddling
- support Connection-time 'C' flag
- time stamping support
- sctp: packetization Layer Path MTU Discovery (RFC 8899)
- xfrm: speed up state addition with seq set
- WiFi:
- hidden AP discovery on 6 GHz and other HE 6 GHz improvements
- aggregation handling improvements for some drivers
- minstrel improvements for no-ack frames
- deferred rate control for TXQs to improve reaction times
- switch from round robin to virtual time-based airtime scheduler
- add trace points:
- tcp checksum errors
- openvswitch - action execution, upcalls
- socket errors via sk_error_report
Device APIs:
- devlink: add rate API for hierarchical control of max egress rate
of virtual devices (VFs, SFs etc.)
- don't require RCU read lock to be held around BPF hooks in NAPI
context
- page_pool: generic buffer recycling
New hardware/drivers:
- mobile:
- iosm: PCIe Driver for Intel M.2 Modem
- support for Qualcomm MSM8998 (ipa)
- WiFi: Qualcomm QCN9074 and WCN6855 PCI devices
- sparx5: Microchip SparX-5 family of Enterprise Ethernet switches
- Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)
- NXP SJA1110 Automotive Ethernet 10-port switch
- Qualcomm QCA8327 switch support (qca8k)
- Mikrotik 10/25G NIC (atl1c)
Driver changes:
- ACPI support for some MDIO, MAC and PHY devices from Marvell and
NXP (our first foray into MAC/PHY description via ACPI)
- HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx
- Mellanox/Nvidia NIC (mlx5)
- NIC VF offload of L2 bridging
- support IRQ distribution to Sub-functions
- Marvell (prestera):
- add flower and match all
- devlink trap
- link aggregation
- Netronome (nfp): connection tracking offload
- Intel 1GE (igc): add AF_XDP support
- Marvell DPU (octeontx2): ingress ratelimit offload
- Google vNIC (gve): new ring/descriptor format support
- Qualcomm mobile (rmnet & ipa): inline checksum offload support
- MediaTek WiFi (mt76)
- mt7915 MSI support
- mt7915 Tx status reporting
- mt7915 thermal sensors support
- mt7921 decapsulation offload
- mt7921 enable runtime pm and deep sleep
- Realtek WiFi (rtw88)
- beacon filter support
- Tx antenna path diversity support
- firmware crash information via devcoredump
- Qualcomm WiFi (wcn36xx)
- Wake-on-WLAN support with magic packets and GTK rekeying
- Micrel PHY (ksz886x/ksz8081): add cable test support"
* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
tcp: change ICSK_CA_PRIV_SIZE definition
tcp_yeah: check struct yeah size at compile time
gve: DQO: Fix off by one in gve_rx_dqo()
stmmac: intel: set PCI_D3hot in suspend
stmmac: intel: Enable PHY WOL option in EHL
net: stmmac: option to enable PHY WOL with PMT enabled
net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
net: use netdev_info in ndo_dflt_fdb_{add,del}
ptp: Set lookup cookie when creating a PTP PPS source.
net: sock: add trace for socket errors
net: sock: introduce sk_error_report
net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
net: dsa: include fdb entries pointing to bridge in the host fdb list
net: dsa: include bridge addresses which are local in the host fdb list
net: dsa: sync static FDB entries on foreign interfaces to hardware
net: dsa: install the host MDB and FDB entries in the master's RX filter
net: dsa: reference count the FDB addresses at the cross-chip notifier level
net: dsa: introduce a separate cross-chip notifier type for host FDBs
net: dsa: reference count the MDB entries at the cross-chip notifier level
...
Diffstat (limited to 'net')
401 files changed, 10884 insertions, 4331 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index fb3d3262dc1a..4cdf8416869d 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -638,7 +638,8 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) case GET_VLAN_REALDEV_NAME_CMD: err = 0; - vlan_dev_get_realdev_name(dev, args.u.device2); + vlan_dev_get_realdev_name(dev, args.u.device2, + sizeof(args.u.device2)); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index fa3ad3d4d58c..1a705a4ef7fa 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -108,7 +108,8 @@ static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev) netdev_features_t ret; ret = real_dev->hw_enc_features & - (NETIF_F_CSUM_MASK | NETIF_F_ALL_TSO | NETIF_F_GSO_ENCAP_ALL); + (NETIF_F_CSUM_MASK | NETIF_F_GSO_SOFTWARE | + NETIF_F_GSO_ENCAP_ALL); if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK)) return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM; @@ -129,7 +130,8 @@ void vlan_dev_set_ingress_priority(const struct net_device *dev, int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); 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); +void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, + size_t size); int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 4db3f0621959..a0367b37512d 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -239,9 +239,9 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) return 0; } -void vlan_dev_get_realdev_name(const struct net_device *dev, char *result) +void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size) { - strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23); + strscpy_pad(result, vlan_dev_priv(dev)->real_dev->name, size); } bool vlan_dev_inherit_address(struct net_device *dev, @@ -360,7 +360,7 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) struct ifreq ifrr; int err = -EOPNOTSUPP; - strncpy(ifrr.ifr_name, real_dev->name, IFNAMSIZ); + strscpy_pad(ifrr.ifr_name, real_dev->name, IFNAMSIZ); ifrr.ifr_ifru = ifr->ifr_ifru; switch (cmd) { diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 93f2f8654882..2bbd7dce0f1d 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -99,7 +99,7 @@ static unsigned int rest_of_page(void *data) * @client: client instance * * This reclaims a channel by freeing its resources and - * reseting its inuse flag. + * resetting its inuse flag. * */ @@ -463,7 +463,7 @@ req_retry_pinned: * For example TREAD have 11. * 11 is the read/write header = PDU Header(7) + IO Size (4). * Arrange in such a way that server places header in the - * alloced memory and payload onto the user buffer. + * allocated memory and payload onto the user buffer. */ in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, req->rc.sdata, in_hdr_len); @@ -760,7 +760,7 @@ static struct p9_trans_module p9_virtio_trans = { .cancelled = p9_virtio_cancelled, /* * We leave one entry for input and one entry for response - * headers. We also skip one more entry to accomodate, address + * headers. We also skip one more entry to accommodate, address * that are not at page boundary, that can result in an extra * page in zero copy. */ diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index ebda397fa95a..8ade5a4ceaf5 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -707,7 +707,7 @@ static int atif_ioctl(int cmd, void __user *arg) /* * Phase 1 is fine on LocalTalk but we don't do - * EtherTalk phase 1. Anyone wanting to add it go ahead. + * EtherTalk phase 1. Anyone wanting to add it, go ahead. */ if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2) return -EPROTONOSUPPORT; @@ -828,7 +828,7 @@ static int atif_ioctl(int cmd, void __user *arg) nr = (struct atalk_netrange *)&(atif->nets); /* * Phase 1 is fine on Localtalk but we don't do - * Ethertalk phase 1. Anyone wanting to add it go ahead. + * Ethertalk phase 1. Anyone wanting to add it, go ahead. */ if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2) return -EPROTONOSUPPORT; @@ -2018,7 +2018,7 @@ module_init(atalk_init); * by the network device layer. * * Ergo, before the AppleTalk module can be removed, all AppleTalk - * sockets be closed from user space. + * sockets should be closed from user space. */ static void __exit atalk_exit(void) { diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c index aa1b57161f3b..0fdbdfd19474 100644 --- a/net/atm/atm_sysfs.c +++ b/net/atm/atm_sysfs.c @@ -11,7 +11,7 @@ #define to_atm_dev(cldev) container_of(cldev, struct atm_dev, class_dev) -static ssize_t show_type(struct device *cdev, +static ssize_t type_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); @@ -19,7 +19,7 @@ static ssize_t show_type(struct device *cdev, return scnprintf(buf, PAGE_SIZE, "%s\n", adev->type); } -static ssize_t show_address(struct device *cdev, +static ssize_t address_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); @@ -27,7 +27,7 @@ static ssize_t show_address(struct device *cdev, return scnprintf(buf, PAGE_SIZE, "%pM\n", adev->esi); } -static ssize_t show_atmaddress(struct device *cdev, +static ssize_t atmaddress_show(struct device *cdev, struct device_attribute *attr, char *buf) { unsigned long flags; @@ -50,7 +50,7 @@ static ssize_t show_atmaddress(struct device *cdev, return count; } -static ssize_t show_atmindex(struct device *cdev, +static ssize_t atmindex_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); @@ -58,7 +58,7 @@ static ssize_t show_atmindex(struct device *cdev, return scnprintf(buf, PAGE_SIZE, "%d\n", adev->number); } -static ssize_t show_carrier(struct device *cdev, +static ssize_t carrier_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); @@ -67,7 +67,7 @@ static ssize_t show_carrier(struct device *cdev, adev->signal == ATM_PHY_SIG_LOST ? 0 : 1); } -static ssize_t show_link_rate(struct device *cdev, +static ssize_t link_rate_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); @@ -90,12 +90,12 @@ static ssize_t show_link_rate(struct device *cdev, return scnprintf(buf, PAGE_SIZE, "%d\n", link_rate); } -static DEVICE_ATTR(address, 0444, show_address, NULL); -static DEVICE_ATTR(atmaddress, 0444, show_atmaddress, NULL); -static DEVICE_ATTR(atmindex, 0444, show_atmindex, NULL); -static DEVICE_ATTR(carrier, 0444, show_carrier, NULL); -static DEVICE_ATTR(type, 0444, show_type, NULL); -static DEVICE_ATTR(link_rate, 0444, show_link_rate, NULL); +static DEVICE_ATTR_RO(address); +static DEVICE_ATTR_RO(atmaddress); +static DEVICE_ATTR_RO(atmindex); +static DEVICE_ATTR_RO(carrier); +static DEVICE_ATTR_RO(type); +static DEVICE_ATTR_RO(link_rate); static struct device_attribute *atm_attrs[] = { &dev_attr_atmaddress, diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 3e17a5ecaa94..dd2a8dabed84 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -93,8 +93,8 @@ struct br2684_dev { * This lock should be held for writing any time the list of devices or * their attached vcc's could be altered. It should be held for reading * any time these are being queried. Note that we sometimes need to - * do read-locking under interrupt context, so write locking must block - * the current CPU's interrupts + * do read-locking under interrupting context, so write locking must block + * the current CPU's interrupts. */ static DEFINE_RWLOCK(devs_lock); diff --git a/net/atm/resources.c b/net/atm/resources.c index 53236986dfe0..2b2d33eeaf20 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -52,10 +52,8 @@ static struct atm_dev *__alloc_atm_dev(const char *type) static struct atm_dev *__atm_dev_lookup(int number) { struct atm_dev *dev; - struct list_head *p; - list_for_each(p, &atm_devs) { - dev = list_entry(p, struct atm_dev, dev_list); + list_for_each_entry(dev, &atm_devs, dev_list) { if (dev->number == number) { atm_dev_hold(dev); return dev; @@ -215,8 +213,7 @@ int atm_getnames(void __user *buf, int __user *iobuf_len) return -ENOMEM; } tmp_p = tmp_buf; - list_for_each(p, &atm_devs) { - dev = list_entry(p, struct atm_dev, dev_list); + list_for_each_entry(dev, &atm_devs, dev_list) { *tmp_p++ = dev->number; } mutex_unlock(&atm_dev_mutex); diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index fc8be49010b9..12022378f892 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1851,6 +1851,8 @@ batadv_iv_ogm_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, orig_node->orig) || nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, neigh_node->addr) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + neigh_node->if_incoming->net_dev->name) || nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, neigh_node->if_incoming->net_dev->ifindex) || nla_put_u8(msg, BATADV_ATTR_TQ, tq_avg) || @@ -2080,6 +2082,8 @@ batadv_iv_ogm_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq, if (nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, hardif_neigh->addr) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + hardif_neigh->if_incoming->net_dev->name) || nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, hardif_neigh->if_incoming->net_dev->ifindex) || nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, @@ -2461,6 +2465,8 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, router->addr) || nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, router->if_incoming->net_dev->name) || + nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + router->if_incoming->net_dev->ifindex) || nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_DOWN, gw_node->bandwidth_down) || nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_UP, diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index e1ca2b8c3152..b98aea958e3d 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -146,6 +146,8 @@ batadv_v_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq, if (nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, hardif_neigh->addr) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + hardif_neigh->if_incoming->net_dev->name) || nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, hardif_neigh->if_incoming->net_dev->ifindex) || nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, @@ -298,6 +300,8 @@ batadv_v_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, orig_node->orig) || nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, neigh_node->addr) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + neigh_node->if_incoming->net_dev->name) || nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, neigh_node->if_incoming->net_dev->ifindex) || nla_put_u32(msg, BATADV_ATTR_THROUGHPUT, throughput) || @@ -739,6 +743,12 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, goto out; } + if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + router->if_incoming->net_dev->ifindex)) { + genlmsg_cancel(msg, hdr); + goto out; + } + if (nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_DOWN, gw_node->bandwidth_down)) { genlmsg_cancel(msg, hdr); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 7dc133cfc363..63d42dcc9324 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -395,7 +395,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, break; case BATADV_CLAIM_TYPE_ANNOUNCE: /* announcement frame - * set HW SRC to the special mac containg the crc + * set HW SRC to the special mac containing the crc */ ether_addr_copy(hw_src, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, @@ -1040,7 +1040,7 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv, /* lets see if this originator is in our mesh */ orig_node = batadv_orig_hash_find(bat_priv, backbone_addr); - /* dont accept claims from gateways which are not in + /* don't accept claims from gateways which are not in * the same mesh or group. */ if (!orig_node) diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 5c22955bb9d5..8673a265995f 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -52,7 +52,6 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, void batadv_bla_status_update(struct net_device *net_dev); int batadv_bla_init(struct batadv_priv *bat_priv); void batadv_bla_free(struct batadv_priv *bat_priv); -int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb); #ifdef CONFIG_BATMAN_ADV_DAT bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr, unsigned short vid); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 4a6a25d551a8..55d97e18aa4a 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -9,7 +9,6 @@ #include <linux/atomic.h> #include <linux/byteorder/generic.h> -#include <linux/errno.h> #include <linux/gfp.h> #include <linux/if.h> #include <linux/if_arp.h> @@ -403,7 +402,7 @@ int batadv_hardif_no_broadcast(struct batadv_hard_iface *if_outgoing, goto out; } - /* >1 neighbors -> (re)brodcast */ + /* >1 neighbors -> (re)broadcast */ if (rcu_dereference(hlist_next_rcu(first))) goto out; @@ -678,43 +677,16 @@ batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface) } /** - * batadv_master_del_slave() - remove hard_iface from the current master iface - * @slave: the interface enslaved in another master - * @master: the master from which slave has to be removed - * - * Invoke ndo_del_slave on master passing slave as argument. In this way the - * slave is free'd and the master can correctly change its internal state. - * - * Return: 0 on success, a negative value representing the error otherwise - */ -static int batadv_master_del_slave(struct batadv_hard_iface *slave, - struct net_device *master) -{ - int ret; - - if (!master) - return 0; - - ret = -EBUSY; - if (master->netdev_ops->ndo_del_slave) - ret = master->netdev_ops->ndo_del_slave(master, slave->net_dev); - - return ret; -} - -/** * batadv_hardif_enable_interface() - Enslave hard interface to soft interface * @hard_iface: hard interface to add to soft interface - * @net: the applicable net namespace - * @iface_name: name of the soft interface + * @soft_iface: netdev struct of the mesh interface * * Return: 0 on success or negative error number in case of failure */ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, - struct net *net, const char *iface_name) + struct net_device *soft_iface) { struct batadv_priv *bat_priv; - struct net_device *soft_iface, *master; __be16 ethertype = htons(ETH_P_BATMAN); int max_header_len = batadv_max_header_len(); int ret; @@ -724,35 +696,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, kref_get(&hard_iface->refcount); - soft_iface = dev_get_by_name(net, iface_name); - - if (!soft_iface) { - soft_iface = batadv_softif_create(net, iface_name); - - if (!soft_iface) { - ret = -ENOMEM; - goto err; - } - - /* dev_get_by_name() increases the reference counter for us */ - dev_hold(soft_iface); - } - - if (!batadv_softif_is_valid(soft_iface)) { - pr_err("Can't create batman mesh interface %s: already exists as regular interface\n", - soft_iface->name); - ret = -EINVAL; - goto err_dev; - } - - /* check if the interface is enslaved in another virtual one and - * in that case unlink it first - */ - master = netdev_master_upper_dev_get(hard_iface->net_dev); - ret = batadv_master_del_slave(hard_iface, master); - if (ret) - goto err_dev; - + dev_hold(soft_iface); hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); @@ -810,7 +754,6 @@ err_upper: err_dev: hard_iface->soft_iface = NULL; dev_put(soft_iface); -err: batadv_hardif_put(hard_iface); return ret; } diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 83d11b46a9d8..8cb2a1f10080 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -16,7 +16,6 @@ #include <linux/rcupdate.h> #include <linux/stddef.h> #include <linux/types.h> -#include <net/net_namespace.h> /** * enum batadv_hard_if_state - State of a hard interface @@ -75,7 +74,7 @@ bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface); struct batadv_hard_iface* batadv_hardif_get_by_netdev(const struct net_device *net_dev); int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, - struct net *net, const char *iface_name); + struct net_device *soft_iface); void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface); int batadv_hardif_min_mtu(struct net_device *soft_iface); void batadv_update_min_mtu(struct net_device *soft_iface); diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 46696759f194..fb251c385a1b 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -18,7 +18,7 @@ #include <linux/stddef.h> #include <linux/types.h> -/* callback to a compare function. should compare 2 element datas for their +/* callback to a compare function. should compare 2 element data for their * keys * * Return: true if same and false if not same diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 8f0102b71656..014235fd4681 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2021.1" +#define BATADV_SOURCE_VERSION "2021.2" #endif /* B.A.T.M.A.N. parameters */ @@ -88,7 +88,6 @@ /* number of packets to send for broadcasts on different interface types */ #define BATADV_NUM_BCASTS_DEFAULT 1 #define BATADV_NUM_BCASTS_WIRELESS 3 -#define BATADV_NUM_BCASTS_MAX 3 /* length of the single packet used by the TP meter */ #define BATADV_TP_PACKET_LEN ETH_DATA_LEN diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 1d63c8cbbfe7..923e2197c2db 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -193,53 +193,22 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get(struct batadv_priv *bat_priv, * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present * The former two OR'd: no multicast router is present */ -#if IS_ENABLED(CONFIG_IPV6) static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv, struct net_device *bridge) { - struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list); struct net_device *dev = bat_priv->soft_iface; - struct br_ip_list *br_ip_entry, *tmp; - u8 flags = BATADV_MCAST_WANT_NO_RTR6; - int ret; + u8 flags = BATADV_NO_FLAGS; if (!bridge) return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; - /* TODO: ask the bridge if a multicast router is present (the bridge - * is capable of performing proper RFC4286 multicast router - * discovery) instead of searching for a ff02::2 listener here - */ - ret = br_multicast_list_adjacent(dev, &bridge_mcast_list); - if (ret < 0) - return BATADV_NO_FLAGS; - - list_for_each_entry_safe(br_ip_entry, tmp, &bridge_mcast_list, list) { - /* the bridge snooping does not maintain IPv4 link-local - * addresses - therefore we won't find any IPv4 multicast router - * address here, only IPv6 ones - */ - if (br_ip_entry->addr.proto == htons(ETH_P_IPV6) && - ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.dst.ip6)) - flags &= ~BATADV_MCAST_WANT_NO_RTR6; - - list_del(&br_ip_entry->list); - kfree(br_ip_entry); - } + if (!br_multicast_has_router_adjacent(dev, ETH_P_IP)) + flags |= BATADV_MCAST_WANT_NO_RTR4; + if (!br_multicast_has_router_adjacent(dev, ETH_P_IPV6)) + flags |= BATADV_MCAST_WANT_NO_RTR6; return flags; } -#else -static inline u8 -batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv, - struct net_device *bridge) -{ - if (bridge) - return BATADV_NO_FLAGS; - else - return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; -} -#endif /** * batadv_mcast_mla_rtr_flags_get() - get multicast router flags diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index f317d206b411..b6cc746e01a6 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -814,6 +814,10 @@ static int batadv_netlink_hardif_fill(struct sk_buff *msg, bat_priv->soft_iface->ifindex)) goto nla_put_failure; + if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, + bat_priv->soft_iface->name)) + goto nla_put_failure; + if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, net_dev->ifindex) || nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, @@ -1045,6 +1049,10 @@ static int batadv_netlink_vlan_fill(struct sk_buff *msg, bat_priv->soft_iface->ifindex)) goto nla_put_failure; + if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, + bat_priv->soft_iface->name)) + goto nla_put_failure; + if (nla_put_u32(msg, BATADV_ATTR_VLANID, vlan->vid & VLAN_VID_MASK)) goto nla_put_failure; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 40f5cffde6a3..bb9e93e3d98c 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1182,9 +1182,9 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, struct batadv_bcast_packet *bcast_packet; struct ethhdr *ethhdr; int hdr_size = sizeof(*bcast_packet); - int ret = NET_RX_DROP; s32 seq_diff; u32 seqno; + int ret; /* drop packet if it has not necessary minimum size */ if (unlikely(!pskb_may_pull(skb, hdr_size))) @@ -1210,7 +1210,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, if (batadv_is_my_mac(bat_priv, bcast_packet->orig)) goto free_skb; - if (bcast_packet->ttl < 2) + if (bcast_packet->ttl-- < 2) goto free_skb; orig_node = batadv_orig_hash_find(bat_priv, bcast_packet->orig); @@ -1249,7 +1249,9 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, batadv_skb_set_priority(skb, sizeof(struct batadv_bcast_packet)); /* rebroadcast packet */ - batadv_add_bcast_packet_to_list(bat_priv, skb, 1, false); + ret = batadv_forw_bcast_packet(bat_priv, skb, 0, false); + if (ret == NETDEV_TX_BUSY) + goto free_skb; /* don't hand the broadcast up if it is from an originator * from the same backbone. @@ -1275,6 +1277,7 @@ spin_unlock: spin_unlock_bh(&orig_node->bcast_seqno_lock); free_skb: kfree_skb(skb); + ret = NET_RX_DROP; out: if (orig_node) batadv_orig_node_put(orig_node); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 157abe92d827..0b9dd29d3b6a 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -737,57 +737,48 @@ void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv, } /** - * batadv_add_bcast_packet_to_list() - queue broadcast packet for multiple sends + * batadv_forw_bcast_packet_to_list() - queue broadcast packet for transmissions * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet + * @if_in: the interface where the packet was received on + * @if_out: the outgoing interface to queue on * - * add a broadcast packet to the queue and setup timers. broadcast packets + * Adds a broadcast packet to the queue and sets up timers. Broadcast packets * are sent multiple times to increase probability for being received. * - * The skb is not consumed, so the caller should make sure that the - * skb is freed. - * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ -int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, - const struct sk_buff *skb, - unsigned long delay, - bool own_packet) +static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet, + struct batadv_hard_iface *if_in, + struct batadv_hard_iface *if_out) { - struct batadv_hard_iface *primary_if; struct batadv_forw_packet *forw_packet; - struct batadv_bcast_packet *bcast_packet; + unsigned long send_time = jiffies; struct sk_buff *newskb; - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) - goto err; - newskb = skb_copy(skb, GFP_ATOMIC); - if (!newskb) { - batadv_hardif_put(primary_if); + if (!newskb) goto err; - } - forw_packet = batadv_forw_packet_alloc(primary_if, NULL, + forw_packet = batadv_forw_packet_alloc(if_in, if_out, &bat_priv->bcast_queue_left, bat_priv, newskb); - batadv_hardif_put(primary_if); if (!forw_packet) goto err_packet_free; - /* as we have a copy now, it is safe to decrease the TTL */ - bcast_packet = (struct batadv_bcast_packet *)newskb->data; - bcast_packet->ttl--; - forw_packet->own = own_packet; INIT_DELAYED_WORK(&forw_packet->delayed_work, batadv_send_outstanding_bcast_packet); - batadv_forw_packet_bcast_queue(bat_priv, forw_packet, jiffies + delay); + send_time += delay ? delay : msecs_to_jiffies(5); + + batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return NETDEV_TX_OK; err_packet_free: @@ -797,9 +788,219 @@ err: } /** + * batadv_forw_bcast_packet_if() - forward and queue a broadcast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: broadcast packet to add + * @delay: number of jiffies to wait before sending + * @own_packet: true if it is a self-generated broadcast packet + * @if_in: the interface where the packet was received on + * @if_out: the outgoing interface to forward to + * + * Transmits a broadcast packet on the specified interface either immediately + * or if a delay is given after that. Furthermore, queues additional + * retransmissions if this interface is a wireless one. + * + * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. + */ +static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet, + struct batadv_hard_iface *if_in, + struct batadv_hard_iface *if_out) +{ + unsigned int num_bcasts = if_out->num_bcasts; + struct sk_buff *newskb; + int ret = NETDEV_TX_OK; + + if (!delay) { + newskb = skb_copy(skb, GFP_ATOMIC); + if (!newskb) + return NETDEV_TX_BUSY; + + batadv_send_broadcast_skb(newskb, if_out); + num_bcasts--; + } + + /* delayed broadcast or rebroadcasts? */ + if (num_bcasts >= 1) { + BATADV_SKB_CB(skb)->num_bcasts = num_bcasts; + + ret = batadv_forw_bcast_packet_to_list(bat_priv, skb, delay, + own_packet, if_in, + if_out); + } + + return ret; +} + +/** + * batadv_send_no_broadcast() - check whether (re)broadcast is necessary + * @bat_priv: the bat priv with all the soft interface information + * @skb: broadcast packet to check + * @own_packet: true if it is a self-generated broadcast packet + * @if_out: the outgoing interface checked and considered for (re)broadcast + * + * Return: False if a packet needs to be (re)broadcasted on the given interface, + * true otherwise. + */ +static bool batadv_send_no_broadcast(struct batadv_priv *bat_priv, + struct sk_buff *skb, bool own_packet, + struct batadv_hard_iface *if_out) +{ + struct batadv_hardif_neigh_node *neigh_node = NULL; + struct batadv_bcast_packet *bcast_packet; + u8 *orig_neigh; + u8 *neigh_addr; + char *type; + int ret; + + if (!own_packet) { + neigh_addr = eth_hdr(skb)->h_source; + neigh_node = batadv_hardif_neigh_get(if_out, + neigh_addr); + } + + bcast_packet = (struct batadv_bcast_packet *)skb->data; + orig_neigh = neigh_node ? neigh_node->orig : NULL; + + ret = batadv_hardif_no_broadcast(if_out, bcast_packet->orig, + orig_neigh); + + if (neigh_node) + batadv_hardif_neigh_put(neigh_node); + + /* ok, may broadcast */ + if (!ret) + return false; + + /* no broadcast */ + switch (ret) { + case BATADV_HARDIF_BCAST_NORECIPIENT: + type = "no neighbor"; + break; + case BATADV_HARDIF_BCAST_DUPFWD: + type = "single neighbor is source"; + break; + case BATADV_HARDIF_BCAST_DUPORIG: + type = "single neighbor is originator"; + break; + default: + type = "unknown"; + } + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "BCAST packet from orig %pM on %s suppressed: %s\n", + bcast_packet->orig, + if_out->net_dev->name, type); + + return true; +} + +/** + * __batadv_forw_bcast_packet() - forward and queue a broadcast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: broadcast packet to add + * @delay: number of jiffies to wait before sending + * @own_packet: true if it is a self-generated broadcast packet + * + * Transmits a broadcast packet either immediately or if a delay is given + * after that. Furthermore, queues additional retransmissions on wireless + * interfaces. + * + * This call clones the given skb, hence the caller needs to take into + * account that the data segment of the given skb might not be + * modifiable anymore. + * + * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. + */ +static int __batadv_forw_bcast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet) +{ + struct batadv_hard_iface *hard_iface; + struct batadv_hard_iface *primary_if; + int ret = NETDEV_TX_OK; + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + return NETDEV_TX_BUSY; + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + if (!kref_get_unless_zero(&hard_iface->refcount)) + continue; + + if (batadv_send_no_broadcast(bat_priv, skb, own_packet, + hard_iface)) { + batadv_hardif_put(hard_iface); + continue; + } + + ret = batadv_forw_bcast_packet_if(bat_priv, skb, delay, + own_packet, primary_if, + hard_iface); + batadv_hardif_put(hard_iface); + + if (ret == NETDEV_TX_BUSY) + break; + } + rcu_read_unlock(); + + batadv_hardif_put(primary_if); + return ret; +} + +/** + * batadv_forw_bcast_packet() - forward and queue a broadcast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: broadcast packet to add + * @delay: number of jiffies to wait before sending + * @own_packet: true if it is a self-generated broadcast packet + * + * Transmits a broadcast packet either immediately or if a delay is given + * after that. Furthermore, queues additional retransmissions on wireless + * interfaces. + * + * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. + */ +int batadv_forw_bcast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet) +{ + return __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); +} + +/** + * batadv_send_bcast_packet() - send and queue a broadcast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: broadcast packet to add + * @delay: number of jiffies to wait before sending + * @own_packet: true if it is a self-generated broadcast packet + * + * Transmits a broadcast packet either immediately or if a delay is given + * after that. Furthermore, queues additional retransmissions on wireless + * interfaces. + * + * Consumes the provided skb. + */ +void batadv_send_bcast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet) +{ + __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); + consume_skb(skb); +} + +/** * batadv_forw_packet_bcasts_left() - check if a retransmission is necessary * @forw_packet: the forwarding packet to check - * @hard_iface: the interface to check on * * Checks whether a given packet has any (re)transmissions left on the provided * interface. @@ -811,28 +1012,20 @@ err: * Return: True if (re)transmissions are left, false otherwise. */ static bool -batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet, - struct batadv_hard_iface *hard_iface) +batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet) { - unsigned int max; - - if (hard_iface) - max = hard_iface->num_bcasts; - else - max = BATADV_NUM_BCASTS_MAX; - - return BATADV_SKB_CB(forw_packet->skb)->num_bcasts < max; + return BATADV_SKB_CB(forw_packet->skb)->num_bcasts; } /** - * batadv_forw_packet_bcasts_inc() - increment retransmission counter of a + * batadv_forw_packet_bcasts_dec() - decrement retransmission counter of a * packet - * @forw_packet: the packet to increase the counter for + * @forw_packet: the packet to decrease the counter for */ static void -batadv_forw_packet_bcasts_inc(struct batadv_forw_packet *forw_packet) +batadv_forw_packet_bcasts_dec(struct batadv_forw_packet *forw_packet) { - BATADV_SKB_CB(forw_packet->skb)->num_bcasts++; + BATADV_SKB_CB(forw_packet->skb)->num_bcasts--; } /** @@ -843,30 +1036,30 @@ batadv_forw_packet_bcasts_inc(struct batadv_forw_packet *forw_packet) */ bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet) { - return BATADV_SKB_CB(forw_packet->skb)->num_bcasts > 0; + unsigned char num_bcasts = BATADV_SKB_CB(forw_packet->skb)->num_bcasts; + + return num_bcasts != forw_packet->if_outgoing->num_bcasts; } +/** + * batadv_send_outstanding_bcast_packet() - transmit a queued broadcast packet + * @work: work queue item + * + * Transmits a queued broadcast packet and if necessary reschedules it. + */ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) { - struct batadv_hard_iface *hard_iface; - struct batadv_hardif_neigh_node *neigh_node; - struct delayed_work *delayed_work; + unsigned long send_time = jiffies + msecs_to_jiffies(5); struct batadv_forw_packet *forw_packet; - struct batadv_bcast_packet *bcast_packet; - struct sk_buff *skb1; - struct net_device *soft_iface; + struct delayed_work *delayed_work; struct batadv_priv *bat_priv; - unsigned long send_time = jiffies + msecs_to_jiffies(5); + struct sk_buff *skb1; bool dropped = false; - u8 *neigh_addr; - u8 *orig_neigh; - int ret = 0; delayed_work = to_delayed_work(work); forw_packet = container_of(delayed_work, struct batadv_forw_packet, delayed_work); - soft_iface = forw_packet->if_incoming->soft_iface; - bat_priv = netdev_priv(soft_iface); + bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface); if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) { dropped = true; @@ -878,76 +1071,15 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) goto out; } - bcast_packet = (struct batadv_bcast_packet *)forw_packet->skb->data; - - /* rebroadcast packet */ - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if (hard_iface->soft_iface != soft_iface) - continue; - - if (!batadv_forw_packet_bcasts_left(forw_packet, hard_iface)) - continue; - - if (forw_packet->own) { - neigh_node = NULL; - } else { - neigh_addr = eth_hdr(forw_packet->skb)->h_source; - neigh_node = batadv_hardif_neigh_get(hard_iface, - neigh_addr); - } - - orig_neigh = neigh_node ? neigh_node->orig : NULL; - - ret = batadv_hardif_no_broadcast(hard_iface, bcast_packet->orig, - orig_neigh); - - if (ret) { - char *type; - - switch (ret) { - case BATADV_HARDIF_BCAST_NORECIPIENT: - type = "no neighbor"; - break; - case BATADV_HARDIF_BCAST_DUPFWD: - type = "single neighbor is source"; - break; - case BATADV_HARDIF_BCAST_DUPORIG: - type = "single neighbor is originator"; - break; - default: - type = "unknown"; - } - - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "BCAST packet from orig %pM on %s suppressed: %s\n", - bcast_packet->orig, - hard_iface->net_dev->name, type); - - if (neigh_node) - batadv_hardif_neigh_put(neigh_node); - - continue; - } - - if (neigh_node) - batadv_hardif_neigh_put(neigh_node); - - if (!kref_get_unless_zero(&hard_iface->refcount)) - continue; - - /* send a copy of the saved skb */ - skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); - if (skb1) - batadv_send_broadcast_skb(skb1, hard_iface); - - batadv_hardif_put(hard_iface); - } - rcu_read_unlock(); + /* send a copy of the saved skb */ + skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); + if (!skb1) + goto out; - batadv_forw_packet_bcasts_inc(forw_packet); + batadv_send_broadcast_skb(skb1, forw_packet->if_outgoing); + batadv_forw_packet_bcasts_dec(forw_packet); - /* if we still have some more bcasts to send */ - if (batadv_forw_packet_bcasts_left(forw_packet, NULL)) { + if (batadv_forw_packet_bcasts_left(forw_packet)) { batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return; diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 2b0daf8b2bc4..08af251b765c 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -39,10 +39,14 @@ int batadv_send_broadcast_skb(struct sk_buff *skb, struct batadv_hard_iface *hard_iface); int batadv_send_unicast_skb(struct sk_buff *skb, struct batadv_neigh_node *neigh_node); -int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, - const struct sk_buff *skb, - unsigned long delay, - bool own_packet); +int batadv_forw_bcast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet); +void batadv_send_bcast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet); void batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, const struct batadv_hard_iface *hard_iface); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 6b8181bc3122..ae368a42a4ad 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -26,7 +26,6 @@ #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/percpu.h> -#include <linux/printk.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/rcupdate.h> @@ -37,6 +36,7 @@ #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> +#include <net/net_namespace.h> #include <net/netlink.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> @@ -191,7 +191,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, struct vlan_ethhdr *vhdr; unsigned int header_len = 0; int data_len = skb->len, ret; - unsigned long brd_delay = 1; + unsigned long brd_delay = 0; bool do_bcast = false, client_added; unsigned short vid; u32 seqno; @@ -330,7 +330,7 @@ send: bcast_packet = (struct batadv_bcast_packet *)skb->data; bcast_packet->version = BATADV_COMPAT_VERSION; - bcast_packet->ttl = BATADV_TTL; + bcast_packet->ttl = BATADV_TTL - 1; /* batman packet type: broadcast */ bcast_packet->packet_type = BATADV_BCAST; @@ -346,13 +346,7 @@ send: seqno = atomic_inc_return(&bat_priv->bcast_seqno); bcast_packet->seqno = htonl(seqno); - batadv_add_bcast_packet_to_list(bat_priv, skb, brd_delay, true); - - /* a copy is stored in the bcast list, therefore removing - * the original skb. - */ - consume_skb(skb); - + batadv_send_bcast_packet(bat_priv, skb, brd_delay, true); /* unicast packet */ } else { /* DHCP packets going to a server will use the GW feature */ @@ -848,14 +842,13 @@ static int batadv_softif_slave_add(struct net_device *dev, struct netlink_ext_ack *extack) { struct batadv_hard_iface *hard_iface; - struct net *net = dev_net(dev); int ret = -EINVAL; hard_iface = batadv_hardif_get_by_netdev(slave_dev); if (!hard_iface || hard_iface->soft_iface) goto out; - ret = batadv_hardif_enable_interface(hard_iface, net, dev->name); + ret = batadv_hardif_enable_interface(hard_iface, dev); out: if (hard_iface) @@ -1093,38 +1086,6 @@ static int batadv_softif_newlink(struct net *src_net, struct net_device *dev, } /** - * batadv_softif_create() - Create and register soft interface - * @net: the applicable net namespace - * @name: name of the new soft interface - * - * Return: newly allocated soft_interface, NULL on errors - */ -struct net_device *batadv_softif_create(struct net *net, const char *name) -{ - struct net_device *soft_iface; - int ret; - - soft_iface = alloc_netdev(sizeof(struct batadv_priv), name, - NET_NAME_UNKNOWN, batadv_softif_init_early); - if (!soft_iface) - return NULL; - - dev_net_set(soft_iface, net); - - soft_iface->rtnl_link_ops = &batadv_link_ops; - - ret = register_netdevice(soft_iface); - if (ret < 0) { - pr_err("Unable to register the batman interface '%s': %i\n", - name, ret); - free_netdev(soft_iface); - return NULL; - } - - return soft_iface; -} - -/** * batadv_softif_destroy_netlink() - deletion of batadv_soft_interface via * netlink * @soft_iface: the to-be-removed batman-adv interface diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 38b0ad182584..67a2ddd6832f 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -12,14 +12,12 @@ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/types.h> -#include <net/net_namespace.h> #include <net/rtnetlink.h> int batadv_skb_head_push(struct sk_buff *skb, unsigned int len); void batadv_interface_rx(struct net_device *soft_iface, struct sk_buff *skb, int hdr_size, struct batadv_orig_node *orig_node); -struct net_device *batadv_softif_create(struct net *net, const char *name); bool batadv_softif_is_valid(const struct net_device *net_dev); extern struct rtnl_link_ops batadv_link_ops; int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 97617d02c8f9..fd164a248569 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -103,34 +103,6 @@ static inline bool peer_del(struct lowpan_btle_dev *dev, return false; } -static inline struct lowpan_peer *peer_lookup_ba(struct lowpan_btle_dev *dev, - bdaddr_t *ba, __u8 type) -{ - struct lowpan_peer *peer; - - BT_DBG("peers %d addr %pMR type %d", atomic_read(&dev->peer_count), - ba, type); - - rcu_read_lock(); - - list_for_each_entry_rcu(peer, &dev->peers, list) { - BT_DBG("dst addr %pMR dst type %d", - &peer->chan->dst, peer->chan->dst_type); - - if (bacmp(&peer->chan->dst, ba)) - continue; - - if (type == peer->chan->dst_type) { - rcu_read_unlock(); - return peer; - } - } - - rcu_read_unlock(); - - return NULL; -} - static inline struct lowpan_peer * __peer_lookup_chan(struct lowpan_btle_dev *dev, struct l2cap_chan *chan) { @@ -195,7 +167,7 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_btle_dev *dev, rcu_read_lock(); list_for_each_entry_rcu(peer, &dev->peers, list) { - BT_DBG("dst addr %pMR dst type %d ip %pI6c", + BT_DBG("dst addr %pMR dst type %u ip %pI6c", &peer->chan->dst, peer->chan->dst_type, &peer->peer_addr); @@ -506,7 +478,7 @@ static int send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev) local_skb = skb_clone(skb, GFP_ATOMIC); - BT_DBG("xmit %s to %pMR type %d IP %pI6c chan %p", + BT_DBG("xmit %s to %pMR type %u IP %pI6c chan %p", netdev->name, &pentry->chan->dst, pentry->chan->dst_type, &pentry->peer_addr, pentry->chan); @@ -549,7 +521,7 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) if (err) { if (lowpan_cb(skb)->chan) { - BT_DBG("xmit %s to %pMR type %d IP %pI6c chan %p", + BT_DBG("xmit %s to %pMR type %u IP %pI6c chan %p", netdev->name, &addr, addr_type, &lowpan_cb(skb)->addr, lowpan_cb(skb)->chan); err = send_pkt(lowpan_cb(skb)->chan, skb, netdev); @@ -691,7 +663,7 @@ static struct l2cap_chan *add_peer_chan(struct l2cap_chan *chan, static int setup_netdev(struct l2cap_chan *chan, struct lowpan_btle_dev **dev) { struct net_device *netdev; - int err = 0; + int err; netdev = alloc_netdev(LOWPAN_PRIV_SIZE(sizeof(struct lowpan_btle_dev)), IFACE_NAME_TEMPLATE, NET_NAME_UNKNOWN, @@ -818,7 +790,7 @@ static void chan_close_cb(struct l2cap_chan *chan) BT_DBG("dev %p removing %speer %p", dev, last ? "last " : "1 ", peer); - BT_DBG("chan %p orig refcnt %d", chan, + BT_DBG("chan %p orig refcnt %u", chan, kref_read(&chan->kref)); l2cap_chan_put(chan); @@ -907,14 +879,6 @@ static const struct l2cap_ops bt_6lowpan_chan_ops = { .set_shutdown = l2cap_chan_no_set_shutdown, }; -static inline __u8 bdaddr_type(__u8 type) -{ - if (type == ADDR_LE_DEV_PUBLIC) - return BDADDR_LE_PUBLIC; - else - return BDADDR_LE_RANDOM; -} - static int bt_6lowpan_connect(bdaddr_t *addr, u8 dst_type) { struct l2cap_chan *chan; @@ -940,7 +904,7 @@ static int bt_6lowpan_disconnect(struct l2cap_conn *conn, u8 dst_type) { struct lowpan_peer *peer; - BT_DBG("conn %p dst type %d", conn, dst_type); + BT_DBG("conn %p dst type %u", conn, dst_type); peer = lookup_peer(conn); if (!peer) @@ -972,7 +936,7 @@ static struct l2cap_chan *bt_6lowpan_listen(void) atomic_set(&chan->nesting, L2CAP_NESTING_PARENT); - BT_DBG("chan %p src type %d", chan, chan->src_type); + BT_DBG("chan %p src type %u", chan, chan->src_type); err = l2cap_add_psm(chan, addr, cpu_to_le16(L2CAP_PSM_IPSP)); if (err) { @@ -1013,7 +977,7 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, *conn = (struct l2cap_conn *)hcon->l2cap_data; - BT_DBG("conn %p dst %pMR type %d", *conn, &hcon->dst, hcon->dst_type); + BT_DBG("conn %p dst %pMR type %u", *conn, &hcon->dst, hcon->dst_type); return 0; } @@ -1155,7 +1119,7 @@ static ssize_t lowpan_control_write(struct file *fp, return -EALREADY; } - BT_DBG("conn %p dst %pMR type %d user %d", conn, + BT_DBG("conn %p dst %pMR type %d user %u", conn, &conn->hcon->dst, conn->hcon->dst_type, addr_type); } diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 463bad58478b..1fcc482397c3 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -120,7 +120,7 @@ static int a2mp_command_rej(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*rej)) return -EINVAL; - BT_DBG("ident %d reason %d", hdr->ident, le16_to_cpu(rej->reason)); + BT_DBG("ident %u reason %d", hdr->ident, le16_to_cpu(rej->reason)); skb_pull(skb, sizeof(*rej)); @@ -219,7 +219,7 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, cl = (void *) skb->data; while (len >= sizeof(*cl)) { - BT_DBG("Remote AMP id %d type %d status %d", cl->id, cl->type, + BT_DBG("Remote AMP id %u type %u status %u", cl->id, cl->type, cl->status); if (cl->id != AMP_ID_BREDR && cl->type != AMP_TYPE_BREDR) { @@ -273,7 +273,7 @@ static int a2mp_change_notify(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cl *cl = (void *) skb->data; while (skb->len >= sizeof(*cl)) { - BT_DBG("Controller id %d type %d status %d", cl->id, cl->type, + BT_DBG("Controller id %u type %u status %u", cl->id, cl->type, cl->status); cl = skb_pull(skb, sizeof(*cl)); } @@ -302,7 +302,7 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; - BT_DBG("id %d", req->id); + BT_DBG("id %u", req->id); hdev = hci_dev_get(req->id); if (!hdev || hdev->dev_type != HCI_AMP) { @@ -344,7 +344,7 @@ static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*rsp)) return -EINVAL; - BT_DBG("id %d status 0x%2.2x", rsp->id, rsp->status); + BT_DBG("id %u status 0x%2.2x", rsp->id, rsp->status); if (rsp->status) return -EINVAL; @@ -373,7 +373,7 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; - BT_DBG("id %d", req->id); + BT_DBG("id %u", req->id); /* Make sure that other request is not processed */ tmp = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC); @@ -423,7 +423,7 @@ static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb, assoc_len = len - sizeof(*rsp); - BT_DBG("id %d status 0x%2.2x assoc len %zu", rsp->id, rsp->status, + BT_DBG("id %u status 0x%2.2x assoc len %zu", rsp->id, rsp->status, assoc_len); if (rsp->status) @@ -457,7 +457,7 @@ static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb, if (!hcon) goto done; - BT_DBG("Created hcon %p: loc:%d -> rem:%d", hcon, hdev->id, rsp->id); + BT_DBG("Created hcon %p: loc:%u -> rem:%u", hcon, hdev->id, rsp->id); mgr->bredr_chan->remote_amp_id = rsp->id; @@ -481,7 +481,7 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; - BT_DBG("local_id %d, remote_id %d", req->local_id, req->remote_id); + BT_DBG("local_id %u, remote_id %u", req->local_id, req->remote_id); memset(&rsp, 0, sizeof(rsp)); @@ -562,7 +562,7 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; - BT_DBG("local_id %d remote_id %d", req->local_id, req->remote_id); + BT_DBG("local_id %u remote_id %u", req->local_id, req->remote_id); memset(&rsp, 0, sizeof(rsp)); @@ -599,7 +599,7 @@ send_rsp: static inline int a2mp_cmd_rsp(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { - BT_DBG("ident %d code 0x%2.2x", hdr->ident, hdr->code); + BT_DBG("ident %u code 0x%2.2x", hdr->ident, hdr->code); skb_pull(skb, le16_to_cpu(hdr->len)); return 0; @@ -620,7 +620,7 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) hdr = (void *) skb->data; len = le16_to_cpu(hdr->len); - BT_DBG("code 0x%2.2x id %d len %u", hdr->code, hdr->ident, len); + BT_DBG("code 0x%2.2x id %u len %u", hdr->code, hdr->ident, len); skb_pull(skb, sizeof(*hdr)); diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index be2d469d6369..2134f92bd7ac 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -78,7 +78,7 @@ struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id) { struct amp_ctrl *ctrl; - BT_DBG("mgr %p id %d", mgr, id); + BT_DBG("mgr %p id %u", mgr, id); mutex_lock(&mgr->amp_ctrls_lock); list_for_each_entry(ctrl, &mgr->amp_ctrls, list) { @@ -179,7 +179,7 @@ int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type) /* Legacy key */ if (conn->key_type < 3) { - bt_dev_err(hdev, "legacy key type %d", conn->key_type); + bt_dev_err(hdev, "legacy key type %u", conn->key_type); return -EACCES; } @@ -257,7 +257,7 @@ void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle) struct hci_request req; int err; - BT_DBG("%s handle %d", hdev->name, phy_handle); + BT_DBG("%s handle %u", hdev->name, phy_handle); cp.phy_handle = phy_handle; cp.max_len = cpu_to_le16(hdev->amp_assoc_size); diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 43c284158f63..72f47b372705 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -126,8 +126,8 @@ static int bnep_ctrl_set_netfilter(struct bnep_session *s, __be16 *data, int len f[i].start = get_unaligned_be16(data++); f[i].end = get_unaligned_be16(data++); - BT_DBG("proto filter start %d end %d", - f[i].start, f[i].end); + BT_DBG("proto filter start %u end %u", + f[i].start, f[i].end); } if (i < BNEP_MAX_PROTO_FILTERS) @@ -266,7 +266,7 @@ static int bnep_rx_extension(struct bnep_session *s, struct sk_buff *skb) break; } - BT_DBG("type 0x%x len %d", h->type, h->len); + BT_DBG("type 0x%x len %u", h->type, h->len); switch (h->type & BNEP_TYPE_MASK) { case BNEP_EXT_CONTROL: @@ -424,7 +424,7 @@ static int bnep_tx_frame(struct bnep_session *s, struct sk_buff *skb) int len = 0, il = 0; u8 type = 0; - BT_DBG("skb %p dev %p type %d", skb, skb->dev, skb->pkt_type); + BT_DBG("skb %p dev %p type %u", skb, skb->dev, skb->pkt_type); if (!skb->dev) { /* Control frame sent by us */ diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index eb41556002e3..f3bedc3b613a 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -74,7 +74,7 @@ static struct cmtp_application *cmtp_application_add(struct cmtp_session *sessio { struct cmtp_application *app = kzalloc(sizeof(*app), GFP_KERNEL); - BT_DBG("session %p application %p appl %d", session, app, appl); + BT_DBG("session %p application %p appl %u", session, app, appl); if (!app) return NULL; @@ -135,7 +135,7 @@ static void cmtp_send_capimsg(struct cmtp_session *session, struct sk_buff *skb) { struct cmtp_scb *scb = (void *) skb->cb; - BT_DBG("session %p skb %p len %d", session, skb, skb->len); + BT_DBG("session %p skb %p len %u", session, skb, skb->len); scb->id = -1; scb->data = (CAPIMSG_COMMAND(skb->data) == CAPI_DATA_B3); @@ -152,7 +152,7 @@ static void cmtp_send_interopmsg(struct cmtp_session *session, struct sk_buff *skb; unsigned char *s; - BT_DBG("session %p subcmd 0x%02x appl %d msgnum %d", session, subcmd, appl, msgnum); + BT_DBG("session %p subcmd 0x%02x appl %u msgnum %u", session, subcmd, appl, msgnum); skb = alloc_skb(CAPI_MSG_BASELEN + 6 + len, GFP_ATOMIC); if (!skb) { @@ -188,7 +188,7 @@ static void cmtp_recv_interopmsg(struct cmtp_session *session, struct sk_buff *s __u16 appl, msgnum, func, info; __u32 controller; - BT_DBG("session %p skb %p len %d", session, skb, skb->len); + BT_DBG("session %p skb %p len %u", session, skb, skb->len); switch (CAPIMSG_SUBCOMMAND(skb->data)) { case CAPI_CONF: @@ -321,7 +321,7 @@ void cmtp_recv_capimsg(struct cmtp_session *session, struct sk_buff *skb) __u16 appl; __u32 contr; - BT_DBG("session %p skb %p len %d", session, skb, skb->len); + BT_DBG("session %p skb %p len %u", session, skb, skb->len); if (skb->len < CAPI_MSG_BASELEN) return; @@ -344,7 +344,7 @@ void cmtp_recv_capimsg(struct cmtp_session *session, struct sk_buff *skb) appl = application->appl; CAPIMSG_SETAPPID(skb->data, appl); } else { - BT_ERR("Can't find application with id %d", appl); + BT_ERR("Can't find application with id %u", appl); kfree_skb(skb); return; } @@ -385,8 +385,8 @@ static void cmtp_register_appl(struct capi_ctr *ctrl, __u16 appl, capi_register_ unsigned char buf[8]; int err = 0, nconn, want = rp->level3cnt; - BT_DBG("ctrl %p appl %d level3cnt %d datablkcnt %d datablklen %d", - ctrl, appl, rp->level3cnt, rp->datablkcnt, rp->datablklen); + BT_DBG("ctrl %p appl %u level3cnt %u datablkcnt %u datablklen %u", + ctrl, appl, rp->level3cnt, rp->datablkcnt, rp->datablklen); application = cmtp_application_add(session, appl); if (!application) { @@ -450,7 +450,7 @@ static void cmtp_release_appl(struct capi_ctr *ctrl, __u16 appl) struct cmtp_session *session = ctrl->driverdata; struct cmtp_application *application; - BT_DBG("ctrl %p appl %d", ctrl, appl); + BT_DBG("ctrl %p appl %u", ctrl, appl); application = cmtp_application_get(session, CMTP_APPLID, appl); if (!application) { @@ -483,7 +483,7 @@ static u16 cmtp_send_message(struct capi_ctr *ctrl, struct sk_buff *skb) application = cmtp_application_get(session, CMTP_APPLID, appl); if ((!application) || (application->state != BT_CONNECTED)) { - BT_ERR("Can't find application with id %d", appl); + BT_ERR("Can't find application with id %u", appl); return CAPI_ILLAPPNR; } @@ -515,7 +515,7 @@ static int cmtp_proc_show(struct seq_file *m, void *v) seq_printf(m, "ctrl %d\n", session->num); list_for_each_entry(app, &session->applications, list) { - seq_printf(m, "appl %d -> %d\n", app->appl, app->mapping); + seq_printf(m, "appl %u -> %u\n", app->appl, app->mapping); } return 0; diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 07cfa3249f83..0a2d78e811cf 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -392,6 +392,11 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) if (!(session->flags & BIT(CMTP_LOOPBACK))) { err = cmtp_attach_device(session); if (err < 0) { + /* Caller will call fput in case of failure, and so + * will cmtp_session kthread. + */ + get_file(session->sock->file); + atomic_inc(&session->terminate); wake_up_interruptible(sk_sleep(session->sock->sk)); up_write(&cmtp_session_sem); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 88ec08978ff4..2b5059a56cda 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -257,7 +257,7 @@ int hci_disconnect(struct hci_conn *conn, __u8 reason) { BT_DBG("hcon %p", conn); - /* When we are master of an established connection and it enters + /* When we are central of an established connection and it enters * the disconnect timeout, then go ahead and try to read the * current clock offset. Processing of the result is done * within the event handling and hci_clock_offset_evt function. @@ -758,7 +758,7 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) conn->state = BT_CLOSED; /* If the status indicates successful cancellation of - * the attempt (i.e. Unkown Connection Id) there's no point of + * the attempt (i.e. Unknown Connection Id) there's no point of * notifying failure since we'll go back to keep trying to * connect. The only exception is explicit connect requests * where a timeout + cancel does indicate an actual failure. @@ -1109,9 +1109,9 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, hci_req_init(&req, hdev); - /* Disable advertising if we're active. For master role + /* Disable advertising if we're active. For central role * connections most controllers will refuse to connect if - * advertising is enabled, and for slave role connections we + * advertising is enabled, and for peripheral role connections we * anyway have to disable it in order to start directed * advertising. Any registered advertisements will be * re-enabled after the connection attempt is finished. @@ -1119,7 +1119,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, if (hci_dev_test_flag(hdev, HCI_LE_ADV)) __hci_req_pause_adv_instances(&req); - /* If requested to connect as slave use directed advertising */ + /* If requested to connect as peripheral use directed advertising */ if (conn->role == HCI_ROLE_SLAVE) { /* If we're active scanning most controllers are unable * to initiate advertising. Simply reject the attempt. @@ -1842,7 +1842,7 @@ u32 hci_conn_get_phy(struct hci_conn *conn) /* BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 2, Part B page 471: * Table 6.2: Packets defined for synchronous, asynchronous, and - * CSB logical transport types. + * CPB logical transport types. */ switch (conn->type) { case SCO_LINK: diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 7d71d104fdfd..2560ed2f144d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -545,24 +545,24 @@ static void hci_set_event_mask_page_2(struct hci_request *req) u8 events[8] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; bool changed = false; - /* If Connectionless Slave Broadcast master role is supported + /* If Connectionless Peripheral Broadcast central role is supported * enable all necessary events for it. */ - if (lmp_csb_master_capable(hdev)) { + if (lmp_cpb_central_capable(hdev)) { events[1] |= 0x40; /* Triggered Clock Capture */ events[1] |= 0x80; /* Synchronization Train Complete */ - events[2] |= 0x10; /* Slave Page Response Timeout */ - events[2] |= 0x20; /* CSB Channel Map Change */ + events[2] |= 0x10; /* Peripheral Page Response Timeout */ + events[2] |= 0x20; /* CPB Channel Map Change */ changed = true; } - /* If Connectionless Slave Broadcast slave role is supported + /* If Connectionless Peripheral Broadcast peripheral role is supported * enable all necessary events for it. */ - if (lmp_csb_slave_capable(hdev)) { + if (lmp_cpb_peripheral_capable(hdev)) { events[2] |= 0x01; /* Synchronization Train Received */ - events[2] |= 0x02; /* CSB Receive */ - events[2] |= 0x04; /* CSB Timeout */ + events[2] |= 0x02; /* CPB Receive */ + events[2] |= 0x04; /* CPB Timeout */ events[2] |= 0x08; /* Truncated Page Complete */ changed = true; } @@ -648,7 +648,7 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) */ /* If the controller supports Extended Scanner Filter - * Policies, enable the correspondig event. + * Policies, enable the corresponding event. */ if (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY) events[1] |= 0x04; /* LE Direct Advertising @@ -749,14 +749,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) } if (hdev->commands[26] & 0x40) { - /* Read LE White List Size */ - hci_req_add(req, HCI_OP_LE_READ_WHITE_LIST_SIZE, + /* Read LE Accept List Size */ + hci_req_add(req, HCI_OP_LE_READ_ACCEPT_LIST_SIZE, 0, NULL); } if (hdev->commands[26] & 0x80) { - /* Clear LE White List */ - hci_req_add(req, HCI_OP_LE_CLEAR_WHITE_LIST, 0, NULL); + /* Clear LE Accept List */ + hci_req_add(req, HCI_OP_LE_CLEAR_ACCEPT_LIST, 0, NULL); } if (hdev->commands[34] & 0x40) { @@ -1454,7 +1454,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) } /* Check for valid public address or a configured static - * random adddress, but let the HCI setup proceed to + * random address, but let the HCI setup proceed to * be able to determine if there is a public address * or not. * @@ -1721,15 +1721,8 @@ int hci_dev_do_close(struct hci_dev *hdev) BT_DBG("%s %p", hdev->name, hdev); - if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) && - !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && - test_bit(HCI_UP, &hdev->flags)) { - /* Execute vendor specific shutdown routine */ - if (hdev->shutdown) - hdev->shutdown(hdev); - } - cancel_delayed_work(&hdev->power_off); + cancel_delayed_work(&hdev->ncmd_timer); hci_request_cancel_all(hdev); hci_req_sync_lock(hdev); @@ -1805,6 +1798,14 @@ int hci_dev_do_close(struct hci_dev *hdev) clear_bit(HCI_INIT, &hdev->flags); } + if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) && + !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + test_bit(HCI_UP, &hdev->flags)) { + /* Execute vendor specific shutdown routine */ + if (hdev->shutdown) + hdev->shutdown(hdev); + } + /* flush cmd work */ flush_work(&hdev->cmd_work); @@ -2777,6 +2778,24 @@ static void hci_cmd_timeout(struct work_struct *work) queue_work(hdev->workqueue, &hdev->cmd_work); } +/* HCI ncmd timer function */ +static void hci_ncmd_timeout(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + ncmd_timer.work); + + bt_dev_err(hdev, "Controller not accepting commands anymore: ncmd = 0"); + + /* During HCI_INIT phase no events can be injected if the ncmd timer + * triggers since the procedure has its own timeout handling. + */ + if (test_bit(HCI_INIT, &hdev->flags)) + return; + + /* This is an irrecoverable state, inject hardware error event */ + hci_reset_dev(hdev); +} + struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { @@ -3549,7 +3568,7 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev) if (params->auto_connect != HCI_AUTO_CONN_DISABLED) continue; - /* If trying to estabilish one time connection to disabled + /* If trying to establish one time connection to disabled * device, leave the params, but mark them as just once. */ if (params->explicit_connect) { @@ -3694,13 +3713,13 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, /* Suspend consists of two actions: * - First, disconnect everything and make the controller not * connectable (disabling scanning) - * - Second, program event filter/whitelist and enable scan + * - Second, program event filter/accept list and enable scan */ ret = hci_change_suspend_state(hdev, BT_SUSPEND_DISCONNECT); if (!ret) state = BT_SUSPEND_DISCONNECT; - /* Only configure whitelist if disconnect succeeded and wake + /* Only configure accept list if disconnect succeeded and wake * isn't being prevented. */ if (!ret && !(hdev->prevent_wake && hdev->prevent_wake(hdev))) { @@ -3808,14 +3827,14 @@ struct hci_dev *hci_alloc_dev(void) mutex_init(&hdev->req_lock); INIT_LIST_HEAD(&hdev->mgmt_pending); - INIT_LIST_HEAD(&hdev->blacklist); - INIT_LIST_HEAD(&hdev->whitelist); + INIT_LIST_HEAD(&hdev->reject_list); + INIT_LIST_HEAD(&hdev->accept_list); INIT_LIST_HEAD(&hdev->uuids); INIT_LIST_HEAD(&hdev->link_keys); INIT_LIST_HEAD(&hdev->long_term_keys); INIT_LIST_HEAD(&hdev->identity_resolving_keys); INIT_LIST_HEAD(&hdev->remote_oob_data); - INIT_LIST_HEAD(&hdev->le_white_list); + INIT_LIST_HEAD(&hdev->le_accept_list); INIT_LIST_HEAD(&hdev->le_resolv_list); INIT_LIST_HEAD(&hdev->le_conn_params); INIT_LIST_HEAD(&hdev->pend_le_conns); @@ -3841,6 +3860,7 @@ struct hci_dev *hci_alloc_dev(void) init_waitqueue_head(&hdev->suspend_wait_q); INIT_DELAYED_WORK(&hdev->cmd_timer, hci_cmd_timeout); + INIT_DELAYED_WORK(&hdev->ncmd_timer, hci_ncmd_timeout); hci_request_setup(hdev); @@ -4027,8 +4047,8 @@ void hci_unregister_dev(struct hci_dev *hdev) destroy_workqueue(hdev->req_workqueue); hci_dev_lock(hdev); - hci_bdaddr_list_clear(&hdev->blacklist); - hci_bdaddr_list_clear(&hdev->whitelist); + hci_bdaddr_list_clear(&hdev->reject_list); + hci_bdaddr_list_clear(&hdev->accept_list); hci_uuids_clear(hdev); hci_link_keys_clear(hdev); hci_smp_ltks_clear(hdev); @@ -4036,7 +4056,7 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_remote_oob_data_clear(hdev); hci_adv_instances_clear(hdev); hci_adv_monitors_clear(hdev); - hci_bdaddr_list_clear(&hdev->le_white_list); + hci_bdaddr_list_clear(&hdev->le_accept_list); hci_bdaddr_list_clear(&hdev->le_resolv_list); hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); @@ -4078,6 +4098,8 @@ int hci_reset_dev(struct hci_dev *hdev) hci_skb_pkt_type(skb) = HCI_EVENT_PKT; skb_put_data(skb, hw_err, 3); + bt_dev_err(hdev, "Injecting HCI hardware error event"); + /* Send Hardware Error to upper stack */ return hci_recv_frame(hdev, skb); } @@ -4284,7 +4306,7 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE; } -/* Send HCI command and wait for command commplete event */ +/* Send HCI command and wait for command complete event */ struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param, u32 timeout) { diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 47f4f21fbc1a..841393389f7b 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -125,7 +125,7 @@ static int device_list_show(struct seq_file *f, void *ptr) struct bdaddr_list *b; hci_dev_lock(hdev); - list_for_each_entry(b, &hdev->whitelist, list) + list_for_each_entry(b, &hdev->accept_list, list) seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); list_for_each_entry(p, &hdev->le_conn_params, list) { seq_printf(f, "%pMR (type %u) %u\n", &p->addr, p->addr_type, @@ -144,7 +144,7 @@ static int blacklist_show(struct seq_file *f, void *p) struct bdaddr_list *b; hci_dev_lock(hdev); - list_for_each_entry(b, &hdev->blacklist, list) + list_for_each_entry(b, &hdev->reject_list, list) seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); hci_dev_unlock(hdev); @@ -784,7 +784,7 @@ static int white_list_show(struct seq_file *f, void *ptr) struct bdaddr_list *b; hci_dev_lock(hdev); - list_for_each_entry(b, &hdev->le_white_list, list) + list_for_each_entry(b, &hdev->le_accept_list, list) seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); hci_dev_unlock(hdev); @@ -1195,7 +1195,7 @@ void hci_debugfs_create_le(struct hci_dev *hdev) &force_static_address_fops); debugfs_create_u8("white_list_size", 0444, hdev->debugfs, - &hdev->le_white_list_size); + &hdev->le_accept_list_size); debugfs_create_file("white_list", 0444, hdev->debugfs, hdev, &white_list_fops); debugfs_create_u8("resolv_list_size", 0444, hdev->debugfs, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 016b2999f219..1c3018202564 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -236,7 +236,7 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) hdev->ssp_debug_mode = 0; - hci_bdaddr_list_clear(&hdev->le_white_list); + hci_bdaddr_list_clear(&hdev->le_accept_list); hci_bdaddr_list_clear(&hdev->le_resolv_list); } @@ -1492,21 +1492,21 @@ static void hci_cc_le_read_num_adv_sets(struct hci_dev *hdev, hdev->le_num_of_adv_sets = rp->num_of_sets; } -static void hci_cc_le_read_white_list_size(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_cc_le_read_accept_list_size(struct hci_dev *hdev, + struct sk_buff *skb) { - struct hci_rp_le_read_white_list_size *rp = (void *) skb->data; + struct hci_rp_le_read_accept_list_size *rp = (void *)skb->data; BT_DBG("%s status 0x%2.2x size %u", hdev->name, rp->status, rp->size); if (rp->status) return; - hdev->le_white_list_size = rp->size; + hdev->le_accept_list_size = rp->size; } -static void hci_cc_le_clear_white_list(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_cc_le_clear_accept_list(struct hci_dev *hdev, + struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); @@ -1515,13 +1515,13 @@ static void hci_cc_le_clear_white_list(struct hci_dev *hdev, if (status) return; - hci_bdaddr_list_clear(&hdev->le_white_list); + hci_bdaddr_list_clear(&hdev->le_accept_list); } -static void hci_cc_le_add_to_white_list(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_cc_le_add_to_accept_list(struct hci_dev *hdev, + struct sk_buff *skb) { - struct hci_cp_le_add_to_white_list *sent; + struct hci_cp_le_add_to_accept_list *sent; __u8 status = *((__u8 *) skb->data); BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -1529,18 +1529,18 @@ static void hci_cc_le_add_to_white_list(struct hci_dev *hdev, if (status) return; - sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_WHITE_LIST); + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_ACCEPT_LIST); if (!sent) return; - hci_bdaddr_list_add(&hdev->le_white_list, &sent->bdaddr, - sent->bdaddr_type); + hci_bdaddr_list_add(&hdev->le_accept_list, &sent->bdaddr, + sent->bdaddr_type); } -static void hci_cc_le_del_from_white_list(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_cc_le_del_from_accept_list(struct hci_dev *hdev, + struct sk_buff *skb) { - struct hci_cp_le_del_from_white_list *sent; + struct hci_cp_le_del_from_accept_list *sent; __u8 status = *((__u8 *) skb->data); BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -1548,11 +1548,11 @@ static void hci_cc_le_del_from_white_list(struct hci_dev *hdev, if (status) return; - sent = hci_sent_cmd_data(hdev, HCI_OP_LE_DEL_FROM_WHITE_LIST); + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_DEL_FROM_ACCEPT_LIST); if (!sent) return; - hci_bdaddr_list_del(&hdev->le_white_list, &sent->bdaddr, + hci_bdaddr_list_del(&hdev->le_accept_list, &sent->bdaddr, sent->bdaddr_type); } @@ -2069,7 +2069,7 @@ static void hci_check_pending_name(struct hci_dev *hdev, struct hci_conn *conn, if (conn && (conn->state == BT_CONFIG || conn->state == BT_CONNECTED) && !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, 0, name, name_len); + mgmt_device_connected(hdev, conn, name, name_len); if (discov->state == DISCOVERY_STOPPED) return; @@ -2367,7 +2367,7 @@ static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr, /* We don't want the connection attempt to stick around * indefinitely since LE doesn't have a page timeout concept * like BR/EDR. Set a timer for any connection that doesn't use - * the white list for connecting. + * the accept list for connecting. */ if (filter_policy == HCI_LE_USE_PEER_ADDR) queue_delayed_work(conn->hdev->workqueue, @@ -2623,7 +2623,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) * only used during suspend. */ if (ev->link_type == ACL_LINK && - hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, + hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &ev->bdaddr, BDADDR_BREDR)) { conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr, @@ -2745,19 +2745,19 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) return; } - if (hci_bdaddr_list_lookup(&hdev->blacklist, &ev->bdaddr, + if (hci_bdaddr_list_lookup(&hdev->reject_list, &ev->bdaddr, BDADDR_BREDR)) { hci_reject_conn(hdev, &ev->bdaddr); return; } - /* Require HCI_CONNECTABLE or a whitelist entry to accept the + /* Require HCI_CONNECTABLE or an accept list entry to accept the * connection. These features are only touched through mgmt so * only do the checks if HCI_MGMT is set. */ if (hci_dev_test_flag(hdev, HCI_MGMT) && !hci_dev_test_flag(hdev, HCI_CONNECTABLE) && - !hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, &ev->bdaddr, + !hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &ev->bdaddr, BDADDR_BREDR)) { hci_reject_conn(hdev, &ev->bdaddr); return; @@ -2795,9 +2795,9 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) bacpy(&cp.bdaddr, &ev->bdaddr); if (lmp_rswitch_capable(hdev) && (mask & HCI_LM_MASTER)) - cp.role = 0x00; /* Become master */ + cp.role = 0x00; /* Become central */ else - cp.role = 0x01; /* Remain slave */ + cp.role = 0x01; /* Remain peripheral */ hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp); } else if (!(flags & HCI_PROTO_DEFER)) { @@ -3256,7 +3256,7 @@ static void hci_remote_features_evt(struct hci_dev *hdev, cp.pscan_rep_mode = 0x02; hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); } else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, 0, NULL, 0); + mgmt_device_connected(hdev, conn, NULL, 0); if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; @@ -3268,6 +3268,23 @@ unlock: hci_dev_unlock(hdev); } +static inline void handle_cmd_cnt_and_timer(struct hci_dev *hdev, + u16 opcode, u8 ncmd) +{ + if (opcode != HCI_OP_NOP) + cancel_delayed_work(&hdev->cmd_timer); + + if (!test_bit(HCI_RESET, &hdev->flags)) { + if (ncmd) { + cancel_delayed_work(&hdev->ncmd_timer); + atomic_set(&hdev->cmd_cnt, 1); + } else { + schedule_delayed_work(&hdev->ncmd_timer, + HCI_NCMD_TIMEOUT); + } + } +} + static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, u16 *opcode, u8 *status, hci_req_complete_t *req_complete, @@ -3521,20 +3538,20 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_le_set_scan_enable(hdev, skb); break; - case HCI_OP_LE_READ_WHITE_LIST_SIZE: - hci_cc_le_read_white_list_size(hdev, skb); + case HCI_OP_LE_READ_ACCEPT_LIST_SIZE: + hci_cc_le_read_accept_list_size(hdev, skb); break; - case HCI_OP_LE_CLEAR_WHITE_LIST: - hci_cc_le_clear_white_list(hdev, skb); + case HCI_OP_LE_CLEAR_ACCEPT_LIST: + hci_cc_le_clear_accept_list(hdev, skb); break; - case HCI_OP_LE_ADD_TO_WHITE_LIST: - hci_cc_le_add_to_white_list(hdev, skb); + case HCI_OP_LE_ADD_TO_ACCEPT_LIST: + hci_cc_le_add_to_accept_list(hdev, skb); break; - case HCI_OP_LE_DEL_FROM_WHITE_LIST: - hci_cc_le_del_from_white_list(hdev, skb); + case HCI_OP_LE_DEL_FROM_ACCEPT_LIST: + hci_cc_le_del_from_accept_list(hdev, skb); break; case HCI_OP_LE_READ_SUPPORTED_STATES: @@ -3630,11 +3647,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, break; } - if (*opcode != HCI_OP_NOP) - cancel_delayed_work(&hdev->cmd_timer); - - if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) - atomic_set(&hdev->cmd_cnt, 1); + handle_cmd_cnt_and_timer(hdev, *opcode, ev->ncmd); hci_req_cmd_complete(hdev, *opcode, *status, req_complete, req_complete_skb); @@ -3735,11 +3748,7 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb, break; } - if (*opcode != HCI_OP_NOP) - cancel_delayed_work(&hdev->cmd_timer); - - if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) - atomic_set(&hdev->cmd_cnt, 1); + handle_cmd_cnt_and_timer(hdev, *opcode, ev->ncmd); /* Indicate request completion if the command failed. Also, if * we're not waiting for a special event and we get a success @@ -4330,7 +4339,7 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev, cp.pscan_rep_mode = 0x02; hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); } else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, 0, NULL, 0); + mgmt_device_connected(hdev, conn, NULL, 0); if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; @@ -4404,12 +4413,12 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, bt_dev_dbg(hdev, "SCO connected with air mode: %02x", ev->air_mode); - switch (conn->setting & SCO_AIRMODE_MASK) { - case SCO_AIRMODE_CVSD: + switch (ev->air_mode) { + case 0x02: if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_ENABLE_SCO_CVSD); break; - case SCO_AIRMODE_TRANSP: + case 0x03: if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_ENABLE_SCO_TRANSP); break; @@ -5122,8 +5131,8 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->dst_type = bdaddr_type; /* If we didn't have a hci_conn object previously - * but we're in master role this must be something - * initiated using a white list. Since white list based + * but we're in central role this must be something + * initiated using an accept list. Since accept list based * connections are not "first class citizens" we don't * have full tracking of them. Therefore, we go ahead * with a "best effort" approach of determining the @@ -5187,6 +5196,23 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->dst_type = irk->addr_type; } + /* When using controller based address resolution, then the new + * address types 0x02 and 0x03 are used. These types need to be + * converted back into either public address or random address type + */ + if (use_ll_privacy(hdev) && + hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && + hci_dev_test_flag(hdev, HCI_LL_RPA_RESOLUTION)) { + switch (conn->dst_type) { + case ADDR_LE_DEV_PUBLIC_RESOLVED: + conn->dst_type = ADDR_LE_DEV_PUBLIC; + break; + case ADDR_LE_DEV_RANDOM_RESOLVED: + conn->dst_type = ADDR_LE_DEV_RANDOM; + break; + } + } + if (status) { hci_le_conn_failed(conn, status); goto unlock; @@ -5198,13 +5224,13 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, addr_type = BDADDR_LE_RANDOM; /* Drop the connection if the device is blocked */ - if (hci_bdaddr_list_lookup(&hdev->blacklist, &conn->dst, addr_type)) { + if (hci_bdaddr_list_lookup(&hdev->reject_list, &conn->dst, addr_type)) { hci_conn_drop(conn); goto unlock; } if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, 0, NULL, 0); + mgmt_device_connected(hdev, conn, NULL, 0); conn->sec_level = BT_SECURITY_LOW; conn->handle = handle; @@ -5217,17 +5243,17 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, hci_debugfs_create_conn(conn); hci_conn_add_sysfs(conn); - /* The remote features procedure is defined for master + /* The remote features procedure is defined for central * role only. So only in case of an initiated connection * request the remote features. * - * If the local controller supports slave-initiated features - * exchange, then requesting the remote features in slave + * If the local controller supports peripheral-initiated features + * exchange, then requesting the remote features in peripheral * role is possible. Otherwise just transition into the * connected state without requesting the remote features. */ if (conn->out || - (hdev->le_features[0] & HCI_LE_SLAVE_FEATURES)) { + (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) { struct hci_cp_le_read_remote_features cp; cp.handle = __cpu_to_le16(conn->handle); @@ -5296,8 +5322,19 @@ static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); - if (ev->status) + if (ev->status) { + struct adv_info *adv; + + adv = hci_find_adv_instance(hdev, ev->handle); + if (!adv) + return; + + /* Remove advertising as it has been terminated */ + hci_remove_adv_instance(hdev, ev->handle); + mgmt_advertising_removed(NULL, hdev, ev->handle); + return; + } conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->conn_handle)); if (conn) { @@ -5354,13 +5391,13 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, return NULL; /* Ignore if the device is blocked */ - if (hci_bdaddr_list_lookup(&hdev->blacklist, addr, addr_type)) + if (hci_bdaddr_list_lookup(&hdev->reject_list, addr, addr_type)) return NULL; /* Most controller will fail if we try to create new connections - * while we have an existing one in slave role. + * while we have an existing one in peripheral role. */ - if (hdev->conn_hash.le_num_slave > 0 && + if (hdev->conn_hash.le_num_peripheral > 0 && (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) || !(hdev->le_states[3] & 0x10))) return NULL; @@ -5378,7 +5415,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, case HCI_AUTO_CONN_DIRECT: /* Only devices advertising with ADV_DIRECT_IND are * triggering a connection attempt. This is allowing - * incoming connections from slave devices. + * incoming connections from peripheral devices. */ if (adv_type != LE_ADV_DIRECT_IND) return NULL; @@ -5386,8 +5423,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, case HCI_AUTO_CONN_ALWAYS: /* Devices advertising with ADV_IND or ADV_DIRECT_IND * are triggering a connection attempt. This means - * that incoming connections from slave device are - * accepted and also outgoing connections to slave + * that incoming connections from peripheral device are + * accepted and also outgoing connections to peripheral * devices are established when found. */ break; @@ -5441,7 +5478,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, struct hci_conn *conn; bool match; u32 flags; - u8 *ptr, real_len; + u8 *ptr; switch (type) { case LE_ADV_IND: @@ -5472,14 +5509,10 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, break; } - real_len = ptr - data; - - /* Adjust for actual length */ - if (len != real_len) { - bt_dev_err_ratelimited(hdev, "advertising data len corrected %u -> %u", - len, real_len); - len = real_len; - } + /* Adjust for actual length. This handles the case when remote + * device is advertising with incorrect data length. + */ + len = ptr - data; /* If the direct address is present, then this report is from * a LE Direct Advertising Report event. In that case it is @@ -5752,7 +5785,7 @@ static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, if (conn->state == BT_CONFIG) { __u8 status; - /* If the local controller supports slave-initiated + /* If the local controller supports peripheral-initiated * features exchange, but the remote controller does * not, then it is possible that the error code 0x1a * for unsupported remote feature gets returned. @@ -5761,8 +5794,8 @@ static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, * transition into connected state and mark it as * successful. */ - if ((hdev->le_features[0] & HCI_LE_SLAVE_FEATURES) && - !conn->out && ev->status == 0x1a) + if (!conn->out && ev->status == 0x1a && + (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) status = 0x00; else status = ev->status; @@ -6032,7 +6065,7 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, return true; } - /* Check if request ended in Command Status - no way to retreive + /* Check if request ended in Command Status - no way to retrieve * any extra parameters in this case. */ if (hdr->evt == HCI_EV_CMD_STATUS) diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index fa9125b782f8..1d14adc023e9 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -745,17 +745,17 @@ void hci_req_add_le_scan_disable(struct hci_request *req, bool rpa_le_conn) } } -static void del_from_white_list(struct hci_request *req, bdaddr_t *bdaddr, - u8 bdaddr_type) +static void del_from_accept_list(struct hci_request *req, bdaddr_t *bdaddr, + u8 bdaddr_type) { - struct hci_cp_le_del_from_white_list cp; + struct hci_cp_le_del_from_accept_list cp; cp.bdaddr_type = bdaddr_type; bacpy(&cp.bdaddr, bdaddr); - bt_dev_dbg(req->hdev, "Remove %pMR (0x%x) from whitelist", &cp.bdaddr, + bt_dev_dbg(req->hdev, "Remove %pMR (0x%x) from accept list", &cp.bdaddr, cp.bdaddr_type); - hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, sizeof(cp), &cp); + hci_req_add(req, HCI_OP_LE_DEL_FROM_ACCEPT_LIST, sizeof(cp), &cp); if (use_ll_privacy(req->hdev) && hci_dev_test_flag(req->hdev, HCI_ENABLE_LL_PRIVACY)) { @@ -774,31 +774,31 @@ static void del_from_white_list(struct hci_request *req, bdaddr_t *bdaddr, } } -/* Adds connection to white list if needed. On error, returns -1. */ -static int add_to_white_list(struct hci_request *req, - struct hci_conn_params *params, u8 *num_entries, - bool allow_rpa) +/* Adds connection to accept list if needed. On error, returns -1. */ +static int add_to_accept_list(struct hci_request *req, + struct hci_conn_params *params, u8 *num_entries, + bool allow_rpa) { - struct hci_cp_le_add_to_white_list cp; + struct hci_cp_le_add_to_accept_list cp; struct hci_dev *hdev = req->hdev; - /* Already in white list */ - if (hci_bdaddr_list_lookup(&hdev->le_white_list, ¶ms->addr, + /* Already in accept list */ + if (hci_bdaddr_list_lookup(&hdev->le_accept_list, ¶ms->addr, params->addr_type)) return 0; /* Select filter policy to accept all advertising */ - if (*num_entries >= hdev->le_white_list_size) + if (*num_entries >= hdev->le_accept_list_size) return -1; - /* White list can not be used with RPAs */ + /* Accept list can not be used with RPAs */ if (!allow_rpa && !hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type)) { return -1; } - /* During suspend, only wakeable devices can be in whitelist */ + /* During suspend, only wakeable devices can be in accept list */ if (hdev->suspended && !hci_conn_test_flag(HCI_CONN_FLAG_REMOTE_WAKEUP, params->current_flags)) return 0; @@ -807,9 +807,9 @@ static int add_to_white_list(struct hci_request *req, cp.bdaddr_type = params->addr_type; bacpy(&cp.bdaddr, ¶ms->addr); - bt_dev_dbg(hdev, "Add %pMR (0x%x) to whitelist", &cp.bdaddr, + bt_dev_dbg(hdev, "Add %pMR (0x%x) to accept list", &cp.bdaddr, cp.bdaddr_type); - hci_req_add(req, HCI_OP_LE_ADD_TO_WHITE_LIST, sizeof(cp), &cp); + hci_req_add(req, HCI_OP_LE_ADD_TO_ACCEPT_LIST, sizeof(cp), &cp); if (use_ll_privacy(hdev) && hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) { @@ -837,15 +837,15 @@ static int add_to_white_list(struct hci_request *req, return 0; } -static u8 update_white_list(struct hci_request *req) +static u8 update_accept_list(struct hci_request *req) { struct hci_dev *hdev = req->hdev; struct hci_conn_params *params; struct bdaddr_list *b; u8 num_entries = 0; bool pend_conn, pend_report; - /* We allow whitelisting even with RPAs in suspend. In the worst case, - * we won't be able to wake from devices that use the privacy1.2 + /* We allow usage of accept list even with RPAs in suspend. In the worst + * case, we won't be able to wake from devices that use the privacy1.2 * features. Additionally, once we support privacy1.2 and IRK * offloading, we can update this to also check for those conditions. */ @@ -855,13 +855,13 @@ static u8 update_white_list(struct hci_request *req) hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) allow_rpa = true; - /* Go through the current white list programmed into the + /* Go through the current accept list programmed into the * controller one by one and check if that address is still * in the list of pending connections or list of devices to * report. If not present in either list, then queue the * command to remove it from the controller. */ - list_for_each_entry(b, &hdev->le_white_list, list) { + list_for_each_entry(b, &hdev->le_accept_list, list) { pend_conn = hci_pend_le_action_lookup(&hdev->pend_le_conns, &b->bdaddr, b->bdaddr_type); @@ -870,14 +870,14 @@ static u8 update_white_list(struct hci_request *req) b->bdaddr_type); /* If the device is not likely to connect or report, - * remove it from the whitelist. + * remove it from the accept list. */ if (!pend_conn && !pend_report) { - del_from_white_list(req, &b->bdaddr, b->bdaddr_type); + del_from_accept_list(req, &b->bdaddr, b->bdaddr_type); continue; } - /* White list can not be used with RPAs */ + /* Accept list can not be used with RPAs */ if (!allow_rpa && !hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && hci_find_irk_by_addr(hdev, &b->bdaddr, b->bdaddr_type)) { @@ -887,27 +887,27 @@ static u8 update_white_list(struct hci_request *req) num_entries++; } - /* Since all no longer valid white list entries have been + /* Since all no longer valid accept list entries have been * removed, walk through the list of pending connections * and ensure that any new device gets programmed into * the controller. * * If the list of the devices is larger than the list of - * available white list entries in the controller, then + * available accept list entries in the controller, then * just abort and return filer policy value to not use the - * white list. + * accept list. */ list_for_each_entry(params, &hdev->pend_le_conns, action) { - if (add_to_white_list(req, params, &num_entries, allow_rpa)) + if (add_to_accept_list(req, params, &num_entries, allow_rpa)) return 0x00; } /* After adding all new pending connections, walk through * the list of pending reports and also add these to the - * white list if there is still space. Abort if space runs out. + * accept list if there is still space. Abort if space runs out. */ list_for_each_entry(params, &hdev->pend_le_reports, action) { - if (add_to_white_list(req, params, &num_entries, allow_rpa)) + if (add_to_accept_list(req, params, &num_entries, allow_rpa)) return 0x00; } @@ -921,7 +921,7 @@ static u8 update_white_list(struct hci_request *req) hdev->interleave_scan_state != INTERLEAVE_SCAN_ALLOWLIST) return 0x00; - /* Select filter policy to use white list */ + /* Select filter policy to use accept list */ return 0x01; } @@ -932,7 +932,7 @@ static bool scan_use_rpa(struct hci_dev *hdev) static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, u16 window, u8 own_addr_type, u8 filter_policy, - bool addr_resolv) + bool filter_dup, bool addr_resolv) { struct hci_dev *hdev = req->hdev; @@ -997,7 +997,7 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, memset(&ext_enable_cp, 0, sizeof(ext_enable_cp)); ext_enable_cp.enable = LE_SCAN_ENABLE; - ext_enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + ext_enable_cp.filter_dup = filter_dup; hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, sizeof(ext_enable_cp), &ext_enable_cp); @@ -1016,7 +1016,7 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, memset(&enable_cp, 0, sizeof(enable_cp)); enable_cp.enable = LE_SCAN_ENABLE; - enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + enable_cp.filter_dup = filter_dup; hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), &enable_cp); } @@ -1053,6 +1053,8 @@ void hci_req_add_le_passive_scan(struct hci_request *req) u8 own_addr_type; u8 filter_policy; u16 window, interval; + /* Default is to enable duplicates filter */ + u8 filter_dup = LE_SCAN_FILTER_DUP_ENABLE; /* Background scanning should run with address resolution */ bool addr_resolv = true; @@ -1076,20 +1078,20 @@ void hci_req_add_le_passive_scan(struct hci_request *req) return; bt_dev_dbg(hdev, "interleave state %d", hdev->interleave_scan_state); - /* Adding or removing entries from the white list must + /* Adding or removing entries from the accept list must * happen before enabling scanning. The controller does - * not allow white list modification while scanning. + * not allow accept list modification while scanning. */ - filter_policy = update_white_list(req); + filter_policy = update_accept_list(req); /* When the controller is using random resolvable addresses and * with that having LE privacy enabled, then controllers with * Extended Scanner Filter Policies support can now enable support * for handling directed advertising. * - * So instead of using filter polices 0x00 (no whitelist) - * and 0x01 (whitelist enabled) use the new filter policies - * 0x02 (no whitelist) and 0x03 (whitelist enabled). + * So instead of using filter polices 0x00 (no accept list) + * and 0x01 (accept list enabled) use the new filter policies + * 0x02 (no accept list) and 0x03 (accept list enabled). */ if (hci_dev_test_flag(hdev, HCI_PRIVACY) && (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY)) @@ -1106,14 +1108,30 @@ void hci_req_add_le_passive_scan(struct hci_request *req) } else if (hci_is_adv_monitoring(hdev)) { window = hdev->le_scan_window_adv_monitor; interval = hdev->le_scan_int_adv_monitor; + + /* Disable duplicates filter when scanning for advertisement + * monitor for the following reasons. + * + * For HW pattern filtering (ex. MSFT), Realtek and Qualcomm + * controllers ignore RSSI_Sampling_Period when the duplicates + * filter is enabled. + * + * For SW pattern filtering, when we're not doing interleaved + * scanning, it is necessary to disable duplicates filter, + * otherwise hosts can only receive one advertisement and it's + * impossible to know if a peer is still in range. + */ + filter_dup = LE_SCAN_FILTER_DUP_DISABLE; } else { window = hdev->le_scan_window; interval = hdev->le_scan_interval; } - bt_dev_dbg(hdev, "LE passive scan with whitelist = %d", filter_policy); + bt_dev_dbg(hdev, "LE passive scan with accept list = %d", + filter_policy); hci_req_start_scan(req, LE_SCAN_PASSIVE, interval, window, - own_addr_type, filter_policy, addr_resolv); + own_addr_type, filter_policy, filter_dup, + addr_resolv); } static bool adv_instance_is_scannable(struct hci_dev *hdev, u8 instance) @@ -1163,7 +1181,7 @@ static void hci_req_set_event_filter(struct hci_request *req) /* Always clear event filter when starting */ hci_req_clear_event_filter(req); - list_for_each_entry(b, &hdev->whitelist, list) { + list_for_each_entry(b, &hdev->accept_list, list) { if (!hci_conn_test_flag(HCI_CONN_FLAG_REMOTE_WAKEUP, b->current_flags)) continue; @@ -1502,13 +1520,14 @@ static bool is_advertising_allowed(struct hci_dev *hdev, bool connectable) if (hci_conn_num(hdev, LE_LINK) == 0) return true; - /* Check le_states if there is any connection in slave role. */ - if (hdev->conn_hash.le_num_slave > 0) { - /* Slave connection state and non connectable mode bit 20. */ + /* Check le_states if there is any connection in peripheral role. */ + if (hdev->conn_hash.le_num_peripheral > 0) { + /* Peripheral connection state and non connectable mode bit 20. + */ if (!connectable && !(hdev->le_states[2] & 0x10)) return false; - /* Slave connection state and connectable mode bit 38 + /* Peripheral connection state and connectable mode bit 38 * and scannable bit 21. */ if (connectable && (!(hdev->le_states[4] & 0x40) || @@ -1516,13 +1535,13 @@ static bool is_advertising_allowed(struct hci_dev *hdev, bool connectable) return false; } - /* Check le_states if there is any connection in master role. */ - if (hci_conn_num(hdev, LE_LINK) != hdev->conn_hash.le_num_slave) { - /* Master connection state and non connectable mode bit 18. */ + /* Check le_states if there is any connection in central role. */ + if (hci_conn_num(hdev, LE_LINK) != hdev->conn_hash.le_num_peripheral) { + /* Central connection state and non connectable mode bit 18. */ if (!connectable && !(hdev->le_states[2] & 0x02)) return false; - /* Master connection state and connectable mode bit 35 and + /* Central connection state and connectable mode bit 35 and * scannable 19. */ if (connectable && (!(hdev->le_states[4] & 0x08) || @@ -1697,30 +1716,33 @@ void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance) return; if (ext_adv_capable(hdev)) { - struct hci_cp_le_set_ext_scan_rsp_data cp; + struct { + struct hci_cp_le_set_ext_scan_rsp_data cp; + u8 data[HCI_MAX_EXT_AD_LENGTH]; + } pdu; - memset(&cp, 0, sizeof(cp)); + memset(&pdu, 0, sizeof(pdu)); if (instance) len = create_instance_scan_rsp_data(hdev, instance, - cp.data); + pdu.data); else - len = create_default_scan_rsp_data(hdev, cp.data); + len = create_default_scan_rsp_data(hdev, pdu.data); if (hdev->scan_rsp_data_len == len && - !memcmp(cp.data, hdev->scan_rsp_data, len)) + !memcmp(pdu.data, hdev->scan_rsp_data, len)) return; - memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); + memcpy(hdev->scan_rsp_data, pdu.data, len); hdev->scan_rsp_data_len = len; - cp.handle = instance; - cp.length = len; - cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; - cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; + pdu.cp.handle = instance; + pdu.cp.length = len; + pdu.cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; + pdu.cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; - hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_RSP_DATA, sizeof(cp), - &cp); + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_RSP_DATA, + sizeof(pdu.cp) + len, &pdu.cp); } else { struct hci_cp_le_set_scan_rsp_data cp; @@ -1843,26 +1865,30 @@ void __hci_req_update_adv_data(struct hci_request *req, u8 instance) return; if (ext_adv_capable(hdev)) { - struct hci_cp_le_set_ext_adv_data cp; + struct { + struct hci_cp_le_set_ext_adv_data cp; + u8 data[HCI_MAX_EXT_AD_LENGTH]; + } pdu; - memset(&cp, 0, sizeof(cp)); + memset(&pdu, 0, sizeof(pdu)); - len = create_instance_adv_data(hdev, instance, cp.data); + len = create_instance_adv_data(hdev, instance, pdu.data); /* There's nothing to do if the data hasn't changed */ if (hdev->adv_data_len == len && - memcmp(cp.data, hdev->adv_data, len) == 0) + memcmp(pdu.data, hdev->adv_data, len) == 0) return; - memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); + memcpy(hdev->adv_data, pdu.data, len); hdev->adv_data_len = len; - cp.length = len; - cp.handle = instance; - cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; - cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; + pdu.cp.length = len; + pdu.cp.handle = instance; + pdu.cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; + pdu.cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; - hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_DATA, sizeof(cp), &cp); + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_DATA, + sizeof(pdu.cp) + len, &pdu.cp); } else { struct hci_cp_le_set_adv_data cp; @@ -2605,11 +2631,11 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, return 0; } -static bool disconnected_whitelist_entries(struct hci_dev *hdev) +static bool disconnected_accept_list_entries(struct hci_dev *hdev) { struct bdaddr_list *b; - list_for_each_entry(b, &hdev->whitelist, list) { + list_for_each_entry(b, &hdev->accept_list, list) { struct hci_conn *conn; conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &b->bdaddr); @@ -2641,7 +2667,7 @@ void __hci_req_update_scan(struct hci_request *req) return; if (hci_dev_test_flag(hdev, HCI_CONNECTABLE) || - disconnected_whitelist_entries(hdev)) + disconnected_accept_list_entries(hdev)) scan = SCAN_PAGE; else scan = SCAN_DISABLED; @@ -3133,8 +3159,10 @@ static int active_scan(struct hci_request *req, unsigned long opt) uint16_t interval = opt; struct hci_dev *hdev = req->hdev; u8 own_addr_type; - /* White list is not used for discovery */ + /* Accept list is not used for discovery */ u8 filter_policy = 0x00; + /* Default is to enable duplicates filter */ + u8 filter_dup = LE_SCAN_FILTER_DUP_ENABLE; /* Discovery doesn't require controller address resolution */ bool addr_resolv = false; int err; @@ -3159,9 +3187,26 @@ static int active_scan(struct hci_request *req, unsigned long opt) if (err < 0) own_addr_type = ADDR_LE_DEV_PUBLIC; + if (hci_is_adv_monitoring(hdev)) { + /* Duplicate filter should be disabled when some advertisement + * monitor is activated, otherwise AdvMon can only receive one + * advertisement for one peer(*) during active scanning, and + * might report loss to these peers. + * + * Note that different controllers have different meanings of + * |duplicate|. Some of them consider packets with the same + * address as duplicate, and others consider packets with the + * same address and the same RSSI as duplicate. Although in the + * latter case we don't need to disable duplicate filter, but + * it is common to have active scanning for a short period of + * time, the power impact should be neglectable. + */ + filter_dup = LE_SCAN_FILTER_DUP_DISABLE; + } + hci_req_start_scan(req, LE_SCAN_ACTIVE, interval, hdev->le_scan_window_discovery, own_addr_type, - filter_policy, addr_resolv); + filter_policy, filter_dup, addr_resolv); return 0; } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index eed0dd066e12..b04a5a02ecf3 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -892,7 +892,7 @@ static int hci_sock_release(struct socket *sock) return 0; } -static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) +static int hci_sock_reject_list_add(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; int err; @@ -902,14 +902,14 @@ static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) hci_dev_lock(hdev); - err = hci_bdaddr_list_add(&hdev->blacklist, &bdaddr, BDADDR_BREDR); + err = hci_bdaddr_list_add(&hdev->reject_list, &bdaddr, BDADDR_BREDR); hci_dev_unlock(hdev); return err; } -static int hci_sock_blacklist_del(struct hci_dev *hdev, void __user *arg) +static int hci_sock_reject_list_del(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; int err; @@ -919,7 +919,7 @@ static int hci_sock_blacklist_del(struct hci_dev *hdev, void __user *arg) hci_dev_lock(hdev); - err = hci_bdaddr_list_del(&hdev->blacklist, &bdaddr, BDADDR_BREDR); + err = hci_bdaddr_list_del(&hdev->reject_list, &bdaddr, BDADDR_BREDR); hci_dev_unlock(hdev); @@ -959,12 +959,12 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, case HCIBLOCKADDR: if (!capable(CAP_NET_ADMIN)) return -EPERM; - return hci_sock_blacklist_add(hdev, (void __user *)arg); + return hci_sock_reject_list_add(hdev, (void __user *)arg); case HCIUNBLOCKADDR: if (!capable(CAP_NET_ADMIN)) return -EPERM; - return hci_sock_blacklist_del(hdev, (void __user *)arg); + return hci_sock_reject_list_del(hdev, (void __user *)arg); } return -ENOIOCTLCMD; @@ -1130,7 +1130,7 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, if (!hci_sock_gen_cookie(sk)) { /* In the case when a cookie has already been assigned, * then there has been already an ioctl issued against - * an unbound socket and with that triggerd an open + * an unbound socket and with that triggered an open * notification. Send a close notification first to * allow the state transition to bounded. */ @@ -1326,9 +1326,9 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, if (hci_pi(sk)->channel == HCI_CHANNEL_CONTROL) { if (!hci_sock_gen_cookie(sk)) { /* In the case when a cookie has already been - * assigned, this socket will transtion from + * assigned, this socket will transition from * a raw socket into a control socket. To - * allow for a clean transtion, send the + * allow for a clean transition, send the * close notification first. */ skb = create_monitor_ctrl_close(sk); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 0db48c812662..80848dfc01db 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -508,7 +508,7 @@ static int hidp_process_data(struct hidp_session *session, struct sk_buff *skb, unsigned char param) { int done_with_skb = 1; - BT_DBG("session %p skb %p len %d param 0x%02x", session, skb, skb->len, param); + BT_DBG("session %p skb %p len %u param 0x%02x", session, skb, skb->len, param); switch (param) { case HIDP_DATA_RTYPE_INPUT: @@ -553,7 +553,7 @@ static void hidp_recv_ctrl_frame(struct hidp_session *session, unsigned char hdr, type, param; int free_skb = 1; - BT_DBG("session %p skb %p len %d", session, skb, skb->len); + BT_DBG("session %p skb %p len %u", session, skb, skb->len); hdr = skb->data[0]; skb_pull(skb, 1); @@ -589,7 +589,7 @@ static void hidp_recv_intr_frame(struct hidp_session *session, { unsigned char hdr; - BT_DBG("session %p skb %p len %d", session, skb, skb->len); + BT_DBG("session %p skb %p len %u", session, skb, skb->len); hdr = skb->data[0]; skb_pull(skb, 1); @@ -794,7 +794,7 @@ static int hidp_setup_hid(struct hidp_session *session, hid->dev.parent = &session->conn->hcon->dev; hid->ll_driver = &hidp_hid_driver; - /* True if device is blacklisted in drivers/hid/hid-quirks.c */ + /* True if device is blocked in drivers/hid/hid-quirks.c */ if (hid_ignore(hid)) { hid_destroy_device(session->hid); session->hid = NULL; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b6a88b8256c7..77ba68209dbd 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1691,7 +1691,7 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) if (hcon->out) smp_conn_security(hcon, hcon->pending_sec_level); - /* For LE slave connections, make sure the connection interval + /* For LE peripheral connections, make sure the connection interval * is in the range of the minimum and maximum interval that has * been configured for this connection. If not, then trigger * the connection update procedure. @@ -4237,7 +4237,7 @@ static int l2cap_connect_req(struct l2cap_conn *conn, hci_dev_lock(hdev); if (hci_dev_test_flag(hdev, HCI_MGMT) && !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags)) - mgmt_device_connected(hdev, hcon, 0, NULL, 0); + mgmt_device_connected(hdev, hcon, NULL, 0); hci_dev_unlock(hdev); l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP, 0); @@ -6066,7 +6066,7 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn, struct l2cap_ecred_conn_rsp *rsp = (void *) data; struct hci_conn *hcon = conn->hcon; u16 mtu, mps, credits, result; - struct l2cap_chan *chan; + struct l2cap_chan *chan, *tmp; int err = 0, sec_level; int i = 0; @@ -6085,7 +6085,7 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn, cmd_len -= sizeof(*rsp); - list_for_each_entry(chan, &conn->chan_l, list) { + list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) { u16 dcid; if (chan->ident != cmd->ident || @@ -6248,7 +6248,7 @@ static inline int l2cap_ecred_reconf_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data) { - struct l2cap_chan *chan; + struct l2cap_chan *chan, *tmp; struct l2cap_ecred_conn_rsp *rsp = (void *) data; u16 result; @@ -6262,7 +6262,7 @@ static inline int l2cap_ecred_reconf_rsp(struct l2cap_conn *conn, if (!result) return 0; - list_for_each_entry(chan, &conn->chan_l, list) { + list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) { if (chan->ident != cmd->ident) continue; @@ -7662,7 +7662,7 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) * at least ensure that we ignore incoming data from them. */ if (hcon->type == LE_LINK && - hci_bdaddr_list_lookup(&hcon->hdev->blacklist, &hcon->dst, + hci_bdaddr_list_lookup(&hcon->hdev->reject_list, &hcon->dst, bdaddr_dst_type(hcon))) { kfree_skb(skb); return; @@ -8119,7 +8119,7 @@ static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) dst_type = bdaddr_dst_type(hcon); /* If device is blocked, do not create channels for it */ - if (hci_bdaddr_list_lookup(&hdev->blacklist, &hcon->dst, dst_type)) + if (hci_bdaddr_list_lookup(&hdev->reject_list, &hcon->dst, dst_type)) return; /* Find fixed channels and notify them of the new connection. We diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index f9be7f9084d6..3663f880df11 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -40,7 +40,7 @@ #include "msft.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 20 +#define MGMT_REVISION 21 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -252,12 +252,15 @@ static const u8 mgmt_status_table[] = { MGMT_STATUS_TIMEOUT, /* Instant Passed */ MGMT_STATUS_NOT_SUPPORTED, /* Pairing Not Supported */ MGMT_STATUS_FAILED, /* Transaction Collision */ + MGMT_STATUS_FAILED, /* Reserved for future use */ MGMT_STATUS_INVALID_PARAMS, /* Unacceptable Parameter */ MGMT_STATUS_REJECTED, /* QoS Rejected */ MGMT_STATUS_NOT_SUPPORTED, /* Classification Not Supported */ MGMT_STATUS_REJECTED, /* Insufficient Security */ MGMT_STATUS_INVALID_PARAMS, /* Parameter Out Of Range */ + MGMT_STATUS_FAILED, /* Reserved for future use */ MGMT_STATUS_BUSY, /* Role Switch Pending */ + MGMT_STATUS_FAILED, /* Reserved for future use */ MGMT_STATUS_FAILED, /* Slot Violation */ MGMT_STATUS_FAILED, /* Role Switch Failed */ MGMT_STATUS_INVALID_PARAMS, /* EIR Too Large */ @@ -2956,7 +2959,7 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, /* When pairing a new device, it is expected to remember * this device for future connections. Adding the connection * parameter information ahead of time allows tracking - * of the slave preferred values and will speed up any + * of the peripheral preferred values and will speed up any * further connection establishment. * * If connection parameters already exist, then they @@ -3341,7 +3344,7 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data, } /* The name is stored in the scan response data and so - * no need to udpate the advertising data here. + * no need to update the advertising data here. */ if (lmp_le_capable(hdev) && hci_dev_test_flag(hdev, HCI_ADVERTISING)) __hci_req_update_scan_rsp_data(&req, hdev->cur_adv_instance); @@ -4058,8 +4061,10 @@ static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); + memset(&rp, 0, sizeof(rp)); + if (cp->addr.type == BDADDR_BREDR) { - br_params = hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, + br_params = hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &cp->addr.bdaddr, cp->addr.type); if (!br_params) @@ -4127,7 +4132,7 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); if (cp->addr.type == BDADDR_BREDR) { - br_params = hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, + br_params = hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &cp->addr.bdaddr, cp->addr.type); @@ -4274,7 +4279,7 @@ int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status) done: hci_dev_unlock(hdev); - bt_dev_dbg(hdev, "add monitor %d complete, status %d", + bt_dev_dbg(hdev, "add monitor %d complete, status %u", rp.monitor_handle, status); return err; @@ -4499,7 +4504,7 @@ int mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status) done: hci_dev_unlock(hdev); - bt_dev_dbg(hdev, "remove monitor %d complete, status %d", + bt_dev_dbg(hdev, "remove monitor %d complete, status %u", rp.monitor_handle, status); return err; @@ -4829,7 +4834,7 @@ void mgmt_start_discovery_complete(struct hci_dev *hdev, u8 status) { struct mgmt_pending_cmd *cmd; - bt_dev_dbg(hdev, "status %d", status); + bt_dev_dbg(hdev, "status %u", status); hci_dev_lock(hdev); @@ -5085,7 +5090,7 @@ void mgmt_stop_discovery_complete(struct hci_dev *hdev, u8 status) { struct mgmt_pending_cmd *cmd; - bt_dev_dbg(hdev, "status %d", status); + bt_dev_dbg(hdev, "status %u", status); hci_dev_lock(hdev); @@ -5204,7 +5209,7 @@ static int block_device(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - err = hci_bdaddr_list_add(&hdev->blacklist, &cp->addr.bdaddr, + err = hci_bdaddr_list_add(&hdev->reject_list, &cp->addr.bdaddr, cp->addr.type); if (err < 0) { status = MGMT_STATUS_FAILED; @@ -5240,7 +5245,7 @@ static int unblock_device(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - err = hci_bdaddr_list_del(&hdev->blacklist, &cp->addr.bdaddr, + err = hci_bdaddr_list_del(&hdev->reject_list, &cp->addr.bdaddr, cp->addr.type); if (err < 0) { status = MGMT_STATUS_INVALID_PARAMS; @@ -5298,7 +5303,7 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data, static void enable_advertising_instance(struct hci_dev *hdev, u8 status, u16 opcode) { - bt_dev_dbg(hdev, "status %d", status); + bt_dev_dbg(hdev, "status %u", status); } static void set_advertising_complete(struct hci_dev *hdev, u8 status, @@ -6164,7 +6169,7 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, static bool ltk_is_valid(struct mgmt_ltk_info *key) { - if (key->master != 0x00 && key->master != 0x01) + if (key->initiator != 0x00 && key->initiator != 0x01) return false; switch (key->addr.type) { @@ -6242,11 +6247,11 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, switch (key->type) { case MGMT_LTK_UNAUTHENTICATED: authenticated = 0x00; - type = key->master ? SMP_LTK : SMP_LTK_SLAVE; + type = key->initiator ? SMP_LTK : SMP_LTK_RESPONDER; break; case MGMT_LTK_AUTHENTICATED: authenticated = 0x01; - type = key->master ? SMP_LTK : SMP_LTK_SLAVE; + type = key->initiator ? SMP_LTK : SMP_LTK_RESPONDER; break; case MGMT_LTK_P256_UNAUTH: authenticated = 0x00; @@ -6342,7 +6347,7 @@ static void conn_info_refresh_complete(struct hci_dev *hdev, u8 hci_status, handle = __le16_to_cpu(cp->handle); conn = hci_conn_hash_lookup_handle(hdev, handle); if (!conn) { - bt_dev_err(hdev, "unknown handle (%d) in conn_info response", + bt_dev_err(hdev, "unknown handle (%u) in conn_info response", handle); goto unlock; } @@ -6731,7 +6736,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - err = hci_bdaddr_list_add_with_flags(&hdev->whitelist, + err = hci_bdaddr_list_add_with_flags(&hdev->accept_list, &cp->addr.bdaddr, cp->addr.type, 0); if (err) @@ -6829,7 +6834,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, } if (cp->addr.type == BDADDR_BREDR) { - err = hci_bdaddr_list_del(&hdev->whitelist, + err = hci_bdaddr_list_del(&hdev->accept_list, &cp->addr.bdaddr, cp->addr.type); if (err) { @@ -6900,7 +6905,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - list_for_each_entry_safe(b, btmp, &hdev->whitelist, list) { + list_for_each_entry_safe(b, btmp, &hdev->accept_list, list) { device_removed(sk, hdev, &b->bdaddr, b->bdaddr_type); list_del(&b->list); kfree(b); @@ -7585,6 +7590,9 @@ static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data, for (i = 0, cur_len = 0; i < len; i += (cur_len + 1)) { cur_len = data[i]; + if (!cur_len) + continue; + if (data[i + 1] == EIR_FLAGS && (!is_adv_data || flags_managed(adv_flags))) return false; @@ -7646,7 +7654,7 @@ static void add_advertising_complete(struct hci_dev *hdev, u8 status, struct adv_info *adv_instance, *n; u8 instance; - bt_dev_dbg(hdev, "status %d", status); + bt_dev_dbg(hdev, "status %u", status); hci_dev_lock(hdev); @@ -8176,7 +8184,7 @@ static void remove_advertising_complete(struct hci_dev *hdev, u8 status, struct mgmt_cp_remove_advertising *cp; struct mgmt_rp_remove_advertising rp; - bt_dev_dbg(hdev, "status %d", status); + bt_dev_dbg(hdev, "status %u", status); hci_dev_lock(hdev); @@ -8641,7 +8649,7 @@ static u8 mgmt_ltk_type(struct smp_ltk *ltk) { switch (ltk->type) { case SMP_LTK: - case SMP_LTK_SLAVE: + case SMP_LTK_RESPONDER: if (ltk->authenticated) return MGMT_LTK_AUTHENTICATED; return MGMT_LTK_UNAUTHENTICATED; @@ -8687,7 +8695,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) ev.key.rand = key->rand; if (key->type == SMP_LTK) - ev.key.master = 1; + ev.key.initiator = 1; /* Make sure we copy only the significant bytes based on the * encryption key size, and set the rest of the value to zeroes. @@ -8767,15 +8775,19 @@ void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, } void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, - u32 flags, u8 *name, u8 name_len) + u8 *name, u8 name_len) { char buf[512]; struct mgmt_ev_device_connected *ev = (void *) buf; u16 eir_len = 0; + u32 flags = 0; bacpy(&ev->addr.bdaddr, &conn->dst); ev->addr.type = link_to_bdaddr(conn->type, conn->dst_type); + if (conn->out) + flags |= MGMT_DEV_FOUND_INITIATED_CONN; + ev->flags = __cpu_to_le32(flags); /* We must ensure that the EIR Data fields are ordered and diff --git a/net/bluetooth/mgmt_config.c b/net/bluetooth/mgmt_config.c index 1deb0ca7a929..6ef701c27da4 100644 --- a/net/bluetooth/mgmt_config.c +++ b/net/bluetooth/mgmt_config.c @@ -146,7 +146,7 @@ int set_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data, const u16 type = le16_to_cpu(TO_TLV(buffer)->type); if (buffer_left < exp_len) { - bt_dev_warn(hdev, "invalid len left %d, exp >= %d", + bt_dev_warn(hdev, "invalid len left %u, exp >= %u", buffer_left, exp_len); return mgmt_cmd_status(sk, hdev->id, @@ -198,7 +198,7 @@ int set_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data, } if (exp_type_len && len != exp_type_len) { - bt_dev_warn(hdev, "invalid length %d, exp %zu for type %d", + bt_dev_warn(hdev, "invalid length %d, exp %zu for type %u", len, exp_type_len, type); return mgmt_cmd_status(sk, hdev->id, diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index e28f15439ce4..b4bfae41e8a5 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -34,12 +34,12 @@ struct msft_le_monitor_advertisement_pattern { __u8 length; __u8 data_type; __u8 start_byte; - __u8 pattern[0]; + __u8 pattern[]; }; struct msft_le_monitor_advertisement_pattern_data { __u8 count; - __u8 data[0]; + __u8 data[]; }; struct msft_cp_le_monitor_advertisement { @@ -49,7 +49,7 @@ struct msft_cp_le_monitor_advertisement { __u8 rssi_low_interval; __u8 rssi_sampling_period; __u8 cond_type; - __u8 data[0]; + __u8 data[]; } __packed; struct msft_rp_le_monitor_advertisement { @@ -311,7 +311,7 @@ static void msft_le_monitor_advertisement_cb(struct hci_dev *hdev, monitor = idr_find(&hdev->adv_monitors_idr, msft->pending_add_handle); if (!monitor) { - bt_dev_err(hdev, "msft add advmon: monitor %d is not found!", + bt_dev_err(hdev, "msft add advmon: monitor %u is not found!", msft->pending_add_handle); status = HCI_ERROR_UNSPECIFIED; goto unlock; diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index a58584949a95..8cb53e10a985 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -198,20 +198,22 @@ static void rfcomm_reparent_device(struct rfcomm_dev *dev) hci_dev_put(hdev); } -static ssize_t show_address(struct device *tty_dev, struct device_attribute *attr, char *buf) +static ssize_t address_show(struct device *tty_dev, + struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); return sprintf(buf, "%pMR\n", &dev->dst); } -static ssize_t show_channel(struct device *tty_dev, struct device_attribute *attr, char *buf) +static ssize_t channel_show(struct device *tty_dev, + struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); return sprintf(buf, "%d\n", dev->channel); } -static DEVICE_ATTR(address, 0444, show_address, NULL); -static DEVICE_ATTR(channel, 0444, show_channel, NULL); +static DEVICE_ATTR_RO(address); +static DEVICE_ATTR_RO(channel); static struct rfcomm_dev *__rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 3bd41563f118..d9a4e88dacbb 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -310,7 +310,7 @@ static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) if (!sk) goto drop; - BT_DBG("sk %p len %d", sk, skb->len); + BT_DBG("sk %p len %u", sk, skb->len); if (sk->sk_state != BT_CONNECTED) goto drop; @@ -905,7 +905,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, opts.mtu = sco_pi(sk)->conn->mtu; - BT_DBG("mtu %d", opts.mtu); + BT_DBG("mtu %u", opts.mtu); len = min_t(unsigned int, len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) @@ -1167,7 +1167,7 @@ static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; - BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); + BT_DBG("hcon %p bdaddr %pMR status %u", hcon, &hcon->dst, status); if (!status) { struct sco_conn *conn; @@ -1196,7 +1196,7 @@ void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) if (!conn) goto drop; - BT_DBG("conn %p len %d", conn, skb->len); + BT_DBG("conn %p len %u", conn, skb->len); if (skb->len) { sco_recv_frame(conn, skb); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 7dd51da73845..11f853d0500f 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -40,7 +40,7 @@ ((struct smp_dev *)((struct l2cap_chan *)((hdev)->smp_data))->data) /* Low-level debug macros to be used for stuff that we don't want - * accidentially in dmesg, i.e. the values of the various crypto keys + * accidentally in dmesg, i.e. the values of the various crypto keys * and the inputs & outputs of crypto functions. */ #ifdef DEBUG @@ -111,9 +111,9 @@ struct smp_chan { u8 id_addr_type; u8 irk[16]; struct smp_csrk *csrk; - struct smp_csrk *slave_csrk; + struct smp_csrk *responder_csrk; struct smp_ltk *ltk; - struct smp_ltk *slave_ltk; + struct smp_ltk *responder_ltk; struct smp_irk *remote_irk; u8 *link_key; unsigned long flags; @@ -560,7 +560,7 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) return err; /* This is unlikely, but we need to check that - * we didn't accidentially generate a debug key. + * we didn't accidentally generate a debug key. */ if (crypto_memneq(smp->local_pk, debug_pk, 64)) break; @@ -753,7 +753,7 @@ static void smp_chan_destroy(struct l2cap_conn *conn) mgmt_smp_complete(hcon, complete); kfree_sensitive(smp->csrk); - kfree_sensitive(smp->slave_csrk); + kfree_sensitive(smp->responder_csrk); kfree_sensitive(smp->link_key); crypto_free_shash(smp->tfm_cmac); @@ -776,9 +776,9 @@ static void smp_chan_destroy(struct l2cap_conn *conn) kfree_rcu(smp->ltk, rcu); } - if (smp->slave_ltk) { - list_del_rcu(&smp->slave_ltk->list); - kfree_rcu(smp->slave_ltk, rcu); + if (smp->responder_ltk) { + list_del_rcu(&smp->responder_ltk->list); + kfree_rcu(smp->responder_ltk, rcu); } if (smp->remote_irk) { @@ -859,7 +859,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, memset(smp->tk, 0, sizeof(smp->tk)); clear_bit(SMP_FLAG_TK_VALID, &smp->flags); - bt_dev_dbg(hcon->hdev, "auth:%d lcl:%d rem:%d", auth, local_io, + bt_dev_dbg(hcon->hdev, "auth:%u lcl:%u rem:%u", auth, local_io, remote_io); /* If neither side wants MITM, either "just" confirm an incoming @@ -909,8 +909,8 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, hcon->pending_sec_level = BT_SECURITY_HIGH; } - /* If both devices have Keyoard-Display I/O, the master - * Confirms and the slave Enters the passkey. + /* If both devices have Keyboard-Display I/O, the initiator + * Confirms and the responder Enters the passkey. */ if (smp->method == OVERLAP) { if (hcon->role == HCI_ROLE_MASTER) @@ -925,7 +925,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, get_random_bytes(&passkey, sizeof(passkey)); passkey %= 1000000; put_unaligned_le32(passkey, smp->tk); - bt_dev_dbg(hcon->hdev, "PassKey: %d", passkey); + bt_dev_dbg(hcon->hdev, "PassKey: %u", passkey); set_bit(SMP_FLAG_TK_VALID, &smp->flags); } @@ -979,7 +979,7 @@ static u8 smp_random(struct smp_chan *smp) int ret; bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn, - conn->hcon->out ? "master" : "slave"); + conn->hcon->out ? "initiator" : "responder"); ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp, hcon->init_addr_type, &hcon->init_addr, @@ -1021,8 +1021,8 @@ static u8 smp_random(struct smp_chan *smp) else auth = 0; - /* Even though there's no _SLAVE suffix this is the - * slave STK we're adding for later lookup (the master + /* Even though there's no _RESPONDER suffix this is the + * responder STK we're adding for later lookup (the initiator * STK never needs to be stored). */ hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, @@ -1077,10 +1077,10 @@ static void smp_notify_keys(struct l2cap_conn *conn) mgmt_new_csrk(hdev, smp->csrk, persistent); } - if (smp->slave_csrk) { - smp->slave_csrk->bdaddr_type = hcon->dst_type; - bacpy(&smp->slave_csrk->bdaddr, &hcon->dst); - mgmt_new_csrk(hdev, smp->slave_csrk, persistent); + if (smp->responder_csrk) { + smp->responder_csrk->bdaddr_type = hcon->dst_type; + bacpy(&smp->responder_csrk->bdaddr, &hcon->dst); + mgmt_new_csrk(hdev, smp->responder_csrk, persistent); } if (smp->ltk) { @@ -1089,10 +1089,10 @@ static void smp_notify_keys(struct l2cap_conn *conn) mgmt_new_ltk(hdev, smp->ltk, persistent); } - if (smp->slave_ltk) { - smp->slave_ltk->bdaddr_type = hcon->dst_type; - bacpy(&smp->slave_ltk->bdaddr, &hcon->dst); - mgmt_new_ltk(hdev, smp->slave_ltk, persistent); + if (smp->responder_ltk) { + smp->responder_ltk->bdaddr_type = hcon->dst_type; + bacpy(&smp->responder_ltk->bdaddr, &hcon->dst); + mgmt_new_ltk(hdev, smp->responder_ltk, persistent); } if (smp->link_key) { @@ -1272,7 +1272,7 @@ static void smp_distribute_keys(struct smp_chan *smp) if (*keydist & SMP_DIST_ENC_KEY) { struct smp_cmd_encrypt_info enc; - struct smp_cmd_master_ident ident; + struct smp_cmd_initiator_ident ident; struct smp_ltk *ltk; u8 authenticated; __le16 ediv; @@ -1293,14 +1293,15 @@ static void smp_distribute_keys(struct smp_chan *smp) authenticated = hcon->sec_level == BT_SECURITY_HIGH; ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, - SMP_LTK_SLAVE, authenticated, enc.ltk, + SMP_LTK_RESPONDER, authenticated, enc.ltk, smp->enc_key_size, ediv, rand); - smp->slave_ltk = ltk; + smp->responder_ltk = ltk; ident.ediv = ediv; ident.rand = rand; - smp_send_cmd(conn, SMP_CMD_MASTER_IDENT, sizeof(ident), &ident); + smp_send_cmd(conn, SMP_CMD_INITIATOR_IDENT, sizeof(ident), + &ident); *keydist &= ~SMP_DIST_ENC_KEY; } @@ -1343,7 +1344,7 @@ static void smp_distribute_keys(struct smp_chan *smp) csrk->type = MGMT_CSRK_LOCAL_UNAUTHENTICATED; memcpy(csrk->val, sign.csrk, sizeof(csrk->val)); } - smp->slave_csrk = csrk; + smp->responder_csrk = csrk; smp_send_cmd(conn, SMP_CMD_SIGN_INFO, sizeof(sign), &sign); @@ -1654,7 +1655,7 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey) case MGMT_OP_USER_PASSKEY_REPLY: value = le32_to_cpu(passkey); memset(smp->tk, 0, sizeof(smp->tk)); - bt_dev_dbg(conn->hcon->hdev, "PassKey: %d", value); + bt_dev_dbg(conn->hcon->hdev, "PassKey: %u", value); put_unaligned_le32(value, smp->tk); fallthrough; case MGMT_OP_USER_CONFIRM_REPLY: @@ -1902,7 +1903,7 @@ static u8 sc_send_public_key(struct smp_chan *smp) return SMP_UNSPECIFIED; /* This is unlikely, but we need to check that - * we didn't accidentially generate a debug key. + * we didn't accidentally generate a debug key. */ if (crypto_memneq(smp->local_pk, debug_pk, 64)) break; @@ -2048,7 +2049,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp) struct smp_cmd_pairing *req, *rsp; u8 auth; - /* The issue is only observed when we're in slave role */ + /* The issue is only observed when we're in responder role */ if (hcon->out) return SMP_UNSPECIFIED; @@ -2084,7 +2085,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; - bt_dev_dbg(hdev, "conn %p %s", conn, hcon->out ? "master" : "slave"); + bt_dev_dbg(hdev, "conn %p %s", conn, + hcon->out ? "initiator" : "responder"); if (skb->len < sizeof(smp->pcnf)) return SMP_INVALID_PARAMS; @@ -2251,7 +2253,7 @@ static bool smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level) hci_le_start_enc(hcon, key->ediv, key->rand, key->val, key->enc_size); hcon->enc_key_size = key->enc_size; - /* We never store STKs for master role, so clear this flag */ + /* We never store STKs for initiator role, so clear this flag */ clear_bit(HCI_CONN_STK_ENCRYPT, &hcon->flags); return true; @@ -2467,7 +2469,7 @@ int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr, /* Set keys to NULL to make sure smp_failure() does not try to * remove and free already invalidated rcu list entries. */ smp->ltk = NULL; - smp->slave_ltk = NULL; + smp->responder_ltk = NULL; smp->remote_irk = NULL; if (test_bit(SMP_FLAG_COMPLETE, &smp->flags)) @@ -2503,7 +2505,7 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) return SMP_INVALID_PARAMS; } - SMP_ALLOW_CMD(smp, SMP_CMD_MASTER_IDENT); + SMP_ALLOW_CMD(smp, SMP_CMD_INITIATOR_IDENT); skb_pull(skb, sizeof(*rp)); @@ -2512,9 +2514,9 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } -static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb) +static int smp_cmd_initiator_ident(struct l2cap_conn *conn, struct sk_buff *skb) { - struct smp_cmd_master_ident *rp = (void *) skb->data; + struct smp_cmd_initiator_ident *rp = (void *)skb->data; struct l2cap_chan *chan = conn->smp; struct smp_chan *smp = chan->data; struct hci_dev *hdev = conn->hcon->hdev; @@ -2913,7 +2915,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } - /* Slave sends DHKey check as response to master */ + /* Responder sends DHKey check as response to initiator */ sc_dhkey_check(smp); } @@ -3000,8 +3002,8 @@ static int smp_sig_channel(struct l2cap_chan *chan, struct sk_buff *skb) reason = smp_cmd_encrypt_info(conn, skb); break; - case SMP_CMD_MASTER_IDENT: - reason = smp_cmd_master_ident(conn, skb); + case SMP_CMD_INITIATOR_IDENT: + reason = smp_cmd_initiator_ident(conn, skb); break; case SMP_CMD_IDENT_INFO: @@ -3081,7 +3083,7 @@ static void bredr_pairing(struct l2cap_chan *chan) if (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags)) return; - /* Only master may initiate SMP over BR/EDR */ + /* Only initiator may initiate SMP over BR/EDR */ if (hcon->role != HCI_ROLE_MASTER) return; diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index fc35a8bf358e..87a59ec2c9f0 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -79,8 +79,8 @@ struct smp_cmd_encrypt_info { __u8 ltk[16]; } __packed; -#define SMP_CMD_MASTER_IDENT 0x07 -struct smp_cmd_master_ident { +#define SMP_CMD_INITIATOR_IDENT 0x07 +struct smp_cmd_initiator_ident { __le16 ediv; __le64 rand; } __packed; @@ -146,7 +146,7 @@ struct smp_cmd_keypress_notify { enum { SMP_STK, SMP_LTK, - SMP_LTK_SLAVE, + SMP_LTK_RESPONDER, SMP_LTK_P256, SMP_LTK_P256_DEBUG, }; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index a5d72c48fb66..aa47af349ba8 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -409,7 +409,7 @@ static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size) return ERR_PTR(-ENOMEM); if (data_in) { - err = bpf_check_uarg_tail_zero(data_in, max_size, size); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(data_in), max_size, size); if (err) { kfree(data); return ERR_PTR(err); @@ -918,3 +918,46 @@ out: kfree(user_ctx); return ret; } + +int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in); + __u32 ctx_size_in = kattr->test.ctx_size_in; + void *ctx = NULL; + u32 retval; + int err = 0; + + /* doesn't support data_in/out, ctx_out, duration, or repeat or flags */ + if (kattr->test.data_in || kattr->test.data_out || + kattr->test.ctx_out || kattr->test.duration || + kattr->test.repeat || kattr->test.flags) + return -EINVAL; + + if (ctx_size_in < prog->aux->max_ctx_offset || + ctx_size_in > U16_MAX) + return -EINVAL; + + if (ctx_size_in) { + ctx = kzalloc(ctx_size_in, GFP_USER); + if (!ctx) + return -ENOMEM; + if (copy_from_user(ctx, ctx_in, ctx_size_in)) { + err = -EFAULT; + goto out; + } + } + retval = bpf_prog_run_pin_on_cpu(prog, ctx); + + if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) { + err = -EFAULT; + goto out; + } + if (ctx_size_in) + if (copy_to_user(ctx_in, ctx, ctx_size_in)) + err = -EFAULT; +out: + kfree(ctx); + return err; +} diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c index 05e1cfc1e5cd..291a92546246 100644 --- a/net/bpfilter/main.c +++ b/net/bpfilter/main.c @@ -57,7 +57,7 @@ int main(void) { debug_f = fopen("/dev/kmsg", "w"); setvbuf(debug_f, 0, _IOLBF, 0); - fprintf(debug_f, "Started bpfilter\n"); + fprintf(debug_f, "<5>Started bpfilter\n"); loop(); fclose(debug_f); return 0; diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c index 001064f7583d..a3c755d0a09d 100644 --- a/net/bridge/br_cfm.c +++ b/net/bridge/br_cfm.c @@ -142,7 +142,7 @@ static void br_cfm_notify(int event, const struct net_bridge_port *port) { u32 filter = RTEXT_FILTER_CFM_STATUS; - return br_info_notify(event, port->br, NULL, filter); + br_info_notify(event, port->br, NULL, filter); } static void cc_peer_enable(struct br_cfm_peer_mep *peer_mep) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 698b79747d32..2b862cffc03a 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -440,9 +440,14 @@ int br_fdb_test_addr(struct net_device *dev, unsigned char *addr) if (!port) ret = 0; else { + const struct net_bridge_port *dst = NULL; + fdb = br_fdb_find_rcu(port->br, addr, 0); - ret = fdb && fdb->dst && fdb->dst->dev != dev && - fdb->dst->state == BR_STATE_FORWARDING; + if (fdb) + dst = READ_ONCE(fdb->dst); + + ret = dst && dst->dev != dev && + dst->state == BR_STATE_FORWARDING; } rcu_read_unlock(); @@ -509,7 +514,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct net_bridge *br, fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC); if (fdb) { memcpy(fdb->key.addr.addr, addr, ETH_ALEN); - fdb->dst = source; + WRITE_ONCE(fdb->dst, source); fdb->key.vlan_id = vid; fdb->flags = flags; fdb->updated = fdb->used = jiffies; @@ -600,10 +605,10 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, } /* fastpath: update of existing entry */ - if (unlikely(source != fdb->dst && + if (unlikely(source != READ_ONCE(fdb->dst) && !test_bit(BR_FDB_STICKY, &fdb->flags))) { - br_switchdev_fdb_notify(fdb, RTM_DELNEIGH); - fdb->dst = source; + br_switchdev_fdb_notify(br, fdb, RTM_DELNEIGH); + WRITE_ONCE(fdb->dst, source); fdb_modified = true; /* Take over HW learned entry */ if (unlikely(test_bit(BR_FDB_ADDED_BY_EXT_LEARN, @@ -650,6 +655,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, u32 portid, u32 seq, int type, unsigned int flags) { + const struct net_bridge_port *dst = READ_ONCE(fdb->dst); unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; @@ -665,7 +671,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_pad2 = 0; ndm->ndm_flags = 0; ndm->ndm_type = 0; - ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex; + ndm->ndm_ifindex = dst ? dst->dev->ifindex : br->dev->ifindex; ndm->ndm_state = fdb_to_nud(br, fdb); if (test_bit(BR_FDB_OFFLOADED, &fdb->flags)) @@ -727,8 +733,9 @@ static inline size_t fdb_nlmsg_size(void) } static int br_fdb_replay_one(struct notifier_block *nb, - struct net_bridge_fdb_entry *fdb, - struct net_device *dev) + const struct net_bridge_fdb_entry *fdb, + struct net_device *dev, unsigned long action, + const void *ctx) { struct switchdev_notifier_fdb_info item; int err; @@ -737,35 +744,46 @@ static int br_fdb_replay_one(struct notifier_block *nb, item.vid = fdb->key.vlan_id; item.added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); item.offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags); + item.is_local = test_bit(BR_FDB_LOCAL, &fdb->flags); item.info.dev = dev; + item.info.ctx = ctx; - err = nb->notifier_call(nb, SWITCHDEV_FDB_ADD_TO_DEVICE, &item); + err = nb->notifier_call(nb, action, &item); return notifier_to_errno(err); } -int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb) +int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, + const void *ctx, bool adding, struct notifier_block *nb) { struct net_bridge_fdb_entry *fdb; struct net_bridge *br; + unsigned long action; int err = 0; - if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev)) + if (!netif_is_bridge_master(br_dev)) + return -EINVAL; + + if (!netif_is_bridge_port(dev) && !netif_is_bridge_master(dev)) return -EINVAL; br = netdev_priv(br_dev); + if (adding) + action = SWITCHDEV_FDB_ADD_TO_DEVICE; + else + action = SWITCHDEV_FDB_DEL_TO_DEVICE; + rcu_read_lock(); hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) { - struct net_bridge_port *dst = READ_ONCE(fdb->dst); + const struct net_bridge_port *dst = READ_ONCE(fdb->dst); struct net_device *dst_dev; dst_dev = dst ? dst->dev : br->dev; if (dst_dev != br_dev && dst_dev != dev) continue; - err = br_fdb_replay_one(nb, fdb, dst_dev); + err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx); if (err) break; } @@ -785,7 +803,7 @@ static void fdb_notify(struct net_bridge *br, int err = -ENOBUFS; if (swdev_notify) - br_switchdev_fdb_notify(fdb, type); + br_switchdev_fdb_notify(br, fdb, type); skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) @@ -955,8 +973,8 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, if (flags & NLM_F_EXCL) return -EEXIST; - if (fdb->dst != source) { - fdb->dst = source; + if (READ_ONCE(fdb->dst) != source) { + WRITE_ONCE(fdb->dst, source); modified = true; } } @@ -1123,7 +1141,7 @@ static int fdb_delete_by_addr_and_port(struct net_bridge *br, struct net_bridge_fdb_entry *fdb; fdb = br_fdb_find(br, addr, vlan); - if (!fdb || fdb->dst != p) + if (!fdb || READ_ONCE(fdb->dst) != p) return -ENOENT; fdb_delete(br, fdb, true); @@ -1272,8 +1290,8 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, } else { fdb->updated = jiffies; - if (fdb->dst != p) { - fdb->dst = p; + if (READ_ONCE(fdb->dst) != p) { + WRITE_ONCE(fdb->dst, p); modified = true; } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 6e9b049ae521..07856362538f 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -276,7 +276,8 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, bool allow_mode_include = true; struct hlist_node *rp; - rp = rcu_dereference(hlist_first_rcu(&br->router_list)); + rp = br_multicast_get_first_rport_node(br, skb); + if (mdst) { p = rcu_dereference(mdst->ports); if (br_multicast_should_handle_mode(br, mdst->addr.proto) && @@ -290,7 +291,7 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, struct net_bridge_port *port, *lport, *rport; lport = p ? p->key.port : NULL; - rport = hlist_entry_safe(rp, struct net_bridge_port, rlist); + rport = br_multicast_rport_from_node_skb(rp, skb); if ((unsigned long)lport > (unsigned long)rport) { port = lport; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 8875e953ac53..1f506309efa8 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -132,7 +132,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && br_multicast_querier_exists(br, eth_hdr(skb), mdst)) { if ((mdst && mdst->host_joined) || - br_multicast_is_router(br)) { + br_multicast_is_router(br, skb)) { local_rcv = true; br->dev->stats.multicast++; } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 95fa4af0e8dd..17a720b4473f 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -16,31 +16,76 @@ #include "br_private.h" +static bool br_rports_have_mc_router(struct net_bridge *br) +{ +#if IS_ENABLED(CONFIG_IPV6) + return !hlist_empty(&br->ip4_mc_router_list) || + !hlist_empty(&br->ip6_mc_router_list); +#else + return !hlist_empty(&br->ip4_mc_router_list); +#endif +} + +static bool +br_ip4_rports_get_timer(struct net_bridge_port *port, unsigned long *timer) +{ + *timer = br_timer_value(&port->ip4_mc_router_timer); + return !hlist_unhashed(&port->ip4_rlist); +} + +static bool +br_ip6_rports_get_timer(struct net_bridge_port *port, unsigned long *timer) +{ +#if IS_ENABLED(CONFIG_IPV6) + *timer = br_timer_value(&port->ip6_mc_router_timer); + return !hlist_unhashed(&port->ip6_rlist); +#else + *timer = 0; + return false; +#endif +} + static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - struct net_bridge_port *p; + bool have_ip4_mc_rtr, have_ip6_mc_rtr; + unsigned long ip4_timer, ip6_timer; struct nlattr *nest, *port_nest; + struct net_bridge_port *p; + + if (!br->multicast_router) + return 0; - if (!br->multicast_router || hlist_empty(&br->router_list)) + if (!br_rports_have_mc_router(br)) return 0; nest = nla_nest_start_noflag(skb, MDBA_ROUTER); if (nest == NULL) return -EMSGSIZE; - hlist_for_each_entry_rcu(p, &br->router_list, rlist) { - if (!p) + list_for_each_entry_rcu(p, &br->port_list, list) { + have_ip4_mc_rtr = br_ip4_rports_get_timer(p, &ip4_timer); + have_ip6_mc_rtr = br_ip6_rports_get_timer(p, &ip6_timer); + + if (!have_ip4_mc_rtr && !have_ip6_mc_rtr) continue; + port_nest = nla_nest_start_noflag(skb, MDBA_ROUTER_PORT); if (!port_nest) goto fail; + if (nla_put_nohdr(skb, sizeof(u32), &p->dev->ifindex) || nla_put_u32(skb, MDBA_ROUTER_PATTR_TIMER, - br_timer_value(&p->multicast_router_timer)) || + max(ip4_timer, ip6_timer)) || nla_put_u8(skb, MDBA_ROUTER_PATTR_TYPE, - p->multicast_router)) { + p->multicast_router) || + (have_ip4_mc_rtr && + nla_put_u32(skb, MDBA_ROUTER_PATTR_INET_TIMER, + ip4_timer)) || + (have_ip6_mc_rtr && + nla_put_u32(skb, MDBA_ROUTER_PATTR_INET6_TIMER, + ip6_timer))) { nla_nest_cancel(skb, port_nest); goto fail; } @@ -522,19 +567,21 @@ static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb, } static int br_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, - struct switchdev_obj_port_mdb *mdb, + const struct switchdev_obj_port_mdb *mdb, + unsigned long action, const void *ctx, struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { .info = { .dev = dev, .extack = extack, + .ctx = ctx, }, .obj = &mdb->obj, }; int err; - err = nb->notifier_call(nb, SWITCHDEV_PORT_OBJ_ADD, &obj_info); + err = nb->notifier_call(nb, action, &obj_info); return notifier_to_errno(err); } @@ -558,11 +605,13 @@ static int br_mdb_queue_one(struct list_head *mdb_list, } int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack) + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - struct net_bridge_mdb_entry *mp; + const struct net_bridge_mdb_entry *mp; struct switchdev_obj *obj, *tmp; struct net_bridge *br; + unsigned long action; LIST_HEAD(mdb_list); int err = 0; @@ -587,8 +636,8 @@ int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, rcu_read_lock(); hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { - struct net_bridge_port_group __rcu **pp; - struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu * const *pp; + const struct net_bridge_port_group *p; if (mp->host_joined) { err = br_mdb_queue_one(&mdb_list, @@ -617,9 +666,14 @@ int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, rcu_read_unlock(); + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + list_for_each_entry(obj, &mdb_list, list) { err = br_mdb_replay_one(nb, dev, SWITCHDEV_OBJ_PORT_MDB(obj), - extack); + action, ctx, extack); if (err) goto out_free_mdb; } diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index cd2b1e424e54..fd2de35ffb3c 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -204,6 +204,33 @@ static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp, hdr->timestamp = cpu_to_be32(jiffies_to_msecs(jiffies)); br_mrp_skb_common(skb, mrp); + + /* In case the node behaves as MRA then the Test frame needs to have + * an Option TLV which includes eventually a sub-option TLV that has + * the type AUTO_MGR + */ + if (mrp->ring_role == BR_MRP_RING_ROLE_MRA) { + struct br_mrp_sub_option1_hdr *sub_opt = NULL; + struct br_mrp_tlv_hdr *sub_tlv = NULL; + struct br_mrp_oui_hdr *oui = NULL; + u8 length; + + length = sizeof(*sub_opt) + sizeof(*sub_tlv) + sizeof(oui) + + MRP_OPT_PADDING; + br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_OPTION, length); + + oui = skb_put(skb, sizeof(*oui)); + memset(oui, 0x0, sizeof(*oui)); + sub_opt = skb_put(skb, sizeof(*sub_opt)); + memset(sub_opt, 0x0, sizeof(*sub_opt)); + + sub_tlv = skb_put(skb, sizeof(*sub_tlv)); + sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; + + /* 32 bit alligment shall be ensured therefore add 2 bytes */ + skb_put(skb, MRP_OPT_PADDING); + } + br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0); return skb; @@ -627,8 +654,7 @@ int br_mrp_set_ring_state(struct net_bridge *br, if (!mrp) return -EINVAL; - if (mrp->ring_state == BR_MRP_RING_STATE_CLOSED && - state->ring_state != BR_MRP_RING_STATE_CLOSED) + if (mrp->ring_state != state->ring_state) mrp->ring_transitions++; mrp->ring_state = state->ring_state; @@ -715,8 +741,7 @@ int br_mrp_set_in_state(struct net_bridge *br, struct br_mrp_in_state *state) if (!mrp) return -EINVAL; - if (mrp->in_state == BR_MRP_IN_STATE_CLOSED && - state->in_state != BR_MRP_IN_STATE_CLOSED) + if (mrp->in_state != state->in_state) mrp->in_transitions++; mrp->in_state = state->in_state; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 226bb05c3b42..53c3a9d80d9c 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -51,8 +51,8 @@ static const struct rhashtable_params br_sg_port_rht_params = { static void br_multicast_start_querier(struct net_bridge *br, struct bridge_mcast_own_query *query); -static void br_multicast_add_router(struct net_bridge *br, - struct net_bridge_port *port); +static void br_ip4_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port); static void br_ip4_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, @@ -60,7 +60,10 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, const unsigned char *src); static void br_multicast_port_group_rexmit(struct timer_list *t); -static void __del_port_router(struct net_bridge_port *p); +static void +br_multicast_rport_del_notify(struct net_bridge_port *p, bool deleted); +static void br_ip6_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port); #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, @@ -1354,23 +1357,64 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, } #endif -static void br_multicast_router_expired(struct timer_list *t) +static bool br_multicast_rport_del(struct hlist_node *rlist) +{ + if (hlist_unhashed(rlist)) + return false; + + hlist_del_init_rcu(rlist); + return true; +} + +static bool br_ip4_multicast_rport_del(struct net_bridge_port *p) +{ + return br_multicast_rport_del(&p->ip4_rlist); +} + +static bool br_ip6_multicast_rport_del(struct net_bridge_port *p) +{ +#if IS_ENABLED(CONFIG_IPV6) + return br_multicast_rport_del(&p->ip6_rlist); +#else + return false; +#endif +} + +static void br_multicast_router_expired(struct net_bridge_port *port, + struct timer_list *t, + struct hlist_node *rlist) { - struct net_bridge_port *port = - from_timer(port, t, multicast_router_timer); struct net_bridge *br = port->br; + bool del; spin_lock(&br->multicast_lock); if (port->multicast_router == MDB_RTR_TYPE_DISABLED || port->multicast_router == MDB_RTR_TYPE_PERM || - timer_pending(&port->multicast_router_timer)) + timer_pending(t)) goto out; - __del_port_router(port); + del = br_multicast_rport_del(rlist); + br_multicast_rport_del_notify(port, del); out: spin_unlock(&br->multicast_lock); } +static void br_ip4_multicast_router_expired(struct timer_list *t) +{ + struct net_bridge_port *port = from_timer(port, t, ip4_mc_router_timer); + + br_multicast_router_expired(port, t, &port->ip4_rlist); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_router_expired(struct timer_list *t) +{ + struct net_bridge_port *port = from_timer(port, t, ip6_mc_router_timer); + + br_multicast_router_expired(port, t, &port->ip6_rlist); +} +#endif + static void br_mc_router_state_change(struct net_bridge *p, bool is_mc_router) { @@ -1384,14 +1428,14 @@ static void br_mc_router_state_change(struct net_bridge *p, switchdev_port_attr_set(p->dev, &attr, NULL); } -static void br_multicast_local_router_expired(struct timer_list *t) +static void br_multicast_local_router_expired(struct net_bridge *br, + struct timer_list *timer) { - struct net_bridge *br = from_timer(br, t, multicast_router_timer); - spin_lock(&br->multicast_lock); if (br->multicast_router == MDB_RTR_TYPE_DISABLED || br->multicast_router == MDB_RTR_TYPE_PERM || - timer_pending(&br->multicast_router_timer)) + br_ip4_multicast_is_router(br) || + br_ip6_multicast_is_router(br)) goto out; br_mc_router_state_change(br, false); @@ -1399,6 +1443,22 @@ out: spin_unlock(&br->multicast_lock); } +static void br_ip4_multicast_local_router_expired(struct timer_list *t) +{ + struct net_bridge *br = from_timer(br, t, ip4_mc_router_timer); + + br_multicast_local_router_expired(br, t); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_local_router_expired(struct timer_list *t) +{ + struct net_bridge *br = from_timer(br, t, ip6_mc_router_timer); + + br_multicast_local_router_expired(br, t); +} +#endif + static void br_multicast_querier_expired(struct net_bridge *br, struct bridge_mcast_own_query *query) { @@ -1613,11 +1673,13 @@ int br_multicast_add_port(struct net_bridge_port *port) port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; port->multicast_eht_hosts_limit = BR_MCAST_DEFAULT_EHT_HOSTS_LIMIT; - timer_setup(&port->multicast_router_timer, - br_multicast_router_expired, 0); + timer_setup(&port->ip4_mc_router_timer, + br_ip4_multicast_router_expired, 0); timer_setup(&port->ip4_own_query.timer, br_ip4_multicast_port_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) + timer_setup(&port->ip6_mc_router_timer, + br_ip6_multicast_router_expired, 0); timer_setup(&port->ip6_own_query.timer, br_ip6_multicast_port_query_expired, 0); #endif @@ -1649,7 +1711,10 @@ void br_multicast_del_port(struct net_bridge_port *port) hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); br_multicast_gc(&deleted_head); - del_timer_sync(&port->multicast_router_timer); + del_timer_sync(&port->ip4_mc_router_timer); +#if IS_ENABLED(CONFIG_IPV6) + del_timer_sync(&port->ip6_mc_router_timer); +#endif free_percpu(port->mcast_stats); } @@ -1673,9 +1738,10 @@ static void __br_multicast_enable_port(struct net_bridge_port *port) #if IS_ENABLED(CONFIG_IPV6) br_multicast_enable(&port->ip6_own_query); #endif - if (port->multicast_router == MDB_RTR_TYPE_PERM && - hlist_unhashed(&port->rlist)) - br_multicast_add_router(br, port); + if (port->multicast_router == MDB_RTR_TYPE_PERM) { + br_ip4_multicast_add_router(br, port); + br_ip6_multicast_add_router(br, port); + } } void br_multicast_enable_port(struct net_bridge_port *port) @@ -1692,19 +1758,22 @@ void br_multicast_disable_port(struct net_bridge_port *port) struct net_bridge *br = port->br; struct net_bridge_port_group *pg; struct hlist_node *n; + bool del = false; spin_lock(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) if (!(pg->flags & MDB_PG_FLAGS_PERMANENT)) br_multicast_find_del_pg(br, pg); - __del_port_router(port); - - del_timer(&port->multicast_router_timer); + del |= br_ip4_multicast_rport_del(port); + del_timer(&port->ip4_mc_router_timer); del_timer(&port->ip4_own_query.timer); + del |= br_ip6_multicast_rport_del(port); #if IS_ENABLED(CONFIG_IPV6) + del_timer(&port->ip6_mc_router_timer); del_timer(&port->ip6_own_query.timer); #endif + br_multicast_rport_del_notify(port, del); spin_unlock(&br->multicast_lock); } @@ -2615,22 +2684,6 @@ update: } #endif -static bool br_multicast_select_querier(struct net_bridge *br, - struct net_bridge_port *port, - struct br_ip *saddr) -{ - switch (saddr->proto) { - case htons(ETH_P_IP): - return br_ip4_multicast_select_querier(br, port, saddr->src.ip4); -#if IS_ENABLED(CONFIG_IPV6) - case htons(ETH_P_IPV6): - return br_ip6_multicast_select_querier(br, port, &saddr->src.ip6); -#endif - } - - return false; -} - static void br_multicast_update_query_timer(struct net_bridge *br, struct bridge_mcast_other_query *query, @@ -2655,45 +2708,122 @@ static void br_port_mc_router_state_change(struct net_bridge_port *p, switchdev_port_attr_set(p->dev, &attr, NULL); } -/* - * Add port to router_list +static struct net_bridge_port * +br_multicast_rport_from_node(struct net_bridge *br, + struct hlist_head *mc_router_list, + struct hlist_node *rlist) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (mc_router_list == &br->ip6_mc_router_list) + return hlist_entry(rlist, struct net_bridge_port, ip6_rlist); +#endif + return hlist_entry(rlist, struct net_bridge_port, ip4_rlist); +} + +static struct hlist_node * +br_multicast_get_rport_slot(struct net_bridge *br, + struct net_bridge_port *port, + struct hlist_head *mc_router_list) + +{ + struct hlist_node *slot = NULL; + struct net_bridge_port *p; + struct hlist_node *rlist; + + hlist_for_each(rlist, mc_router_list) { + p = br_multicast_rport_from_node(br, mc_router_list, rlist); + + if ((unsigned long)port >= (unsigned long)p) + break; + + slot = rlist; + } + + return slot; +} + +static bool br_multicast_no_router_otherpf(struct net_bridge_port *port, + struct hlist_node *rnode) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (rnode != &port->ip6_rlist) + return hlist_unhashed(&port->ip6_rlist); + else + return hlist_unhashed(&port->ip4_rlist); +#else + return true; +#endif +} + +/* Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ static void br_multicast_add_router(struct net_bridge *br, - struct net_bridge_port *port) + struct net_bridge_port *port, + struct hlist_node *rlist, + struct hlist_head *mc_router_list) { - struct net_bridge_port *p; - struct hlist_node *slot = NULL; + struct hlist_node *slot; - if (!hlist_unhashed(&port->rlist)) + if (!hlist_unhashed(rlist)) return; - hlist_for_each_entry(p, &br->router_list, rlist) { - if ((unsigned long) port >= (unsigned long) p) - break; - slot = &p->rlist; - } + slot = br_multicast_get_rport_slot(br, port, mc_router_list); if (slot) - hlist_add_behind_rcu(&port->rlist, slot); + hlist_add_behind_rcu(rlist, slot); else - hlist_add_head_rcu(&port->rlist, &br->router_list); - br_rtr_notify(br->dev, port, RTM_NEWMDB); - br_port_mc_router_state_change(port, true); + hlist_add_head_rcu(rlist, mc_router_list); + + /* For backwards compatibility for now, only notify if we + * switched from no IPv4/IPv6 multicast router to a new + * IPv4 or IPv6 multicast router. + */ + if (br_multicast_no_router_otherpf(port, rlist)) { + br_rtr_notify(br->dev, port, RTM_NEWMDB); + br_port_mc_router_state_change(port, true); + } +} + +/* Add port to router_list + * list is maintained ordered by pointer value + * and locked by br->multicast_lock and RCU + */ +static void br_ip4_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port) +{ + br_multicast_add_router(br, port, &port->ip4_rlist, + &br->ip4_mc_router_list); +} + +/* Add port to router_list + * list is maintained ordered by pointer value + * and locked by br->multicast_lock and RCU + */ +static void br_ip6_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port) +{ +#if IS_ENABLED(CONFIG_IPV6) + br_multicast_add_router(br, port, &port->ip6_rlist, + &br->ip6_mc_router_list); +#endif } static void br_multicast_mark_router(struct net_bridge *br, - struct net_bridge_port *port) + struct net_bridge_port *port, + struct timer_list *timer, + struct hlist_node *rlist, + struct hlist_head *mc_router_list) { unsigned long now = jiffies; if (!port) { if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) { - if (!timer_pending(&br->multicast_router_timer)) + if (!br_ip4_multicast_is_router(br) && + !br_ip6_multicast_is_router(br)) br_mc_router_state_change(br, true); - mod_timer(&br->multicast_router_timer, - now + br->multicast_querier_interval); + mod_timer(timer, now + br->multicast_querier_interval); } return; } @@ -2702,24 +2832,71 @@ static void br_multicast_mark_router(struct net_bridge *br, port->multicast_router == MDB_RTR_TYPE_PERM) return; - br_multicast_add_router(br, port); + br_multicast_add_router(br, port, rlist, mc_router_list); + mod_timer(timer, now + br->multicast_querier_interval); +} + +static void br_ip4_multicast_mark_router(struct net_bridge *br, + struct net_bridge_port *port) +{ + struct timer_list *timer = &br->ip4_mc_router_timer; + struct hlist_node *rlist = NULL; + + if (port) { + timer = &port->ip4_mc_router_timer; + rlist = &port->ip4_rlist; + } - mod_timer(&port->multicast_router_timer, - now + br->multicast_querier_interval); + br_multicast_mark_router(br, port, timer, rlist, + &br->ip4_mc_router_list); } -static void br_multicast_query_received(struct net_bridge *br, - struct net_bridge_port *port, - struct bridge_mcast_other_query *query, - struct br_ip *saddr, - unsigned long max_delay) +static void br_ip6_multicast_mark_router(struct net_bridge *br, + struct net_bridge_port *port) +{ +#if IS_ENABLED(CONFIG_IPV6) + struct timer_list *timer = &br->ip6_mc_router_timer; + struct hlist_node *rlist = NULL; + + if (port) { + timer = &port->ip6_mc_router_timer; + rlist = &port->ip6_rlist; + } + + br_multicast_mark_router(br, port, timer, rlist, + &br->ip6_mc_router_list); +#endif +} + +static void +br_ip4_multicast_query_received(struct net_bridge *br, + struct net_bridge_port *port, + struct bridge_mcast_other_query *query, + struct br_ip *saddr, + unsigned long max_delay) +{ + if (!br_ip4_multicast_select_querier(br, port, saddr->src.ip4)) + return; + + br_multicast_update_query_timer(br, query, max_delay); + br_ip4_multicast_mark_router(br, port); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void +br_ip6_multicast_query_received(struct net_bridge *br, + struct net_bridge_port *port, + struct bridge_mcast_other_query *query, + struct br_ip *saddr, + unsigned long max_delay) { - if (!br_multicast_select_querier(br, port, saddr)) + if (!br_ip6_multicast_select_querier(br, port, &saddr->src.ip6)) return; br_multicast_update_query_timer(br, query, max_delay); - br_multicast_mark_router(br, port); + br_ip6_multicast_mark_router(br, port); } +#endif static void br_ip4_multicast_query(struct net_bridge *br, struct net_bridge_port *port, @@ -2768,8 +2945,8 @@ static void br_ip4_multicast_query(struct net_bridge *br, saddr.proto = htons(ETH_P_IP); saddr.src.ip4 = iph->saddr; - br_multicast_query_received(br, port, &br->ip4_other_query, - &saddr, max_delay); + br_ip4_multicast_query_received(br, port, &br->ip4_other_query, + &saddr, max_delay); goto out; } @@ -2856,8 +3033,8 @@ static int br_ip6_multicast_query(struct net_bridge *br, saddr.proto = htons(ETH_P_IPV6); saddr.src.ip6 = ipv6_hdr(skb)->saddr; - br_multicast_query_received(br, port, &br->ip6_other_query, - &saddr, max_delay); + br_ip6_multicast_query_received(br, port, &br->ip6_other_query, + &saddr, max_delay); goto out; } else if (!group) { goto out; @@ -3087,7 +3264,7 @@ static void br_multicast_pim(struct net_bridge *br, pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; - br_multicast_mark_router(br, port); + br_ip4_multicast_mark_router(br, port); } static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, @@ -3098,7 +3275,7 @@ static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, igmp_hdr(skb)->type != IGMP_MRDISC_ADV) return -ENOMSG; - br_multicast_mark_router(br, port); + br_ip4_multicast_mark_router(br, port); return 0; } @@ -3166,7 +3343,7 @@ static void br_ip6_multicast_mrd_rcv(struct net_bridge *br, if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) return; - br_multicast_mark_router(br, port); + br_ip6_multicast_mark_router(br, port); } static int br_multicast_ipv6_rcv(struct net_bridge *br, @@ -3316,13 +3493,15 @@ void br_multicast_init(struct net_bridge *br) br_opt_toggle(br, BROPT_HAS_IPV6_ADDR, true); spin_lock_init(&br->multicast_lock); - timer_setup(&br->multicast_router_timer, - br_multicast_local_router_expired, 0); + timer_setup(&br->ip4_mc_router_timer, + br_ip4_multicast_local_router_expired, 0); timer_setup(&br->ip4_other_query.timer, br_ip4_multicast_querier_expired, 0); timer_setup(&br->ip4_own_query.timer, br_ip4_multicast_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) + timer_setup(&br->ip6_mc_router_timer, + br_ip6_multicast_local_router_expired, 0); timer_setup(&br->ip6_other_query.timer, br_ip6_multicast_querier_expired, 0); timer_setup(&br->ip6_own_query.timer, @@ -3416,10 +3595,11 @@ void br_multicast_open(struct net_bridge *br) void br_multicast_stop(struct net_bridge *br) { - del_timer_sync(&br->multicast_router_timer); + del_timer_sync(&br->ip4_mc_router_timer); del_timer_sync(&br->ip4_other_query.timer); del_timer_sync(&br->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) + del_timer_sync(&br->ip6_mc_router_timer); del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif @@ -3453,7 +3633,10 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) case MDB_RTR_TYPE_DISABLED: case MDB_RTR_TYPE_PERM: br_mc_router_state_change(br, val == MDB_RTR_TYPE_PERM); - del_timer(&br->multicast_router_timer); + del_timer(&br->ip4_mc_router_timer); +#if IS_ENABLED(CONFIG_IPV6) + del_timer(&br->ip6_mc_router_timer); +#endif br->multicast_router = val; err = 0; break; @@ -3470,11 +3653,22 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) return err; } -static void __del_port_router(struct net_bridge_port *p) +static void +br_multicast_rport_del_notify(struct net_bridge_port *p, bool deleted) { - if (hlist_unhashed(&p->rlist)) + if (!deleted) + return; + + /* For backwards compatibility for now, only notify if there is + * no multicast router anymore for both IPv4 and IPv6. + */ + if (!hlist_unhashed(&p->ip4_rlist)) return; - hlist_del_init_rcu(&p->rlist); +#if IS_ENABLED(CONFIG_IPV6) + if (!hlist_unhashed(&p->ip6_rlist)) + return; +#endif + br_rtr_notify(p->br->dev, p, RTM_DELMDB); br_port_mc_router_state_change(p, false); @@ -3488,34 +3682,52 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) struct net_bridge *br = p->br; unsigned long now = jiffies; int err = -EINVAL; + bool del = false; spin_lock(&br->multicast_lock); if (p->multicast_router == val) { /* Refresh the temp router port timer */ - if (p->multicast_router == MDB_RTR_TYPE_TEMP) - mod_timer(&p->multicast_router_timer, + if (p->multicast_router == MDB_RTR_TYPE_TEMP) { + mod_timer(&p->ip4_mc_router_timer, now + br->multicast_querier_interval); +#if IS_ENABLED(CONFIG_IPV6) + mod_timer(&p->ip6_mc_router_timer, + now + br->multicast_querier_interval); +#endif + } err = 0; goto unlock; } switch (val) { case MDB_RTR_TYPE_DISABLED: p->multicast_router = MDB_RTR_TYPE_DISABLED; - __del_port_router(p); - del_timer(&p->multicast_router_timer); + del |= br_ip4_multicast_rport_del(p); + del_timer(&p->ip4_mc_router_timer); + del |= br_ip6_multicast_rport_del(p); +#if IS_ENABLED(CONFIG_IPV6) + del_timer(&p->ip6_mc_router_timer); +#endif + br_multicast_rport_del_notify(p, del); break; case MDB_RTR_TYPE_TEMP_QUERY: p->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; - __del_port_router(p); + del |= br_ip4_multicast_rport_del(p); + del |= br_ip6_multicast_rport_del(p); + br_multicast_rport_del_notify(p, del); break; case MDB_RTR_TYPE_PERM: p->multicast_router = MDB_RTR_TYPE_PERM; - del_timer(&p->multicast_router_timer); - br_multicast_add_router(br, p); + del_timer(&p->ip4_mc_router_timer); + br_ip4_multicast_add_router(br, p); +#if IS_ENABLED(CONFIG_IPV6) + del_timer(&p->ip6_mc_router_timer); +#endif + br_ip6_multicast_add_router(br, p); break; case MDB_RTR_TYPE_TEMP: p->multicast_router = MDB_RTR_TYPE_TEMP; - br_multicast_mark_router(br, p); + br_ip4_multicast_mark_router(br, p); + br_ip6_multicast_mark_router(br, p); break; default: goto unlock; @@ -3621,7 +3833,7 @@ bool br_multicast_router(const struct net_device *dev) bool is_router; spin_lock_bh(&br->multicast_lock); - is_router = br_multicast_is_router(br); + is_router = br_multicast_is_router(br, NULL); spin_unlock_bh(&br->multicast_lock); return is_router; } @@ -3842,6 +4054,61 @@ unlock: } EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent); +/** + * br_multicast_has_router_adjacent - Checks for a router behind a bridge port + * @dev: The bridge port adjacent to which to check for a multicast router + * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 + * + * Checks whether the given interface has a bridge on top and if so returns + * true if a multicast router is behind one of the other ports of this + * bridge. Otherwise returns false. + */ +bool br_multicast_has_router_adjacent(struct net_device *dev, int proto) +{ + struct net_bridge_port *port, *p; + bool ret = false; + + rcu_read_lock(); + port = br_port_get_check_rcu(dev); + if (!port) + goto unlock; + + switch (proto) { + case ETH_P_IP: + hlist_for_each_entry_rcu(p, &port->br->ip4_mc_router_list, + ip4_rlist) { + if (p == port) + continue; + + ret = true; + goto unlock; + } + break; +#if IS_ENABLED(CONFIG_IPV6) + case ETH_P_IPV6: + hlist_for_each_entry_rcu(p, &port->br->ip6_mc_router_list, + ip6_rlist) { + if (p == port) + continue; + + ret = true; + goto unlock; + } + break; +#endif + default: + /* when compiled without IPv6 support, be conservative and + * always assume presence of an IPv6 multicast router + */ + ret = true; + } + +unlock: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(br_multicast_has_router_adjacent); + static void br_mcast_stats_add(struct bridge_mcast_stats __percpu *stats, const struct sk_buff *skb, u8 type, u8 dir) { diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e4e6e991313e..8642e56059fb 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1644,7 +1644,6 @@ static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) p = br_port_get_rtnl(dev); if (!p) return 0; - br = p->br; vg = nbp_vlan_group(p); break; default: diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e013d33f1c7c..2b48b204205e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -307,16 +307,18 @@ struct net_bridge_port { #ifdef CONFIG_BRIDGE_IGMP_SNOOPING struct bridge_mcast_own_query ip4_own_query; + struct timer_list ip4_mc_router_timer; + struct hlist_node ip4_rlist; #if IS_ENABLED(CONFIG_IPV6) struct bridge_mcast_own_query ip6_own_query; + struct timer_list ip6_mc_router_timer; + struct hlist_node ip6_rlist; #endif /* IS_ENABLED(CONFIG_IPV6) */ u32 multicast_eht_hosts_limit; u32 multicast_eht_hosts_cnt; unsigned char multicast_router; struct bridge_mcast_stats __percpu *mcast_stats; - struct timer_list multicast_router_timer; struct hlist_head mglist; - struct hlist_node rlist; #endif #ifdef CONFIG_SYSFS @@ -449,14 +451,16 @@ struct net_bridge { struct hlist_head mcast_gc_list; struct hlist_head mdb_list; - struct hlist_head router_list; - struct timer_list multicast_router_timer; + struct hlist_head ip4_mc_router_list; + struct timer_list ip4_mc_router_timer; struct bridge_mcast_other_query ip4_other_query; struct bridge_mcast_own_query ip4_own_query; struct bridge_mcast_querier ip4_querier; struct bridge_mcast_stats __percpu *mcast_stats; #if IS_ENABLED(CONFIG_IPV6) + struct hlist_head ip6_mc_router_list; + struct timer_list ip6_mc_router_timer; struct bridge_mcast_other_query ip6_other_query; struct bridge_mcast_own_query ip6_own_query; struct bridge_mcast_querier ip6_querier; @@ -864,11 +868,58 @@ static inline bool br_group_is_l2(const struct br_ip *group) #define mlock_dereference(X, br) \ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) -static inline bool br_multicast_is_router(struct net_bridge *br) +static inline struct hlist_node * +br_multicast_get_first_rport_node(struct net_bridge *b, struct sk_buff *skb) { +#if IS_ENABLED(CONFIG_IPV6) + if (skb->protocol == htons(ETH_P_IPV6)) + return rcu_dereference(hlist_first_rcu(&b->ip6_mc_router_list)); +#endif + return rcu_dereference(hlist_first_rcu(&b->ip4_mc_router_list)); +} + +static inline struct net_bridge_port * +br_multicast_rport_from_node_skb(struct hlist_node *rp, struct sk_buff *skb) { +#if IS_ENABLED(CONFIG_IPV6) + if (skb->protocol == htons(ETH_P_IPV6)) + return hlist_entry_safe(rp, struct net_bridge_port, ip6_rlist); +#endif + return hlist_entry_safe(rp, struct net_bridge_port, ip4_rlist); +} + +static inline bool br_ip4_multicast_is_router(struct net_bridge *br) +{ + return timer_pending(&br->ip4_mc_router_timer); +} + +static inline bool br_ip6_multicast_is_router(struct net_bridge *br) { - return br->multicast_router == 2 || - (br->multicast_router == 1 && - timer_pending(&br->multicast_router_timer)); +#if IS_ENABLED(CONFIG_IPV6) + return timer_pending(&br->ip6_mc_router_timer); +#else + return false; +#endif +} + +static inline bool +br_multicast_is_router(struct net_bridge *br, struct sk_buff *skb) +{ + switch (br->multicast_router) { + case MDB_RTR_TYPE_PERM: + return true; + case MDB_RTR_TYPE_TEMP_QUERY: + if (skb) { + if (skb->protocol == htons(ETH_P_IP)) + return br_ip4_multicast_is_router(br); + else if (skb->protocol == htons(ETH_P_IPV6)) + return br_ip6_multicast_is_router(br); + } else { + return br_ip4_multicast_is_router(br) || + br_ip6_multicast_is_router(br); + } + fallthrough; + default: + return false; + } } static inline bool @@ -1017,7 +1068,8 @@ static inline void br_multicast_flood(struct net_bridge_mdb_entry *mdst, { } -static inline bool br_multicast_is_router(struct net_bridge *br) +static inline bool br_multicast_is_router(struct net_bridge *br, + struct sk_buff *skb) { return false; } @@ -1602,8 +1654,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, unsigned long flags, unsigned long mask, struct netlink_ext_ack *extack); -void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, - int type); +void br_switchdev_fdb_notify(struct net_bridge *br, + const struct net_bridge_fdb_entry *fdb, int type); int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags, struct netlink_ext_ack *extack); int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid); @@ -1650,7 +1702,8 @@ static inline int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid) } static inline void -br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) +br_switchdev_fdb_notify(struct net_bridge *br, + const struct net_bridge_fdb_entry *fdb, int type) { } diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h index 9559aa2750fb..bda8e1896712 100644 --- a/net/bridge/br_private_mrp.h +++ b/net/bridge/br_private_mrp.h @@ -6,6 +6,8 @@ #include "br_private.h" #include <uapi/linux/mrp_bridge.h> +#define MRP_OPT_PADDING 0x2 + struct br_mrp { /* list of mrp instances */ struct hlist_node list; @@ -134,4 +136,13 @@ struct br_mrp_in_test_hdr { __be32 timestamp; } __attribute__((__packed__)); +struct br_mrp_oui_hdr { + __u8 oui[MRP_OUI_LENGTH]; +}; + +struct br_mrp_sub_option1_hdr { + __u8 type; + __u8 data[MRP_MANUFACTURE_DATA_LENGTH]; +}; + #endif /* _BR_PRIVATE_MRP_H */ diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 3dafb6143cff..1d80f34a139c 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -639,9 +639,9 @@ int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time) return 0; } -clock_t br_get_ageing_time(struct net_device *br_dev) +clock_t br_get_ageing_time(const struct net_device *br_dev) { - struct net_bridge *br; + const struct net_bridge *br; if (!netif_is_bridge_master(br_dev)) return 0; diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index a5e601e41cb9..d3adee0f91f9 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -108,8 +108,11 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, } void -br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) +br_switchdev_fdb_notify(struct net_bridge *br, + const struct net_bridge_fdb_entry *fdb, int type) { + const struct net_bridge_port *dst = READ_ONCE(fdb->dst); + struct net_device *dev = dst ? dst->dev : br->dev; struct switchdev_notifier_fdb_info info = { .addr = fdb->key.addr.addr, .vid = fdb->key.vlan_id, @@ -118,17 +121,14 @@ br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) .offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags), }; - if (!fdb->dst) - return; - switch (type) { case RTM_DELNEIGH: call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_DEVICE, - fdb->dst->dev, &info.info, NULL); + dev, &info.info, NULL); break; case RTM_NEWNEIGH: call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_DEVICE, - fdb->dst->dev, &info.info, NULL); + dev, &info.info, NULL); break; } } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index da3256a3eed0..a08e9f193009 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -113,9 +113,7 @@ static void __vlan_add_list(struct net_bridge_vlan *v) headp = &vg->vlan_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct net_bridge_vlan, vlist); - if (v->vid < vent->vid) - continue; - else + if (v->vid >= vent->vid) break; } list_add_rcu(&v->vlist, hpos); @@ -1809,28 +1807,32 @@ out_kfree: static int br_vlan_replay_one(struct notifier_block *nb, struct net_device *dev, struct switchdev_obj_port_vlan *vlan, + const void *ctx, unsigned long action, struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { .info = { .dev = dev, .extack = extack, + .ctx = ctx, }, .obj = &vlan->obj, }; int err; - err = nb->notifier_call(nb, SWITCHDEV_PORT_OBJ_ADD, &obj_info); + err = nb->notifier_call(nb, action, &obj_info); return notifier_to_errno(err); } int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack) + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; struct net_bridge *br; + unsigned long action; int err = 0; u16 pvid; @@ -1857,6 +1859,11 @@ int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, if (!vg) return 0; + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { @@ -1870,7 +1877,7 @@ int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, if (!br_vlan_should_use(v)) continue; - err = br_vlan_replay_one(nb, dev, &vlan, extack); + err = br_vlan_replay_one(nb, dev, &vlan, ctx, action, extack); if (err) return err; } diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 3ad0a1df6712..647554c9813b 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -243,7 +243,7 @@ static void caif_ctrl_cb(struct cflayer *layr, cf_sk->sk.sk_shutdown = SHUTDOWN_MASK; cf_sk->sk.sk_err = ECONNRESET; set_rx_flow_on(cf_sk); - cf_sk->sk.sk_error_report(&cf_sk->sk); + sk_error_report(&cf_sk->sk); break; default: diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index cac30e676ac9..23267c8db7c4 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -480,7 +480,7 @@ got_phyid: phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC); if (!phyinfo) { res = -ENOMEM; - goto out_err; + goto out; } phy_layer->id = phyid; diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index fadc7c8a3107..37b67194c0df 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -76,8 +76,6 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) u8 buf; priv = container_of(layr, struct chnl_net, chnl); - if (!priv) - return -EINVAL; skb = (struct sk_buff *) cfpkt_tonative(pkt); diff --git a/net/can/bcm.c b/net/can/bcm.c index f3e4d9528fa3..508f67de0b80 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -785,6 +785,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, bcm_rx_handler, op); list_del(&op->list); + synchronize_rcu(); bcm_remove_op(op); return 1; /* done */ } @@ -1417,7 +1418,7 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, if (notify_enodev) { sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } break; @@ -1425,7 +1426,7 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, if (bo->bound && bo->ifindex == dev->ifindex) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } } } @@ -1533,9 +1534,13 @@ static int bcm_release(struct socket *sock) REGMASK(op->can_id), bcm_rx_handler, op); - bcm_remove_op(op); } + synchronize_rcu(); + + list_for_each_entry_safe(op, next, &bo->rx_ops, list) + bcm_remove_op(op); + #if IS_ENABLED(CONFIG_PROC_FS) /* remove procfs entry */ if (net->can.bcmproc_dir && bo->bcm_proc_read) diff --git a/net/can/gw.c b/net/can/gw.c index ba4124805602..d8861e862f15 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -596,6 +596,7 @@ static int cgw_notifier(struct notifier_block *nb, if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); } } @@ -1154,6 +1155,7 @@ static void cgw_remove_all_jobs(struct net *net) hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); } } @@ -1222,6 +1224,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); err = 0; break; diff --git a/net/can/isotp.c b/net/can/isotp.c index be6183f8ca11..caaa532ece94 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -168,7 +168,7 @@ static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) /* report 'connection timed out' */ sk->sk_err = ETIMEDOUT; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; @@ -225,8 +225,8 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) can_send_ret = can_send(nskb, 1); if (can_send_ret) - pr_notice_once("can-isotp: %s: can_send_ret %d\n", - __func__, can_send_ret); + pr_notice_once("can-isotp: %s: can_send_ret %pe\n", + __func__, ERR_PTR(can_send_ret)); dev_put(dev); @@ -339,7 +339,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); @@ -392,7 +392,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) /* overflow on receiver side - report 'message too long' */ sk->sk_err = EMSGSIZE; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); fallthrough; default: @@ -420,7 +420,7 @@ static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen, /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); return 1; } @@ -535,7 +535,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, /* wrong sn detected - report 'illegal byte sequence' */ sk->sk_err = EILSEQ; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; @@ -559,7 +559,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); return 1; } @@ -758,7 +758,7 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) /* report 'communication error on send' */ sk->sk_err = ECOMM; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); /* reset tx state */ so->tx.state = ISOTP_IDLE; @@ -801,10 +801,12 @@ isotp_tx_burst: can_skb_set_owner(skb, sk); can_send_ret = can_send(skb, 1); - if (can_send_ret) - pr_notice_once("can-isotp: %s: can_send_ret %d\n", - __func__, can_send_ret); - + if (can_send_ret) { + pr_notice_once("can-isotp: %s: can_send_ret %pe\n", + __func__, ERR_PTR(can_send_ret)); + if (can_send_ret == -ENOBUFS) + pr_notice_once("can-isotp: tx queue is full, increasing txqueuelen may prevent this error\n"); + } if (so->tx.idx >= so->tx.len) { /* we are done */ so->tx.state = ISOTP_IDLE; @@ -950,8 +952,8 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) err = can_send(skb, 1); dev_put(dev); if (err) { - pr_notice_once("can-isotp: %s: can_send_ret %d\n", - __func__, err); + pr_notice_once("can-isotp: %s: can_send_ret %pe\n", + __func__, ERR_PTR(err)); return err; } @@ -1028,9 +1030,6 @@ static int isotp_release(struct socket *sock) lock_sock(sk); - hrtimer_cancel(&so->txtimer); - hrtimer_cancel(&so->rxtimer); - /* remove current filters & unregister */ if (so->bound && (!(so->opt.flags & CAN_ISOTP_SF_BROADCAST))) { if (so->ifindex) { @@ -1042,10 +1041,14 @@ static int isotp_release(struct socket *sock) SINGLE_MASK(so->rxid), isotp_rcv, sk); dev_put(dev); + synchronize_rcu(); } } } + hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->rxtimer); + so->ifindex = 0; so->bound = 0; @@ -1155,7 +1158,7 @@ out: if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } return err; @@ -1354,13 +1357,13 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; } } @@ -1482,7 +1485,7 @@ static __init int isotp_module_init(void) err = can_proto_register(&isotp_can_proto); if (err < 0) - pr_err("can: registration of isotp protocol failed\n"); + pr_err("can: registration of isotp protocol failed %pe\n", ERR_PTR(err)); else register_netdevice_notifier(&canisotp_notifier); diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index da3a7a7bcff2..08c8606cfd9c 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -193,6 +193,10 @@ static void j1939_can_rx_unregister(struct j1939_priv *priv) can_rx_unregister(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, j1939_can_recv, priv); + /* The last reference of priv is dropped by the RCU deferred + * j1939_sk_sock_destruct() of the last socket, so we can + * safely drop this reference here. + */ j1939_priv_put(priv); } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 56aa66147d5a..54f6d521492f 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -398,6 +398,9 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + + /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ + sock_set_flag(sk, SOCK_RCU_FREE); sk->sk_destruct = j1939_sk_sock_destruct; sk->sk_protocol = CAN_J1939; @@ -673,7 +676,7 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, switch (optname) { case SO_J1939_FILTER: - if (!sockptr_is_null(optval)) { + if (!sockptr_is_null(optval) && optlen != 0) { struct j1939_filter *f; int c; @@ -1009,7 +1012,7 @@ void j1939_sk_send_loop_abort(struct sock *sk, int err) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } static int j1939_sk_send_loop(struct j1939_priv *priv, struct sock *sk, @@ -1189,7 +1192,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) list_for_each_entry(jsk, &priv->j1939_socks, list) { jsk->sk.sk_err = error_code; if (!sock_flag(&jsk->sk, SOCK_DEAD)) - jsk->sk.sk_error_report(&jsk->sk); + sk_error_report(&jsk->sk); j1939_sk_queue_drop_all(priv, jsk, error_code); } diff --git a/net/can/proc.c b/net/can/proc.c index d1fe49e6f16d..b3099f0a3cb8 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -99,8 +99,6 @@ static void can_init_stats(struct net *net) static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif, unsigned long count) { - unsigned long rate; - if (oldjif == newjif) return 0; @@ -111,9 +109,7 @@ static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif, return 99999999; } - rate = (count * HZ) / (newjif - oldjif); - - return rate; + return (count * HZ) / (newjif - oldjif); } void can_stat_update(struct timer_list *t) diff --git a/net/can/raw.c b/net/can/raw.c index ac96fc210025..ed4fcb7ab0c3 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -295,13 +295,13 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; } } @@ -488,7 +488,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } return err; diff --git a/net/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h index 792fcb974dc3..9c60feeb1bcb 100644 --- a/net/ceph/auth_x_protocol.h +++ b/net/ceph/auth_x_protocol.h @@ -87,7 +87,7 @@ struct ceph_x_authorize_reply { /* - * encyption bundle + * encryption bundle */ #define CEPHX_ENC_MAGIC 0xff009cad8826aa55ull diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 195ceb8afb06..013cbdb6cfe2 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1508,7 +1508,7 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, return get_generic_reply(con, hdr, skip); /* - * Older OSDs don't set reply tid even if the orignal + * Older OSDs don't set reply tid even if the original * request had a non-zero tid. Work around this weirdness * by allocating a new message. */ diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index c959320c4775..75b738083523 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1309,7 +1309,7 @@ static int get_osdmap_client_data_v(void **p, void *end, return -EINVAL; } - /* old osdmap enconding */ + /* old osdmap encoding */ struct_v = 0; } @@ -3010,7 +3010,7 @@ static bool is_valid_crush_name(const char *name) * parent, returns 0. * * Does a linear search, as there are no parent pointers of any - * kind. Note that the result is ambigous for items that occur + * kind. Note that the result is ambiguous for items that occur * multiple times in the map. */ static int get_immediate_parent(struct crush_map *c, int id, diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index cc3712ad8716..f564f82e91d9 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -524,8 +524,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) nr_maps++; } - diag = kzalloc(sizeof(*diag) + sizeof(diag->maps[0]) * nr_maps, - GFP_KERNEL); + diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); if (!diag) return ERR_PTR(-ENOMEM); diff --git a/net/core/dev.c b/net/core/dev.c index 2512f672bf8a..c253c2aafe97 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -148,6 +148,7 @@ #include <net/devlink.h> #include <linux/pm_runtime.h> #include <linux/prandom.h> +#include <linux/once_lite.h> #include "net-sysfs.h" @@ -3487,13 +3488,16 @@ EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG +static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) +{ + pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>"); + skb_dump(KERN_ERR, skb, true); + dump_stack(); +} + void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { - if (net_ratelimit()) { - pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>"); - skb_dump(KERN_ERR, skb, true); - dump_stack(); - } + DO_ONCE_LITE(do_netdev_rx_csum_fault, dev, skb); } EXPORT_SYMBOL(netdev_rx_csum_fault); #endif @@ -3852,10 +3856,33 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { + if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) && + qdisc_run_begin(q)) { + /* Retest nolock_qdisc_is_empty() within the protection + * of q->seqlock to protect from racing with requeuing. + */ + if (unlikely(!nolock_qdisc_is_empty(q))) { + rc = q->enqueue(skb, q, &to_free) & + NET_XMIT_MASK; + __qdisc_run(q); + qdisc_run_end(q); + + goto no_lock_out; + } + + qdisc_bstats_cpu_update(q, skb); + if (sch_direct_xmit(skb, q, dev, txq, NULL, true) && + !nolock_qdisc_is_empty(q)) + __qdisc_run(q); + + qdisc_run_end(q); + return NET_XMIT_SUCCESS; + } + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - if (likely(!netif_xmit_frozen_or_stopped(txq))) - qdisc_run(q); + qdisc_run(q); +no_lock_out: if (unlikely(to_free)) kfree_skb_list(to_free); return rc; @@ -5277,9 +5304,9 @@ another_round: if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret2; - preempt_disable(); + migrate_disable(); ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); - preempt_enable(); + migrate_enable(); if (ret2 != XDP_PASS) { ret = NET_RX_DROP; @@ -6520,11 +6547,18 @@ EXPORT_SYMBOL(napi_schedule_prep); * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule * - * Variant of __napi_schedule() assuming hard irqs are masked + * Variant of __napi_schedule() assuming hard irqs are masked. + * + * On PREEMPT_RT enabled kernels this maps to __napi_schedule() + * because the interrupt disabled assumption might not be true + * due to force-threaded interrupts and spinlock substitution. */ void __napi_schedule_irqoff(struct napi_struct *n) { - ____napi_schedule(this_cpu_ptr(&softnet_data), n); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + else + __napi_schedule(n); } EXPORT_SYMBOL(__napi_schedule_irqoff); diff --git a/net/core/devlink.c b/net/core/devlink.c index 051432ea4f69..8fdd04f00fd7 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -190,6 +190,80 @@ static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, return devlink_port_get_from_attrs(devlink, info->attrs); } +static inline bool +devlink_rate_is_leaf(struct devlink_rate *devlink_rate) +{ + return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF; +} + +static inline bool +devlink_rate_is_node(struct devlink_rate *devlink_rate) +{ + return devlink_rate->type == DEVLINK_RATE_TYPE_NODE; +} + +static struct devlink_rate * +devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info) +{ + struct devlink_rate *devlink_rate; + struct devlink_port *devlink_port; + + devlink_port = devlink_port_get_from_attrs(devlink, info->attrs); + if (IS_ERR(devlink_port)) + return ERR_CAST(devlink_port); + devlink_rate = devlink_port->devlink_rate; + return devlink_rate ?: ERR_PTR(-ENODEV); +} + +static struct devlink_rate * +devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name) +{ + static struct devlink_rate *devlink_rate; + + list_for_each_entry(devlink_rate, &devlink->rate_list, list) { + if (devlink_rate_is_node(devlink_rate) && + !strcmp(node_name, devlink_rate->name)) + return devlink_rate; + } + return ERR_PTR(-ENODEV); +} + +static struct devlink_rate * +devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) +{ + const char *rate_node_name; + size_t len; + + if (!attrs[DEVLINK_ATTR_RATE_NODE_NAME]) + return ERR_PTR(-EINVAL); + rate_node_name = nla_data(attrs[DEVLINK_ATTR_RATE_NODE_NAME]); + len = strlen(rate_node_name); + /* Name cannot be empty or decimal number */ + if (!len || strspn(rate_node_name, "0123456789") == len) + return ERR_PTR(-EINVAL); + + return devlink_rate_node_get_by_name(devlink, rate_node_name); +} + +static struct devlink_rate * +devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info) +{ + return devlink_rate_node_get_from_attrs(devlink, info->attrs); +} + +static struct devlink_rate * +devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info) +{ + struct nlattr **attrs = info->attrs; + + if (attrs[DEVLINK_ATTR_PORT_INDEX]) + return devlink_rate_leaf_get_from_info(devlink, info); + else if (attrs[DEVLINK_ATTR_RATE_NODE_NAME]) + return devlink_rate_node_get_from_info(devlink, info); + else + return ERR_PTR(-EINVAL); +} + struct devlink_sb { struct list_head list; unsigned int index; @@ -408,12 +482,14 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) #define DEVLINK_NL_FLAG_NEED_PORT BIT(0) #define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1) +#define DEVLINK_NL_FLAG_NEED_RATE BIT(2) +#define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3) /* The per devlink instance lock is taken by default in the pre-doit * operation, yet several commands do not require this. The global * devlink lock is taken and protects from disruption by user-calls. */ -#define DEVLINK_NL_FLAG_NO_LOCK BIT(2) +#define DEVLINK_NL_FLAG_NO_LOCK BIT(4) static int devlink_nl_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) @@ -442,6 +518,24 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops, devlink_port = devlink_port_get_from_info(devlink, info); if (!IS_ERR(devlink_port)) info->user_ptr[1] = devlink_port; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) { + struct devlink_rate *devlink_rate; + + devlink_rate = devlink_rate_get_from_info(devlink, info); + if (IS_ERR(devlink_rate)) { + err = PTR_ERR(devlink_rate); + goto unlock; + } + info->user_ptr[1] = devlink_rate; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) { + struct devlink_rate *rate_node; + + rate_node = devlink_rate_node_get_from_info(devlink, info); + if (IS_ERR(rate_node)) { + err = PTR_ERR(rate_node); + goto unlock; + } + info->user_ptr[1] = rate_node; } return 0; @@ -748,6 +842,56 @@ devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops * return 0; } +static int devlink_nl_rate_fill(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_rate *devlink_rate, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, + struct netlink_ext_ack *extack) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type)) + goto nla_put_failure; + + if (devlink_rate_is_leaf(devlink_rate)) { + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, + devlink_rate->devlink_port->index)) + goto nla_put_failure; + } else if (devlink_rate_is_node(devlink_rate)) { + if (nla_put_string(msg, DEVLINK_ATTR_RATE_NODE_NAME, + devlink_rate->name)) + goto nla_put_failure; + } + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE, + devlink_rate->tx_share, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_MAX, + devlink_rate->tx_max, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (devlink_rate->parent) + if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, + devlink_rate->parent->name)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + static bool devlink_port_fn_state_valid(enum devlink_port_fn_state state) { @@ -919,6 +1063,111 @@ static void devlink_port_notify(struct devlink_port *devlink_port, msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } +static void devlink_rate_notify(struct devlink_rate *devlink_rate, + enum devlink_command cmd) +{ + struct devlink *devlink = devlink_rate->devlink; + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && + cmd != DEVLINK_CMD_RATE_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_rate_fill(msg, devlink, devlink_rate, + cmd, 0, 0, 0, NULL); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_rate *devlink_rate; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err = 0; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_rate, &devlink->rate_list, list) { + enum devlink_command cmd = DEVLINK_CMD_RATE_NEW; + u32 id = NETLINK_CB(cb->skb).portid; + + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_rate_fill(msg, devlink, + devlink_rate, + cmd, id, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, NULL); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_rate *devlink_rate = info->user_ptr[1]; + struct devlink *devlink = devlink_rate->devlink; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_rate_fill(msg, devlink, devlink_rate, + DEVLINK_CMD_RATE_NEW, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static bool +devlink_rate_is_parent_node(struct devlink_rate *devlink_rate, + struct devlink_rate *parent) +{ + while (parent) { + if (parent == devlink_rate) + return true; + parent = parent->parent; + } + return false; +} + static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; @@ -1339,6 +1588,255 @@ static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, return devlink->ops->port_del(devlink, port_index, extack); } +static int +devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate, + struct genl_info *info, + struct nlattr *nla_parent) +{ + struct devlink *devlink = devlink_rate->devlink; + const char *parent_name = nla_data(nla_parent); + const struct devlink_ops *ops = devlink->ops; + size_t len = strlen(parent_name); + struct devlink_rate *parent; + int err = -EOPNOTSUPP; + + parent = devlink_rate->parent; + if (parent && len) { + NL_SET_ERR_MSG_MOD(info->extack, "Rate object already has parent."); + return -EBUSY; + } else if (parent && !len) { + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_parent_set(devlink_rate, NULL, + devlink_rate->priv, NULL, + info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_parent_set(devlink_rate, NULL, + devlink_rate->priv, NULL, + info->extack); + if (err) + return err; + + refcount_dec(&parent->refcnt); + devlink_rate->parent = NULL; + } else if (!parent && len) { + parent = devlink_rate_node_get_by_name(devlink, parent_name); + if (IS_ERR(parent)) + return -ENODEV; + + if (parent == devlink_rate) { + NL_SET_ERR_MSG_MOD(info->extack, "Parent to self is not allowed"); + return -EINVAL; + } + + if (devlink_rate_is_node(devlink_rate) && + devlink_rate_is_parent_node(devlink_rate, parent->parent)) { + NL_SET_ERR_MSG_MOD(info->extack, "Node is already a parent of parent node."); + return -EEXIST; + } + + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_parent_set(devlink_rate, parent, + devlink_rate->priv, parent->priv, + info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_parent_set(devlink_rate, parent, + devlink_rate->priv, parent->priv, + info->extack); + if (err) + return err; + + refcount_inc(&parent->refcnt); + devlink_rate->parent = parent; + } + + return 0; +} + +static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, + const struct devlink_ops *ops, + struct genl_info *info) +{ + struct nlattr *nla_parent, **attrs = info->attrs; + int err = -EOPNOTSUPP; + u64 rate; + + if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) { + rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_share_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + if (err) + return err; + devlink_rate->tx_share = rate; + } + + if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) { + rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_max_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + if (err) + return err; + devlink_rate->tx_max = rate; + } + + nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]; + if (nla_parent) { + err = devlink_nl_rate_parent_node_set(devlink_rate, info, + nla_parent); + if (err) + return err; + } + + return 0; +} + +static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, + struct genl_info *info, + enum devlink_rate_type type) +{ + struct nlattr **attrs = info->attrs; + + if (type == DEVLINK_RATE_TYPE_LEAF) { + if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_leaf_tx_share_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the leafs"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_leaf_tx_max_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the leafs"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] && + !ops->rate_leaf_parent_set) { + NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs"); + return false; + } + } else if (type == DEVLINK_RATE_TYPE_NODE) { + if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_node_tx_max_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the nodes"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] && + !ops->rate_node_parent_set) { + NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes"); + return false; + } + } else { + WARN(1, "Unknown type of rate object"); + return false; + } + + return true; +} + +static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_rate *devlink_rate = info->user_ptr[1]; + struct devlink *devlink = devlink_rate->devlink; + const struct devlink_ops *ops = devlink->ops; + int err; + + if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type)) + return -EOPNOTSUPP; + + err = devlink_nl_rate_set(devlink_rate, ops, info); + + if (!err) + devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW); + return err; +} + +static int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_rate *rate_node; + const struct devlink_ops *ops; + int err; + + ops = devlink->ops; + if (!ops || !ops->rate_node_new || !ops->rate_node_del) { + NL_SET_ERR_MSG_MOD(info->extack, "Rate nodes aren't supported"); + return -EOPNOTSUPP; + } + + if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE)) + return -EOPNOTSUPP; + + rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs); + if (!IS_ERR(rate_node)) + return -EEXIST; + else if (rate_node == ERR_PTR(-EINVAL)) + return -EINVAL; + + rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL); + if (!rate_node) + return -ENOMEM; + + rate_node->devlink = devlink; + rate_node->type = DEVLINK_RATE_TYPE_NODE; + rate_node->name = nla_strdup(info->attrs[DEVLINK_ATTR_RATE_NODE_NAME], GFP_KERNEL); + if (!rate_node->name) { + err = -ENOMEM; + goto err_strdup; + } + + err = ops->rate_node_new(rate_node, &rate_node->priv, info->extack); + if (err) + goto err_node_new; + + err = devlink_nl_rate_set(rate_node, ops, info); + if (err) + goto err_rate_set; + + refcount_set(&rate_node->refcnt, 1); + list_add(&rate_node->list, &devlink->rate_list); + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW); + return 0; + +err_rate_set: + ops->rate_node_del(rate_node, rate_node->priv, info->extack); +err_node_new: + kfree(rate_node->name); +err_strdup: + kfree(rate_node); + return err; +} + +static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_rate *rate_node = info->user_ptr[1]; + struct devlink *devlink = rate_node->devlink; + const struct devlink_ops *ops = devlink->ops; + int err; + + if (refcount_read(&rate_node->refcnt) > 1) { + NL_SET_ERR_MSG_MOD(info->extack, "Node has children. Cannot delete node."); + return -EBUSY; + } + + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL); + err = ops->rate_node_del(rate_node, rate_node->priv, info->extack); + if (rate_node->parent) + refcount_dec(&rate_node->parent->refcnt); + list_del(&rate_node->list); + kfree(rate_node->name); + kfree(rate_node); + return err; +} + static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, enum devlink_command cmd, u32 portid, @@ -2207,6 +2705,23 @@ static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } +static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) +{ + struct devlink_rate *devlink_rate; + + /* Take the lock to sync with devlink_rate_nodes_destroy() */ + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_rate, &devlink->rate_list, list) + if (devlink_rate_is_node(devlink_rate)) { + mutex_unlock(&devlink->lock); + NL_SET_ERR_MSG_MOD(extack, "Rate node(s) exists."); + return -EBUSY; + } + mutex_unlock(&devlink->lock); + return 0; +} + static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) { @@ -2221,6 +2736,9 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, if (!ops->eswitch_mode_set) return -EOPNOTSUPP; mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); + err = devlink_rate_nodes_check(devlink, mode, info->extack); + if (err) + return err; err = ops->eswitch_mode_set(devlink, mode, info->extack); if (err) return err; @@ -6994,8 +7512,9 @@ static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats, } } -static int devlink_trap_stats_put(struct sk_buff *msg, - struct devlink_stats __percpu *trap_stats) +static int +devlink_trap_group_stats_put(struct sk_buff *msg, + struct devlink_stats __percpu *trap_stats) { struct devlink_stats stats; struct nlattr *attr; @@ -7023,6 +7542,50 @@ nla_put_failure: return -EMSGSIZE; } +static int devlink_trap_stats_put(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_item *trap_item) +{ + struct devlink_stats stats; + struct nlattr *attr; + u64 drops = 0; + int err; + + if (devlink->ops->trap_drop_counter_get) { + err = devlink->ops->trap_drop_counter_get(devlink, + trap_item->trap, + &drops); + if (err) + return err; + } + + devlink_trap_stats_read(trap_item->stats, &stats); + + attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); + if (!attr) + return -EMSGSIZE; + + if (devlink->ops->trap_drop_counter_get && + nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops, + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, + stats.rx_packets, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, + stats.rx_bytes, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink, const struct devlink_trap_item *trap_item, enum devlink_command cmd, u32 portid, u32 seq, @@ -7060,7 +7623,7 @@ static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink, if (err) goto nla_put_failure; - err = devlink_trap_stats_put(msg, trap_item->stats); + err = devlink_trap_stats_put(msg, devlink, trap_item); if (err) goto nla_put_failure; @@ -7277,7 +7840,7 @@ devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink, group_item->policer_item->policer->id)) goto nla_put_failure; - err = devlink_trap_stats_put(msg, group_item->stats); + err = devlink_trap_group_stats_put(msg, group_item->stats); if (err) goto nla_put_failure; @@ -7801,6 +8364,11 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, + [DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 }, + [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING }, }; static const struct genl_small_ops devlink_nl_ops[] = { @@ -7827,6 +8395,30 @@ static const struct genl_small_ops devlink_nl_ops[] = { .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, }, { + .cmd = DEVLINK_CMD_RATE_GET, + .doit = devlink_nl_cmd_rate_get_doit, + .dumpit = devlink_nl_cmd_rate_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_RATE_SET, + .doit = devlink_nl_cmd_rate_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, + }, + { + .cmd = DEVLINK_CMD_RATE_NEW, + .doit = devlink_nl_cmd_rate_new_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_RATE_DEL, + .doit = devlink_nl_cmd_rate_del_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_RATE_NODE, + }, + { .cmd = DEVLINK_CMD_PORT_SPLIT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_port_split_doit, @@ -8201,6 +8793,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC); __devlink_net_set(devlink, &init_net); INIT_LIST_HEAD(&devlink->port_list); + INIT_LIST_HEAD(&devlink->rate_list); INIT_LIST_HEAD(&devlink->sb_list); INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); INIT_LIST_HEAD(&devlink->resource_list); @@ -8303,6 +8896,7 @@ void devlink_free(struct devlink *devlink) WARN_ON(!list_empty(&devlink->resource_list)); WARN_ON(!list_empty(&devlink->dpipe_table_list)); WARN_ON(!list_empty(&devlink->sb_list)); + WARN_ON(!list_empty(&devlink->rate_list)); WARN_ON(!list_empty(&devlink->port_list)); xa_destroy(&devlink->snapshot_ids); @@ -8619,6 +9213,110 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); +/** + * devlink_rate_leaf_create - create devlink rate leaf + * + * @devlink_port: devlink port object to create rate object on + * @priv: driver private data + * + * Create devlink rate object of type leaf on provided @devlink_port. + * Throws call trace if @devlink_port already has a devlink rate object. + * + * Context: Takes and release devlink->lock <mutex>. + * + * Return: -ENOMEM if failed to allocate rate object, 0 otherwise. + */ +int +devlink_rate_leaf_create(struct devlink_port *devlink_port, void *priv) +{ + struct devlink *devlink = devlink_port->devlink; + struct devlink_rate *devlink_rate; + + devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL); + if (!devlink_rate) + return -ENOMEM; + + mutex_lock(&devlink->lock); + WARN_ON(devlink_port->devlink_rate); + devlink_rate->type = DEVLINK_RATE_TYPE_LEAF; + devlink_rate->devlink = devlink; + devlink_rate->devlink_port = devlink_port; + devlink_rate->priv = priv; + list_add_tail(&devlink_rate->list, &devlink->rate_list); + devlink_port->devlink_rate = devlink_rate; + devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW); + mutex_unlock(&devlink->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_rate_leaf_create); + +/** + * devlink_rate_leaf_destroy - destroy devlink rate leaf + * + * @devlink_port: devlink port linked to the rate object + * + * Context: Takes and release devlink->lock <mutex>. + */ +void devlink_rate_leaf_destroy(struct devlink_port *devlink_port) +{ + struct devlink_rate *devlink_rate = devlink_port->devlink_rate; + struct devlink *devlink = devlink_port->devlink; + + if (!devlink_rate) + return; + + mutex_lock(&devlink->lock); + devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL); + if (devlink_rate->parent) + refcount_dec(&devlink_rate->parent->refcnt); + list_del(&devlink_rate->list); + devlink_port->devlink_rate = NULL; + mutex_unlock(&devlink->lock); + kfree(devlink_rate); +} +EXPORT_SYMBOL_GPL(devlink_rate_leaf_destroy); + +/** + * devlink_rate_nodes_destroy - destroy all devlink rate nodes on device + * + * @devlink: devlink instance + * + * Unset parent for all rate objects and destroy all rate nodes + * on specified device. + * + * Context: Takes and release devlink->lock <mutex>. + */ +void devlink_rate_nodes_destroy(struct devlink *devlink) +{ + static struct devlink_rate *devlink_rate, *tmp; + const struct devlink_ops *ops = devlink->ops; + + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_rate, &devlink->rate_list, list) { + if (!devlink_rate->parent) + continue; + + refcount_dec(&devlink_rate->parent->refcnt); + if (devlink_rate_is_leaf(devlink_rate)) + ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv, + NULL, NULL); + else if (devlink_rate_is_node(devlink_rate)) + ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv, + NULL, NULL); + } + list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) { + if (devlink_rate_is_node(devlink_rate)) { + ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL); + list_del(&devlink_rate->list); + kfree(devlink_rate->name); + kfree(devlink_rate); + } + } + mutex_unlock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devlink_rate_nodes_destroy); + static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, char *name, size_t len) { @@ -8630,12 +9328,18 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: + case DEVLINK_PORT_FLAVOUR_VIRTUAL: + n = snprintf(name, len, "p%u", attrs->phys.port_number); + if (n < len && attrs->split) + n += snprintf(name + n, len - n, "s%u", + attrs->phys.split_subport_number); if (!attrs->split) n = snprintf(name, len, "p%u", attrs->phys.port_number); else n = snprintf(name, len, "p%us%u", attrs->phys.port_number, attrs->phys.split_subport_number); + break; case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -8677,8 +9381,6 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, attrs->pci_sf.sf); break; - case DEVLINK_PORT_FLAVOUR_VIRTUAL: - return -EOPNOTSUPP; } if (n >= len) diff --git a/net/core/filter.c b/net/core/filter.c index d81352ca1b5c..d70187ce851b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3241,9 +3241,6 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) - return -ENOTSUPP; - ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -3255,19 +3252,11 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); - /* SKB_GSO_TCPV4 needs to be changed into - * SKB_GSO_TCPV6. - */ + /* SKB_GSO_TCPV4 needs to be changed into SKB_GSO_TCPV6. */ if (shinfo->gso_type & SKB_GSO_TCPV4) { shinfo->gso_type &= ~SKB_GSO_TCPV4; shinfo->gso_type |= SKB_GSO_TCPV6; } - - /* Due to IPv6 header, MSS needs to be downgraded. */ - skb_decrease_gso_size(shinfo, len_diff); - /* Header must be checked, and gso_segs recomputed. */ - shinfo->gso_type |= SKB_GSO_DODGY; - shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IPV6); @@ -3282,9 +3271,6 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) - return -ENOTSUPP; - ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -3296,19 +3282,11 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); - /* SKB_GSO_TCPV6 needs to be changed into - * SKB_GSO_TCPV4. - */ + /* SKB_GSO_TCPV6 needs to be changed into SKB_GSO_TCPV4. */ if (shinfo->gso_type & SKB_GSO_TCPV6) { shinfo->gso_type &= ~SKB_GSO_TCPV6; shinfo->gso_type |= SKB_GSO_TCPV4; } - - /* Due to IPv4 header, MSS can be upgraded. */ - skb_increase_gso_size(shinfo, len_diff); - /* Header must be checked, and gso_segs recomputed. */ - shinfo->gso_type |= SKB_GSO_DODGY; - shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IP); @@ -3919,6 +3897,34 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .arg2_type = ARG_ANYTHING, }; +/* XDP_REDIRECT works by a three-step process, implemented in the functions + * below: + * + * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target + * of the redirect and store it (along with some other metadata) in a per-CPU + * struct bpf_redirect_info. + * + * 2. When the program returns the XDP_REDIRECT return code, the driver will + * call xdp_do_redirect() which will use the information in struct + * bpf_redirect_info to actually enqueue the frame into a map type-specific + * bulk queue structure. + * + * 3. Before exiting its NAPI poll loop, the driver will call xdp_do_flush(), + * which will flush all the different bulk queues, thus completing the + * redirect. + * + * Pointers to the map entries will be kept around for this whole sequence of + * steps, protected by RCU. However, there is no top-level rcu_read_lock() in + * the core code; instead, the RCU protection relies on everything happening + * inside a single NAPI poll sequence, which means it's between a pair of calls + * to local_bh_disable()/local_bh_enable(). + * + * The map entries are marked as __rcu and the map code makes sure to + * dereference those pointers with rcu_dereference_check() in a way that works + * for both sections that to hold an rcu_read_lock() and sections that are + * called from NAPI without a separate rcu_read_lock(). The code below does not + * use RCU annotations, but relies on those in the map code. + */ void xdp_do_flush(void) { __dev_flush(); @@ -3927,6 +3933,23 @@ void xdp_do_flush(void) } EXPORT_SYMBOL_GPL(xdp_do_flush); +void bpf_clear_redirect_map(struct bpf_map *map) +{ + struct bpf_redirect_info *ri; + int cpu; + + for_each_possible_cpu(cpu) { + ri = per_cpu_ptr(&bpf_redirect_info, cpu); + /* Avoid polluting remote cacheline due to writes if + * not needed. Once we pass this test, we need the + * cmpxchg() to make sure it hasn't been changed in + * the meantime by remote CPU. + */ + if (unlikely(READ_ONCE(ri->map) == map)) + cmpxchg(&ri->map, map, NULL); + } +} + int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { @@ -3934,6 +3957,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ @@ -3943,7 +3967,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - err = dev_map_enqueue(fwd, xdp, dev); + map = READ_ONCE(ri->map); + if (unlikely(map)) { + WRITE_ONCE(ri->map, NULL); + err = dev_map_enqueue_multi(xdp, dev, map, + ri->flags & BPF_F_EXCLUDE_INGRESS); + } else { + err = dev_map_enqueue(fwd, xdp, dev); + } break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_enqueue(fwd, xdp, dev); @@ -3985,13 +4016,21 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, enum bpf_map_type map_type, u32 map_id) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_map *map; int err; switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - err = dev_map_generic_redirect(fwd, skb, xdp_prog); + map = READ_ONCE(ri->map); + if (unlikely(map)) { + WRITE_ONCE(ri->map, NULL); + err = dev_map_redirect_multi(dev, skb, xdp_prog, map, + ri->flags & BPF_F_EXCLUDE_INGRESS); + } else { + err = dev_map_generic_redirect(fwd, skb, xdp_prog); + } if (unlikely(err)) goto err; break; @@ -10008,11 +10047,13 @@ out: static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { reuse_kern->skb = skb; reuse_kern->sk = sk; reuse_kern->selected_sk = NULL; + reuse_kern->migrating_sk = migrating_sk; reuse_kern->data_end = skb->data + skb_headlen(skb); reuse_kern->hash = hash; reuse_kern->reuseport_id = reuse->reuseport_id; @@ -10021,12 +10062,13 @@ static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { struct sk_reuseport_kern reuse_kern; enum sk_action action; - bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash); + bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); action = BPF_PROG_RUN(prog, &reuse_kern); if (action == SK_PASS) @@ -10136,6 +10178,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, return &sk_reuseport_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &sk_reuseport_load_bytes_relative_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_ptr_cookie_proto; default: return bpf_base_func_proto(func_id); } @@ -10165,6 +10209,14 @@ sk_reuseport_is_valid_access(int off, int size, case offsetof(struct sk_reuseport_md, hash): return size == size_default; + case offsetof(struct sk_reuseport_md, sk): + info->reg_type = PTR_TO_SOCKET; + return size == sizeof(__u64); + + case offsetof(struct sk_reuseport_md, migrating_sk): + info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; + return size == sizeof(__u64); + /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) @@ -10237,6 +10289,14 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_reuseport_md, bind_inany): SK_REUSEPORT_LOAD_FIELD(bind_inany); break; + + case offsetof(struct sk_reuseport_md, sk): + SK_REUSEPORT_LOAD_FIELD(sk); + break; + + case offsetof(struct sk_reuseport_md, migrating_sk): + SK_REUSEPORT_LOAD_FIELD(migrating_sk); + break; } return insn - insn_buf; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3ed7c98a98e1..2aadbfc5193b 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -943,8 +943,8 @@ bool __skb_flow_dissect(const struct net *net, int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; - /* Tail taggers don't break flow dissection */ - if (!ops->tail_tag) { + /* Only DSA header taggers break flow dissection */ + if (ops->needed_headroom) { if (ops->flow_dissect) ops->flow_dissect(skb, &proto, &offset); else diff --git a/net/core/neighbour.c b/net/core/neighbour.c index bf774575ad71..53e85c70c6e5 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3142,7 +3142,7 @@ static struct pneigh_entry *pneigh_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; struct pneigh_entry *pn = NULL; - int bucket = state->bucket; + int bucket; state->flags |= NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) { diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 283ddb2dbc7d..c40cd8dd75c7 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -60,3 +60,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll); EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset); +EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_bad_csum); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index c310c7c1cef7..0a6b04714558 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -36,6 +36,7 @@ #include <net/ip6_checksum.h> #include <asm/unaligned.h> #include <trace/events/napi.h> +#include <linux/kconfig.h> /* * We maintain a small pool of fully-sized skbs, to make sure the @@ -389,7 +390,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) static atomic_t ip_ident; struct ipv6hdr *ip6h; - WARN_ON_ONCE(!irqs_disabled()); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + WARN_ON_ONCE(!irqs_disabled()); udp_len = len + sizeof(*udph); if (np->ipv6) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 3c4c4c7a0402..5e4eb45b139c 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -17,6 +17,7 @@ #include <linux/dma-mapping.h> #include <linux/page-flags.h> #include <linux/mm.h> /* for __put_page() */ +#include <linux/poison.h> #include <trace/events/page_pool.h> @@ -221,6 +222,8 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool, return NULL; } + page->pp_magic |= PP_SIGNATURE; + /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt); @@ -263,6 +266,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, put_page(page); continue; } + page->pp_magic |= PP_SIGNATURE; pool->alloc.cache[pool->alloc.count++] = page; /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; @@ -341,6 +345,8 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) DMA_ATTR_SKIP_CPU_SYNC); page_pool_set_dma_addr(page, 0); skip_dma_unmap: + page->pp_magic = 0; + /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. */ @@ -622,3 +628,25 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) } } EXPORT_SYMBOL(page_pool_update_nid); + +bool page_pool_return_skb_page(struct page *page) +{ + struct page_pool *pp; + + page = compound_head(page); + if (unlikely(page->pp_magic != PP_SIGNATURE)) + return false; + + pp = page->pp; + + /* Driver set this to memory recycling info. Reset it on recycle. + * This will *not* work for NIC using a split-page memory model. + * The page will be returned to the pool here regardless of the + * 'flipped' fragment being in use or not. + */ + page->pp = NULL; + page_pool_put_full_page(pp, page, false); + + return true; +} +EXPORT_SYMBOL(page_pool_return_skb_page); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 3fba429f1f57..7e258d255e90 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -467,7 +467,7 @@ static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, static int pktgen_device_event(struct notifier_block *, unsigned long, void *); static void pktgen_run_all_threads(struct pktgen_net *pn); static void pktgen_reset_all_threads(struct pktgen_net *pn); -static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn); +static void pktgen_stop_all_threads(struct pktgen_net *pn); static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); @@ -516,14 +516,11 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, data[count - 1] = 0; /* Strip trailing '\n' and terminate string */ if (!strcmp(data, "stop")) - pktgen_stop_all_threads_ifs(pn); - + pktgen_stop_all_threads(pn); else if (!strcmp(data, "start")) pktgen_run_all_threads(pn); - else if (!strcmp(data, "reset")) pktgen_reset_all_threads(pn); - else return -EINVAL; @@ -3027,20 +3024,25 @@ static void pktgen_run(struct pktgen_thread *t) t->control &= ~(T_STOP); } -static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn) +static void pktgen_handle_all_threads(struct pktgen_net *pn, u32 flags) { struct pktgen_thread *t; - func_enter(); - mutex_lock(&pktgen_thread_lock); list_for_each_entry(t, &pn->pktgen_threads, th_list) - t->control |= T_STOP; + t->control |= (flags); mutex_unlock(&pktgen_thread_lock); } +static void pktgen_stop_all_threads(struct pktgen_net *pn) +{ + func_enter(); + + pktgen_handle_all_threads(pn, T_STOP); +} + static int thread_is_running(const struct pktgen_thread *t) { const struct pktgen_dev *pkt_dev; @@ -3103,16 +3105,9 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn) static void pktgen_run_all_threads(struct pktgen_net *pn) { - struct pktgen_thread *t; - func_enter(); - mutex_lock(&pktgen_thread_lock); - - list_for_each_entry(t, &pn->pktgen_threads, th_list) - t->control |= (T_RUN); - - mutex_unlock(&pktgen_thread_lock); + pktgen_handle_all_threads(pn, T_RUN); /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); @@ -3122,16 +3117,9 @@ static void pktgen_run_all_threads(struct pktgen_net *pn) static void pktgen_reset_all_threads(struct pktgen_net *pn) { - struct pktgen_thread *t; - func_enter(); - mutex_lock(&pktgen_thread_lock); - - list_for_each_entry(t, &pn->pktgen_threads, th_list) - t->control |= (T_REMDEVALL); - - mutex_unlock(&pktgen_thread_lock); + pktgen_handle_all_threads(pn, T_REMDEVALL); /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ec931b080156..f6af3e74fc44 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -9,7 +9,7 @@ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: - * Vitaly E. Lavrov RTA_OK arithmetics was wrong. + * Vitaly E. Lavrov RTA_OK arithmetic was wrong. */ #include <linux/bitops.h> @@ -234,7 +234,7 @@ unlock: * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message - * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions + * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions * * Like rtnl_register, but for use by removable modules. */ @@ -254,7 +254,7 @@ EXPORT_SYMBOL_GPL(rtnl_register_module); * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message - * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions + * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions * * Registers the specified function pointers (at least one of them has * to be non-NULL) to be called whenever a request message for the @@ -376,12 +376,12 @@ int __rtnl_link_register(struct rtnl_link_ops *ops) if (rtnl_link_ops_get(ops->kind)) return -EEXIST; - /* The check for setup is here because if ops + /* The check for alloc/setup is here because if ops * does not have that filled up, it is not possible * to use the ops for creating device. So do not * fill up dellink as well. That disables rtnl_dellink. */ - if (ops->setup && !ops->dellink) + if ((ops->alloc || ops->setup) && !ops->dellink) ops->dellink = unregister_netdevice_queue; list_add_tail(&ops->list, &link_ops); @@ -543,7 +543,9 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) { const struct rtnl_af_ops *ops; - list_for_each_entry_rcu(ops, &rtnl_af_ops, list) { + ASSERT_RTNL(); + + list_for_each_entry(ops, &rtnl_af_ops, list) { if (ops->family == family) return ops; } @@ -1819,6 +1821,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, if (rtnl_fill_prop_list(skb, dev)) goto nla_put_failure; + if (dev->dev.parent && + nla_put_string(skb, IFLA_PARENT_DEV_NAME, + dev_name(dev->dev.parent))) + goto nla_put_failure; + + if (dev->dev.parent && dev->dev.parent->bus && + nla_put_string(skb, IFLA_PARENT_DEV_BUS_NAME, + dev->dev.parent->bus->name)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -1878,6 +1890,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PERM_ADDRESS] = { .type = NLA_REJECT }, [IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED }, [IFLA_NEW_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), + [IFLA_PARENT_DEV_NAME] = { .type = NLA_NUL_STRING }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -2274,27 +2287,18 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { const struct rtnl_af_ops *af_ops; - rcu_read_lock(); af_ops = rtnl_af_lookup(nla_type(af)); - if (!af_ops) { - rcu_read_unlock(); + if (!af_ops) return -EAFNOSUPPORT; - } - if (!af_ops->set_link_af) { - rcu_read_unlock(); + if (!af_ops->set_link_af) return -EOPNOTSUPP; - } if (af_ops->validate_link_af) { err = af_ops->validate_link_af(dev, af); - if (err < 0) { - rcu_read_unlock(); + if (err < 0) return err; - } } - - rcu_read_unlock(); } } @@ -2574,7 +2578,7 @@ static int do_set_proto_down(struct net_device *dev, if (nl_proto_down) { proto_down = nla_get_u8(nl_proto_down); - /* Dont turn off protodown if there are active reasons */ + /* Don't turn off protodown if there are active reasons */ if (!proto_down && dev->proto_down_reason) { NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons"); return -EBUSY; @@ -2868,17 +2872,12 @@ static int do_setlink(const struct sk_buff *skb, nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { const struct rtnl_af_ops *af_ops; - rcu_read_lock(); - BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af)))); err = af_ops->set_link_af(dev, af, extack); - if (err < 0) { - rcu_read_unlock(); + if (err < 0) goto errout; - } - rcu_read_unlock(); status |= DO_SETLINK_NOTIFY; } } @@ -3177,8 +3176,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, return ERR_PTR(-EINVAL); } - dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type, - ops->setup, num_tx_queues, num_rx_queues); + if (ops->alloc) { + dev = ops->alloc(tb, ifname, name_assign_type, + num_tx_queues, num_rx_queues); + if (IS_ERR(dev)) + return dev; + } else { + dev = alloc_netdev_mqs(ops->priv_size, ifname, + name_assign_type, ops->setup, + num_tx_queues, num_rx_queues); + } + if (!dev) return ERR_PTR(-ENOMEM); @@ -3411,7 +3419,7 @@ replay: return -EOPNOTSUPP; } - if (!ops->setup) + if (!ops->alloc && !ops->setup) return -EOPNOTSUPP; if (!ifname[0]) { @@ -3939,12 +3947,12 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm, * implement its own handler for this. */ if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) { - pr_info("%s: FDB only supports static addresses\n", dev->name); + netdev_info(dev, "default FDB implementation only supports local addresses\n"); return err; } if (vid) { - pr_info("%s: vlans aren't supported yet for dev_uc|mc_add()\n", dev->name); + netdev_info(dev, "vlans aren't supported yet for dev_uc|mc_add()\n"); return err; } @@ -4078,7 +4086,7 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, * implement its own handler for this. */ if (!(ndm->ndm_state & NUD_PERMANENT)) { - pr_info("%s: FDB only supports static addresses\n", dev->name); + netdev_info(dev, "default FDB implementation only supports local addresses\n"); return err; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bbc3b4b62032..12aabcda6db2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -70,6 +70,7 @@ #include <net/xfrm.h> #include <net/mpls.h> #include <net/mptcp.h> +#include <net/page_pool.h> #include <linux/uaccess.h> #include <trace/events/skb.h> @@ -645,10 +646,13 @@ static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; - if (skb->head_frag) + if (skb->head_frag) { + if (skb_pp_recycle(skb, head)) + return; skb_free_frag(head); - else + } else { kfree(head); + } } static void skb_release_data(struct sk_buff *skb) @@ -664,7 +668,7 @@ static void skb_release_data(struct sk_buff *skb) skb_zcopy_clear(skb, true); for (i = 0; i < shinfo->nr_frags; i++) - __skb_frag_unref(&shinfo->frags[i]); + __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); @@ -1046,6 +1050,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) n->nohdr = 0; n->peeked = 0; C(pfmemalloc); + C(pp_recycle); n->destructor = NULL; C(tail); C(end); @@ -1289,7 +1294,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) } spin_unlock_irqrestore(&q->lock, flags); - sk->sk_error_report(sk); + sk_error_report(sk); release: consume_skb(skb); @@ -3497,7 +3502,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, skb_frag_size(fragfrom)); - __skb_frag_unref(fragfrom); + __skb_frag_unref(fragfrom, skb->pp_recycle); } /* Reposition in the original skb */ @@ -4680,7 +4685,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@ -4711,7 +4716,7 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk) sk->sk_err = 0; if (skb_next) - sk->sk_error_report(sk); + sk_error_report(sk); return skb; } @@ -5287,6 +5292,13 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; + /* The page pool signature of struct page will eventually figure out + * which pages can be recycled or not but for now let's prohibit slab + * allocated and page_pool allocated SKBs from being coalesced. + */ + if (to->pp_recycle != from->pp_recycle) + return false; + if (len <= skb_tailroom(to)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 43ce17a6a585..9b6160a191f8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -399,29 +399,6 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, - long timeo, int *err) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - int ret = 0; - - if (sk->sk_shutdown & RCV_SHUTDOWN) - return 1; - - if (!timeo) - return ret; - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - ret = sk_wait_event(sk, &timeo, - !list_empty(&psock->ingress_msg) || - !skb_queue_empty(&sk->sk_receive_queue), &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - return ret; -} -EXPORT_SYMBOL_GPL(sk_msg_wait_data); - /* Receive sk_msg from psock->ingress_msg to @msg. */ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags) @@ -601,6 +578,12 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return sk_psock_skb_ingress(psock, skb); } +static void sock_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + kfree_skb(skb); +} + static void sk_psock_backlog(struct work_struct *work) { struct sk_psock *psock = container_of(work, struct sk_psock, work); @@ -640,7 +623,7 @@ start: /* Hard errors break pipe and stop xmit. */ sk_psock_report_error(psock, ret ? -ret : EPIPE); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); - kfree_skb(skb); + sock_drop(psock->sk, skb); goto end; } off += ret; @@ -731,7 +714,7 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) while ((skb = skb_dequeue(&psock->ingress_skb)) != NULL) { skb_bpf_redirect_clear(skb); - kfree_skb(skb); + sock_drop(psock->sk, skb); } __sk_psock_purge_ingress_msg(psock); } @@ -847,7 +830,7 @@ out: } EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); -static void sk_psock_skb_redirect(struct sk_buff *skb) +static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; @@ -857,8 +840,8 @@ static void sk_psock_skb_redirect(struct sk_buff *skb) * return code, but then didn't set a redirect interface. */ if (unlikely(!sk_other)) { - kfree_skb(skb); - return; + sock_drop(from->sk, skb); + return -EIO; } psock_other = sk_psock(sk_other); /* This error indicates the socket is being torn down or had another @@ -866,26 +849,30 @@ static void sk_psock_skb_redirect(struct sk_buff *skb) * a socket that is in this state so we drop the skb. */ if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) { - kfree_skb(skb); - return; + skb_bpf_redirect_clear(skb); + sock_drop(from->sk, skb); + return -EIO; } spin_lock_bh(&psock_other->ingress_lock); if (!sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) { spin_unlock_bh(&psock_other->ingress_lock); - kfree_skb(skb); - return; + skb_bpf_redirect_clear(skb); + sock_drop(from->sk, skb); + return -EIO; } skb_queue_tail(&psock_other->ingress_skb, skb); schedule_work(&psock_other->work); spin_unlock_bh(&psock_other->ingress_lock); + return 0; } -static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict) +static void sk_psock_tls_verdict_apply(struct sk_buff *skb, + struct sk_psock *from, int verdict) { switch (verdict) { case __SK_REDIRECT: - sk_psock_skb_redirect(skb); + sk_psock_skb_redirect(from, skb); break; case __SK_PASS: case __SK_DROP: @@ -909,20 +896,21 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } - sk_psock_tls_verdict_apply(skb, psock->sk, ret); + sk_psock_tls_verdict_apply(skb, psock, ret); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); -static void sk_psock_verdict_apply(struct sk_psock *psock, - struct sk_buff *skb, int verdict) +static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, + int verdict) { struct sock *sk_other; - int err = -EIO; + int err = 0; switch (verdict) { case __SK_PASS: + err = -EIO; sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { @@ -945,18 +933,25 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { skb_queue_tail(&psock->ingress_skb, skb); schedule_work(&psock->work); + err = 0; } spin_unlock_bh(&psock->ingress_lock); + if (err < 0) { + skb_bpf_redirect_clear(skb); + goto out_free; + } } break; case __SK_REDIRECT: - sk_psock_skb_redirect(skb); + err = sk_psock_skb_redirect(psock, skb); break; case __SK_DROP: default: out_free: - kfree_skb(skb); + sock_drop(psock->sk, skb); } + + return err; } static void sk_psock_write_space(struct sock *sk) @@ -988,7 +983,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) sk = strp->sk; psock = sk_psock(sk); if (unlikely(!psock)) { - kfree_skb(skb); + sock_drop(sk, skb); goto out; } prog = READ_ONCE(psock->progs.stream_verdict); @@ -1109,7 +1104,7 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, psock = sk_psock(sk); if (unlikely(!psock)) { len = 0; - kfree_skb(skb); + sock_drop(sk, skb); goto out; } prog = READ_ONCE(psock->progs.stream_verdict); @@ -1123,7 +1118,8 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } - sk_psock_verdict_apply(psock, skb, ret); + if (sk_psock_verdict_apply(psock, skb, ret) < 0) + len = 0; out: rcu_read_unlock(); return len; diff --git a/net/core/sock.c b/net/core/sock.c index 946888afef88..ba1c0f75cd45 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -331,6 +331,22 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(__sk_backlog_rcv); +void sk_error_report(struct sock *sk) +{ + sk->sk_error_report(sk); + + switch (sk->sk_family) { + case AF_INET: + fallthrough; + case AF_INET6: + trace_inet_sk_error_report(sk); + break; + default: + break; + } +} +EXPORT_SYMBOL(sk_error_report); + static int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; @@ -776,6 +792,58 @@ void sock_enable_timestamps(struct sock *sk) } EXPORT_SYMBOL(sock_enable_timestamps); +void sock_set_timestamp(struct sock *sk, int optname, bool valbool) +{ + switch (optname) { + case SO_TIMESTAMP_OLD: + __sock_set_timestamps(sk, valbool, false, false); + break; + case SO_TIMESTAMP_NEW: + __sock_set_timestamps(sk, valbool, true, false); + break; + case SO_TIMESTAMPNS_OLD: + __sock_set_timestamps(sk, valbool, false, true); + break; + case SO_TIMESTAMPNS_NEW: + __sock_set_timestamps(sk, valbool, true, true); + break; + } +} + +int sock_set_timestamping(struct sock *sk, int optname, int val) +{ + if (val & ~SOF_TIMESTAMPING_MASK) + return -EINVAL; + + if (val & SOF_TIMESTAMPING_OPT_ID && + !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) { + if ((1 << sk->sk_state) & + (TCPF_CLOSE | TCPF_LISTEN)) + return -EINVAL; + sk->sk_tskey = tcp_sk(sk)->snd_una; + } else { + sk->sk_tskey = 0; + } + } + + if (val & SOF_TIMESTAMPING_OPT_STATS && + !(val & SOF_TIMESTAMPING_OPT_TSONLY)) + return -EINVAL; + + sk->sk_tsflags = val; + sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); + + if (val & SOF_TIMESTAMPING_RX_SOFTWARE) + sock_enable_timestamp(sk, + SOCK_TIMESTAMPING_RX_SOFTWARE); + else + sock_disable_timestamp(sk, + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); + return 0; +} + void sock_set_keepalive(struct sock *sk) { lock_sock(sk); @@ -997,54 +1065,15 @@ set_sndbuf: break; case SO_TIMESTAMP_OLD: - __sock_set_timestamps(sk, valbool, false, false); - break; case SO_TIMESTAMP_NEW: - __sock_set_timestamps(sk, valbool, true, false); - break; case SO_TIMESTAMPNS_OLD: - __sock_set_timestamps(sk, valbool, false, true); - break; case SO_TIMESTAMPNS_NEW: - __sock_set_timestamps(sk, valbool, true, true); + sock_set_timestamp(sk, valbool, optname); break; + case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: - if (val & ~SOF_TIMESTAMPING_MASK) { - ret = -EINVAL; - break; - } - - if (val & SOF_TIMESTAMPING_OPT_ID && - !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { - if (sk->sk_protocol == IPPROTO_TCP && - sk->sk_type == SOCK_STREAM) { - if ((1 << sk->sk_state) & - (TCPF_CLOSE | TCPF_LISTEN)) { - ret = -EINVAL; - break; - } - sk->sk_tskey = tcp_sk(sk)->snd_una; - } else { - sk->sk_tskey = 0; - } - } - - if (val & SOF_TIMESTAMPING_OPT_STATS && - !(val & SOF_TIMESTAMPING_OPT_TSONLY)) { - ret = -EINVAL; - break; - } - - sk->sk_tsflags = val; - sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); - - if (val & SOF_TIMESTAMPING_RX_SOFTWARE) - sock_enable_timestamp(sk, - SOCK_TIMESTAMPING_RX_SOFTWARE); - else - sock_disable_timestamp(sk, - (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); + ret = sock_set_timestamping(sk, optname, val); break; case SO_RCVLOWAT: @@ -1622,6 +1651,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_bound_dev_if; break; + case SO_NETNS_COOKIE: + lv = sizeof(u64); + if (len != lv) + return -EINVAL; + v.val64 = sock_net(sk)->net_cookie; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 6f1b82b8ad49..60decd6420ca 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -48,7 +48,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) bpf_map_init_from_attr(&stab->map, attr); raw_spin_lock_init(&stab->lock); - stab->sks = bpf_map_area_alloc(stab->map.max_entries * + stab->sks = bpf_map_area_alloc((u64) stab->map.max_entries * sizeof(struct sock *), stab->map.numa_node); if (!stab->sks) { diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index b065f0a103ed..3f00a28fe762 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -6,6 +6,7 @@ * selecting the socket index from the array of available sockets. */ +#include <net/ip.h> #include <net/sock_reuseport.h> #include <linux/bpf.h> #include <linux/idr.h> @@ -17,6 +18,74 @@ DEFINE_SPINLOCK(reuseport_lock); static DEFINE_IDA(reuseport_ida); +static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, + struct sock_reuseport *reuse, bool bind_inany); + +static int reuseport_sock_index(struct sock *sk, + const struct sock_reuseport *reuse, + bool closed) +{ + int left, right; + + if (!closed) { + left = 0; + right = reuse->num_socks; + } else { + left = reuse->max_socks - reuse->num_closed_socks; + right = reuse->max_socks; + } + + for (; left < right; left++) + if (reuse->socks[left] == sk) + return left; + return -1; +} + +static void __reuseport_add_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + reuse->socks[reuse->num_socks] = sk; + /* paired with smp_rmb() in reuseport_(select|migrate)_sock() */ + smp_wmb(); + reuse->num_socks++; +} + +static bool __reuseport_detach_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + int i = reuseport_sock_index(sk, reuse, false); + + if (i == -1) + return false; + + reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; + reuse->num_socks--; + + return true; +} + +static void __reuseport_add_closed_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk; + /* paired with READ_ONCE() in inet_csk_bind_conflict() */ + WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1); +} + +static bool __reuseport_detach_closed_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + int i = reuseport_sock_index(sk, reuse, true); + + if (i == -1) + return false; + + reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; + /* paired with READ_ONCE() in inet_csk_bind_conflict() */ + WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1); + + return true; +} static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { @@ -49,6 +118,12 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (reuse) { + if (reuse->num_closed_socks) { + /* sk was shutdown()ed before */ + ret = reuseport_resurrect(sk, reuse, NULL, bind_inany); + goto out; + } + /* Only set reuse->bind_inany if the bind_inany is true. * Otherwise, it will overwrite the reuse->bind_inany * which was set by the bind/hash path. @@ -72,9 +147,9 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) } reuse->reuseport_id = id; + reuse->bind_inany = bind_inany; reuse->socks[0] = sk; reuse->num_socks = 1; - reuse->bind_inany = bind_inany; rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: @@ -90,14 +165,30 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) u32 more_socks_size, i; more_socks_size = reuse->max_socks * 2U; - if (more_socks_size > U16_MAX) + if (more_socks_size > U16_MAX) { + if (reuse->num_closed_socks) { + /* Make room by removing a closed sk. + * The child has already been migrated. + * Only reqsk left at this point. + */ + struct sock *sk; + + sk = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; + RCU_INIT_POINTER(sk->sk_reuseport_cb, NULL); + __reuseport_detach_closed_sock(sk, reuse); + + return reuse; + } + return NULL; + } more_reuse = __reuseport_alloc(more_socks_size); if (!more_reuse) return NULL; more_reuse->num_socks = reuse->num_socks; + more_reuse->num_closed_socks = reuse->num_closed_socks; more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; @@ -105,9 +196,13 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); + memcpy(more_reuse->socks + + (more_reuse->max_socks - more_reuse->num_closed_socks), + reuse->socks + (reuse->max_socks - reuse->num_closed_socks), + reuse->num_closed_socks * sizeof(struct sock *)); more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts); - for (i = 0; i < reuse->num_socks; ++i) + for (i = 0; i < reuse->max_socks; ++i) rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, more_reuse); @@ -152,13 +247,21 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)); + lockdep_is_held(&reuseport_lock)); + if (old_reuse && old_reuse->num_closed_socks) { + /* sk was shutdown()ed before */ + int err = reuseport_resurrect(sk, old_reuse, reuse, reuse->bind_inany); + + spin_unlock_bh(&reuseport_lock); + return err; + } + if (old_reuse && old_reuse->num_socks != 1) { spin_unlock_bh(&reuseport_lock); return -EBUSY; } - if (reuse->num_socks == reuse->max_socks) { + if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) { spin_unlock_bh(&reuseport_lock); @@ -166,10 +269,7 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) } } - reuse->socks[reuse->num_socks] = sk; - /* paired with smp_rmb() in reuseport_select_sock() */ - smp_wmb(); - reuse->num_socks++; + __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); spin_unlock_bh(&reuseport_lock); @@ -180,15 +280,77 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) } EXPORT_SYMBOL(reuseport_add_sock); +static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, + struct sock_reuseport *reuse, bool bind_inany) +{ + if (old_reuse == reuse) { + /* If sk was in the same reuseport group, just pop sk out of + * the closed section and push sk into the listening section. + */ + __reuseport_detach_closed_sock(sk, old_reuse); + __reuseport_add_sock(sk, old_reuse); + return 0; + } + + if (!reuse) { + /* In bind()/listen() path, we cannot carry over the eBPF prog + * for the shutdown()ed socket. In setsockopt() path, we should + * not change the eBPF prog of listening sockets by attaching a + * prog to the shutdown()ed socket. Thus, we will allocate a new + * reuseport group and detach sk from the old group. + */ + int id; + + reuse = __reuseport_alloc(INIT_SOCKS); + if (!reuse) + return -ENOMEM; + + id = ida_alloc(&reuseport_ida, GFP_ATOMIC); + if (id < 0) { + kfree(reuse); + return id; + } + + reuse->reuseport_id = id; + reuse->bind_inany = bind_inany; + } else { + /* Move sk from the old group to the new one if + * - all the other listeners in the old group were close()d or + * shutdown()ed, and then sk2 has listen()ed on the same port + * OR + * - sk listen()ed without bind() (or with autobind), was + * shutdown()ed, and then listen()s on another port which + * sk2 listen()s on. + */ + if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { + reuse = reuseport_grow(reuse); + if (!reuse) + return -ENOMEM; + } + } + + __reuseport_detach_closed_sock(sk, old_reuse); + __reuseport_add_sock(sk, reuse); + rcu_assign_pointer(sk->sk_reuseport_cb, reuse); + + if (old_reuse->num_socks + old_reuse->num_closed_socks == 0) + call_rcu(&old_reuse->rcu, reuseport_free_rcu); + + return 0; +} + void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; - int i; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); + /* reuseport_grow() has detached a closed sk */ + if (!reuse) + goto out; + /* Notify the bpf side. The sk may be added to a sockarray * map. If so, sockarray logic will remove it from the map. * @@ -201,19 +363,52 @@ void reuseport_detach_sock(struct sock *sk) rcu_assign_pointer(sk->sk_reuseport_cb, NULL); - for (i = 0; i < reuse->num_socks; i++) { - if (reuse->socks[i] == sk) { - reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; - reuse->num_socks--; - if (reuse->num_socks == 0) - call_rcu(&reuse->rcu, reuseport_free_rcu); - break; - } - } + if (!__reuseport_detach_closed_sock(sk, reuse)) + __reuseport_detach_sock(sk, reuse); + + if (reuse->num_socks + reuse->num_closed_socks == 0) + call_rcu(&reuse->rcu, reuseport_free_rcu); + +out: spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_detach_sock); +void reuseport_stop_listen_sock(struct sock *sk) +{ + if (sk->sk_protocol == IPPROTO_TCP) { + struct sock_reuseport *reuse; + struct bpf_prog *prog; + + spin_lock_bh(&reuseport_lock); + + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + prog = rcu_dereference_protected(reuse->prog, + lockdep_is_held(&reuseport_lock)); + + if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req || + (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) { + /* Migration capable, move sk from the listening section + * to the closed section. + */ + bpf_sk_reuseport_detach(sk); + + __reuseport_detach_sock(sk, reuse); + __reuseport_add_closed_sock(sk, reuse); + + spin_unlock_bh(&reuseport_lock); + return; + } + + spin_unlock_bh(&reuseport_lock); + } + + /* Not capable to do migration, detach immediately */ + reuseport_detach_sock(sk); +} +EXPORT_SYMBOL(reuseport_stop_listen_sock); + static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, struct bpf_prog *prog, struct sk_buff *skb, int hdr_len) @@ -244,6 +439,23 @@ static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, return reuse->socks[index]; } +static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse, + u32 hash, u16 num_socks) +{ + int i, j; + + i = j = reciprocal_scale(hash, num_socks); + while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { + i++; + if (i >= num_socks) + i = 0; + if (i == j) + return NULL; + } + + return reuse->socks[i]; +} + /** * reuseport_select_sock - Select a socket from an SO_REUSEPORT group. * @sk: First socket in the group. @@ -274,32 +486,21 @@ struct sock *reuseport_select_sock(struct sock *sk, prog = rcu_dereference(reuse->prog); socks = READ_ONCE(reuse->num_socks); if (likely(socks)) { - /* paired with smp_wmb() in reuseport_add_sock() */ + /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); if (!prog || !skb) goto select_by_hash; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) - sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash); + sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash); else sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len); select_by_hash: /* no bpf or invalid bpf result: fall back to hash usage */ - if (!sk2) { - int i, j; - - i = j = reciprocal_scale(hash, socks); - while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { - i++; - if (i >= socks) - i = 0; - if (i == j) - goto out; - } - sk2 = reuse->socks[i]; - } + if (!sk2) + sk2 = reuseport_select_sock_by_hash(reuse, hash, socks); } out: @@ -308,14 +509,90 @@ out: } EXPORT_SYMBOL(reuseport_select_sock); +/** + * reuseport_migrate_sock - Select a socket from an SO_REUSEPORT group. + * @sk: close()ed or shutdown()ed socket in the group. + * @migrating_sk: ESTABLISHED/SYN_RECV full socket in the accept queue or + * NEW_SYN_RECV request socket during 3WHS. + * @skb: skb to run through BPF filter. + * Returns a socket (with sk_refcnt +1) that should accept the child socket + * (or NULL on error). + */ +struct sock *reuseport_migrate_sock(struct sock *sk, + struct sock *migrating_sk, + struct sk_buff *skb) +{ + struct sock_reuseport *reuse; + struct sock *nsk = NULL; + bool allocated = false; + struct bpf_prog *prog; + u16 socks; + u32 hash; + + rcu_read_lock(); + + reuse = rcu_dereference(sk->sk_reuseport_cb); + if (!reuse) + goto out; + + socks = READ_ONCE(reuse->num_socks); + if (unlikely(!socks)) + goto failure; + + /* paired with smp_wmb() in __reuseport_add_sock() */ + smp_rmb(); + + hash = migrating_sk->sk_hash; + prog = rcu_dereference(reuse->prog); + if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) { + if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req) + goto select_by_hash; + goto failure; + } + + if (!skb) { + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) + goto failure; + allocated = true; + } + + nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash); + + if (allocated) + kfree_skb(skb); + +select_by_hash: + if (!nsk) + nsk = reuseport_select_sock_by_hash(reuse, hash, socks); + + if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) { + nsk = NULL; + goto failure; + } + +out: + rcu_read_unlock(); + return nsk; + +failure: + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); + goto out; +} +EXPORT_SYMBOL(reuseport_migrate_sock); + int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; - if (sk_unhashed(sk) && sk->sk_reuseport) { - int err = reuseport_alloc(sk, false); + if (sk_unhashed(sk)) { + int err; + if (!sk->sk_reuseport) + return -EINVAL; + + err = reuseport_alloc(sk, false); if (err) return err; } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { @@ -341,13 +618,24 @@ int reuseport_detach_prog(struct sock *sk) struct sock_reuseport *reuse; struct bpf_prog *old_prog; - if (!rcu_access_pointer(sk->sk_reuseport_cb)) - return sk->sk_reuseport ? -ENOENT : -EINVAL; - old_prog = NULL; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); + + /* reuse must be checked after acquiring the reuseport_lock + * because reuseport_grow() can detach a closed sk. + */ + if (!reuse) { + spin_unlock_bh(&reuseport_lock); + return sk->sk_reuseport ? -ENOENT : -EINVAL; + } + + if (sk_unhashed(sk) && reuse->num_closed_socks) { + spin_unlock_bh(&reuseport_lock); + return -ENOENT; + } + old_prog = rcu_replace_pointer(reuse->prog, old_prog, lockdep_is_held(&reuseport_lock)); spin_unlock_bh(&reuseport_lock); diff --git a/net/core/xdp.c b/net/core/xdp.c index 858276e72c68..cc92ccb38432 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -113,8 +113,13 @@ static void mem_allocator_disconnect(void *allocator) void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { struct xdp_mem_allocator *xa; + int type = xdp_rxq->mem.type; int id = xdp_rxq->mem.id; + /* Reset mem info to defaults */ + xdp_rxq->mem.id = 0; + xdp_rxq->mem.type = 0; + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return; @@ -123,7 +128,7 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) if (id == 0) return; - if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) { + if (type == MEM_TYPE_PAGE_POOL) { rcu_read_lock(); xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); @@ -144,10 +149,6 @@ void xdp_rxq_info_unreg(struct xdp_rxq_info *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); @@ -584,3 +585,31 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, return __xdp_build_skb_from_frame(xdpf, skb, dev); } EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); + +struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) +{ + unsigned int headroom, totalsize; + struct xdp_frame *nxdpf; + struct page *page; + void *addr; + + headroom = xdpf->headroom + sizeof(*xdpf); + totalsize = headroom + xdpf->len; + + if (unlikely(totalsize > PAGE_SIZE)) + return NULL; + page = dev_alloc_page(); + if (!page) + return NULL; + addr = page_to_virt(page); + + memcpy(addr, xdpf, totalsize); + + nxdpf = addr; + nxdpf->data = addr + headroom; + nxdpf->frame_sz = PAGE_SIZE; + nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0; + nxdpf->mem.id = 0; + + return nxdpf; +} diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 653e3bc9c87b..b441ab330fd3 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1381,7 +1381,7 @@ static int dcbnl_notify(struct net_device *dev, int event, int cmd, skb = dcbnl_newmsg(event, cmd, portid, seq, 0, &nlh); if (!skb) - return -ENOBUFS; + return -ENOMEM; if (dcbx_ver == DCB_CAP_DCBX_VER_IEEE) err = dcbnl_ieee_fill(skb, dev); @@ -1781,7 +1781,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, portid, nlh->nlmsg_seq, nlh->nlmsg_flags, &reply_nlh); if (!reply_skb) - return -ENOBUFS; + return -ENOMEM; ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb); if (ret < 0) { @@ -2075,8 +2075,6 @@ EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask); static int __init dcbnl_init(void) { - INIT_LIST_HEAD(&dcb_app_list); - rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, 0); rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, 0); diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index e2a337fa9ff7..92a8c6bea316 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -688,6 +688,7 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) /** * tfrc_invert_loss_event_rate - Compute p so that 10^6 corresponds to 100% + * @loss_event_rate: loss event rate to invert * When @loss_event_rate is large, there is a chance that p is truncated to 0. * To avoid re-entering slow-start in that case, we set p = TFRC_SMALLEST_P > 0. */ diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ffc601a3b329..0ea29270d7e5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -329,7 +329,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) __DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); dccp_done(sk); } else @@ -356,7 +356,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else /* Only an error on timeout */ sk->sk_err_soft = err; out: @@ -977,7 +977,6 @@ static const struct net_protocol dccp_v4_protocol = { .handler = dccp_v4_rcv, .err_handler = dccp_v4_err, .no_policy = 1, - .netns_ok = 1, .icmp_strict_tag_validation = 1, }; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 6f5304db5a67..fa663518fa0e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -172,7 +172,7 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, * Wake people up to see the error * (see connect in sock.c) */ - sk->sk_error_report(sk); + sk_error_report(sk); dccp_done(sk); } else sk->sk_err_soft = err; @@ -181,7 +181,7 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else sk->sk_err_soft = err; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 6d705d90c614..7eb0fb231940 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -302,7 +302,7 @@ int dccp_disconnect(struct sock *sk, int flags) WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); - sk->sk_error_report(sk); + sk_error_report(sk); return 0; } diff --git a/net/dccp/timer.c b/net/dccp/timer.c index db768f223ef7..27a3b37acd2e 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -20,7 +20,7 @@ int sysctl_dccp_retries2 __read_mostly = TCP_RETR2; static void dccp_write_err(struct sock *sk) { sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_done(sk); diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index 1a12912b88d6..7ab788f41a3f 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -870,7 +870,7 @@ int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb) /* * Read out ack data here, this applies equally - * to data, other data, link serivce and both + * to data, other data, link service and both * ack data and ack otherdata. */ dn_process_ack(sk, skb, other); diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 00f2ed721ec1..eadc89583168 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -179,7 +179,7 @@ static void dn_nsp_rtt(struct sock *sk, long rtt) scp->nsp_srtt = 1; /* - * Add new rtt varience to smoothed varience + * Add new rtt variance to smoothed varience */ delta >>= 1; rttvar += ((((delta>0)?(delta):(-delta)) - rttvar) >> 2); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 32b1bed8ae51..729d3de6020d 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -604,7 +604,7 @@ drop_it: static int dn_route_discard(struct net *net, struct sock *sk, struct sk_buff *skb) { /* - * I know we drop the packet here, but thats considered success in + * I know we drop the packet here, but that's considered success in * this case */ kfree_skb(skb); diff --git a/net/devres.c b/net/devres.c index 1f9be2133787..5ccf6ca311dc 100644 --- a/net/devres.c +++ b/net/devres.c @@ -60,7 +60,7 @@ static int netdev_devres_match(struct device *dev, void *this, void *match_data) * @ndev: device to register * * This is a devres variant of register_netdev() for which the unregister - * function will be call automatically when the managing device is + * function will be called automatically when the managing device is * detached. Note: the net_device used must also be resource managed by * the same struct device. */ diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index b71e87909f0e..185629f27f80 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -219,21 +219,6 @@ static void dsa_tree_put(struct dsa_switch_tree *dst) kref_put(&dst->refcount, dsa_tree_release); } -static bool dsa_port_is_dsa(struct dsa_port *port) -{ - return port->type == DSA_PORT_TYPE_DSA; -} - -static bool dsa_port_is_cpu(struct dsa_port *port) -{ - return port->type == DSA_PORT_TYPE_CPU; -} - -static bool dsa_port_is_user(struct dsa_port *dp) -{ - return dp->type == DSA_PORT_TYPE_USER; -} - static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, struct device_node *dn) { @@ -363,6 +348,9 @@ static int dsa_port_setup(struct dsa_port *dp) if (dp->setup) return 0; + INIT_LIST_HEAD(&dp->fdbs); + INIT_LIST_HEAD(&dp->mdbs); + switch (dp->type) { case DSA_PORT_TYPE_UNUSED: dsa_port_disable(dp); @@ -458,6 +446,7 @@ static int dsa_port_devlink_setup(struct dsa_port *dp) static void dsa_port_teardown(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; + struct dsa_mac_addr *a, *tmp; if (!dp->setup) return; @@ -483,6 +472,16 @@ static void dsa_port_teardown(struct dsa_port *dp) break; } + list_for_each_entry_safe(a, tmp, &dp->fdbs, list) { + list_del(&a->list); + kfree(a); + } + + list_for_each_entry_safe(a, tmp, &dp->mdbs, list) { + list_del(&a->list); + kfree(a); + } + dp->setup = false; } @@ -1259,6 +1258,13 @@ static int dsa_switch_parse_member_of(struct dsa_switch *ds, if (!ds->dst) return -ENOMEM; + if (dsa_switch_find(ds->dst->index, ds->index)) { + dev_err(ds->dev, + "A DSA switch with index %d already exists in tree %d\n", + ds->index, ds->dst->index); + return -EEXIST; + } + return 0; } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 92282de54230..f201c33980bf 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -20,6 +20,8 @@ enum { DSA_NOTIFIER_BRIDGE_LEAVE, DSA_NOTIFIER_FDB_ADD, DSA_NOTIFIER_FDB_DEL, + DSA_NOTIFIER_HOST_FDB_ADD, + DSA_NOTIFIER_HOST_FDB_DEL, DSA_NOTIFIER_HSR_JOIN, DSA_NOTIFIER_HSR_LEAVE, DSA_NOTIFIER_LAG_CHANGE, @@ -27,6 +29,8 @@ enum { DSA_NOTIFIER_LAG_LEAVE, DSA_NOTIFIER_MDB_ADD, DSA_NOTIFIER_MDB_DEL, + DSA_NOTIFIER_HOST_MDB_ADD, + DSA_NOTIFIER_HOST_MDB_DEL, DSA_NOTIFIER_VLAN_ADD, DSA_NOTIFIER_VLAN_DEL, DSA_NOTIFIER_MTU, @@ -84,7 +88,7 @@ struct dsa_notifier_vlan_info { /* DSA_NOTIFIER_MTU */ struct dsa_notifier_mtu_info { - bool propagate_upstream; + bool targeted_match; int sw_index; int port; int mtu; @@ -112,6 +116,7 @@ struct dsa_notifier_mrp_ring_role_info { struct dsa_switchdev_event_work { struct dsa_switch *ds; int port; + struct net_device *dev; struct work_struct work; unsigned long event; /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and @@ -119,6 +124,7 @@ struct dsa_switchdev_event_work { */ unsigned char addr[ETH_ALEN]; u16 vid; + bool host_addr; }; /* DSA_NOTIFIER_HSR_* */ @@ -154,6 +160,11 @@ const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); bool dsa_schedule_work(struct work_struct *work); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); +static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) +{ + return ops->needed_headroom + ops->needed_tailroom; +} + /* master.c */ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp); void dsa_master_teardown(struct net_device *dev); @@ -183,28 +194,40 @@ void dsa_port_disable_rt(struct dsa_port *dp); void dsa_port_disable(struct dsa_port *dp); int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, struct netlink_ext_ack *extack); +int dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br, + struct netlink_ext_ack *extack); void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); int dsa_port_lag_change(struct dsa_port *dp, struct netdev_lag_lower_state_info *linfo); int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev, struct netdev_lag_upper_info *uinfo, struct netlink_ext_ack *extack); +int dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev, + struct netlink_ext_ack *extack); void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, struct netlink_ext_ack *extack); bool dsa_port_skip_vlan_configuration(struct dsa_port *dp); int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock); int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, - bool propagate_upstream); + bool targeted_match); int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, u16 vid); int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, u16 vid); +int dsa_port_host_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_host_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid); int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data); int dsa_port_mdb_add(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb); int dsa_port_mdb_del(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb); +int dsa_port_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_host_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); int dsa_port_pre_bridge_flags(const struct dsa_port *dp, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); diff --git a/net/dsa/master.c b/net/dsa/master.c index 63adbc21a735..3fc90e36772d 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -346,10 +346,12 @@ static struct lock_class_key dsa_master_addr_list_lock_key; int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { - int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead; + const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops; struct dsa_switch *ds = cpu_dp->ds; struct device_link *consumer_link; - int ret; + int mtu, ret; + + mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops); /* The DSA master must use SET_NETDEV_DEV for this to work. */ consumer_link = device_link_add(ds->dev, dev->dev.parent, diff --git a/net/dsa/port.c b/net/dsa/port.c index 6379d66a6bb3..28b45b7e66df 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -194,26 +194,63 @@ static int dsa_port_switchdev_sync(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - err = br_mdb_replay(br, brport_dev, - &dsa_slave_switchdev_blocking_notifier, - extack); + err = br_mdb_replay(br, brport_dev, dp, true, + &dsa_slave_switchdev_blocking_notifier, extack); if (err && err != -EOPNOTSUPP) return err; - err = br_fdb_replay(br, brport_dev, &dsa_slave_switchdev_notifier); + /* Forwarding and termination FDB entries on the port */ + err = br_fdb_replay(br, brport_dev, dp, true, + &dsa_slave_switchdev_notifier); if (err && err != -EOPNOTSUPP) return err; - err = br_vlan_replay(br, brport_dev, - &dsa_slave_switchdev_blocking_notifier, - extack); + /* Termination FDB entries on the bridge itself */ + err = br_fdb_replay(br, br, dp, true, &dsa_slave_switchdev_notifier); + if (err && err != -EOPNOTSUPP) + return err; + + err = br_vlan_replay(br, brport_dev, dp, true, + &dsa_slave_switchdev_blocking_notifier, extack); + if (err && err != -EOPNOTSUPP) + return err; + + return 0; +} + +static int dsa_port_switchdev_unsync_objs(struct dsa_port *dp, + struct net_device *br, + struct netlink_ext_ack *extack) +{ + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + int err; + + /* Delete the switchdev objects left on this port */ + err = br_mdb_replay(br, brport_dev, dp, false, + &dsa_slave_switchdev_blocking_notifier, extack); + if (err && err != -EOPNOTSUPP) + return err; + + /* Forwarding and termination FDB entries on the port */ + err = br_fdb_replay(br, brport_dev, dp, false, + &dsa_slave_switchdev_notifier); + if (err && err != -EOPNOTSUPP) + return err; + + /* Termination FDB entries on the bridge itself */ + err = br_fdb_replay(br, br, dp, false, &dsa_slave_switchdev_notifier); + if (err && err != -EOPNOTSUPP) + return err; + + err = br_vlan_replay(br, brport_dev, dp, false, + &dsa_slave_switchdev_blocking_notifier, extack); if (err && err != -EOPNOTSUPP) return err; return 0; } -static void dsa_port_switchdev_unsync(struct dsa_port *dp) +static void dsa_port_switchdev_unsync_attrs(struct dsa_port *dp) { /* Configure the port for standalone mode (no address learning, * flood everything). @@ -279,6 +316,12 @@ out_rollback: return err; } +int dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br, + struct netlink_ext_ack *extack) +{ + return dsa_port_switchdev_unsync_objs(dp, br, extack); +} + void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) { struct dsa_notifier_bridge_info info = { @@ -298,7 +341,7 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) if (err) pr_err("DSA: failed to notify DSA_NOTIFIER_BRIDGE_LEAVE\n"); - dsa_port_switchdev_unsync(dp); + dsa_port_switchdev_unsync_attrs(dp); } int dsa_port_lag_change(struct dsa_port *dp, @@ -366,6 +409,15 @@ err_lag_join: return err; } +int dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag, + struct netlink_ext_ack *extack) +{ + if (dp->bridge_dev) + return dsa_port_pre_bridge_leave(dp, dp->bridge_dev, extack); + + return 0; +} + void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag) { struct dsa_notifier_lag_info info = { @@ -567,11 +619,11 @@ int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, } int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, - bool propagate_upstream) + bool targeted_match) { struct dsa_notifier_mtu_info info = { .sw_index = dp->ds->index, - .propagate_upstream = propagate_upstream, + .targeted_match = targeted_match, .port = dp->index, .mtu = new_mtu, }; @@ -606,6 +658,44 @@ int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, return dsa_port_notify(dp, DSA_NOTIFIER_FDB_DEL, &info); } +int dsa_port_host_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid) +{ + struct dsa_notifier_fdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .addr = addr, + .vid = vid, + }; + struct dsa_port *cpu_dp = dp->cpu_dp; + int err; + + err = dev_uc_add(cpu_dp->master, addr); + if (err) + return err; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_FDB_ADD, &info); +} + +int dsa_port_host_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid) +{ + struct dsa_notifier_fdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .addr = addr, + .vid = vid, + }; + struct dsa_port *cpu_dp = dp->cpu_dp; + int err; + + err = dev_uc_del(cpu_dp->master, addr); + if (err) + return err; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_FDB_DEL, &info); +} + int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data) { struct dsa_switch *ds = dp->ds; @@ -641,6 +731,42 @@ int dsa_port_mdb_del(const struct dsa_port *dp, return dsa_port_notify(dp, DSA_NOTIFIER_MDB_DEL, &info); } +int dsa_port_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_notifier_mdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mdb = mdb, + }; + struct dsa_port *cpu_dp = dp->cpu_dp; + int err; + + err = dev_mc_add(cpu_dp->master, mdb->addr); + if (err) + return err; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_MDB_ADD, &info); +} + +int dsa_port_host_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_notifier_mdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mdb = mdb, + }; + struct dsa_port *cpu_dp = dp->cpu_dp; + int err; + + err = dev_mc_del(cpu_dp->master, mdb->addr); + if (err) + return err; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_MDB_DEL, &info); +} + int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d4756b920108..ffbba1e71551 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -271,13 +271,16 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } -static int dsa_slave_port_attr_set(struct net_device *dev, +static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); int ret; + if (ctx && ctx != dp) + return 0; + switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) @@ -394,13 +397,16 @@ static int dsa_slave_vlan_add(struct net_device *dev, return vlan_vid_add(master, htons(ETH_P_8021Q), vlan.vid); } -static int dsa_slave_port_obj_add(struct net_device *dev, +static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); int err; + if (ctx && ctx != dp) + return 0; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) @@ -412,10 +418,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev, if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; - /* DSA can directly translate this to a normal MDB add, - * but on the CPU port. - */ - err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); + err = dsa_port_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) @@ -469,12 +472,15 @@ static int dsa_slave_vlan_del(struct net_device *dev, return 0; } -static int dsa_slave_port_obj_del(struct net_device *dev, +static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_slave_to_port(dev); int err; + if (ctx && ctx != dp) + return 0; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) @@ -486,10 +492,7 @@ static int dsa_slave_port_obj_del(struct net_device *dev, if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; - /* DSA can directly translate this to a normal MDB add, - * but on the CPU port. - */ - err = dsa_port_mdb_del(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); + err = dsa_port_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) @@ -1528,6 +1531,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp_iter; struct dsa_port *cpu_dp; int port = p->dp->index; int largest_mtu = 0; @@ -1535,31 +1539,31 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) int old_master_mtu; int mtu_limit; int cpu_mtu; - int err, i; + int err; if (!ds->ops->port_change_mtu) return -EOPNOTSUPP; - for (i = 0; i < ds->num_ports; i++) { + list_for_each_entry(dp_iter, &ds->dst->ports, list) { int slave_mtu; - if (!dsa_is_user_port(ds, i)) + if (!dsa_port_is_user(dp_iter)) continue; /* During probe, this function will be called for each slave * device, while not all of them have been allocated. That's * ok, it doesn't change what the maximum is, so ignore it. */ - if (!dsa_to_port(ds, i)->slave) + if (!dp_iter->slave) continue; /* Pretend that we already applied the setting, which we * actually haven't (still haven't done all integrity checks) */ - if (i == port) + if (dp_iter == dp) slave_mtu = new_mtu; else - slave_mtu = dsa_to_port(ds, i)->slave->mtu; + slave_mtu = dp_iter->slave->mtu; if (largest_mtu < slave_mtu) largest_mtu = slave_mtu; @@ -1569,7 +1573,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) mtu_limit = min_t(int, master->max_mtu, dev->max_mtu); old_master_mtu = master->mtu; - new_master_mtu = largest_mtu + cpu_dp->tag_ops->overhead; + new_master_mtu = largest_mtu + dsa_tag_protocol_overhead(cpu_dp->tag_ops); if (new_master_mtu > mtu_limit) return -ERANGE; @@ -1585,14 +1589,15 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) goto out_master_failed; /* We only need to propagate the MTU of the CPU port to - * upstream switches. + * upstream switches, so create a non-targeted notifier which + * updates all switches. */ - err = dsa_port_mtu_change(cpu_dp, cpu_mtu, true); + err = dsa_port_mtu_change(cpu_dp, cpu_mtu, false); if (err) goto out_cpu_failed; } - err = dsa_port_mtu_change(dp, new_mtu, false); + err = dsa_port_mtu_change(dp, new_mtu, true); if (err) goto out_port_failed; @@ -1605,8 +1610,8 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) out_port_failed: if (new_master_mtu != old_master_mtu) dsa_port_mtu_change(cpu_dp, old_master_mtu - - cpu_dp->tag_ops->overhead, - true); + dsa_tag_protocol_overhead(cpu_dp->tag_ops), + false); out_cpu_failed: if (new_master_mtu != old_master_mtu) dev_set_mtu(master, old_master_mtu); @@ -1640,27 +1645,6 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .self_test = dsa_slave_net_selftest, }; -/* legacy way, bypassing the bridge *****************************************/ -static int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid, - u16 flags, - struct netlink_ext_ack *extack) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return dsa_port_fdb_add(dp, addr, vid); -} - -static int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return dsa_port_fdb_del(dp, addr, vid); -} - static struct devlink_port *dsa_slave_get_devlink_port(struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); @@ -1702,8 +1686,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_change_rx_flags = dsa_slave_change_rx_flags, .ndo_set_rx_mode = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, - .ndo_fdb_add = dsa_legacy_fdb_add, - .ndo_fdb_del = dsa_legacy_fdb_del, .ndo_fdb_dump = dsa_slave_fdb_dump, .ndo_do_ioctl = dsa_slave_ioctl, .ndo_get_iflink = dsa_slave_get_iflink, @@ -1749,7 +1731,8 @@ static void dsa_slave_phylink_fixed_state(struct phylink_config *config, } /* slave device setup *******************************************************/ -static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) +static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr, + u32 flags) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_switch *ds = dp->ds; @@ -1760,6 +1743,8 @@ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) return -ENODEV; } + slave_dev->phydev->dev_flags |= flags; + return phylink_connect_phy(dp->pl, slave_dev->phydev); } @@ -1804,7 +1789,7 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) /* We could not connect to a designated PHY or SFP, so try to * use the switch internal MDIO bus instead */ - ret = dsa_slave_phy_connect(slave_dev, dp->index); + ret = dsa_slave_phy_connect(slave_dev, dp->index, phy_flags); if (ret) { netdev_err(slave_dev, "failed to connect to port %d: %d\n", @@ -1824,10 +1809,8 @@ void dsa_slave_setup_tagger(struct net_device *slave) const struct dsa_port *cpu_dp = dp->cpu_dp; struct net_device *master = cpu_dp->master; - if (cpu_dp->tag_ops->tail_tag) - slave->needed_tailroom = cpu_dp->tag_ops->overhead; - else - slave->needed_headroom = cpu_dp->tag_ops->overhead; + slave->needed_headroom = cpu_dp->tag_ops->needed_headroom; + slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; /* Try to save one extra realloc later in the TX path (in the master) * by also inheriting the master's needed headroom and tailroom. * The 8021q driver also does this. @@ -2065,6 +2048,26 @@ static int dsa_slave_changeupper(struct net_device *dev, return err; } +static int dsa_slave_prechangeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct netlink_ext_ack *extack; + int err = 0; + + extack = netdev_notifier_info_to_extack(&info->info); + + if (netif_is_bridge_master(info->upper_dev) && !info->linking) + err = dsa_port_pre_bridge_leave(dp, info->upper_dev, extack); + else if (netif_is_lag_master(info->upper_dev) && !info->linking) + err = dsa_port_pre_lag_leave(dp, info->upper_dev, extack); + /* dsa_port_pre_hsr_leave is not yet necessary since hsr cannot be + * meaningfully enslaved to a bridge yet + */ + + return notifier_from_errno(err); +} + static int dsa_slave_lag_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) @@ -2091,6 +2094,35 @@ dsa_slave_lag_changeupper(struct net_device *dev, return err; } +/* Same as dsa_slave_lag_changeupper() except that it calls + * dsa_slave_prechangeupper() + */ +static int +dsa_slave_lag_prechangeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct net_device *lower; + struct list_head *iter; + int err = NOTIFY_DONE; + struct dsa_port *dp; + + netdev_for_each_lower_dev(dev, lower, iter) { + if (!dsa_slave_dev_check(lower)) + continue; + + dp = dsa_slave_to_port(lower); + if (!dp->lag_dev) + /* Software LAG */ + continue; + + err = dsa_slave_prechangeupper(lower, info); + if (notifier_to_errno(err)) + break; + } + + return err; +} + static int dsa_prevent_bridging_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) @@ -2154,6 +2186,32 @@ dsa_slave_check_8021q_upper(struct net_device *dev, return NOTIFY_DONE; } +static int +dsa_slave_prechangeupper_sanity_check(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct dsa_switch *ds; + struct dsa_port *dp; + int err; + + if (!dsa_slave_dev_check(dev)) + return dsa_prevent_bridging_8021q_upper(dev, info); + + dp = dsa_slave_to_port(dev); + ds = dp->ds; + + if (ds->ops->port_prechangeupper) { + err = ds->ops->port_prechangeupper(ds, dp->index, info); + if (err) + return notifier_from_errno(err); + } + + if (is_vlan_dev(info->upper_dev)) + return dsa_slave_check_8021q_upper(dev, info); + + return NOTIFY_DONE; +} + static int dsa_slave_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { @@ -2162,24 +2220,18 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, switch (event) { case NETDEV_PRECHANGEUPPER: { struct netdev_notifier_changeupper_info *info = ptr; - struct dsa_switch *ds; - struct dsa_port *dp; int err; - if (!dsa_slave_dev_check(dev)) - return dsa_prevent_bridging_8021q_upper(dev, ptr); + err = dsa_slave_prechangeupper_sanity_check(dev, info); + if (err != NOTIFY_DONE) + return err; - dp = dsa_slave_to_port(dev); - ds = dp->ds; + if (dsa_slave_dev_check(dev)) + return dsa_slave_prechangeupper(dev, ptr); - if (ds->ops->port_prechangeupper) { - err = ds->ops->port_prechangeupper(ds, dp->index, info); - if (err) - return notifier_from_errno(err); - } + if (netif_is_lag_master(dev)) + return dsa_slave_lag_prechangeupper(dev, ptr); - if (is_vlan_dev(info->upper_dev)) - return dsa_slave_check_8021q_upper(dev, ptr); break; } case NETDEV_CHANGEUPPER: @@ -2263,8 +2315,12 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) rtnl_lock(); switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: - err = dsa_port_fdb_add(dp, switchdev_work->addr, - switchdev_work->vid); + if (switchdev_work->host_addr) + err = dsa_port_host_fdb_add(dp, switchdev_work->addr, + switchdev_work->vid); + else + err = dsa_port_fdb_add(dp, switchdev_work->addr, + switchdev_work->vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", @@ -2276,8 +2332,12 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) break; case SWITCHDEV_FDB_DEL_TO_DEVICE: - err = dsa_port_fdb_del(dp, switchdev_work->addr, - switchdev_work->vid); + if (switchdev_work->host_addr) + err = dsa_port_host_fdb_del(dp, switchdev_work->addr, + switchdev_work->vid); + else + err = dsa_port_fdb_del(dp, switchdev_work->addr, + switchdev_work->vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", @@ -2289,9 +2349,8 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) } rtnl_unlock(); + dev_put(switchdev_work->dev); kfree(switchdev_work); - if (dsa_is_user_port(ds, dp->index)) - dev_put(dp->slave); } static int dsa_lower_dev_walk(struct net_device *lower_dev, @@ -2323,6 +2382,7 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, struct net_device *dev = switchdev_notifier_info_to_dev(ptr); const struct switchdev_notifier_fdb_info *fdb_info; struct dsa_switchdev_event_work *switchdev_work; + bool host_addr = false; struct dsa_port *dp; int err; @@ -2337,19 +2397,28 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, fdb_info = ptr; if (dsa_slave_dev_check(dev)) { - if (!fdb_info->added_by_user || fdb_info->is_local) - return NOTIFY_OK; - dp = dsa_slave_to_port(dev); + + if (fdb_info->is_local) + host_addr = true; + else if (!fdb_info->added_by_user) + return NOTIFY_OK; } else { - /* Snoop addresses learnt on foreign interfaces - * bridged with us, for switches that don't - * automatically learn SA from CPU-injected traffic + /* Snoop addresses added to foreign interfaces + * bridged with us, or the bridge + * itself. Dynamically learned addresses can + * also be added for switches that don't + * automatically learn SA from CPU-injected + * traffic. */ struct net_device *br_dev; struct dsa_slave_priv *p; - br_dev = netdev_master_upper_dev_get_rcu(dev); + if (netif_is_bridge_master(dev)) + br_dev = dev; + else + br_dev = netdev_master_upper_dev_get_rcu(dev); + if (!br_dev) return NOTIFY_DONE; @@ -2360,17 +2429,30 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, if (!p) return NOTIFY_DONE; - dp = p->dp->cpu_dp; + dp = p->dp; + host_addr = fdb_info->is_local; - if (!dp->ds->assisted_learning_on_cpu_port) + /* FDB entries learned by the software bridge should + * be installed as host addresses only if the driver + * requests assisted learning. + * On the other hand, FDB entries for local termination + * should always be installed. + */ + if (!fdb_info->added_by_user && !fdb_info->is_local && + !dp->ds->assisted_learning_on_cpu_port) return NOTIFY_DONE; /* When the bridge learns an address on an offloaded * LAG we don't want to send traffic to the CPU, the * other ports bridged with the LAG should be able to * autonomously forward towards it. + * On the other hand, if the address is local + * (therefore not learned) then we want to trap it to + * the CPU regardless of whether the interface it + * belongs to is offloaded or not. */ - if (dsa_tree_offloads_bridge_port(dp->ds->dst, dev)) + if (dsa_tree_offloads_bridge_port(dp->ds->dst, dev) && + !fdb_info->is_local) return NOTIFY_DONE; } @@ -2386,14 +2468,15 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, switchdev_work->ds = dp->ds; switchdev_work->port = dp->index; switchdev_work->event = event; + switchdev_work->dev = dev; ether_addr_copy(switchdev_work->addr, fdb_info->addr); switchdev_work->vid = fdb_info->vid; + switchdev_work->host_addr = host_addr; - /* Hold a reference on the slave for dsa_fdb_offload_notify */ - if (dsa_is_user_port(dp->ds, dp->index)) - dev_hold(dev); + /* Hold a reference for dsa_fdb_offload_notify */ + dev_hold(dev); dsa_schedule_work(&switchdev_work->work); break; default: diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 9bf8e20ecdf3..af71b8638098 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -52,10 +52,13 @@ static int dsa_switch_ageing_time(struct dsa_switch *ds, static bool dsa_switch_mtu_match(struct dsa_switch *ds, int port, struct dsa_notifier_mtu_info *info) { - if (ds->index == info->sw_index) - return (port == info->port) || dsa_is_dsa_port(ds, port); + if (ds->index == info->sw_index && port == info->port) + return true; - if (!info->propagate_upstream) + /* Do not propagate to other switches in the tree if the notifier was + * targeted for a single switch. + */ + if (info->targeted_match) return false; if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) @@ -151,6 +154,214 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, return 0; } +/* Matches for all upstream-facing ports (the CPU port and all upstream-facing + * DSA links) that sit between the targeted port on which the notifier was + * emitted and its dedicated CPU port. + */ +static bool dsa_switch_host_address_match(struct dsa_switch *ds, int port, + int info_sw_index, int info_port) +{ + struct dsa_port *targeted_dp, *cpu_dp; + struct dsa_switch *targeted_ds; + + targeted_ds = dsa_switch_find(ds->dst->index, info_sw_index); + targeted_dp = dsa_to_port(targeted_ds, info_port); + cpu_dp = targeted_dp->cpu_dp; + + if (dsa_switch_is_upstream_of(ds, targeted_ds)) + return port == dsa_towards_port(ds, cpu_dp->ds->index, + cpu_dp->index); + + return false; +} + +static struct dsa_mac_addr *dsa_mac_addr_find(struct list_head *addr_list, + const unsigned char *addr, + u16 vid) +{ + struct dsa_mac_addr *a; + + list_for_each_entry(a, addr_list, list) + if (ether_addr_equal(a->addr, addr) && a->vid == vid) + return a; + + return NULL; +} + +static int dsa_switch_do_mdb_add(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_mac_addr *a; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->port_mdb_add(ds, port, mdb); + + a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid); + if (a) { + refcount_inc(&a->refcount); + return 0; + } + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) + return -ENOMEM; + + err = ds->ops->port_mdb_add(ds, port, mdb); + if (err) { + kfree(a); + return err; + } + + ether_addr_copy(a->addr, mdb->addr); + a->vid = mdb->vid; + refcount_set(&a->refcount, 1); + list_add_tail(&a->list, &dp->mdbs); + + return 0; +} + +static int dsa_switch_do_mdb_del(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_mac_addr *a; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->port_mdb_del(ds, port, mdb); + + a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid); + if (!a) + return -ENOENT; + + if (!refcount_dec_and_test(&a->refcount)) + return 0; + + err = ds->ops->port_mdb_del(ds, port, mdb); + if (err) { + refcount_inc(&a->refcount); + return err; + } + + list_del(&a->list); + kfree(a); + + return 0; +} + +static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_mac_addr *a; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->port_fdb_add(ds, port, addr, vid); + + a = dsa_mac_addr_find(&dp->fdbs, addr, vid); + if (a) { + refcount_inc(&a->refcount); + return 0; + } + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) + return -ENOMEM; + + err = ds->ops->port_fdb_add(ds, port, addr, vid); + if (err) { + kfree(a); + return err; + } + + ether_addr_copy(a->addr, addr); + a->vid = vid; + refcount_set(&a->refcount, 1); + list_add_tail(&a->list, &dp->fdbs); + + return 0; +} + +static int dsa_switch_do_fdb_del(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_mac_addr *a; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->port_fdb_del(ds, port, addr, vid); + + a = dsa_mac_addr_find(&dp->fdbs, addr, vid); + if (!a) + return -ENOENT; + + if (!refcount_dec_and_test(&a->refcount)) + return 0; + + err = ds->ops->port_fdb_del(ds, port, addr, vid); + if (err) { + refcount_inc(&a->refcount); + return err; + } + + list_del(&a->list); + kfree(a); + + return 0; +} + +static int dsa_switch_host_fdb_add(struct dsa_switch *ds, + struct dsa_notifier_fdb_info *info) +{ + int err = 0; + int port; + + if (!ds->ops->port_fdb_add) + return -EOPNOTSUPP; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_host_address_match(ds, port, info->sw_index, + info->port)) { + err = dsa_switch_do_fdb_add(ds, port, info->addr, + info->vid); + if (err) + break; + } + } + + return err; +} + +static int dsa_switch_host_fdb_del(struct dsa_switch *ds, + struct dsa_notifier_fdb_info *info) +{ + int err = 0; + int port; + + if (!ds->ops->port_fdb_del) + return -EOPNOTSUPP; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_host_address_match(ds, port, info->sw_index, + info->port)) { + err = dsa_switch_do_fdb_del(ds, port, info->addr, + info->vid); + if (err) + break; + } + } + + return err; +} + static int dsa_switch_fdb_add(struct dsa_switch *ds, struct dsa_notifier_fdb_info *info) { @@ -159,7 +370,7 @@ static int dsa_switch_fdb_add(struct dsa_switch *ds, if (!ds->ops->port_fdb_add) return -EOPNOTSUPP; - return ds->ops->port_fdb_add(ds, port, info->addr, info->vid); + return dsa_switch_do_fdb_add(ds, port, info->addr, info->vid); } static int dsa_switch_fdb_del(struct dsa_switch *ds, @@ -170,7 +381,7 @@ static int dsa_switch_fdb_del(struct dsa_switch *ds, if (!ds->ops->port_fdb_del) return -EOPNOTSUPP; - return ds->ops->port_fdb_del(ds, port, info->addr, info->vid); + return dsa_switch_do_fdb_del(ds, port, info->addr, info->vid); } static int dsa_switch_hsr_join(struct dsa_switch *ds, @@ -232,21 +443,31 @@ static int dsa_switch_lag_leave(struct dsa_switch *ds, return 0; } -static bool dsa_switch_mdb_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mdb_info *info) +static int dsa_switch_mdb_add(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) { - if (ds->index == info->sw_index && port == info->port) - return true; + int port = dsa_towards_port(ds, info->sw_index, info->port); - if (dsa_is_dsa_port(ds, port)) - return true; + if (!ds->ops->port_mdb_add) + return -EOPNOTSUPP; - return false; + return dsa_switch_do_mdb_add(ds, port, info->mdb); } -static int dsa_switch_mdb_add(struct dsa_switch *ds, +static int dsa_switch_mdb_del(struct dsa_switch *ds, struct dsa_notifier_mdb_info *info) { + int port = dsa_towards_port(ds, info->sw_index, info->port); + + if (!ds->ops->port_mdb_del) + return -EOPNOTSUPP; + + return dsa_switch_do_mdb_del(ds, port, info->mdb); +} + +static int dsa_switch_host_mdb_add(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) +{ int err = 0; int port; @@ -254,8 +475,9 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds, return -EOPNOTSUPP; for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mdb_match(ds, port, info)) { - err = ds->ops->port_mdb_add(ds, port, info->mdb); + if (dsa_switch_host_address_match(ds, port, info->sw_index, + info->port)) { + err = dsa_switch_do_mdb_add(ds, port, info->mdb); if (err) break; } @@ -264,16 +486,25 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds, return err; } -static int dsa_switch_mdb_del(struct dsa_switch *ds, - struct dsa_notifier_mdb_info *info) +static int dsa_switch_host_mdb_del(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) { + int err = 0; + int port; + if (!ds->ops->port_mdb_del) return -EOPNOTSUPP; - if (ds->index == info->sw_index) - return ds->ops->port_mdb_del(ds, info->port, info->mdb); + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_host_address_match(ds, port, info->sw_index, + info->port)) { + err = dsa_switch_do_mdb_del(ds, port, info->mdb); + if (err) + break; + } + } - return 0; + return err; } static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port, @@ -364,36 +595,16 @@ static int dsa_switch_change_tag_proto(struct dsa_switch *ds, return 0; } -static bool dsa_switch_mrp_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mrp_info *info) -{ - if (ds->index == info->sw_index && port == info->port) - return true; - - if (dsa_is_dsa_port(ds, port)) - return true; - - return false; -} - static int dsa_switch_mrp_add(struct dsa_switch *ds, struct dsa_notifier_mrp_info *info) { - int err = 0; - int port; - if (!ds->ops->port_mrp_add) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mrp_match(ds, port, info)) { - err = ds->ops->port_mrp_add(ds, port, info->mrp); - if (err) - break; - } - } + if (ds->index == info->sw_index) + return ds->ops->port_mrp_add(ds, info->port, info->mrp); - return err; + return 0; } static int dsa_switch_mrp_del(struct dsa_switch *ds, @@ -408,39 +619,18 @@ static int dsa_switch_mrp_del(struct dsa_switch *ds, return 0; } -static bool -dsa_switch_mrp_ring_role_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mrp_ring_role_info *info) -{ - if (ds->index == info->sw_index && port == info->port) - return true; - - if (dsa_is_dsa_port(ds, port)) - return true; - - return false; -} - static int dsa_switch_mrp_add_ring_role(struct dsa_switch *ds, struct dsa_notifier_mrp_ring_role_info *info) { - int err = 0; - int port; - if (!ds->ops->port_mrp_add) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mrp_ring_role_match(ds, port, info)) { - err = ds->ops->port_mrp_add_ring_role(ds, port, - info->mrp); - if (err) - break; - } - } + if (ds->index == info->sw_index) + return ds->ops->port_mrp_add_ring_role(ds, info->port, + info->mrp); - return err; + return 0; } static int @@ -479,6 +669,12 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_FDB_DEL: err = dsa_switch_fdb_del(ds, info); break; + case DSA_NOTIFIER_HOST_FDB_ADD: + err = dsa_switch_host_fdb_add(ds, info); + break; + case DSA_NOTIFIER_HOST_FDB_DEL: + err = dsa_switch_host_fdb_del(ds, info); + break; case DSA_NOTIFIER_HSR_JOIN: err = dsa_switch_hsr_join(ds, info); break; @@ -500,6 +696,12 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_MDB_DEL: err = dsa_switch_mdb_del(ds, info); break; + case DSA_NOTIFIER_HOST_MDB_ADD: + err = dsa_switch_host_mdb_add(ds, info); + break; + case DSA_NOTIFIER_HOST_MDB_DEL: + err = dsa_switch_host_mdb_del(ds, info); + break; case DSA_NOTIFIER_VLAN_ADD: err = dsa_switch_vlan_add(ds, info); break; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 122ad5833fb1..4aa29f90ecea 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -471,4 +471,27 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, } EXPORT_SYMBOL_GPL(dsa_8021q_xmit); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *subvlan) +{ + u16 vid, tci; + + skb_push_rcsum(skb, ETH_HLEN); + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + __skb_vlan_pop(skb, &tci); + } + skb_pull_rcsum(skb, ETH_HLEN); + + vid = tci & VLAN_VID_MASK; + + *source_port = dsa_8021q_rx_source_port(vid); + *switch_id = dsa_8021q_rx_switch_id(vid); + *subvlan = dsa_8021q_rx_subvlan(vid); + skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; +} +EXPORT_SYMBOL_GPL(dsa_8021q_rcv); + MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 002cf7f952e2..0efae1a372b3 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -85,7 +85,7 @@ static const struct dsa_device_ops ar9331_netdev_ops = { .proto = DSA_TAG_PROTO_AR9331, .xmit = ar9331_tag_xmit, .rcv = ar9331_tag_rcv, - .overhead = AR9331_HDR_LEN, + .needed_headroom = AR9331_HDR_LEN, }; MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 40e9f3098c8d..0750af951fc9 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -205,7 +205,7 @@ static const struct dsa_device_ops brcm_netdev_ops = { .proto = DSA_TAG_PROTO_BRCM, .xmit = brcm_tag_xmit, .rcv = brcm_tag_rcv, - .overhead = BRCM_TAG_LEN, + .needed_headroom = BRCM_TAG_LEN, }; DSA_TAG_DRIVER(brcm_netdev_ops); @@ -286,7 +286,7 @@ static const struct dsa_device_ops brcm_legacy_netdev_ops = { .proto = DSA_TAG_PROTO_BRCM_LEGACY, .xmit = brcm_leg_tag_xmit, .rcv = brcm_leg_tag_rcv, - .overhead = BRCM_LEG_TAG_LEN, + .needed_headroom = BRCM_LEG_TAG_LEN, }; DSA_TAG_DRIVER(brcm_legacy_netdev_ops); @@ -314,7 +314,7 @@ static const struct dsa_device_ops brcm_prepend_netdev_ops = { .proto = DSA_TAG_PROTO_BRCM_PREPEND, .xmit = brcm_tag_xmit_prepend, .rcv = brcm_tag_rcv_prepend, - .overhead = BRCM_TAG_LEN, + .needed_headroom = BRCM_TAG_LEN, }; DSA_TAG_DRIVER(brcm_prepend_netdev_ops); diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 7e7b7decdf39..a822355afc90 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -303,7 +303,7 @@ static const struct dsa_device_ops dsa_netdev_ops = { .proto = DSA_TAG_PROTO_DSA, .xmit = dsa_xmit, .rcv = dsa_rcv, - .overhead = DSA_HLEN, + .needed_headroom = DSA_HLEN, }; DSA_TAG_DRIVER(dsa_netdev_ops); @@ -346,7 +346,7 @@ static const struct dsa_device_ops edsa_netdev_ops = { .proto = DSA_TAG_PROTO_EDSA, .xmit = edsa_xmit, .rcv = edsa_rcv, - .overhead = EDSA_HLEN, + .needed_headroom = EDSA_HLEN, }; DSA_TAG_DRIVER(edsa_netdev_ops); diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c index 2f5bd5e338ab..5985dab06ab8 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -103,7 +103,7 @@ static const struct dsa_device_ops gswip_netdev_ops = { .proto = DSA_TAG_PROTO_GSWIP, .xmit = gswip_tag_xmit, .rcv = gswip_tag_rcv, - .overhead = GSWIP_RX_HEADER_LEN, + .needed_headroom = GSWIP_RX_HEADER_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index a09805c8e1ab..424130f85f59 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -54,8 +54,7 @@ static const struct dsa_device_ops hellcreek_netdev_ops = { .proto = DSA_TAG_PROTO_HELLCREEK, .xmit = hellcreek_xmit, .rcv = hellcreek_rcv, - .overhead = HELLCREEK_TAG_LEN, - .tail_tag = true, + .needed_tailroom = HELLCREEK_TAG_LEN, }; MODULE_LICENSE("Dual MIT/GPL"); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 4820dbcedfa2..53565f48934c 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -77,8 +77,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ8795, .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, - .overhead = KSZ_INGRESS_TAG_LEN, - .tail_tag = true, + .needed_tailroom = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz8795_netdev_ops); @@ -149,8 +148,7 @@ static const struct dsa_device_ops ksz9477_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ9477, .xmit = ksz9477_xmit, .rcv = ksz9477_rcv, - .overhead = KSZ9477_INGRESS_TAG_LEN, - .tail_tag = true, + .needed_tailroom = KSZ9477_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz9477_netdev_ops); @@ -183,8 +181,7 @@ static const struct dsa_device_ops ksz9893_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ9893, .xmit = ksz9893_xmit, .rcv = ksz9477_rcv, - .overhead = KSZ_INGRESS_TAG_LEN, - .tail_tag = true, + .needed_tailroom = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz9893_netdev_ops); diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index aa1318dccaf0..26207ef39ebc 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -125,7 +125,7 @@ static const struct dsa_device_ops lan9303_netdev_ops = { .proto = DSA_TAG_PROTO_LAN9303, .xmit = lan9303_xmit, .rcv = lan9303_rcv, - .overhead = LAN9303_TAG_LEN, + .needed_headroom = LAN9303_TAG_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index f9b2966d1936..cc3ba864ad5b 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -102,7 +102,7 @@ static const struct dsa_device_ops mtk_netdev_ops = { .proto = DSA_TAG_PROTO_MTK, .xmit = mtk_tag_xmit, .rcv = mtk_tag_rcv, - .overhead = MTK_HDR_LEN, + .needed_headroom = MTK_HDR_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 91f0fd1242cd..190f4bfd3bef 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -143,7 +143,7 @@ static const struct dsa_device_ops ocelot_netdev_ops = { .proto = DSA_TAG_PROTO_OCELOT, .xmit = ocelot_xmit, .rcv = ocelot_rcv, - .overhead = OCELOT_TOTAL_TAG_LEN, + .needed_headroom = OCELOT_TOTAL_TAG_LEN, .promisc_on_master = true, }; @@ -155,7 +155,7 @@ static const struct dsa_device_ops seville_netdev_ops = { .proto = DSA_TAG_PROTO_SEVILLE, .xmit = seville_xmit, .rcv = ocelot_rcv, - .overhead = OCELOT_TOTAL_TAG_LEN, + .needed_headroom = OCELOT_TOTAL_TAG_LEN, .promisc_on_master = true, }; diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 62a93303bd63..85ac85c3af8c 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -41,29 +41,15 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { - int src_port, switch_id, qos_class; - u16 vid, tci; + int src_port, switch_id, subvlan; - skb_push_rcsum(skb, ETH_HLEN); - if (skb_vlan_tag_present(skb)) { - tci = skb_vlan_tag_get(skb); - __vlan_hwaccel_clear_tag(skb); - } else { - __skb_vlan_pop(skb, &tci); - } - skb_pull_rcsum(skb, ETH_HLEN); - - vid = tci & VLAN_VID_MASK; - src_port = dsa_8021q_rx_source_port(vid); - switch_id = dsa_8021q_rx_switch_id(vid); - qos_class = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + dsa_8021q_rcv(skb, &src_port, &switch_id, &subvlan); skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); if (!skb->dev) return NULL; skb->offload_fwd_mark = 1; - skb->priority = qos_class; return skb; } @@ -73,7 +59,7 @@ static const struct dsa_device_ops ocelot_8021q_netdev_ops = { .proto = DSA_TAG_PROTO_OCELOT_8021Q, .xmit = ocelot_xmit, .rcv = ocelot_rcv, - .overhead = VLAN_HLEN, + .needed_headroom = VLAN_HLEN, .promisc_on_master = true, }; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 88181b52f480..693bda013065 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -91,7 +91,7 @@ static const struct dsa_device_ops qca_netdev_ops = { .proto = DSA_TAG_PROTO_QCA, .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, - .overhead = QCA_HDR_LEN, + .needed_headroom = QCA_HDR_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index cf8ac316f4c7..57c46b4ab2b3 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -124,7 +124,7 @@ static const struct dsa_device_ops rtl4a_netdev_ops = { .proto = DSA_TAG_PROTO_RTL4_A, .xmit = rtl4a_tag_xmit, .rcv = rtl4a_tag_rcv, - .overhead = RTL4_A_HDR_LEN, + .needed_headroom = RTL4_A_HDR_LEN, }; module_dsa_tag_driver(rtl4a_netdev_ops); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 50496013cdb7..9c2df9ece01b 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -7,6 +7,52 @@ #include <linux/packing.h> #include "dsa_priv.h" +/* Is this a TX or an RX header? */ +#define SJA1110_HEADER_HOST_TO_SWITCH BIT(15) + +/* RX header */ +#define SJA1110_RX_HEADER_IS_METADATA BIT(14) +#define SJA1110_RX_HEADER_HOST_ONLY BIT(13) +#define SJA1110_RX_HEADER_HAS_TRAILER BIT(12) + +/* Trap-to-host format (no trailer present) */ +#define SJA1110_RX_HEADER_SRC_PORT(x) (((x) & GENMASK(7, 4)) >> 4) +#define SJA1110_RX_HEADER_SWITCH_ID(x) ((x) & GENMASK(3, 0)) + +/* Timestamp format (trailer present) */ +#define SJA1110_RX_HEADER_TRAILER_POS(x) ((x) & GENMASK(11, 0)) + +#define SJA1110_RX_TRAILER_SWITCH_ID(x) (((x) & GENMASK(7, 4)) >> 4) +#define SJA1110_RX_TRAILER_SRC_PORT(x) ((x) & GENMASK(3, 0)) + +/* Meta frame format (for 2-step TX timestamps) */ +#define SJA1110_RX_HEADER_N_TS(x) (((x) & GENMASK(8, 4)) >> 4) + +/* TX header */ +#define SJA1110_TX_HEADER_UPDATE_TC BIT(14) +#define SJA1110_TX_HEADER_TAKE_TS BIT(13) +#define SJA1110_TX_HEADER_TAKE_TS_CASC BIT(12) +#define SJA1110_TX_HEADER_HAS_TRAILER BIT(11) + +/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is false */ +#define SJA1110_TX_HEADER_PRIO(x) (((x) << 7) & GENMASK(10, 7)) +#define SJA1110_TX_HEADER_TSTAMP_ID(x) ((x) & GENMASK(7, 0)) + +/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is true */ +#define SJA1110_TX_HEADER_TRAILER_POS(x) ((x) & GENMASK(10, 0)) + +#define SJA1110_TX_TRAILER_TSTAMP_ID(x) (((x) << 24) & GENMASK(31, 24)) +#define SJA1110_TX_TRAILER_PRIO(x) (((x) << 21) & GENMASK(23, 21)) +#define SJA1110_TX_TRAILER_SWITCHID(x) (((x) << 12) & GENMASK(15, 12)) +#define SJA1110_TX_TRAILER_DESTPORTS(x) (((x) << 1) & GENMASK(11, 1)) + +#define SJA1110_META_TSTAMP_SIZE 10 + +#define SJA1110_HEADER_LEN 4 +#define SJA1110_RX_TRAILER_LEN 13 +#define SJA1110_TX_TRAILER_LEN 4 +#define SJA1110_MAX_PADDING_LEN 15 + /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ static inline bool sja1105_is_link_local(const struct sk_buff *skb) { @@ -140,6 +186,57 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); } +static struct sk_buff *sja1110_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; + struct dsa_port *dp = dsa_slave_to_port(netdev); + u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + struct ethhdr *eth_hdr; + __be32 *tx_trailer; + __be16 *tx_header; + int trailer_pos; + + /* Transmitting control packets is done using in-band control + * extensions, while data packets are transmitted using + * tag_8021q TX VLANs. + */ + if (likely(!sja1105_is_link_local(skb))) + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); + + skb_push(skb, SJA1110_HEADER_LEN); + + /* Move Ethernet header to the left, making space for DSA tag */ + memmove(skb->data, skb->data + SJA1110_HEADER_LEN, 2 * ETH_ALEN); + + trailer_pos = skb->len; + + /* On TX, skb->data points to skb_mac_header(skb) */ + eth_hdr = (struct ethhdr *)skb->data; + tx_header = (__be16 *)(eth_hdr + 1); + tx_trailer = skb_put(skb, SJA1110_TX_TRAILER_LEN); + + eth_hdr->h_proto = htons(ETH_P_SJA1110); + + *tx_header = htons(SJA1110_HEADER_HOST_TO_SWITCH | + SJA1110_TX_HEADER_HAS_TRAILER | + SJA1110_TX_HEADER_TRAILER_POS(trailer_pos)); + *tx_trailer = cpu_to_be32(SJA1110_TX_TRAILER_PRIO(pcp) | + SJA1110_TX_TRAILER_SWITCHID(dp->ds->index) | + SJA1110_TX_TRAILER_DESTPORTS(BIT(dp->index))); + if (clone) { + u8 ts_id = SJA1105_SKB_CB(clone)->ts_id; + + *tx_header |= htons(SJA1110_TX_HEADER_TAKE_TS); + *tx_trailer |= cpu_to_be32(SJA1110_TX_TRAILER_TSTAMP_ID(ts_id)); + } + + return skb; +} + static void sja1105_transfer_meta(struct sk_buff *skb, const struct sja1105_meta *meta) { @@ -147,7 +244,7 @@ static void sja1105_transfer_meta(struct sk_buff *skb, hdr->h_dest[3] = meta->dmac_byte_3; hdr->h_dest[4] = meta->dmac_byte_4; - SJA1105_SKB_CB(skb)->meta_tstamp = meta->tstamp; + SJA1105_SKB_CB(skb)->tstamp = meta->tstamp; } /* This is a simple state machine which follows the hardware mechanism of @@ -275,46 +372,38 @@ static void sja1105_decode_subvlan(struct sk_buff *skb, u16 subvlan) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); } +static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) +{ + u16 tpid = ntohs(eth_hdr(skb)->h_proto); + + return tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || + skb_vlan_tag_present(skb); +} + +static bool sja1110_skb_has_inband_control_extension(const struct sk_buff *skb) +{ + return ntohs(eth_hdr(skb)->h_proto) == ETH_P_SJA1110; +} + static struct sk_buff *sja1105_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { + int source_port, switch_id, subvlan = 0; struct sja1105_meta meta = {0}; - int source_port, switch_id; struct ethhdr *hdr; - u16 tpid, vid, tci; bool is_link_local; - u16 subvlan = 0; - bool is_tagged; bool is_meta; hdr = eth_hdr(skb); - tpid = ntohs(hdr->h_proto); - is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || - skb_vlan_tag_present(skb)); is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); skb->offload_fwd_mark = 1; - if (is_tagged) { + if (sja1105_skb_has_tag_8021q(skb)) { /* Normal traffic path. */ - skb_push_rcsum(skb, ETH_HLEN); - if (skb_vlan_tag_present(skb)) { - tci = skb_vlan_tag_get(skb); - __vlan_hwaccel_clear_tag(skb); - } else { - __skb_vlan_pop(skb, &tci); - } - skb_pull_rcsum(skb, ETH_HLEN); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - - vid = tci & VLAN_VID_MASK; - source_port = dsa_8021q_rx_source_port(vid); - switch_id = dsa_8021q_rx_switch_id(vid); - skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - subvlan = dsa_8021q_rx_subvlan(vid); + dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); } else if (is_link_local) { /* Management traffic path. Switch embeds the switch ID and * port ID into bytes of the destination MAC, courtesy of @@ -346,6 +435,138 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } +static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) +{ + int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); + int n_ts = SJA1110_RX_HEADER_N_TS(rx_header); + struct net_device *master = skb->dev; + struct dsa_port *cpu_dp; + u8 *buf = skb->data + 2; + struct dsa_switch *ds; + int i; + + cpu_dp = master->dsa_ptr; + ds = dsa_switch_find(cpu_dp->dst->index, switch_id); + if (!ds) { + net_err_ratelimited("%s: cannot find switch id %d\n", + master->name, switch_id); + return NULL; + } + + for (i = 0; i <= n_ts; i++) { + u8 ts_id, source_port, dir; + u64 tstamp; + + ts_id = buf[0]; + source_port = (buf[1] & GENMASK(7, 4)) >> 4; + dir = (buf[1] & BIT(3)) >> 3; + tstamp = be64_to_cpu(*(__be64 *)(buf + 2)); + + sja1110_process_meta_tstamp(ds, source_port, ts_id, dir, + tstamp); + + buf += SJA1110_META_TSTAMP_SIZE; + } + + /* Discard the meta frame, we've consumed the timestamps it contained */ + return NULL; +} + +static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, + int *source_port, + int *switch_id) +{ + u16 rx_header; + + if (unlikely(!pskb_may_pull(skb, SJA1110_HEADER_LEN))) + return NULL; + + /* skb->data points to skb_mac_header(skb) + ETH_HLEN, which is exactly + * what we need because the caller has checked the EtherType (which is + * located 2 bytes back) and we just need a pointer to the header that + * comes afterwards. + */ + rx_header = ntohs(*(__be16 *)skb->data); + + if (rx_header & SJA1110_RX_HEADER_IS_METADATA) + return sja1110_rcv_meta(skb, rx_header); + + /* Timestamp frame, we have a trailer */ + if (rx_header & SJA1110_RX_HEADER_HAS_TRAILER) { + int start_of_padding = SJA1110_RX_HEADER_TRAILER_POS(rx_header); + u8 *rx_trailer = skb_tail_pointer(skb) - SJA1110_RX_TRAILER_LEN; + u64 *tstamp = &SJA1105_SKB_CB(skb)->tstamp; + u8 last_byte = rx_trailer[12]; + + /* The timestamp is unaligned, so we need to use packing() + * to get it + */ + packing(rx_trailer, tstamp, 63, 0, 8, UNPACK, 0); + + *source_port = SJA1110_RX_TRAILER_SRC_PORT(last_byte); + *switch_id = SJA1110_RX_TRAILER_SWITCH_ID(last_byte); + + /* skb->len counts from skb->data, while start_of_padding + * counts from the destination MAC address. Right now skb->data + * is still as set by the DSA master, so to trim away the + * padding and trailer we need to account for the fact that + * skb->data points to skb_mac_header(skb) + ETH_HLEN. + */ + pskb_trim_rcsum(skb, start_of_padding - ETH_HLEN); + /* Trap-to-host frame, no timestamp trailer */ + } else { + *source_port = SJA1110_RX_HEADER_SRC_PORT(rx_header); + *switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); + } + + /* Advance skb->data past the DSA header */ + skb_pull_rcsum(skb, SJA1110_HEADER_LEN); + + /* Remove the DSA header */ + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - SJA1110_HEADER_LEN, + 2 * ETH_ALEN); + + /* With skb->data in its final place, update the MAC header + * so that eth_hdr() continues to works properly. + */ + skb_set_mac_header(skb, -ETH_HLEN); + + return skb; +} + +static struct sk_buff *sja1110_rcv(struct sk_buff *skb, + struct net_device *netdev, + struct packet_type *pt) +{ + int source_port = -1, switch_id = -1, subvlan = 0; + + skb->offload_fwd_mark = 1; + + if (sja1110_skb_has_inband_control_extension(skb)) { + skb = sja1110_rcv_inband_control_extension(skb, &source_port, + &switch_id); + if (!skb) + return NULL; + } + + /* Packets with in-band control extensions might still have RX VLANs */ + if (likely(sja1105_skb_has_tag_8021q(skb))) + dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); + + skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + if (!skb->dev) { + netdev_warn(netdev, + "Couldn't decode source port %d and switch id %d\n", + source_port, switch_id); + return NULL; + } + + if (subvlan) + sja1105_decode_subvlan(skb, subvlan); + + return skb; +} + static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { @@ -356,18 +577,53 @@ static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto, dsa_tag_generic_flow_dissect(skb, proto, offset); } +static void sja1110_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + /* Management frames have 2 DSA tags on RX, so the needed_headroom we + * declared is fine for the generic dissector adjustment procedure. + */ + if (unlikely(sja1105_is_link_local(skb))) + return dsa_tag_generic_flow_dissect(skb, proto, offset); + + /* For the rest, there is a single DSA tag, the tag_8021q one */ + *offset = VLAN_HLEN; + *proto = ((__be16 *)skb->data)[(VLAN_HLEN / 2) - 1]; +} + static const struct dsa_device_ops sja1105_netdev_ops = { .name = "sja1105", .proto = DSA_TAG_PROTO_SJA1105, .xmit = sja1105_xmit, .rcv = sja1105_rcv, .filter = sja1105_filter, - .overhead = VLAN_HLEN, + .needed_headroom = VLAN_HLEN, .flow_dissect = sja1105_flow_dissect, .promisc_on_master = true, }; -MODULE_LICENSE("GPL v2"); +DSA_TAG_DRIVER(sja1105_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105); -module_dsa_tag_driver(sja1105_netdev_ops); +static const struct dsa_device_ops sja1110_netdev_ops = { + .name = "sja1110", + .proto = DSA_TAG_PROTO_SJA1110, + .xmit = sja1110_xmit, + .rcv = sja1110_rcv, + .filter = sja1105_filter, + .flow_dissect = sja1110_flow_dissect, + .needed_headroom = SJA1110_HEADER_LEN + VLAN_HLEN, + .needed_tailroom = SJA1110_RX_TRAILER_LEN + SJA1110_MAX_PADDING_LEN, +}; + +DSA_TAG_DRIVER(sja1110_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1110); + +static struct dsa_tag_driver *sja1105_tag_driver_array[] = { + &DSA_TAG_DRIVER_NAME(sja1105_netdev_ops), + &DSA_TAG_DRIVER_NAME(sja1110_netdev_ops), +}; + +module_dsa_tag_drivers(sja1105_tag_driver_array); + +MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 5b97ede56a0f..ba73804340a5 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -55,8 +55,7 @@ static const struct dsa_device_ops trailer_netdev_ops = { .proto = DSA_TAG_PROTO_TRAILER, .xmit = trailer_xmit, .rcv = trailer_rcv, - .overhead = 4, - .tail_tag = true, + .needed_tailroom = 4, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c index 858cdf9d2913..a31ff7fcb45f 100644 --- a/net/dsa/tag_xrs700x.c +++ b/net/dsa/tag_xrs700x.c @@ -56,8 +56,7 @@ static const struct dsa_device_ops xrs700x_netdev_ops = { .proto = DSA_TAG_PROTO_XRS700X, .xmit = xrs700x_xmit, .rcv = xrs700x_rcv, - .overhead = 1, - .tail_tag = true, + .needed_tailroom = 1, }; MODULE_LICENSE("GPL"); diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c index 5d38e90895ac..7e6b37a54add 100644 --- a/net/ethtool/eeprom.c +++ b/net/ethtool/eeprom.c @@ -159,9 +159,6 @@ static int eeprom_parse_request(struct ethnl_req_info *req_info, struct nlattr * request->offset = nla_get_u32(tb[ETHTOOL_A_MODULE_EEPROM_OFFSET]); request->length = nla_get_u32(tb[ETHTOOL_A_MODULE_EEPROM_LENGTH]); - if (!request->length) - return -EINVAL; - /* The following set of conditions limit the API to only dump 1/2 * EEPROM page without crossing low page boundary located at offset 128. * This means user may only request dumps of length limited to 128 from @@ -180,10 +177,6 @@ static int eeprom_parse_request(struct ethnl_req_info *req_info, struct nlattr * NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_LENGTH], "reading cross half page boundary is illegal"); return -EINVAL; - } else if (request->offset >= ETH_MODULE_EEPROM_PAGE_LEN * 2) { - NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_OFFSET], - "offset is out of bounds"); - return -EINVAL; } else if (request->offset + request->length > ETH_MODULE_EEPROM_PAGE_LEN * 2) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_LENGTH], "reading cross page boundary is illegal"); @@ -236,8 +229,10 @@ const struct ethnl_request_ops ethnl_module_eeprom_request_ops = { const struct nla_policy ethnl_module_eeprom_get_policy[] = { [ETHTOOL_A_MODULE_EEPROM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), - [ETHTOOL_A_MODULE_EEPROM_OFFSET] = { .type = NLA_U32 }, - [ETHTOOL_A_MODULE_EEPROM_LENGTH] = { .type = NLA_U32 }, + [ETHTOOL_A_MODULE_EEPROM_OFFSET] = + NLA_POLICY_MAX(NLA_U32, ETH_MODULE_EEPROM_PAGE_LEN * 2 - 1), + [ETHTOOL_A_MODULE_EEPROM_LENGTH] = + NLA_POLICY_RANGE(NLA_U32, 1, ETH_MODULE_EEPROM_PAGE_LEN), [ETHTOOL_A_MODULE_EEPROM_PAGE] = { .type = NLA_U8 }, [ETHTOOL_A_MODULE_EEPROM_BANK] = { .type = NLA_U8 }, [ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS] = diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 88d8a0243f35..a7346346114f 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -315,9 +315,9 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) struct ethnl_req_info *req_info = NULL; const u8 cmd = info->genlhdr->cmd; const struct ethnl_request_ops *ops; + int hdr_len, reply_len; struct sk_buff *rskb; void *reply_payload; - int reply_len; int ret; ops = ethnl_default_requests[cmd]; @@ -346,15 +346,20 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; - reply_len = ret + ethnl_reply_header_size(); + reply_len = ret; ret = -ENOMEM; - rskb = ethnl_reply_init(reply_len, req_info->dev, ops->reply_cmd, + rskb = ethnl_reply_init(reply_len + ethnl_reply_header_size(), + req_info->dev, ops->reply_cmd, ops->hdr_attr, info, &reply_payload); if (!rskb) goto err_cleanup; + hdr_len = rskb->len; ret = ops->fill_reply(rskb, req_info, reply_data); if (ret < 0) goto err_msg; + WARN_ONCE(rskb->len - hdr_len > reply_len, + "ethnl cmd %d: calculated reply length %d, but consumed %d\n", + cmd, reply_len, rskb->len - hdr_len); if (ops->cleanup_data) ops->cleanup_data(reply_data); diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 8abcbc10796c..3e25a47fd482 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -138,7 +138,7 @@ static inline void ethnl_update_bool32(u32 *dst, const struct nlattr *attr, } /** - * ethnl_update_binary() - update binary data from NLA_BINARY atribute + * ethnl_update_binary() - update binary data from NLA_BINARY attribute * @dst: value to update * @len: destination buffer length * @attr: netlink attribute with new value or null @@ -380,7 +380,7 @@ extern const struct nla_policy ethnl_cable_test_tdr_act_policy[ETHTOOL_A_CABLE_T extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INFO_HEADER + 1]; extern const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1]; extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; -extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_DATA + 1]; +extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index bb1351c38397..e31949479305 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -397,7 +397,8 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, * ensures entries of restarted nodes gets pruned so that they can * re-register and resume communications. */ - if (seq_nr_before(sequence_nr, node->seq_out[port->type])) + if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && + seq_nr_before(sequence_nr, node->seq_out[port->type])) return; node->time_in[port->type] = jiffies; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 2f94d221c00e..54648181dd56 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -318,7 +318,7 @@ lookup_protocol: WARN_ON(!answer_prot->slab); - err = -ENOBUFS; + err = -ENOMEM; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; @@ -1720,7 +1720,6 @@ EXPORT_SYMBOL_GPL(snmp_fold_field64); #ifdef CONFIG_IP_MULTICAST static const struct net_protocol igmp_protocol = { .handler = igmp_rcv, - .netns_ok = 1, }; #endif @@ -1733,7 +1732,6 @@ static struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, - .netns_ok = 1, .icmp_strict_tag_validation = 1, }; @@ -1746,14 +1744,12 @@ static struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, - .netns_ok = 1, }; static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, .no_policy = 1, - .netns_ok = 1, }; static __net_init int ipv4_mib_init_net(struct net *net) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index fab0958c41be..6eea1e9e998d 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -555,7 +555,6 @@ static int ah4_rcv_cb(struct sk_buff *skb, int err) static const struct xfrm_type ah_type = { - .description = "AH4", .owner = THIS_MODULE, .proto = IPPROTO_AH, .flags = XFRM_TYPE_REPLAY_PROT, diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index e0480c6cebaa..099259fc826a 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -187,8 +187,7 @@ static int __init cipso_v4_cache_init(void) * cipso_v4_cache_invalidate - Invalidates the current CIPSO cache * * Description: - * Invalidates and frees any entries in the CIPSO cache. Returns zero on - * success and negative values on failure. + * Invalidates and frees any entries in the CIPSO cache. * */ void cipso_v4_cache_invalidate(void) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 1c6429c353a9..73721a4448bd 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1955,7 +1955,7 @@ static int inet_validate_link_af(const struct net_device *dev, struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; - if (dev && !__in_dev_get_rcu(dev)) + if (dev && !__in_dev_get_rtnl(dev)) return -EAFNOSUPPORT; err = nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, @@ -1981,7 +1981,7 @@ static int inet_validate_link_af(const struct net_device *dev, static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { - struct in_device *in_dev = __in_dev_get_rcu(dev); + struct in_device *in_dev = __in_dev_get_rtnl(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 8e3b445a8c21..a09e36c4a413 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -673,7 +673,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; - padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); + padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } @@ -1199,7 +1199,6 @@ static int esp4_rcv_cb(struct sk_buff *skb, int err) static const struct xfrm_type esp_type = { - .description = "ESP4", .owner = THIS_MODULE, .proto = IPPROTO_ESP, .flags = XFRM_TYPE_REPLAY_PROT, diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 33687cf58286..8e4e9aa12130 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -33,12 +33,11 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, struct xfrm_state *x; __be32 seq; __be32 spi; - int err; if (!pskb_pull(skb, offset)) return NULL; - if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0) + if (xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq) != 0) goto out; xo = xfrm_offload(skb); @@ -343,7 +342,6 @@ static const struct net_offload esp4_offload = { }; static const struct xfrm_type_offload esp_type_offload = { - .description = "ESP4 OFFLOAD", .owner = THIS_MODULE, .proto = IPPROTO_ESP, .input_tail = esp_input_tail, diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 84bb707bd88d..a933bd6345b1 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -371,6 +371,8 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; + } else { + swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) @@ -1122,10 +1124,8 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) prefix, ifa->ifa_prefixlen, prim, ifa->ifa_rt_priority); - /* Add network specific broadcasts, when it takes a sense */ + /* Add the network broadcast address, when it makes sense */ if (ifa->ifa_prefixlen < 31) { - fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, - prim, 0); fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, 32, prim, 0); } @@ -1516,6 +1516,12 @@ static int __net_init ip_fib_net_init(struct net *net) if (err) return err; +#ifdef CONFIG_IP_ROUTE_MULTIPATH + /* Default to 3-tuple */ + net->ipv4.sysctl_fib_multipath_hash_fields = + FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; +#endif + /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index b58db1ca4bfb..e184bcb19943 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -25,7 +25,7 @@ struct fib_alias { #define FA_S_ACCESSED 0x01 -/* Dont write on fa_state unless needed, to keep it shared on all cpus */ +/* Don't write on fa_state unless needed, to keep it shared on all cpus */ static inline void fib_alias_accessed(struct fib_alias *fa) { if (!(fa->fa_state & FA_S_ACCESSED)) diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 5d1e6fe9d838..cbb2b4bb0dfa 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -195,7 +195,6 @@ static int gre_err(struct sk_buff *skb, u32 info) static const struct net_protocol net_gre_protocol = { .handler = gre_rcv, .err_handler = gre_err, - .netns_ok = 1, }; static int __init gre_init(void) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 752e392083e6..c695d294a5df 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -993,14 +993,8 @@ static bool icmp_redirect(struct sk_buff *skb) static bool icmp_echo(struct sk_buff *skb) { - struct icmp_ext_hdr *ext_hdr, _ext_hdr; - struct icmp_ext_echo_iio *iio, _iio; struct icmp_bxm icmp_param; - struct net_device *dev; - char buff[IFNAMSIZ]; struct net *net; - u16 ident_len; - u8 status; net = dev_net(skb_dst(skb)->dev); /* should there be an ICMP stat for ignored echos? */ @@ -1013,20 +1007,46 @@ static bool icmp_echo(struct sk_buff *skb) icmp_param.data_len = skb->len; icmp_param.head_len = sizeof(struct icmphdr); - if (icmp_param.data.icmph.type == ICMP_ECHO) { + if (icmp_param.data.icmph.type == ICMP_ECHO) icmp_param.data.icmph.type = ICMP_ECHOREPLY; - goto send_reply; - } - if (!net->ipv4.sysctl_icmp_echo_enable_probe) + else if (!icmp_build_probe(skb, &icmp_param.data.icmph)) return true; + + icmp_reply(&icmp_param, skb); + return true; +} + +/* Helper for icmp_echo and icmpv6_echo_reply. + * Searches for net_device that matches PROBE interface identifier + * and builds PROBE reply message in icmphdr. + * + * Returns false if PROBE responses are disabled via sysctl + */ + +bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) +{ + struct icmp_ext_hdr *ext_hdr, _ext_hdr; + struct icmp_ext_echo_iio *iio, _iio; + struct net *net = dev_net(skb->dev); + struct net_device *dev; + char buff[IFNAMSIZ]; + u16 ident_len; + u8 status; + + if (!net->ipv4.sysctl_icmp_echo_enable_probe) + return false; + /* We currently only support probing interfaces on the proxy node * Check to ensure L-bit is set */ - if (!(ntohs(icmp_param.data.icmph.un.echo.sequence) & 1)) - return true; + if (!(ntohs(icmphdr->un.echo.sequence) & 1)) + return false; /* Clear status bits in reply message */ - icmp_param.data.icmph.un.echo.sequence &= htons(0xFF00); - icmp_param.data.icmph.type = ICMP_EXT_ECHOREPLY; + icmphdr->un.echo.sequence &= htons(0xFF00); + if (icmphdr->type == ICMP_EXT_ECHO) + icmphdr->type = ICMP_EXT_ECHOREPLY; + else + icmphdr->type = ICMPV6_EXT_ECHO_REPLY; ext_hdr = skb_header_pointer(skb, 0, sizeof(_ext_hdr), &_ext_hdr); /* Size of iio is class_type dependent. * Only check header here and assign length based on ctype in the switch statement @@ -1066,7 +1086,7 @@ static bool icmp_echo(struct sk_buff *skb) if (ident_len != sizeof(iio->ident.addr.ctype3_hdr) + sizeof(struct in_addr)) goto send_mal_query; - dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr.s_addr); + dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr); break; #if IS_ENABLED(CONFIG_IPV6) case ICMP_AFI_IP6: @@ -1087,8 +1107,8 @@ static bool icmp_echo(struct sk_buff *skb) goto send_mal_query; } if (!dev) { - icmp_param.data.icmph.code = ICMP_EXT_CODE_NO_IF; - goto send_reply; + icmphdr->code = ICMP_EXT_CODE_NO_IF; + return true; } /* Fill bits in reply message */ if (dev->flags & IFF_UP) @@ -1098,14 +1118,13 @@ static bool icmp_echo(struct sk_buff *skb) if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list)) status |= ICMP_EXT_ECHOREPLY_IPV6; dev_put(dev); - icmp_param.data.icmph.un.echo.sequence |= htons(status); -send_reply: - icmp_reply(&icmp_param, skb); - return true; + icmphdr->un.echo.sequence |= htons(status); + return true; send_mal_query: - icmp_param.data.icmph.code = ICMP_EXT_CODE_MAL_QUERY; - goto send_reply; + icmphdr->code = ICMP_EXT_CODE_MAL_QUERY; + return true; } +EXPORT_SYMBOL_GPL(icmp_build_probe); /* * Handle ICMP Timestamp requests. diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index fd472eae4f5c..754013fa393b 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -135,10 +135,18 @@ static int inet_csk_bind_conflict(const struct sock *sk, bool relax, bool reuseport_ok) { struct sock *sk2; + bool reuseport_cb_ok; bool reuse = sk->sk_reuse; bool reuseport = !!sk->sk_reuseport; + struct sock_reuseport *reuseport_cb; kuid_t uid = sock_i_uid((struct sock *)sk); + rcu_read_lock(); + reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); + /* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */ + reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks); + rcu_read_unlock(); + /* * Unlike other sk lookup places we do not check * for sk_net here, since _all_ the socks listed @@ -156,14 +164,14 @@ static int inet_csk_bind_conflict(const struct sock *sk, if ((!relax || (!reuseport_ok && reuseport && sk2->sk_reuseport && - !rcu_access_pointer(sk->sk_reuseport_cb) && + reuseport_cb_ok && (sk2->sk_state == TCP_TIME_WAIT || uid_eq(uid, sock_i_uid(sk2))))) && inet_rcv_saddr_equal(sk, sk2, true)) break; } else if (!reuseport_ok || !reuseport || !sk2->sk_reuseport || - rcu_access_pointer(sk->sk_reuseport_cb) || + !reuseport_cb_ok || (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(uid, sock_i_uid(sk2)))) { if (inet_rcv_saddr_equal(sk, sk2, true)) @@ -687,6 +695,66 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) } EXPORT_SYMBOL(inet_rtx_syn_ack); +static struct request_sock *inet_reqsk_clone(struct request_sock *req, + struct sock *sk) +{ + struct sock *req_sk, *nreq_sk; + struct request_sock *nreq; + + nreq = kmem_cache_alloc(req->rsk_ops->slab, GFP_ATOMIC | __GFP_NOWARN); + if (!nreq) { + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); + + /* paired with refcount_inc_not_zero() in reuseport_migrate_sock() */ + sock_put(sk); + return NULL; + } + + req_sk = req_to_sk(req); + nreq_sk = req_to_sk(nreq); + + memcpy(nreq_sk, req_sk, + offsetof(struct sock, sk_dontcopy_begin)); + memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, + req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end)); + + sk_node_init(&nreq_sk->sk_node); + nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; +#ifdef CONFIG_XPS + nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping; +#endif + nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu; + + nreq->rsk_listener = sk; + + /* We need not acquire fastopenq->lock + * because the child socket is locked in inet_csk_listen_stop(). + */ + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) + rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq); + + return nreq; +} + +static void reqsk_queue_migrated(struct request_sock_queue *queue, + const struct request_sock *req) +{ + if (req->num_timeout == 0) + atomic_inc(&queue->young); + atomic_inc(&queue->qlen); +} + +static void reqsk_migrate_reset(struct request_sock *req) +{ + req->saved_syn = NULL; +#if IS_ENABLED(CONFIG_IPV6) + inet_rsk(req)->ipv6_opt = NULL; + inet_rsk(req)->pktopts = NULL; +#else + inet_rsk(req)->ireq_opt = NULL; +#endif +} + /* return true if req was found in the ehash table */ static bool reqsk_queue_unlink(struct request_sock *req) { @@ -727,15 +795,39 @@ EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); static void reqsk_timer_handler(struct timer_list *t) { struct request_sock *req = from_timer(req, t, rsk_timer); + struct request_sock *nreq = NULL, *oreq = req; struct sock *sk_listener = req->rsk_listener; - struct net *net = sock_net(sk_listener); - struct inet_connection_sock *icsk = inet_csk(sk_listener); - struct request_sock_queue *queue = &icsk->icsk_accept_queue; + struct inet_connection_sock *icsk; + struct request_sock_queue *queue; + struct net *net; int max_syn_ack_retries, qlen, expire = 0, resend = 0; - if (inet_sk_state_load(sk_listener) != TCP_LISTEN) - goto drop; + if (inet_sk_state_load(sk_listener) != TCP_LISTEN) { + struct sock *nsk; + + nsk = reuseport_migrate_sock(sk_listener, req_to_sk(req), NULL); + if (!nsk) + goto drop; + nreq = inet_reqsk_clone(req, nsk); + if (!nreq) + goto drop; + + /* The new timer for the cloned req can decrease the 2 + * by calling inet_csk_reqsk_queue_drop_and_put(), so + * hold another count to prevent use-after-free and + * call reqsk_put() just before return. + */ + refcount_set(&nreq->rsk_refcnt, 2 + 1); + timer_setup(&nreq->rsk_timer, reqsk_timer_handler, TIMER_PINNED); + reqsk_queue_migrated(&inet_csk(nsk)->icsk_accept_queue, req); + + req = nreq; + sk_listener = nsk; + } + + icsk = inet_csk(sk_listener); + net = sock_net(sk_listener); max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries; /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. @@ -754,6 +846,7 @@ static void reqsk_timer_handler(struct timer_list *t) * embrions; and abort old ones without pity, if old * ones are about to clog our table. */ + queue = &icsk->icsk_accept_queue; qlen = reqsk_queue_len(queue); if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) { int young = reqsk_queue_len_young(queue) << 1; @@ -778,10 +871,39 @@ static void reqsk_timer_handler(struct timer_list *t) atomic_dec(&queue->young); timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); mod_timer(&req->rsk_timer, jiffies + timeo); + + if (!nreq) + return; + + if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { + /* delete timer */ + inet_csk_reqsk_queue_drop(sk_listener, nreq); + goto no_ownership; + } + + __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQSUCCESS); + reqsk_migrate_reset(oreq); + reqsk_queue_removed(&inet_csk(oreq->rsk_listener)->icsk_accept_queue, oreq); + reqsk_put(oreq); + + reqsk_put(nreq); return; } + + /* Even if we can clone the req, we may need not retransmit any more + * SYN+ACKs (nreq->num_timeout > max_syn_ack_retries, etc), or another + * CPU may win the "own_req" race so that inet_ehash_insert() fails. + */ + if (nreq) { + __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQFAILURE); +no_ownership: + reqsk_migrate_reset(nreq); + reqsk_queue_removed(queue, nreq); + __reqsk_free(nreq); + } + drop: - inet_csk_reqsk_queue_drop_and_put(sk_listener, req); + inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq); } static void reqsk_queue_hash_req(struct request_sock *req, @@ -997,12 +1119,42 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req) { if (own_req) { - inet_csk_reqsk_queue_drop(sk, req); - reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - if (inet_csk_reqsk_queue_add(sk, req, child)) + inet_csk_reqsk_queue_drop(req->rsk_listener, req); + reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); + + if (sk != req->rsk_listener) { + /* another listening sk has been selected, + * migrate the req to it. + */ + struct request_sock *nreq; + + /* hold a refcnt for the nreq->rsk_listener + * which is assigned in inet_reqsk_clone() + */ + sock_hold(sk); + nreq = inet_reqsk_clone(req, sk); + if (!nreq) { + inet_child_forget(sk, req, child); + goto child_put; + } + + refcount_set(&nreq->rsk_refcnt, 1); + if (inet_csk_reqsk_queue_add(sk, nreq, child)) { + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQSUCCESS); + reqsk_migrate_reset(req); + reqsk_put(req); + return child; + } + + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); + reqsk_migrate_reset(nreq); + __reqsk_free(nreq); + } else if (inet_csk_reqsk_queue_add(sk, req, child)) { return child; + } } /* Too bad, another child took ownership of the request, undo. */ +child_put: bh_unlock_sock(child); sock_put(child); return NULL; @@ -1028,14 +1180,40 @@ void inet_csk_listen_stop(struct sock *sk) * of the variants now. --ANK */ while ((req = reqsk_queue_remove(queue, sk)) != NULL) { - struct sock *child = req->sk; + struct sock *child = req->sk, *nsk; + struct request_sock *nreq; local_bh_disable(); bh_lock_sock(child); WARN_ON(sock_owned_by_user(child)); sock_hold(child); + nsk = reuseport_migrate_sock(sk, child, NULL); + if (nsk) { + nreq = inet_reqsk_clone(req, nsk); + if (nreq) { + refcount_set(&nreq->rsk_refcnt, 1); + + if (inet_csk_reqsk_queue_add(nsk, nreq, child)) { + __NET_INC_STATS(sock_net(nsk), + LINUX_MIB_TCPMIGRATEREQSUCCESS); + reqsk_migrate_reset(req); + } else { + __NET_INC_STATS(sock_net(nsk), + LINUX_MIB_TCPMIGRATEREQFAILURE); + reqsk_migrate_reset(nreq); + __reqsk_free(nreq); + } + + /* inet_csk_reqsk_queue_add() has already + * called inet_child_forget() on failure case. + */ + goto skip_child_forget; + } + } + inet_child_forget(sk, req, child); +skip_child_forget: reqsk_put(req); bh_unlock_sock(child); local_bh_enable(); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 93474b1bea4e..e65f4ef024a4 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -416,7 +416,7 @@ EXPORT_SYMBOL_GPL(inet_sk_diag_fill); static int inet_twsk_diag_fill(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, - u16 nlmsg_flags) + u16 nlmsg_flags, bool net_admin) { struct inet_timewait_sock *tw = inet_twsk(sk); struct inet_diag_msg *r; @@ -444,6 +444,12 @@ static int inet_twsk_diag_fill(struct sock *sk, r->idiag_uid = 0; r->idiag_inode = 0; + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, + tw->tw_mark)) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } + nlmsg_end(skb, nlh); return 0; } @@ -494,7 +500,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, u16 nlmsg_flags, bool net_admin) { if (sk->sk_state == TCP_TIME_WAIT) - return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags); + return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); if (sk->sk_state == TCP_NEW_SYN_RECV) return inet_req_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); @@ -801,6 +807,8 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.mark = sk->sk_mark; else if (sk->sk_state == TCP_NEW_SYN_RECV) entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; + else if (sk->sk_state == TCP_TIME_WAIT) + entry.mark = inet_twsk(sk)->tw_mark; else entry.mark = 0; #ifdef CONFIG_SOCK_CGROUP_DATA diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c96866a53a66..80aeaf9e6e16 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -697,7 +697,7 @@ void inet_unhash(struct sock *sk) goto unlock; if (rcu_access_pointer(sk->sk_reuseport_cb)) - reuseport_detach_sock(sk); + reuseport_stop_listen_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); ilb->count--; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a68bf4c6fe9b..12dca0c85f3c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -107,6 +107,8 @@ module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static struct rtnl_link_ops ipgre_link_ops __read_mostly; +static const struct header_ops ipgre_header_ops; + static int ipgre_tunnel_init(struct net_device *dev); static void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, @@ -364,7 +366,10 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, raw_proto, false) < 0) goto drop; - if (tunnel->dev->type != ARPHRD_NONE) + /* Special case for ipgre_header_parse(), which expects the + * mac_header to point to the outer IP header. + */ + if (tunnel->dev->header_ops == &ipgre_header_ops) skb_pop_mac_header(skb); else skb_reset_mac_header(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c3efc7d658f6..8d8a8da3ae7e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1054,7 +1054,7 @@ static int __ip_append_data(struct sock *sk, unsigned int datalen; unsigned int fraglen; unsigned int fraggap; - unsigned int alloclen; + unsigned int alloclen, alloc_extra; unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: @@ -1074,35 +1074,39 @@ alloc_new_skb: fraglen = datalen + fragheaderlen; pagedlen = 0; + alloc_extra = hh_len + 15; + alloc_extra += exthdrlen; + + /* The last fragment gets additional space at tail. + * Note, with MSG_MORE we overallocate on fragments, + * because we have no idea what fragment will be + * the last. + */ + if (datalen == length + fraggap) + alloc_extra += rt->dst.trailer_len; + if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; - else if (!paged) + else if (!paged && + (fraglen + alloc_extra < SKB_MAX_ALLOC || + !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; } - alloclen += exthdrlen; - - /* The last fragment gets additional space at tail. - * Note, with MSG_MORE we overallocate on fragments, - * because we have no idea what fragment will be - * the last. - */ - if (datalen == length + fraggap) - alloclen += rt->dst.trailer_len; + alloclen += alloc_extra; if (transhdrlen) { - skb = sock_alloc_send_skb(sk, - alloclen + hh_len + 15, + skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) - skb = alloc_skb(alloclen + hh_len + 15, + skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index bbb56f5e06dd..366094c1ce6c 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -153,7 +153,6 @@ static int ipcomp4_rcv_cb(struct sk_buff *skb, int err) } static const struct xfrm_type ipcomp_type = { - .description = "IPCOMP4", .owner = THIS_MODULE, .proto = IPPROTO_COMP, .init_state = ipcomp4_init_state, diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index d5bfa087c23a..266c65577ba6 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -242,6 +242,8 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) if (!tun_dst) return 0; } + skb_reset_mac_header(skb); + return ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 939792a38814..7b12a40dd465 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1317,7 +1317,7 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags) } /* called from ip_ra_control(), before an RCU grace period, - * we dont need to call synchronize_rcu() here + * we don't need to call synchronize_rcu() here */ static void mrtsock_destruct(struct sock *sk) { @@ -1938,7 +1938,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; - /* For an (*,G) entry, we only check that the incomming + /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ cache_proxy = mr_mfc_find_any_parent(mrt, vif); @@ -3007,7 +3007,6 @@ static const struct seq_operations ipmr_mfc_seq_ops = { #ifdef CONFIG_IP_PIMSM_V2 static const struct net_protocol pim_protocol = { .handler = pim_rcv, - .netns_ok = 1, }; #endif diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index ff437e4ed6db..55fc23a8f7a7 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -27,7 +27,7 @@ static void nft_reject_ipv4_eval(const struct nft_expr *expr, nf_send_unreach(pkt->skb, priv->icmp_code, nft_hook(pkt)); break; case NFT_REJECT_TCP_RST: - nf_send_reset(nft_net(pkt), pkt->xt.state->sk, pkt->skb, + nf_send_reset(nft_net(pkt), nft_sk(pkt), pkt->skb, nft_hook(pkt)); break; default: diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 95a718397fd1..1e44a43acfe2 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -573,7 +573,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info) } } sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: sock_put(sk); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 6d46297a99f8..b0d3a09dc84e 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -295,6 +295,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH), SNMP_MIB_ITEM("TCPDSACKRecvSegs", LINUX_MIB_TCPDSACKRECVSEGS), SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), + SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), + SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index 9a8c0892622b..6913979948d7 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -31,12 +31,6 @@ EXPORT_SYMBOL(inet_offloads); int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) { - if (!prot->netns_ok) { - pr_err("Protocol %u is not namespace aware, cannot register.\n", - protocol); - return -EINVAL; - } - return !cmpxchg((const struct net_protocol **)&inet_protos[protocol], NULL, prot) ? 0 : -1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 50a73178d63a..bb446e60cf58 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -280,7 +280,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) if (inet->recverr || harderr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } } @@ -929,7 +929,7 @@ int raw_abort(struct sock *sk, int err) lock_sock(sk); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); __udp_disconnect(sk, 0); release_sock(sk); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6a36ac98476f..99c06944501a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1306,7 +1306,7 @@ INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; mtu = READ_ONCE(dst->dev->mtu); @@ -1315,6 +1315,7 @@ INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = 576; } +out: mtu = min_t(unsigned int, mtu, IP_MAX_MTU); return mtu - lwtunnel_headroom(dst->lwtstate, mtu); @@ -1906,13 +1907,128 @@ out: hash_keys->addrs.v4addrs.dst = key_iph->daddr; } +static u32 fib_multipath_custom_hash_outer(const struct net *net, + const struct sk_buff *skb, + bool *p_has_inner) +{ + u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + struct flow_keys keys, hash_keys; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); + + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) + hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) + hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + hash_keys.basic.ip_proto = keys.basic.ip_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) + hash_keys.ports.src = keys.ports.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) + hash_keys.ports.dst = keys.ports.dst; + + *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); + return flow_hash_from_keys(&hash_keys); +} + +static u32 fib_multipath_custom_hash_inner(const struct net *net, + const struct sk_buff *skb, + bool has_inner) +{ + u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + struct flow_keys keys, hash_keys; + + /* We assume the packet carries an encapsulation, but if none was + * encountered during dissection of the outer flow, then there is no + * point in calling the flow dissector again. + */ + if (!has_inner) + return 0; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + skb_flow_dissect_flow_keys(skb, &keys, 0); + + if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) + return 0; + + if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) + hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) + hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; + } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) + hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) + hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) + hash_keys.tags.flow_label = keys.tags.flow_label; + } + + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) + hash_keys.basic.ip_proto = keys.basic.ip_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) + hash_keys.ports.src = keys.ports.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) + hash_keys.ports.dst = keys.ports.dst; + + return flow_hash_from_keys(&hash_keys); +} + +static u32 fib_multipath_custom_hash_skb(const struct net *net, + const struct sk_buff *skb) +{ + u32 mhash, mhash_inner; + bool has_inner = true; + + mhash = fib_multipath_custom_hash_outer(net, skb, &has_inner); + mhash_inner = fib_multipath_custom_hash_inner(net, skb, has_inner); + + return jhash_2words(mhash, mhash_inner, 0); +} + +static u32 fib_multipath_custom_hash_fl4(const struct net *net, + const struct flowi4 *fl4) +{ + u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + struct flow_keys hash_keys; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) + hash_keys.addrs.v4addrs.src = fl4->saddr; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) + hash_keys.addrs.v4addrs.dst = fl4->daddr; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + hash_keys.basic.ip_proto = fl4->flowi4_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) + hash_keys.ports.src = fl4->fl4_sport; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) + hash_keys.ports.dst = fl4->fl4_dport; + + return flow_hash_from_keys(&hash_keys); +} + /* if skb is set it will be used and fl4 can be NULL */ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys) { u32 multipath_hash = fl4 ? fl4->flowi4_multipath_hash : 0; struct flow_keys hash_keys; - u32 mhash; + u32 mhash = 0; switch (net->ipv4.sysctl_fib_multipath_hash_policy) { case 0: @@ -1924,6 +2040,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } + mhash = flow_hash_from_keys(&hash_keys); break; case 1: /* skb is currently provided only when forwarding */ @@ -1957,6 +2074,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.ports.dst = fl4->fl4_dport; hash_keys.basic.ip_proto = fl4->flowi4_proto; } + mhash = flow_hash_from_keys(&hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); @@ -1987,9 +2105,15 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } + mhash = flow_hash_from_keys(&hash_keys); + break; + case 3: + if (skb) + mhash = fib_multipath_custom_hash_skb(net, skb); + else + mhash = fib_multipath_custom_hash_fl4(net, fl4); break; } - mhash = flow_hash_from_keys(&hash_keys); if (multipath_hash) mhash = jhash_2words(mhash, multipath_hash, 0); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a62934b9f15a..6f1e64d49232 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -19,6 +19,7 @@ #include <net/snmp.h> #include <net/icmp.h> #include <net/ip.h> +#include <net/ip_fib.h> #include <net/route.h> #include <net/tcp.h> #include <net/udp.h> @@ -29,6 +30,7 @@ #include <net/netevent.h> static int two = 2; +static int three __maybe_unused = 3; static int four = 4; static int thousand = 1000; static int tcp_retr1_max = 255; @@ -48,6 +50,8 @@ static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static u32 u32_max_div_HZ = UINT_MAX / HZ; static int one_day_secs = 24 * 3600; +static u32 fib_multipath_hash_fields_all_mask __maybe_unused = + FIB_MULTIPATH_HASH_FIELD_ALL_MASK; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -461,6 +465,22 @@ static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, return ret; } + +static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write, + void *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net; + int ret; + + net = container_of(table->data, struct net, + ipv4.sysctl_fib_multipath_hash_fields); + ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos); + if (write && ret == 0) + call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); + + return ret; +} #endif static struct ctl_table ipv4_table[] = { @@ -941,6 +961,15 @@ static struct ctl_table ipv4_net_table[] = { }, #endif { + .procname = "tcp_migrate_req", + .data = &init_net.ipv4.sysctl_tcp_migrate_req, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, + { .procname = "tcp_reordering", .data = &init_net.ipv4.sysctl_tcp_reordering, .maxlen = sizeof(int), @@ -1050,7 +1079,16 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_fib_multipath_hash_policy, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = &three, + }, + { + .procname = "fib_multipath_hash_fields", + .data = &init_net.ipv4.sysctl_fib_multipath_hash_fields, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_fib_multipath_hash_fields, + .extra1 = SYSCTL_ONE, + .extra2 = &fib_multipath_hash_fields_all_mask, }, #endif { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 64bf179cc915..d5ab5f243640 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1738,8 +1738,8 @@ int tcp_set_rcvlowat(struct sock *sk, int val) } EXPORT_SYMBOL(tcp_set_rcvlowat); -static void tcp_update_recv_tstamps(struct sk_buff *skb, - struct scm_timestamping_internal *tss) +void tcp_update_recv_tstamps(struct sk_buff *skb, + struct scm_timestamping_internal *tss) { if (skb->tstamp) tss->ts[0] = ktime_to_timespec64(skb->tstamp); @@ -2024,8 +2024,6 @@ static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, } #define TCP_VALID_ZC_MSG_FLAGS (TCP_CMSG_TS) -static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, - struct scm_timestamping_internal *tss); static void tcp_zc_finalize_rx_tstamp(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) @@ -2197,8 +2195,8 @@ out: #endif /* Similar to __sock_recv_timestamp, but does not require an skb */ -static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, - struct scm_timestamping_internal *tss) +void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, + struct scm_timestamping_internal *tss) { int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); bool has_timestamping = false; @@ -3061,7 +3059,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_frag.offset = 0; } - sk->sk_error_report(sk); + sk_error_report(sk); return 0; } EXPORT_SYMBOL(tcp_disconnect); @@ -4450,7 +4448,7 @@ int tcp_abort(struct sock *sk, int err) sk->sk_err = err; /* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb(); - sk->sk_error_report(sk); + sk_error_report(sk); if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC); tcp_done(sk); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ad9d17923fc5..f26916a62f25 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -163,6 +163,28 @@ static bool tcp_bpf_stream_read(const struct sock *sk) return !empty; } +static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, + long timeo) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = sk_wait_event(sk, &timeo, + !list_empty(&psock->ingress_msg) || + !skb_queue_empty(&sk->sk_receive_queue), &wait); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -184,11 +206,11 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { - int data, err = 0; long timeo; + int data; timeo = sock_rcvtimeo(sk, nonblock); - data = sk_msg_wait_data(sk, psock, flags, timeo, &err); + data = tcp_msg_wait_data(sk, psock, timeo); if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; @@ -196,14 +218,9 @@ msg_bytes_ready: sk_psock_put(sk, psock); return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); } - if (err) { - ret = err; - goto out; - } copied = -EAGAIN; } ret = copied; -out: release_sock(sk); sk_psock_put(sk, psock); return ret; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index af2814c9342a..47c32604d38f 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -526,7 +526,7 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) if (!tfo_da_times) return false; - /* Limit timout to max: 2^6 * initial timeout */ + /* Limit timeout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); timeout = multiplier * tfo_bh_timeout * HZ; if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout)) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4cf4dd532d1c..e6ca5a1f3b59 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2816,8 +2816,17 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, *rexmit = REXMIT_LOST; } +static bool tcp_force_fast_retransmit(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + return after(tcp_highest_sack_seq(tp), + tp->snd_una + tp->reordering * tp->mss_cache); +} + /* Undo during fast recovery after partial ACK. */ -static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) +static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una, + bool *do_lost) { struct tcp_sock *tp = tcp_sk(sk); @@ -2842,7 +2851,9 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) tcp_undo_cwnd_reduction(sk, true); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); tcp_try_keep_open(sk); - return true; + } else { + /* Partial ACK arrived. Force fast retransmit. */ + *do_lost = tcp_force_fast_retransmit(sk); } return false; } @@ -2866,14 +2877,6 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag) } } -static bool tcp_force_fast_retransmit(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - return after(tcp_highest_sack_seq(tp), - tp->snd_una + tp->reordering * tp->mss_cache); -} - /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2943,17 +2946,21 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, if (!(flag & FLAG_SND_UNA_ADVANCED)) { if (tcp_is_reno(tp)) tcp_add_reno_sack(sk, num_dupack, ece_ack); - } else { - if (tcp_try_undo_partial(sk, prior_snd_una)) - return; - /* Partial ACK arrived. Force fast retransmit. */ - do_lost = tcp_force_fast_retransmit(sk); - } - if (tcp_try_undo_dsack(sk)) { - tcp_try_keep_open(sk); + } else if (tcp_try_undo_partial(sk, prior_snd_una, &do_lost)) return; - } + + if (tcp_try_undo_dsack(sk)) + tcp_try_keep_open(sk); + tcp_identify_packet_loss(sk, ack_flag); + if (icsk->icsk_ca_state != TCP_CA_Recovery) { + if (!tcp_time_to_recover(sk, flag)) + return; + /* Undo reverts the recovery state. If loss is evident, + * starts a new recovery (e.g. reordering then loss); + */ + tcp_enter_recovery(sk, ece_ack); + } break; case TCP_CA_Loss: tcp_process_loss(sk, flag, num_dupack, rexmit); @@ -4263,7 +4270,7 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb) tcp_done(sk); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } /* @@ -5885,6 +5892,7 @@ step5: return; csum_error: + trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 312184cead57..e66ad6bfe808 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -585,7 +585,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) if (!sock_owned_by_user(sk)) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); tcp_done(sk); } else { @@ -613,7 +613,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else { /* Only an error on timeout */ sk->sk_err_soft = err; } @@ -1731,6 +1731,7 @@ discard: return 0; csum_err: + trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; @@ -1801,6 +1802,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); + trace_tcp_bad_csum(skb); __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); return true; @@ -2000,13 +2002,21 @@ process: goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { - inet_csk_reqsk_queue_drop_and_put(sk, req); - goto lookup; + nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); + if (!nsk) { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } + sk = nsk; + /* reuseport_migrate_sock() has already held one sk_refcnt + * before returning. + */ + } else { + /* We own a reference on the listener, increase it again + * as we might lose it too soon. + */ + sock_hold(sk); } - /* We own a reference on the listener, increase it again - * as we might lose it too soon. - */ - sock_hold(sk); refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { @@ -2098,6 +2108,7 @@ no_tcp_socket: if (tcp_checksum_complete(skb)) { csum_error: + trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7513ba45553d..0a4f3f16140a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -775,8 +775,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, goto listen_overflow; if (own_req && rsk_drop_req(req)) { - reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - inet_csk_reqsk_queue_drop_and_put(sk, req); + reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); return child; } @@ -786,6 +786,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, return inet_csk_complete_hashdance(sk, child, req, own_req); listen_overflow: + if (sk != req->rsk_listener) + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); + if (!sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow) { inet_rsk(req)->acked = 1; return NULL; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4ef08079ccfa..20cf4a98c69d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -68,7 +68,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) static void tcp_write_err(struct sock *sk) { sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); tcp_write_queue_purge(sk); tcp_done(sk); @@ -441,7 +441,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) * This function gets called when the kernel timer for a TCP packet * of this socket expires. * - * It handles retransmission, timer adjustment and other necesarry measures. + * It handles retransmission, timer adjustment and other necessary measures. * * Returns: Nothing (void) */ @@ -766,7 +766,7 @@ static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer) if (!sock_owned_by_user(sk)) { if (tp->compressed_ack) { /* Since we have to send one ack finally, - * substract one from tp->compressed_ack to keep + * subtract one from tp->compressed_ack to keep * LINUX_MIB_TCPACKCOMPRESSED accurate. */ tp->compressed_ack--; diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 3bb448761ca3..07c4c93b9fdb 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -221,7 +221,7 @@ static struct tcp_congestion_ops tcp_yeah __read_mostly = { static int __init tcp_yeah_register(void) { - BUG_ON(sizeof(struct yeah) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct yeah) > ICSK_CA_PRIV_SIZE); tcp_register_congestion_control(&tcp_yeah); return 0; } diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index e44aaf41a138..5048c47c79b2 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -218,7 +218,6 @@ static const struct net_protocol tunnel4_protocol = { .handler = tunnel4_rcv, .err_handler = tunnel4_err, .no_policy = 1, - .netns_ok = 1, }; #if IS_ENABLED(CONFIG_IPV6) @@ -226,7 +225,6 @@ static const struct net_protocol tunnel64_protocol = { .handler = tunnel64_rcv, .err_handler = tunnel64_err, .no_policy = 1, - .netns_ok = 1, }; #endif @@ -235,7 +233,6 @@ static const struct net_protocol tunnelmpls4_protocol = { .handler = tunnelmpls4_rcv, .err_handler = tunnelmpls4_err, .no_policy = 1, - .netns_ok = 1, }; #endif diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1307ad0d3b9e..62682807b4b2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -776,7 +776,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1)); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: return 0; } @@ -1798,11 +1798,13 @@ int udp_read_sock(struct sock *sk, read_descriptor_t *desc, if (used <= 0) { if (!copied) copied = used; + kfree_skb(skb); break; } else if (used <= skb->len) { copied += used; } + kfree_skb(skb); if (!desc->count) break; } @@ -2867,7 +2869,7 @@ int udp_abort(struct sock *sk, int err) goto out; sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); __udp_disconnect(sk, 0); out: diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 954c4591a6fd..45b8782aec0c 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -21,6 +21,45 @@ static int sk_udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, return udp_prot.recvmsg(sk, msg, len, noblock, flags, addr_len); } +static bool udp_sk_has_data(struct sock *sk) +{ + return !skb_queue_empty(&udp_sk(sk)->reader_queue) || + !skb_queue_empty(&sk->sk_receive_queue); +} + +static bool psock_has_data(struct sk_psock *psock) +{ + return !skb_queue_empty(&psock->ingress_skb) || + !sk_psock_queue_empty(psock); +} + +#define udp_msg_has_data(__sk, __psock) \ + ({ udp_sk_has_data(__sk) || psock_has_data(__psock); }) + +static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock, + long timeo) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = udp_msg_has_data(sk, psock); + if (!ret) { + wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + ret = udp_msg_has_data(sk, psock); + } + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -34,8 +73,7 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(!psock)) return sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - lock_sock(sk); - if (sk_psock_queue_empty(psock)) { + if (!psock_has_data(psock)) { ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); goto out; } @@ -43,26 +81,21 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { - int data, err = 0; long timeo; + int data; timeo = sock_rcvtimeo(sk, nonblock); - data = sk_msg_wait_data(sk, psock, flags, timeo, &err); + data = udp_msg_wait_data(sk, psock, timeo); if (data) { - if (!sk_psock_queue_empty(psock)) + if (psock_has_data(psock)) goto msg_bytes_ready; ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); goto out; } - if (err) { - ret = err; - goto out; - } copied = -EAGAIN; } ret = copied; out: - release_sock(sk); sk_psock_put(sk, psock); return ret; } diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index bd8773b49e72..cd1cd68adeec 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -31,7 +31,6 @@ static const struct net_protocol udplite_protocol = { .handler = udplite_rcv, .err_handler = udplite_err, .no_policy = 1, - .netns_ok = 1, }; struct proto udplite_prot = { diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c index ea595c8549c7..2fe5860c21d6 100644 --- a/net/ipv4/xfrm4_protocol.c +++ b/net/ipv4/xfrm4_protocol.c @@ -181,21 +181,18 @@ static const struct net_protocol esp4_protocol = { .handler = xfrm4_esp_rcv, .err_handler = xfrm4_esp_err, .no_policy = 1, - .netns_ok = 1, }; static const struct net_protocol ah4_protocol = { .handler = xfrm4_ah_rcv, .err_handler = xfrm4_ah_err, .no_policy = 1, - .netns_ok = 1, }; static const struct net_protocol ipcomp4_protocol = { .handler = xfrm4_ipcomp_rcv, .err_handler = xfrm4_ipcomp_err, .no_policy = 1, - .netns_ok = 1, }; static const struct xfrm_input_afinfo xfrm4_input_afinfo = { diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index fb0648e7fb32..f4555a88f86b 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -42,7 +42,6 @@ static void ipip_destroy(struct xfrm_state *x) } static const struct xfrm_type ipip_type = { - .description = "IPIP", .owner = THIS_MODULE, .proto = IPPROTO_IPIP, .init_state = ipip_init_state, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 701eb82acd1c..3bf685fe64b9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6903,10 +6903,10 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, { - .procname = "addr_gen_mode", - .data = &ipv6_devconf.addr_gen_mode, - .maxlen = sizeof(int), - .mode = 0644, + .procname = "addr_gen_mode", + .data = &ipv6_devconf.addr_gen_mode, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = addrconf_sysctl_addr_gen_mode, }, { diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 20d492da725a..828e62514260 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -755,7 +755,6 @@ static int ah6_rcv_cb(struct sk_buff *skb, int err) } static const struct xfrm_type ah6_type = { - .description = "AH6", .owner = THIS_MODULE, .proto = IPPROTO_AH, .flags = XFRM_TYPE_REPLAY_PROT, @@ -763,7 +762,6 @@ static const struct xfrm_type ah6_type = { .destructor = ah6_destroy, .input = ah6_input, .output = ah6_output, - .hdr_offset = xfrm6_find_1stfragopt, }; static struct xfrm6_protocol ah6_protocol = { diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 393ae2b78e7d..ed2f061b8768 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -708,7 +708,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; - padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); + padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } @@ -1243,7 +1243,6 @@ static int esp6_rcv_cb(struct sk_buff *skb, int err) } static const struct xfrm_type esp6_type = { - .description = "ESP6", .owner = THIS_MODULE, .proto = IPPROTO_ESP, .flags = XFRM_TYPE_REPLAY_PROT, @@ -1251,7 +1250,6 @@ static const struct xfrm_type esp6_type = { .destructor = esp6_destroy, .input = esp6_input, .output = esp6_output, - .hdr_offset = xfrm6_find_1stfragopt, }; static struct xfrm6_protocol esp6_protocol = { diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 40ed4fcf1cf4..a349d4798077 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -377,7 +377,6 @@ static const struct net_offload esp6_offload = { }; static const struct xfrm_type_offload esp6_type_offload = { - .description = "ESP6 OFFLOAD", .owner = THIS_MODULE, .proto = IPPROTO_ESP, .input_tail = esp6_input_tail, diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 56e479d158b7..26882e165c9e 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -135,18 +135,23 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, len -= 2; while (len > 0) { - int optlen = nh[off + 1] + 2; - int i; + int optlen, i; - switch (nh[off]) { - case IPV6_TLV_PAD1: - optlen = 1; + if (nh[off] == IPV6_TLV_PAD1) { padlen++; if (padlen > 7) goto bad; - break; + off++; + len--; + continue; + } + if (len < 2) + goto bad; + optlen = nh[off + 1] + 2; + if (optlen > len) + goto bad; - case IPV6_TLV_PADN: + if (nh[off] == IPV6_TLV_PADN) { /* RFC 2460 states that the purpose of PadN is * to align the containing header to multiples * of 8. 7 is therefore the highest valid value. @@ -163,12 +168,7 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, if (nh[off + i] != 0) goto bad; } - break; - - default: /* Other TLV code so scan list */ - if (optlen > len) - goto bad; - + } else { tlv_count++; if (tlv_count > max_count) goto bad; @@ -188,7 +188,6 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, return false; padlen = 0; - break; } off += optlen; len -= optlen; @@ -306,7 +305,7 @@ fail_and_free: #endif if (ip6_parse_tlv(tlvprocdestopt_lst, skb, - init_net.ipv6.sysctl.max_dst_opts_cnt)) { + net->ipv6.sysctl.max_dst_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) @@ -1037,7 +1036,7 @@ fail_and_free: opt->flags |= IP6SKB_HOPBYHOP; if (ip6_parse_tlv(tlvprochopopt_lst, skb, - init_net.ipv6.sysctl.max_hbh_opts_cnt)) { + net->ipv6.sysctl.max_hbh_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 8f9a83314de7..40f3e4f9f33a 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -467,7 +467,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { static int __net_init fib6_rules_net_init(struct net *net) { struct fib_rules_ops *ops; - int err = -ENOMEM; + int err; ops = fib_rules_register(&fib6_rules_ops_template, net); if (IS_ERR(ops)) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index e8398ffb5e35..a7c31ab67c5d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -725,6 +725,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct ipcm6_cookie ipc6; u32 mark = IP6_REPLY_MARK(net, skb->mark); bool acast; + u8 type; if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) && net->ipv6.sysctl.icmpv6_echo_ignore_multicast) @@ -740,8 +741,13 @@ static void icmpv6_echo_reply(struct sk_buff *skb) !(net->ipv6.sysctl.anycast_src_echo_reply && acast)) saddr = NULL; + if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST) + type = ICMPV6_EXT_ECHO_REPLY; + else + type = ICMPV6_ECHO_REPLY; + memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr)); - tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY; + tmp_hdr.icmp6_type = type; memset(&fl6, 0, sizeof(fl6)); if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES) @@ -752,7 +758,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (saddr) fl6.saddr = *saddr; fl6.flowi6_oif = icmp6_iif(skb); - fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY; + fl6.fl6_icmp_type = type; fl6.flowi6_mark = mark; fl6.flowi6_uid = sock_net_uid(net, NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); @@ -783,13 +789,17 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.skb = skb; msg.offset = 0; - msg.type = ICMPV6_ECHO_REPLY; + msg.type = type; ipcm6_init_sk(&ipc6, np); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); ipc6.sockc.mark = mark; + if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST) + if (!icmp_build_probe(skb, (struct icmphdr *)&tmp_hdr)) + goto out_dst_release; + if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, @@ -911,6 +921,11 @@ static int icmpv6_rcv(struct sk_buff *skb) if (!net->ipv6.sysctl.icmpv6_echo_ignore_all) icmpv6_echo_reply(skb); break; + case ICMPV6_EXT_ECHO_REQUEST: + if (!net->ipv6.sysctl.icmpv6_echo_ignore_all && + net->ipv4.sysctl_icmp_echo_enable_probe) + icmpv6_echo_reply(skb); + break; case ICMPV6_ECHO_REPLY: success = ping_rcv(skb); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 679699e953f1..2d650dc24349 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -32,6 +32,7 @@ #include <net/lwtunnel.h> #include <net/fib_notifier.h> +#include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> @@ -2355,6 +2356,10 @@ static int __net_init fib6_net_init(struct net *net) if (err) return err; + /* Default to 3-tuple */ + net->ipv6.sysctl.multipath_hash_fields = + FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; + spin_lock_init(&net->ipv6.fib6_gc_lock); rwlock_init(&net->ipv6.fib6_walker_lock); INIT_LIST_HEAD(&net->ipv6.fib6_walkers); @@ -2362,7 +2367,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); if (!net->ipv6.rt6_stats) - goto out_timer; + goto out_notifier; /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); @@ -2407,7 +2412,7 @@ out_fib_table_hash: kfree(net->ipv6.fib_table_hash); out_rt6_stats: kfree(net->ipv6.rt6_stats); -out_timer: +out_notifier: fib6_notifier_exit(net); return -ENOMEM; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ff4f9ebcf7f6..984050f35c61 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1055,13 +1055,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, * ip6_route_output will fail given src=any saddr, though, so * that's why we try it again later. */ - if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) { + if (ipv6_addr_any(&fl6->saddr)) { struct fib6_info *from; struct rt6_info *rt; - bool had_dst = *dst != NULL; - if (!had_dst) - *dst = ip6_route_output(net, sk, fl6); + *dst = ip6_route_output(net, sk, fl6); rt = (*dst)->error ? NULL : (struct rt6_info *)*dst; rcu_read_lock(); @@ -1078,7 +1076,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, * never existed and let the SA-enabled version take * over. */ - if (!had_dst && (*dst)->error) { + if ((*dst)->error) { dst_release(*dst); *dst = NULL; } @@ -1555,7 +1553,7 @@ emsgsize: unsigned int datalen; unsigned int fraglen; unsigned int fraggap; - unsigned int alloclen; + unsigned int alloclen, alloc_extra; unsigned int pagedlen; alloc_new_skb: /* There's no room in the current skb */ @@ -1582,17 +1580,28 @@ alloc_new_skb: fraglen = datalen + fragheaderlen; pagedlen = 0; + alloc_extra = hh_len; + alloc_extra += dst_exthdrlen; + alloc_extra += rt->dst.trailer_len; + + /* We just reserve space for fragment header. + * Note: this may be overallocation if the message + * (without MSG_MORE) fits into the MTU. + */ + alloc_extra += sizeof(struct frag_hdr); + if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; - else if (!paged) + else if (!paged && + (fraglen + alloc_extra < SKB_MAX_ALLOC || + !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; } - - alloclen += dst_exthdrlen; + alloclen += alloc_extra; if (datalen != length + fraggap) { /* @@ -1602,30 +1611,21 @@ alloc_new_skb: datalen += rt->dst.trailer_len; } - alloclen += rt->dst.trailer_len; fraglen = datalen + fragheaderlen; - /* - * We just reserve space for fragment header. - * Note: this may be overallocation if the message - * (without MSG_MORE) fits into the MTU. - */ - alloclen += sizeof(struct frag_hdr); - copy = datalen - transhdrlen - fraggap - pagedlen; if (copy < 0) { err = -EINVAL; goto error; } if (transhdrlen) { - skb = sock_alloc_send_skb(sk, - alloclen + hh_len, + skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) - skb = alloc_skb(alloclen + hh_len, + skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 288bafded998..322698d9fcf4 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -837,6 +837,7 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; + skb_reset_mac_header(skb); } skb_reset_network_header(skb); @@ -1239,8 +1240,6 @@ route_lookup: if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; - skb_set_inner_ipproto(skb, proto); - err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) return err; @@ -1377,6 +1376,8 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; + skb_set_inner_ipproto(skb, protocol); + err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, protocol); if (err != 0) { diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index daef890460b7..15f984be3570 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -172,14 +172,12 @@ static int ipcomp6_rcv_cb(struct sk_buff *skb, int err) } static const struct xfrm_type ipcomp6_type = { - .description = "IPCOMP6", .owner = THIS_MODULE, .proto = IPPROTO_COMP, .init_state = ipcomp6_init_state, .destructor = ipcomp_destroy, .input = ipcomp_input, .output = ipcomp_output, - .hdr_offset = xfrm6_find_1stfragopt, }; static struct xfrm6_protocol ipcomp6_protocol = { diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index d36ef9d25e73..54ec163fbafa 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1729,22 +1729,25 @@ static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb, static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) { + u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, + 2, 0, 0, IPV6_TLV_PADN, 0 }; struct net_device *dev = idev->dev; - struct net *net = dev_net(dev); - struct sock *sk = net->ipv6.igmp_sk; - struct sk_buff *skb; - struct mld2_report *pmr; - struct in6_addr addr_buf; - const struct in6_addr *saddr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - unsigned int size = mtu + hlen + tlen; + struct net *net = dev_net(dev); + const struct in6_addr *saddr; + struct in6_addr addr_buf; + struct mld2_report *pmr; + struct sk_buff *skb; + unsigned int size; + struct sock *sk; int err; - u8 ra[8] = { IPPROTO_ICMPV6, 0, - IPV6_TLV_ROUTERALERT, 2, 0, 0, - IPV6_TLV_PADN, 0 }; - /* we assume size > sizeof(ra) here */ + sk = net->ipv6.igmp_sk; + /* we assume size > sizeof(ra) here + * Also try to not allocate high-order pages for big MTU + */ + size = min_t(int, mtu, PAGE_SIZE / 2) + hlen + tlen; skb = sock_alloc_send_skb(sk, size, 1, &err); if (!skb) return NULL; diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 878fcec14949..aeb35d26e474 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -247,54 +247,6 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, return err; } -static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb, - u8 **nexthdr) -{ - u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = - (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); - const unsigned char *nh = skb_network_header(skb); - unsigned int packet_len = skb_tail_pointer(skb) - - skb_network_header(skb); - int found_rhdr = 0; - - *nexthdr = &ipv6_hdr(skb)->nexthdr; - - while (offset + 1 <= packet_len) { - - switch (**nexthdr) { - case NEXTHDR_HOP: - break; - case NEXTHDR_ROUTING: - found_rhdr = 1; - break; - case NEXTHDR_DEST: - /* - * HAO MUST NOT appear more than once. - * XXX: It is better to try to find by the end of - * XXX: packet if HAO exists. - */ - if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) { - net_dbg_ratelimited("mip6: hao exists already, override\n"); - return offset; - } - - if (found_rhdr) - return offset; - - break; - default: - return offset; - } - - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr *)(nh + offset); - } - - return offset; -} - static int mip6_destopt_init_state(struct xfrm_state *x) { if (x->id.spi) { @@ -324,7 +276,6 @@ static void mip6_destopt_destroy(struct xfrm_state *x) } static const struct xfrm_type mip6_destopt_type = { - .description = "MIP6DESTOPT", .owner = THIS_MODULE, .proto = IPPROTO_DSTOPTS, .flags = XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_LOCAL_COADDR, @@ -333,7 +284,6 @@ static const struct xfrm_type mip6_destopt_type = { .input = mip6_destopt_input, .output = mip6_destopt_output, .reject = mip6_destopt_reject, - .hdr_offset = mip6_destopt_offset, }; static int mip6_rthdr_input(struct xfrm_state *x, struct sk_buff *skb) @@ -383,53 +333,6 @@ static int mip6_rthdr_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } -static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb, - u8 **nexthdr) -{ - u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = - (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); - const unsigned char *nh = skb_network_header(skb); - unsigned int packet_len = skb_tail_pointer(skb) - - skb_network_header(skb); - int found_rhdr = 0; - - *nexthdr = &ipv6_hdr(skb)->nexthdr; - - while (offset + 1 <= packet_len) { - - switch (**nexthdr) { - case NEXTHDR_HOP: - break; - case NEXTHDR_ROUTING: - if (offset + 3 <= packet_len) { - struct ipv6_rt_hdr *rt; - rt = (struct ipv6_rt_hdr *)(nh + offset); - if (rt->type != 0) - return offset; - } - found_rhdr = 1; - break; - case NEXTHDR_DEST: - if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) - return offset; - - if (found_rhdr) - return offset; - - break; - default: - return offset; - } - - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr *)(nh + offset); - } - - return offset; -} - static int mip6_rthdr_init_state(struct xfrm_state *x) { if (x->id.spi) { @@ -456,7 +359,6 @@ static void mip6_rthdr_destroy(struct xfrm_state *x) } static const struct xfrm_type mip6_rthdr_type = { - .description = "MIP6RT", .owner = THIS_MODULE, .proto = IPPROTO_ROUTING, .flags = XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_REMOTE_COADDR, @@ -464,7 +366,6 @@ static const struct xfrm_type mip6_rthdr_type = { .destructor = mip6_rthdr_destroy, .input = mip6_rthdr_input, .output = mip6_rthdr_output, - .hdr_offset = mip6_rthdr_offset, }; static int __init mip6_init(void) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index e810a23baf99..de2cf3943b91 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -51,7 +51,7 @@ ip6_packet_match(const struct sk_buff *skb, const char *outdev, const struct ip6t_ip6 *ip6info, unsigned int *protoff, - int *fragoff, bool *hotdrop) + u16 *fragoff, bool *hotdrop) { unsigned long ret; const struct ipv6hdr *ipv6 = ipv6_hdr(skb); diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c index 7969d1f3018d..ed69c768797e 100644 --- a/net/ipv6/netfilter/nft_reject_ipv6.c +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -28,7 +28,7 @@ static void nft_reject_ipv6_eval(const struct nft_expr *expr, nft_hook(pkt)); break; case NFT_REJECT_TCP_RST: - nf_send_reset6(nft_net(pkt), pkt->xt.state->sk, pkt->skb, + nf_send_reset6(nft_net(pkt), nft_sk(pkt), pkt->skb, nft_hook(pkt)); break; default: diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index af36acc1a644..2880dc7d9a49 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -15,29 +15,11 @@ static u32 __ipv6_select_ident(struct net *net, const struct in6_addr *dst, const struct in6_addr *src) { - const struct { - struct in6_addr dst; - struct in6_addr src; - } __aligned(SIPHASH_ALIGNMENT) combined = { - .dst = *dst, - .src = *src, - }; - u32 hash, id; - - /* Note the following code is not safe, but this is okay. */ - if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) - get_random_bytes(&net->ipv4.ip_id_key, - sizeof(net->ipv4.ip_id_key)); - - hash = siphash(&combined, sizeof(combined), &net->ipv4.ip_id_key); - - /* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve, - * set the hight order instead thus minimizing possible future - * collisions. - */ - id = ip_idents_reserve(hash, 1); - if (unlikely(!id)) - id = 1 << 31; + u32 id; + + do { + id = prandom_u32(); + } while (!id); return id; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index bf3646b57c68..60f1e4f5be5a 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -354,7 +354,7 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, if (np->recverr || harderr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d417e514bd52..7b756a7dc036 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2326,12 +2326,131 @@ out: } } +static u32 rt6_multipath_custom_hash_outer(const struct net *net, + const struct sk_buff *skb, + bool *p_has_inner) +{ + u32 hash_fields = ip6_multipath_hash_fields(net); + struct flow_keys keys, hash_keys; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); + + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) + hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) + hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + hash_keys.basic.ip_proto = keys.basic.ip_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) + hash_keys.tags.flow_label = keys.tags.flow_label; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) + hash_keys.ports.src = keys.ports.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) + hash_keys.ports.dst = keys.ports.dst; + + *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); + return flow_hash_from_keys(&hash_keys); +} + +static u32 rt6_multipath_custom_hash_inner(const struct net *net, + const struct sk_buff *skb, + bool has_inner) +{ + u32 hash_fields = ip6_multipath_hash_fields(net); + struct flow_keys keys, hash_keys; + + /* We assume the packet carries an encapsulation, but if none was + * encountered during dissection of the outer flow, then there is no + * point in calling the flow dissector again. + */ + if (!has_inner) + return 0; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + skb_flow_dissect_flow_keys(skb, &keys, 0); + + if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) + return 0; + + if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) + hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) + hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; + } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) + hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) + hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) + hash_keys.tags.flow_label = keys.tags.flow_label; + } + + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) + hash_keys.basic.ip_proto = keys.basic.ip_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) + hash_keys.ports.src = keys.ports.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) + hash_keys.ports.dst = keys.ports.dst; + + return flow_hash_from_keys(&hash_keys); +} + +static u32 rt6_multipath_custom_hash_skb(const struct net *net, + const struct sk_buff *skb) +{ + u32 mhash, mhash_inner; + bool has_inner = true; + + mhash = rt6_multipath_custom_hash_outer(net, skb, &has_inner); + mhash_inner = rt6_multipath_custom_hash_inner(net, skb, has_inner); + + return jhash_2words(mhash, mhash_inner, 0); +} + +static u32 rt6_multipath_custom_hash_fl6(const struct net *net, + const struct flowi6 *fl6) +{ + u32 hash_fields = ip6_multipath_hash_fields(net); + struct flow_keys hash_keys; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) + hash_keys.addrs.v6addrs.src = fl6->saddr; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) + hash_keys.addrs.v6addrs.dst = fl6->daddr; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + hash_keys.basic.ip_proto = fl6->flowi6_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) + hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) + hash_keys.ports.src = fl6->fl6_sport; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) + hash_keys.ports.dst = fl6->fl6_dport; + + return flow_hash_from_keys(&hash_keys); +} + /* if skb is set it will be used and fl6 can be NULL */ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *flkeys) { struct flow_keys hash_keys; - u32 mhash; + u32 mhash = 0; switch (ip6_multipath_hash_policy(net)) { case 0: @@ -2345,6 +2464,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } + mhash = flow_hash_from_keys(&hash_keys); break; case 1: if (skb) { @@ -2376,6 +2496,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.ports.dst = fl6->fl6_dport; hash_keys.basic.ip_proto = fl6->flowi6_proto; } + mhash = flow_hash_from_keys(&hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); @@ -2412,9 +2533,15 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } + mhash = flow_hash_from_keys(&hash_keys); + break; + case 3: + if (skb) + mhash = rt6_multipath_custom_hash_skb(net, skb); + else + mhash = rt6_multipath_custom_hash_fl6(net, fl6); break; } - mhash = flow_hash_from_keys(&hash_keys); return mhash >> 1; } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 4ff38cb08f4b..60bf3b877957 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -87,10 +87,10 @@ struct seg6_end_dt_info { int vrf_ifindex; int vrf_table; - /* tunneled packet proto and family (IPv4 or IPv6) */ - __be16 proto; + /* tunneled packet family (IPv4 or IPv6). + * Protocol and header length are inferred from family. + */ u16 family; - int hdrlen; }; struct pcpu_seg6_local_counters { @@ -521,19 +521,6 @@ static int __seg6_end_dt_vrf_build(struct seg6_local_lwt *slwt, const void *cfg, info->net = net; info->vrf_ifindex = vrf_ifindex; - switch (family) { - case AF_INET: - info->proto = htons(ETH_P_IP); - info->hdrlen = sizeof(struct iphdr); - break; - case AF_INET6: - info->proto = htons(ETH_P_IPV6); - info->hdrlen = sizeof(struct ipv6hdr); - break; - default: - return -EINVAL; - } - info->family = family; info->mode = DT_VRF_MODE; @@ -622,22 +609,44 @@ error: } static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb, - struct seg6_local_lwt *slwt) + struct seg6_local_lwt *slwt, u16 family) { struct seg6_end_dt_info *info = &slwt->dt_info; struct net_device *vrf; + __be16 protocol; + int hdrlen; vrf = end_dt_get_vrf_rcu(skb, info); if (unlikely(!vrf)) goto drop; - skb->protocol = info->proto; + switch (family) { + case AF_INET: + protocol = htons(ETH_P_IP); + hdrlen = sizeof(struct iphdr); + break; + case AF_INET6: + protocol = htons(ETH_P_IPV6); + hdrlen = sizeof(struct ipv6hdr); + break; + case AF_UNSPEC: + fallthrough; + default: + goto drop; + } + + if (unlikely(info->family != AF_UNSPEC && info->family != family)) { + pr_warn_once("seg6local: SRv6 End.DT* family mismatch"); + goto drop; + } + + skb->protocol = protocol; skb_dst_drop(skb); - skb_set_transport_header(skb, info->hdrlen); + skb_set_transport_header(skb, hdrlen); - return end_dt_vrf_rcv(skb, info->family, vrf); + return end_dt_vrf_rcv(skb, family, vrf); drop: kfree_skb(skb); @@ -656,7 +665,7 @@ static int input_action_end_dt4(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto drop; - skb = end_dt_vrf_core(skb, slwt); + skb = end_dt_vrf_core(skb, slwt, AF_INET); if (!skb) /* packet has been processed and consumed by the VRF */ return 0; @@ -739,7 +748,7 @@ static int input_action_end_dt6(struct sk_buff *skb, goto legacy_mode; /* DT6_VRF_MODE */ - skb = end_dt_vrf_core(skb, slwt); + skb = end_dt_vrf_core(skb, slwt, AF_INET6); if (!skb) /* packet has been processed and consumed by the VRF */ return 0; @@ -767,6 +776,36 @@ drop: return -EINVAL; } +#ifdef CONFIG_NET_L3_MASTER_DEV +static int seg6_end_dt46_build(struct seg6_local_lwt *slwt, const void *cfg, + struct netlink_ext_ack *extack) +{ + return __seg6_end_dt_vrf_build(slwt, cfg, AF_UNSPEC, extack); +} + +static int input_action_end_dt46(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + unsigned int off = 0; + int nexthdr; + + nexthdr = ipv6_find_hdr(skb, &off, -1, NULL, NULL); + if (unlikely(nexthdr < 0)) + goto drop; + + switch (nexthdr) { + case IPPROTO_IPIP: + return input_action_end_dt4(skb, slwt); + case IPPROTO_IPV6: + return input_action_end_dt6(skb, slwt); + } + +drop: + kfree_skb(skb); + return -EINVAL; +} +#endif + /* push an SRH on top of the current one */ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt) { @@ -969,6 +1008,17 @@ static struct seg6_action_desc seg6_action_table[] = { .input = input_action_end_dt6, }, { + .action = SEG6_LOCAL_ACTION_END_DT46, + .attrs = SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE), + .optattrs = SEG6_F_LOCAL_COUNTERS, +#ifdef CONFIG_NET_L3_MASTER_DEV + .input = input_action_end_dt46, + .slwt_ops = { + .build_state = seg6_end_dt46_build, + }, +#endif + }, + { .action = SEG6_LOCAL_ACTION_END_B6, .attrs = SEG6_F_ATTR(SEG6_LOCAL_SRH), .optattrs = SEG6_F_LOCAL_COUNTERS, diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index f7c8110ece5f..df5bea818410 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -710,6 +710,8 @@ static int ipip6_rcv(struct sk_buff *skb) * old iph is no longer valid */ iph = (const struct iphdr *)skb_mac_header(skb); + skb_reset_mac_header(skb); + err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -780,6 +782,8 @@ static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto) tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; + skb_reset_mac_header(skb); + return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error); } @@ -973,7 +977,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (df) { mtu = dst_mtu(&rt->dst) - t_hlen; - if (mtu < 68) { + if (mtu < IPV4_MIN_MTU) { dev->stats.collisions++; ip_rt_put(rt); goto tx_error; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 27102c3d6e1d..d7cf26f730d7 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -17,13 +17,17 @@ #include <net/addrconf.h> #include <net/inet_frag.h> #include <net/netevent.h> +#include <net/ip_fib.h> #ifdef CONFIG_NETLABEL #include <net/calipso.h> #endif static int two = 2; +static int three = 3; static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; +static u32 rt6_multipath_hash_fields_all_mask = + FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -40,6 +44,22 @@ static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, return ret; } +static int +proc_rt6_multipath_hash_fields(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + struct net *net; + int ret; + + net = container_of(table->data, struct net, + ipv6.sysctl.multipath_hash_fields); + ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos); + if (write && ret == 0) + call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); + + return ret; +} + static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", @@ -149,7 +169,16 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_rt6_multipath_hash_policy, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = &three, + }, + { + .procname = "fib_multipath_hash_fields", + .data = &init_net.ipv6.sysctl.multipath_hash_fields, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_rt6_multipath_hash_fields, + .extra1 = SYSCTL_ONE, + .extra2 = &rt6_multipath_hash_fields_all_mask, }, { .procname = "seg6_flowlabel", diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5f47c0b6e3de..578ab6305c3f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -467,7 +467,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk)) { sk->sk_err = err; - sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ + sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ tcp_done(sk); } else @@ -486,7 +486,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else sk->sk_err_soft = err; @@ -1538,6 +1538,7 @@ discard: kfree_skb(skb); return 0; csum_err: + trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; @@ -1663,10 +1664,18 @@ process: goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { - inet_csk_reqsk_queue_drop_and_put(sk, req); - goto lookup; + nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); + if (!nsk) { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } + sk = nsk; + /* reuseport_migrate_sock() has already held one sk_refcnt + * before returning. + */ + } else { + sock_hold(sk); } - sock_hold(sk); refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { @@ -1754,6 +1763,7 @@ no_tcp_socket: if (tcp_checksum_complete(skb)) { csum_error: + trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3fcd86f4dfdc..368972dbd919 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -610,7 +610,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: return 0; } diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8b84d534b19d..57fa27c1cdf9 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -16,13 +16,6 @@ #include <net/ip6_route.h> #include <net/xfrm.h> -int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, - u8 **prevhdr) -{ - return ip6_find_1stfragopt(skb, prevhdr); -} -EXPORT_SYMBOL(xfrm6_find_1stfragopt); - void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu) { struct flowi6 fl6; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f696d46e6910..2b31112c0856 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -291,7 +291,6 @@ static void xfrm6_tunnel_destroy(struct xfrm_state *x) } static const struct xfrm_type xfrm6_tunnel_type = { - .description = "IP6IP6", .owner = THIS_MODULE, .proto = IPPROTO_IPV6, .init_state = xfrm6_tunnel_init_state, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 0fdb389c3390..44453b35c7b7 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -44,6 +44,7 @@ static struct proto iucv_proto = { }; static struct iucv_interface *pr_iucv; +static struct iucv_handler af_iucv_handler; /* special AF_IUCV IPRM messages */ static const u8 iprm_shutdown[8] = @@ -91,28 +92,11 @@ static void iucv_sock_close(struct sock *sk); static void afiucv_hs_callback_txnotify(struct sock *sk, enum iucv_tx_notify); -/* Call Back functions */ -static void iucv_callback_rx(struct iucv_path *, struct iucv_message *); -static void iucv_callback_txdone(struct iucv_path *, struct iucv_message *); -static void iucv_callback_connack(struct iucv_path *, u8 *); -static int iucv_callback_connreq(struct iucv_path *, u8 *, u8 *); -static void iucv_callback_connrej(struct iucv_path *, u8 *); -static void iucv_callback_shutdown(struct iucv_path *, u8 *); - static struct iucv_sock_list iucv_sk_list = { .lock = __RW_LOCK_UNLOCKED(iucv_sk_list.lock), .autobind_name = ATOMIC_INIT(0) }; -static struct iucv_handler af_iucv_handler = { - .path_pending = iucv_callback_connreq, - .path_complete = iucv_callback_connack, - .path_severed = iucv_callback_connrej, - .message_pending = iucv_callback_rx, - .message_complete = iucv_callback_txdone, - .path_quiesced = iucv_callback_shutdown, -}; - static inline void high_nmcpy(unsigned char *dst, char *src) { memcpy(dst, src, 8); @@ -1817,6 +1801,15 @@ static void iucv_callback_shutdown(struct iucv_path *path, u8 ipuser[16]) bh_unlock_sock(sk); } +static struct iucv_handler af_iucv_handler = { + .path_pending = iucv_callback_connreq, + .path_complete = iucv_callback_connack, + .path_severed = iucv_callback_connrej, + .message_pending = iucv_callback_rx, + .message_complete = iucv_callback_txdone, + .path_quiesced = iucv_callback_shutdown, +}; + /***************** HiperSockets transport callbacks ********************/ static void afiucv_swap_src_dest(struct sk_buff *skb) { diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 6201965bd822..11a715d76a4f 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -47,7 +47,7 @@ static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb) static void report_csk_error(struct sock *csk, int err) { csk->sk_err = EPIPE; - csk->sk_error_report(csk); + sk_error_report(csk); } static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, diff --git a/net/key/af_key.c b/net/key/af_key.c index ef9b4ac03e7b..de24a7d474df 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -141,7 +141,6 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; struct pfkey_sock *pfk; - int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -150,10 +149,9 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, if (protocol != PF_KEY_V2) return -EPROTONOSUPPORT; - err = -ENOMEM; sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto, kern); if (sk == NULL) - goto out; + return -ENOMEM; pfk = pfkey_sk(sk); mutex_init(&pfk->dump_lock); @@ -169,8 +167,6 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, pfkey_insert(sk); return 0; -out: - return err; } static int pfkey_release(struct socket *sock) diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 97ae1255fcb6..b3edafa5fba4 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -488,7 +488,7 @@ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } } - /* We dont need to clone dst here, it is guaranteed to not disappear. + /* We don't need to clone dst here, it is guaranteed to not disappear. * __dev_xmit_skb() might force a refcount if needed. */ skb_dst_set_noref(skb, &rt->dst); @@ -635,7 +635,6 @@ static struct inet_protosw l2tp_ip_protosw = { static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, - .netns_ok = 1, }; static int __init l2tp_ip_init(void) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index aea85f91f059..bf35710127dd 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -226,7 +226,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int /* If the first two bytes are 0xFF03, consider that it is the PPP's * Address and Control fields and skip them. The L2TP module has always * worked this way, although, in theory, the use of these fields should - * be negociated and handled at the PPP layer. These fields are + * be negotiated and handled at the PPP layer. These fields are * constant: 0xFF is the All-Stations Address and 0x03 the Unnumbered * Information command with Poll/Final bit set to zero (RFC 1662). */ diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index 1078e14f1acf..0971ca48ba15 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -80,11 +80,9 @@ static void __lapb_insert_cb(struct lapb_cb *lapb) static struct lapb_cb *__lapb_devtostruct(struct net_device *dev) { - struct list_head *entry; struct lapb_cb *lapb, *use = NULL; - list_for_each(entry, &lapb_list) { - lapb = list_entry(entry, struct lapb_cb, node); + list_for_each_entry(lapb, &lapb_list, node) { if (lapb->dev == dev) { use = lapb; break; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 7a99892e5aba..84cc7733ea66 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1442,6 +1442,38 @@ static void sta_apply_mesh_params(struct ieee80211_local *local, #endif } +static void sta_apply_airtime_params(struct ieee80211_local *local, + struct sta_info *sta, + struct station_parameters *params) +{ + u8 ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + struct airtime_sched_info *air_sched = &local->airtime[ac]; + struct airtime_info *air_info = &sta->airtime[ac]; + struct txq_info *txqi; + u8 tid; + + spin_lock_bh(&air_sched->lock); + for (tid = 0; tid < IEEE80211_NUM_TIDS + 1; tid++) { + if (air_info->weight == params->airtime_weight || + !sta->sta.txq[tid] || + ac != ieee80211_ac_from_tid(tid)) + continue; + + airtime_weight_set(air_info, params->airtime_weight); + + txqi = to_txq_info(sta->sta.txq[tid]); + if (RB_EMPTY_NODE(&txqi->schedule_order)) + continue; + + ieee80211_update_airtime_weight(local, air_sched, + 0, true); + } + spin_unlock_bh(&air_sched->lock); + } +} + static int sta_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) @@ -1629,7 +1661,8 @@ static int sta_apply_parameters(struct ieee80211_local *local, sta_apply_mesh_params(local, sta, params); if (params->airtime_weight) - sta->airtime_weight = params->airtime_weight; + sta_apply_airtime_params(local, sta, params); + /* set the STA state after all sta info from usermode has been set */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) || @@ -1693,15 +1726,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, test_sta_flag(sta, WLAN_STA_ASSOC)) rate_control_rate_init(sta); - err = sta_info_insert_rcu(sta); - if (err) { - rcu_read_unlock(); - return err; - } - - rcu_read_unlock(); - - return 0; + return sta_info_insert(sta); } static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 907bb1f748a1..76fc36a68750 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * mac80211 - channel management + * Copyright 2020 - 2021 Intel Corporation */ #include <linux/nl80211.h> @@ -308,8 +309,8 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, * the max of min required widths of all the interfaces bound to this * channel context. */ -void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) +static u32 _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) { enum nl80211_chan_width max_bw; struct cfg80211_chan_def min_def; @@ -326,7 +327,7 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, ctx->conf.def.width == NL80211_CHAN_WIDTH_16 || ctx->conf.radar_enabled) { ctx->conf.min_def = ctx->conf.def; - return; + return 0; } max_bw = ieee80211_get_chanctx_max_required_bw(local, &ctx->conf); @@ -337,17 +338,21 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, ieee80211_chandef_downgrade(&min_def); if (cfg80211_chandef_identical(&ctx->conf.min_def, &min_def)) - return; + return 0; ctx->conf.min_def = min_def; if (!ctx->driver_present) - return; + return 0; - drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_MIN_WIDTH); + return IEEE80211_CHANCTX_CHANGE_MIN_WIDTH; } +/* calling this function is assuming that station vif is updated to + * lates changes by calling ieee80211_vif_update_chandef + */ static void ieee80211_chan_bw_change(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) + struct ieee80211_chanctx *ctx, + bool narrowed) { struct sta_info *sta; struct ieee80211_supported_band *sband = @@ -366,9 +371,16 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, continue; new_sta_bw = ieee80211_sta_cur_vht_bw(sta); + + /* nothing change */ if (new_sta_bw == sta->sta.bandwidth) continue; + /* vif changed to narrow BW and narrow BW for station wasn't + * requested or vise versa */ + if ((new_sta_bw < sta->sta.bandwidth) == !narrowed) + continue; + sta->sta.bandwidth = new_sta_bw; rate_control_rate_update(local, sband, sta, IEEE80211_RC_BW_CHANGED); @@ -376,21 +388,34 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, rcu_read_unlock(); } -static void ieee80211_change_chanctx(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx, - const struct cfg80211_chan_def *chandef) +/* + * recalc the min required chan width of the channel context, which is + * the max of min required widths of all the interfaces bound to this + * channel context. + */ +void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) { - enum nl80211_chan_width width; + u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx); - if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) { - ieee80211_recalc_chanctx_min_def(local, ctx); + if (!changed) return; - } - WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef)); + /* check is BW narrowed */ + ieee80211_chan_bw_change(local, ctx, true); - width = ctx->conf.def.width; - ctx->conf.def = *chandef; + drv_change_chanctx(local, ctx, changed); + + /* check is BW wider */ + ieee80211_chan_bw_change(local, ctx, false); +} + +static void ieee80211_change_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_chanctx *old_ctx, + const struct cfg80211_chan_def *chandef) +{ + u32 changed; /* expected to handle only 20/40/80/160 channel widths */ switch (chandef->width) { @@ -405,19 +430,33 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, WARN_ON(1); } - if (chandef->width < width) - ieee80211_chan_bw_change(local, ctx); + /* Check maybe BW narrowed - we do this _before_ calling recalc_chanctx_min_def + * due to maybe not returning from it, e.g in case new context was added + * first time with all parameters up to date. + */ + ieee80211_chan_bw_change(local, old_ctx, true); + + if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) { + ieee80211_recalc_chanctx_min_def(local, ctx); + return; + } - drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_WIDTH); - ieee80211_recalc_chanctx_min_def(local, ctx); + WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef)); + + ctx->conf.def = *chandef; + + /* check if min chanctx also changed */ + changed = IEEE80211_CHANCTX_CHANGE_WIDTH | + _ieee80211_recalc_chanctx_min_def(local, ctx); + drv_change_chanctx(local, ctx, changed); if (!local->use_chanctx) { local->_oper_chandef = *chandef; ieee80211_hw_config(local, 0); } - if (chandef->width > width) - ieee80211_chan_bw_change(local, ctx); + /* check is BW wider */ + ieee80211_chan_bw_change(local, old_ctx, false); } static struct ieee80211_chanctx * @@ -450,7 +489,7 @@ ieee80211_find_chanctx(struct ieee80211_local *local, if (!compat) continue; - ieee80211_change_chanctx(local, ctx, compat); + ieee80211_change_chanctx(local, ctx, ctx, compat); return ctx; } @@ -679,7 +718,7 @@ void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, if (!compat) return; - ieee80211_change_chanctx(local, ctx, compat); + ieee80211_change_chanctx(local, ctx, ctx, compat); } static void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local, @@ -1107,13 +1146,12 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata) if (WARN_ON(!chandef)) return -EINVAL; - if (old_ctx->conf.def.width > new_ctx->conf.def.width) - ieee80211_chan_bw_change(local, new_ctx); + if (sdata->vif.bss_conf.chandef.width != sdata->reserved_chandef.width) + changed = BSS_CHANGED_BANDWIDTH; - ieee80211_change_chanctx(local, new_ctx, chandef); + ieee80211_vif_update_chandef(sdata, &sdata->reserved_chandef); - if (old_ctx->conf.def.width < new_ctx->conf.def.width) - ieee80211_chan_bw_change(local, new_ctx); + ieee80211_change_chanctx(local, new_ctx, old_ctx, chandef); vif_chsw[0].vif = &sdata->vif; vif_chsw[0].old_ctx = &old_ctx->conf; @@ -1142,14 +1180,9 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata) if (ieee80211_chanctx_refcount(local, old_ctx) == 0) ieee80211_free_chanctx(local, old_ctx); - if (sdata->vif.bss_conf.chandef.width != sdata->reserved_chandef.width) - changed = BSS_CHANGED_BANDWIDTH; - - ieee80211_vif_update_chandef(sdata, &sdata->reserved_chandef); - + ieee80211_recalc_chanctx_min_def(local, new_ctx); ieee80211_recalc_smps_chanctx(local, new_ctx); ieee80211_recalc_radar_chanctx(local, new_ctx); - ieee80211_recalc_chanctx_min_def(local, new_ctx); if (changed) ieee80211_bss_info_change_notify(sdata, changed); @@ -1188,7 +1221,7 @@ ieee80211_vif_use_reserved_assign(struct ieee80211_sub_if_data *sdata) if (WARN_ON(!chandef)) return -EINVAL; - ieee80211_change_chanctx(local, new_ctx, chandef); + ieee80211_change_chanctx(local, new_ctx, new_ctx, chandef); list_del(&sdata->reserved_chanctx_list); sdata->reserved_chanctx = NULL; @@ -1505,7 +1538,6 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) ieee80211_recalc_smps_chanctx(local, ctx); ieee80211_recalc_radar_chanctx(local, ctx); ieee80211_recalc_chanctx_min_def(local, ctx); - ieee80211_chan_bw_change(local, ctx); list_for_each_entry_safe(sdata, sdata_tmp, &ctx->reserved_vifs, reserved_chanctx_list) { diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index fc34ae2b604c..8dbfe325ee66 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -216,14 +216,14 @@ static ssize_t aql_txq_limit_read(struct file *file, "VI %u %u\n" "BE %u %u\n" "BK %u %u\n", - local->aql_txq_limit_low[IEEE80211_AC_VO], - local->aql_txq_limit_high[IEEE80211_AC_VO], - local->aql_txq_limit_low[IEEE80211_AC_VI], - local->aql_txq_limit_high[IEEE80211_AC_VI], - local->aql_txq_limit_low[IEEE80211_AC_BE], - local->aql_txq_limit_high[IEEE80211_AC_BE], - local->aql_txq_limit_low[IEEE80211_AC_BK], - local->aql_txq_limit_high[IEEE80211_AC_BK]); + local->airtime[IEEE80211_AC_VO].aql_txq_limit_low, + local->airtime[IEEE80211_AC_VO].aql_txq_limit_high, + local->airtime[IEEE80211_AC_VI].aql_txq_limit_low, + local->airtime[IEEE80211_AC_VI].aql_txq_limit_high, + local->airtime[IEEE80211_AC_BE].aql_txq_limit_low, + local->airtime[IEEE80211_AC_BE].aql_txq_limit_high, + local->airtime[IEEE80211_AC_BK].aql_txq_limit_low, + local->airtime[IEEE80211_AC_BK].aql_txq_limit_high); return simple_read_from_buffer(user_buf, count, ppos, buf, len); } @@ -255,11 +255,11 @@ static ssize_t aql_txq_limit_write(struct file *file, if (ac >= IEEE80211_NUM_ACS) return -EINVAL; - q_limit_low_old = local->aql_txq_limit_low[ac]; - q_limit_high_old = local->aql_txq_limit_high[ac]; + q_limit_low_old = local->airtime[ac].aql_txq_limit_low; + q_limit_high_old = local->airtime[ac].aql_txq_limit_high; - local->aql_txq_limit_low[ac] = q_limit_low; - local->aql_txq_limit_high[ac] = q_limit_high; + local->airtime[ac].aql_txq_limit_low = q_limit_low; + local->airtime[ac].aql_txq_limit_high = q_limit_high; mutex_lock(&local->sta_mtx); list_for_each_entry(sta, &local->sta_list, list) { @@ -382,6 +382,46 @@ static const struct file_operations force_tx_status_ops = { .llseek = default_llseek, }; +static ssize_t airtime_read(struct file *file, + char __user *user_buf, + size_t count, + loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + char buf[200]; + u64 v_t[IEEE80211_NUM_ACS]; + u64 wt[IEEE80211_NUM_ACS]; + int len = 0, ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->airtime[ac].lock); + v_t[ac] = local->airtime[ac].v_t; + wt[ac] = local->airtime[ac].weight_sum; + spin_unlock_bh(&local->airtime[ac].lock); + } + len = scnprintf(buf, sizeof(buf), + "\tVO VI BE BK\n" + "Virt-t\t%-10llu %-10llu %-10llu %-10llu\n" + "Weight\t%-10llu %-10llu %-10llu %-10llu\n", + v_t[0], + v_t[1], + v_t[2], + v_t[3], + wt[0], + wt[1], + wt[2], + wt[3]); + + return simple_read_from_buffer(user_buf, count, ppos, + buf, len); +} + +static const struct file_operations airtime_ops = { + .read = airtime_read, + .open = simple_open, + .llseek = default_llseek, +}; + #ifdef CONFIG_PM static ssize_t reset_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) @@ -632,7 +672,11 @@ void debugfs_hw_add(struct ieee80211_local *local) if (local->ops->wake_tx_queue) DEBUGFS_ADD_MODE(aqm, 0600); - DEBUGFS_ADD_MODE(airtime_flags, 0600); + if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) { + DEBUGFS_ADD_MODE(airtime, 0600); + DEBUGFS_ADD_MODE(airtime_flags, 0600); + } DEBUGFS_ADD(aql_txq_limit); debugfs_create_u32("aql_threshold", 0600, diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 0ad3860852ff..db724fc10a5f 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -57,7 +57,6 @@ static ssize_t ieee80211_if_write( return -EFAULT; buf[count] = '\0'; - ret = -ENODEV; rtnl_lock(); ret = (*write)(sdata, buf, count); rtnl_unlock(); @@ -513,6 +512,34 @@ static ssize_t ieee80211_if_fmt_aqm( } IEEE80211_IF_FILE_R(aqm); +static ssize_t ieee80211_if_fmt_airtime( + const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_txq *txq = sdata->vif.txq; + struct airtime_info *air_info; + int len; + + if (!txq) + return 0; + + spin_lock_bh(&local->airtime[txq->ac].lock); + air_info = to_airtime_info(txq); + len = scnprintf(buf, + buflen, + "RX: %llu us\nTX: %llu us\nWeight: %u\n" + "Virt-T: %lld us\n", + air_info->rx_airtime, + air_info->tx_airtime, + air_info->weight, + air_info->v_t); + spin_unlock_bh(&local->airtime[txq->ac].lock); + + return len; +} + +IEEE80211_IF_FILE_R(airtime); + IEEE80211_IF_FILE(multicast_to_unicast, u.ap.multicast_to_unicast, HEX); /* IBSS attributes */ @@ -658,8 +685,10 @@ static void add_common_files(struct ieee80211_sub_if_data *sdata) if (sdata->local->ops->wake_tx_queue && sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && - sdata->vif.type != NL80211_IFTYPE_NAN) + sdata->vif.type != NL80211_IFTYPE_NAN) { DEBUGFS_ADD(aqm); + DEBUGFS_ADD(airtime); + } } static void add_sta_files(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 936c9dfa86c8..8be28cfd6f64 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -202,7 +202,7 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, size_t bufsz = 400; char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; u64 rx_airtime = 0, tx_airtime = 0; - s64 deficit[IEEE80211_NUM_ACS]; + u64 v_t[IEEE80211_NUM_ACS]; ssize_t rv; int ac; @@ -210,18 +210,18 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, return -ENOMEM; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - spin_lock_bh(&local->active_txq_lock[ac]); + spin_lock_bh(&local->airtime[ac].lock); rx_airtime += sta->airtime[ac].rx_airtime; tx_airtime += sta->airtime[ac].tx_airtime; - deficit[ac] = sta->airtime[ac].deficit; - spin_unlock_bh(&local->active_txq_lock[ac]); + v_t[ac] = sta->airtime[ac].v_t; + spin_unlock_bh(&local->airtime[ac].lock); } p += scnprintf(p, bufsz + buf - p, "RX: %llu us\nTX: %llu us\nWeight: %u\n" - "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", - rx_airtime, tx_airtime, sta->airtime_weight, - deficit[0], deficit[1], deficit[2], deficit[3]); + "Virt-T: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", + rx_airtime, tx_airtime, sta->airtime[0].weight, + v_t[0], v_t[1], v_t[2], v_t[3]); rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); @@ -236,11 +236,11 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, int ac; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - spin_lock_bh(&local->active_txq_lock[ac]); + spin_lock_bh(&local->airtime[ac].lock); sta->airtime[ac].rx_airtime = 0; sta->airtime[ac].tx_airtime = 0; - sta->airtime[ac].deficit = sta->airtime_weight; - spin_unlock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].v_t = 0; + spin_unlock_bh(&local->airtime[ac].lock); } return count; @@ -263,10 +263,10 @@ static ssize_t sta_aql_read(struct file *file, char __user *userbuf, return -ENOMEM; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - spin_lock_bh(&local->active_txq_lock[ac]); + spin_lock_bh(&local->airtime[ac].lock); q_limit_l[ac] = sta->airtime[ac].aql_limit_low; q_limit_h[ac] = sta->airtime[ac].aql_limit_high; - spin_unlock_bh(&local->active_txq_lock[ac]); + spin_unlock_bh(&local->airtime[ac].lock); q_depth[ac] = atomic_read(&sta->airtime[ac].aql_tx_pending); } diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 604ca59937f0..bcb7cc06db3d 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -2,7 +2,7 @@ /* * Portions of this file * Copyright(c) 2016 Intel Deutschland GmbH -* Copyright (C) 2018 - 2019 Intel Corporation +* Copyright (C) 2018 - 2019, 2021 Intel Corporation */ #ifndef __MAC80211_DRIVER_OPS @@ -821,7 +821,7 @@ 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, - u16 duration) + struct ieee80211_prep_tx_info *info) { might_sleep(); @@ -829,9 +829,27 @@ 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, duration); + trace_drv_mgd_prepare_tx(local, sdata, info->duration, + info->subtype, info->success); if (local->ops->mgd_prepare_tx) - local->ops->mgd_prepare_tx(&local->hw, &sdata->vif, duration); + local->ops->mgd_prepare_tx(&local->hw, &sdata->vif, info); + trace_drv_return_void(local); +} + +static inline void drv_mgd_complete_tx(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_prep_tx_info *info) +{ + might_sleep(); + + if (!check_sdata_in_driver(sdata)) + return; + WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION); + + trace_drv_mgd_complete_tx(local, sdata, info->duration, + info->subtype, info->success); + if (local->ops->mgd_complete_tx) + local->ops->mgd_complete_tx(&local->hw, &sdata->vif, info); trace_drv_return_void(local); } diff --git a/net/mac80211/he.c b/net/mac80211/he.c index 0c0b970835ce..c05af7018f79 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -111,7 +111,7 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap; - struct ieee80211_sta_he_cap own_he_cap = sband->iftype_data->he_cap; + struct ieee80211_sta_he_cap own_he_cap; struct ieee80211_he_cap_elem *he_cap_ie_elem = (void *)he_cap_ie; u8 he_ppe_size; u8 mcs_nss_size; @@ -120,9 +120,13 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, memset(he_cap, 0, sizeof(*he_cap)); - if (!he_cap_ie || !ieee80211_get_he_sta_cap(sband)) + if (!he_cap_ie || + !ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif))) return; + own_he_cap = sband->iftype_data->he_cap; + /* Make sure size is OK */ mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap_ie_elem); he_ppe_size = diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 3d62a80b5790..2eb7641f5556 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright 2017 Intel Deutschland GmbH - * Copyright(c) 2020 Intel Corporation + * Copyright(c) 2020-2021 Intel Corporation */ #include <linux/ieee80211.h> @@ -555,17 +555,15 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); - if (WARN_ON_ONCE(vif->type != NL80211_IFTYPE_STATION && - vif->type != NL80211_IFTYPE_AP)) + if (WARN_ON_ONCE(vif->type != NL80211_IFTYPE_STATION)) return; - if (vif->type == NL80211_IFTYPE_STATION) { - if (sdata->u.mgd.driver_smps_mode == smps_mode) - return; - sdata->u.mgd.driver_smps_mode = smps_mode; - ieee80211_queue_work(&sdata->local->hw, - &sdata->u.mgd.request_smps_work); - } + if (sdata->u.mgd.driver_smps_mode == smps_mode) + return; + + sdata->u.mgd.driver_smps_mode = smps_mode; + ieee80211_queue_work(&sdata->local->hw, + &sdata->u.mgd.request_smps_work); } /* this might change ... don't want non-open drivers using it */ EXPORT_SYMBOL_GPL(ieee80211_request_smps); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 648696b49f89..22549b95d1aa 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2015 Intel Mobile Communications GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #ifndef IEEE80211_I_H @@ -831,17 +831,16 @@ enum txq_info_flags { * @def_flow: used as a fallback flow when a packet destined to @tin hashes to * a fq_flow which is already owned by a different tin * @def_cvars: codel vars for @def_flow - * @frags: used to keep fragments created after dequeue * @schedule_order: used with ieee80211_local->active_txqs - * @schedule_round: counter to prevent infinite loops on TXQ scheduling + * @frags: used to keep fragments created after dequeue */ struct txq_info { struct fq_tin tin; struct codel_vars def_cvars; struct codel_stats cstats; + struct rb_node schedule_order; + struct sk_buff_head frags; - struct list_head schedule_order; - u16 schedule_round; unsigned long flags; /* keep last! */ @@ -918,6 +917,8 @@ struct ieee80211_sub_if_data { struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS]; struct mac80211_qos_map __rcu *qos_map; + struct airtime_info airtime[IEEE80211_NUM_ACS]; + struct work_struct csa_finalize_work; bool csa_block_tx; /* write-protected by sdata_lock and local->mtx */ struct cfg80211_chan_def csa_chandef; @@ -1130,6 +1131,44 @@ enum mac80211_scan_state { SCAN_ABORT, }; +/** + * struct airtime_sched_info - state used for airtime scheduling and AQL + * + * @lock: spinlock that protects all the fields in this struct + * @active_txqs: rbtree of currently backlogged queues, sorted by virtual time + * @schedule_pos: the current position maintained while a driver walks the tree + * with ieee80211_next_txq() + * @active_list: list of struct airtime_info structs that were active within + * the last AIRTIME_ACTIVE_DURATION (100 ms), used to compute + * weight_sum + * @last_weight_update: used for rate limiting walking active_list + * @last_schedule_time: tracks the last time a transmission was scheduled; used + * for catching up v_t if no stations are eligible for + * transmission. + * @v_t: global virtual time; queues with v_t < this are eligible for + * transmission + * @weight_sum: total sum of all active stations used for dividing airtime + * @weight_sum_reciprocal: reciprocal of weight_sum (to avoid divisions in fast + * path - see comment above + * IEEE80211_RECIPROCAL_DIVISOR_64) + * @aql_txq_limit_low: AQL limit when total outstanding airtime + * is < IEEE80211_AQL_THRESHOLD + * @aql_txq_limit_high: AQL limit when total outstanding airtime + * is > IEEE80211_AQL_THRESHOLD + */ +struct airtime_sched_info { + spinlock_t lock; + struct rb_root_cached active_txqs; + struct rb_node *schedule_pos; + struct list_head active_list; + u64 last_weight_update; + u64 last_schedule_activity; + u64 v_t; + u64 weight_sum; + u64 weight_sum_reciprocal; + u32 aql_txq_limit_low; + u32 aql_txq_limit_high; +}; DECLARE_STATIC_KEY_FALSE(aql_disable); struct ieee80211_local { @@ -1143,13 +1182,8 @@ struct ieee80211_local { struct codel_params cparams; /* protects active_txqs and txqi->schedule_order */ - spinlock_t active_txq_lock[IEEE80211_NUM_ACS]; - struct list_head active_txqs[IEEE80211_NUM_ACS]; - u16 schedule_round[IEEE80211_NUM_ACS]; - + struct airtime_sched_info airtime[IEEE80211_NUM_ACS]; u16 airtime_flags; - u32 aql_txq_limit_low[IEEE80211_NUM_ACS]; - u32 aql_txq_limit_high[IEEE80211_NUM_ACS]; u32 aql_threshold; atomic_t aql_total_pending_airtime; @@ -1414,10 +1448,6 @@ struct ieee80211_local { /* extended capabilities provided by mac80211 */ u8 ext_capa[8]; - - /* TDLS channel switch */ - struct work_struct tdls_chsw_work; - struct sk_buff_head skb_queue_tdls_chsw; }; static inline struct ieee80211_sub_if_data * @@ -1567,6 +1597,125 @@ static inline bool txq_has_queue(struct ieee80211_txq *txq) return !(skb_queue_empty(&txqi->frags) && !txqi->tin.backlog_packets); } +static inline struct airtime_info *to_airtime_info(struct ieee80211_txq *txq) +{ + struct ieee80211_sub_if_data *sdata; + struct sta_info *sta; + + if (txq->sta) { + sta = container_of(txq->sta, struct sta_info, sta); + return &sta->airtime[txq->ac]; + } + + sdata = vif_to_sdata(txq->vif); + return &sdata->airtime[txq->ac]; +} + +/* To avoid divisions in the fast path, we keep pre-computed reciprocals for + * airtime weight calculations. There are two different weights to keep track + * of: The per-station weight and the sum of weights per phy. + * + * For the per-station weights (kept in airtime_info below), we use 32-bit + * reciprocals with a devisor of 2^19. This lets us keep the multiplications and + * divisions for the station weights as 32-bit operations at the cost of a bit + * of rounding error for high weights; but the choice of divisor keeps rounding + * errors <10% for weights <2^15, assuming no more than 8ms of airtime is + * reported at a time. + * + * For the per-phy sum of weights the values can get higher, so we use 64-bit + * operations for those with a 32-bit divisor, which should avoid any + * significant rounding errors. + */ +#define IEEE80211_RECIPROCAL_DIVISOR_64 0x100000000ULL +#define IEEE80211_RECIPROCAL_SHIFT_64 32 +#define IEEE80211_RECIPROCAL_DIVISOR_32 0x80000U +#define IEEE80211_RECIPROCAL_SHIFT_32 19 + +static inline void airtime_weight_set(struct airtime_info *air_info, u16 weight) +{ + if (air_info->weight == weight) + return; + + air_info->weight = weight; + if (weight) { + air_info->weight_reciprocal = + IEEE80211_RECIPROCAL_DIVISOR_32 / weight; + } else { + air_info->weight_reciprocal = 0; + } +} + +static inline void airtime_weight_sum_set(struct airtime_sched_info *air_sched, + int weight_sum) +{ + if (air_sched->weight_sum == weight_sum) + return; + + air_sched->weight_sum = weight_sum; + if (air_sched->weight_sum) { + air_sched->weight_sum_reciprocal = IEEE80211_RECIPROCAL_DIVISOR_64; + do_div(air_sched->weight_sum_reciprocal, air_sched->weight_sum); + } else { + air_sched->weight_sum_reciprocal = 0; + } +} + +/* A problem when trying to enforce airtime fairness is that we want to divide + * the airtime between the currently *active* stations. However, basing this on + * the instantaneous queue state of stations doesn't work, as queues tend to + * oscillate very quickly between empty and occupied, leading to the scheduler + * thinking only a single station is active when deciding whether to allow + * transmission (and thus not throttling correctly). + * + * To fix this we use a timer-based notion of activity: a station is considered + * active if it has been scheduled within the last 100 ms; we keep a separate + * list of all the stations considered active in this manner, and lazily update + * the total weight of active stations from this list (filtering the stations in + * the list by their 'last active' time). + * + * We add one additional safeguard to guard against stations that manage to get + * scheduled every 100 ms but don't transmit a lot of data, and thus don't use + * up any airtime. Such stations would be able to get priority for an extended + * period of time if they do start transmitting at full capacity again, and so + * we add an explicit maximum for how far behind a station is allowed to fall in + * the virtual airtime domain. This limit is set to a relatively high value of + * 20 ms because the main mechanism for catching up idle stations is the active + * state as described above; i.e., the hard limit should only be hit in + * pathological cases. + */ +#define AIRTIME_ACTIVE_DURATION (100 * NSEC_PER_MSEC) +#define AIRTIME_MAX_BEHIND 20000 /* 20 ms */ + +static inline bool airtime_is_active(struct airtime_info *air_info, u64 now) +{ + return air_info->last_scheduled >= now - AIRTIME_ACTIVE_DURATION; +} + +static inline void airtime_set_active(struct airtime_sched_info *air_sched, + struct airtime_info *air_info, u64 now) +{ + air_info->last_scheduled = now; + air_sched->last_schedule_activity = now; + list_move_tail(&air_info->list, &air_sched->active_list); +} + +static inline bool airtime_catchup_v_t(struct airtime_sched_info *air_sched, + u64 v_t, u64 now) +{ + air_sched->v_t = v_t; + return true; +} + +static inline void init_airtime_info(struct airtime_info *air_info, + struct airtime_sched_info *air_sched) +{ + atomic_set(&air_info->aql_tx_pending, 0); + air_info->aql_limit_low = air_sched->aql_txq_limit_low; + air_info->aql_limit_high = air_sched->aql_txq_limit_high; + airtime_weight_set(air_info, IEEE80211_DEFAULT_AIRTIME_WEIGHT); + INIT_LIST_HEAD(&air_info->list); +} + static inline int ieee80211_bssid_match(const u8 *raddr, const u8 *addr) { return ether_addr_equal(raddr, addr) || @@ -1809,6 +1958,14 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, u64 *cookie); int ieee80211_probe_mesh_link(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len); +void ieee80211_resort_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq); +void ieee80211_unschedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, + bool purge); +void ieee80211_update_airtime_weight(struct ieee80211_local *local, + struct airtime_sched_info *air_sched, + u64 now, bool force); /* HT */ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, @@ -1879,7 +2036,6 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta); enum ieee80211_sta_rx_bandwidth ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width); enum nl80211_chan_width ieee80211_sta_cap_chan_bw(struct sta_info *sta); -void ieee80211_sta_set_rx_nss(struct sta_info *sta); void ieee80211_process_mu_groups(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt); u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, @@ -2287,9 +2443,13 @@ void ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy, struct net_device *dev, const u8 *addr); void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata); -void ieee80211_tdls_chsw_work(struct work_struct *wk); void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata, const u8 *peer, u16 reason); +void +ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb); + + const char *ieee80211_get_reason_code_string(u16 reason_code); u16 ieee80211_encode_usf(int val); u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 137fa4c50e07..1e5e9fc45523 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1318,13 +1318,130 @@ static void ieee80211_if_setup_no_queue(struct net_device *dev) dev->priv_flags |= IFF_NO_QUEUE; } +static void ieee80211_iface_process_skb(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (void *)skb->data; + + if (ieee80211_is_action(mgmt->frame_control) && + mgmt->u.action.category == WLAN_CATEGORY_BACK) { + struct sta_info *sta; + int len = skb->len; + + mutex_lock(&local->sta_mtx); + sta = sta_info_get_bss(sdata, mgmt->sa); + if (sta) { + switch (mgmt->u.action.u.addba_req.action_code) { + case WLAN_ACTION_ADDBA_REQ: + ieee80211_process_addba_request(local, sta, + mgmt, len); + break; + case WLAN_ACTION_ADDBA_RESP: + ieee80211_process_addba_resp(local, sta, + mgmt, len); + break; + case WLAN_ACTION_DELBA: + ieee80211_process_delba(sdata, sta, + mgmt, len); + break; + default: + WARN_ON(1); + break; + } + } + mutex_unlock(&local->sta_mtx); + } else if (ieee80211_is_action(mgmt->frame_control) && + mgmt->u.action.category == WLAN_CATEGORY_VHT) { + switch (mgmt->u.action.u.vht_group_notif.action_code) { + case WLAN_VHT_ACTION_OPMODE_NOTIF: { + struct ieee80211_rx_status *status; + enum nl80211_band band; + struct sta_info *sta; + u8 opmode; + + status = IEEE80211_SKB_RXCB(skb); + band = status->band; + opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode; + + mutex_lock(&local->sta_mtx); + sta = sta_info_get_bss(sdata, mgmt->sa); + + if (sta) + ieee80211_vht_handle_opmode(sdata, sta, opmode, + band); + + mutex_unlock(&local->sta_mtx); + break; + } + case WLAN_VHT_ACTION_GROUPID_MGMT: + ieee80211_process_mu_groups(sdata, mgmt); + break; + default: + WARN_ON(1); + break; + } + } else if (ieee80211_is_ext(mgmt->frame_control)) { + if (sdata->vif.type == NL80211_IFTYPE_STATION) + ieee80211_sta_rx_queued_ext(sdata, skb); + else + WARN_ON(1); + } else if (ieee80211_is_data_qos(mgmt->frame_control)) { + struct ieee80211_hdr *hdr = (void *)mgmt; + struct sta_info *sta; + + /* + * So the frame isn't mgmt, but frame_control + * is at the right place anyway, of course, so + * the if statement is correct. + * + * Warn if we have other data frame types here, + * they must not get here. + */ + WARN_ON(hdr->frame_control & + cpu_to_le16(IEEE80211_STYPE_NULLFUNC)); + WARN_ON(!(hdr->seq_ctrl & + cpu_to_le16(IEEE80211_SCTL_FRAG))); + /* + * This was a fragment of a frame, received while + * a block-ack session was active. That cannot be + * right, so terminate the session. + */ + mutex_lock(&local->sta_mtx); + sta = sta_info_get_bss(sdata, mgmt->sa); + if (sta) { + u16 tid = ieee80211_get_tid(hdr); + + __ieee80211_stop_rx_ba_session( + sta, tid, WLAN_BACK_RECIPIENT, + WLAN_REASON_QSTA_REQUIRE_SETUP, + true); + } + mutex_unlock(&local->sta_mtx); + } else switch (sdata->vif.type) { + case NL80211_IFTYPE_STATION: + ieee80211_sta_rx_queued_mgmt(sdata, skb); + break; + case NL80211_IFTYPE_ADHOC: + ieee80211_ibss_rx_queued_mgmt(sdata, skb); + break; + case NL80211_IFTYPE_MESH_POINT: + if (!ieee80211_vif_is_mesh(&sdata->vif)) + break; + ieee80211_mesh_rx_queued_mgmt(sdata, skb); + break; + default: + WARN(1, "frame for unexpected interface type"); + break; + } +} + static void ieee80211_iface_work(struct work_struct *work) { struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, work); struct ieee80211_local *local = sdata->local; struct sk_buff *skb; - struct sta_info *sta; if (!ieee80211_sdata_running(sdata)) return; @@ -1337,116 +1454,12 @@ static void ieee80211_iface_work(struct work_struct *work) /* first process frames */ while ((skb = skb_dequeue(&sdata->skb_queue))) { - struct ieee80211_mgmt *mgmt = (void *)skb->data; - kcov_remote_start_common(skb_get_kcov_handle(skb)); - if (ieee80211_is_action(mgmt->frame_control) && - mgmt->u.action.category == WLAN_CATEGORY_BACK) { - int len = skb->len; - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, mgmt->sa); - if (sta) { - switch (mgmt->u.action.u.addba_req.action_code) { - case WLAN_ACTION_ADDBA_REQ: - ieee80211_process_addba_request( - local, sta, mgmt, len); - break; - case WLAN_ACTION_ADDBA_RESP: - ieee80211_process_addba_resp(local, sta, - mgmt, len); - break; - case WLAN_ACTION_DELBA: - ieee80211_process_delba(sdata, sta, - mgmt, len); - break; - default: - WARN_ON(1); - break; - } - } - mutex_unlock(&local->sta_mtx); - } else if (ieee80211_is_action(mgmt->frame_control) && - mgmt->u.action.category == WLAN_CATEGORY_VHT) { - switch (mgmt->u.action.u.vht_group_notif.action_code) { - case WLAN_VHT_ACTION_OPMODE_NOTIF: { - struct ieee80211_rx_status *status; - enum nl80211_band band; - u8 opmode; - - status = IEEE80211_SKB_RXCB(skb); - band = status->band; - opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode; - - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, mgmt->sa); - - if (sta) - ieee80211_vht_handle_opmode(sdata, sta, - opmode, - band); - - mutex_unlock(&local->sta_mtx); - break; - } - case WLAN_VHT_ACTION_GROUPID_MGMT: - ieee80211_process_mu_groups(sdata, mgmt); - break; - default: - WARN_ON(1); - break; - } - } else if (ieee80211_is_ext(mgmt->frame_control)) { - if (sdata->vif.type == NL80211_IFTYPE_STATION) - ieee80211_sta_rx_queued_ext(sdata, skb); - else - WARN_ON(1); - } else if (ieee80211_is_data_qos(mgmt->frame_control)) { - struct ieee80211_hdr *hdr = (void *)mgmt; - /* - * So the frame isn't mgmt, but frame_control - * is at the right place anyway, of course, so - * the if statement is correct. - * - * Warn if we have other data frame types here, - * they must not get here. - */ - WARN_ON(hdr->frame_control & - cpu_to_le16(IEEE80211_STYPE_NULLFUNC)); - WARN_ON(!(hdr->seq_ctrl & - cpu_to_le16(IEEE80211_SCTL_FRAG))); - /* - * This was a fragment of a frame, received while - * a block-ack session was active. That cannot be - * right, so terminate the session. - */ - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, mgmt->sa); - if (sta) { - u16 tid = ieee80211_get_tid(hdr); - - __ieee80211_stop_rx_ba_session( - sta, tid, WLAN_BACK_RECIPIENT, - WLAN_REASON_QSTA_REQUIRE_SETUP, - true); - } - mutex_unlock(&local->sta_mtx); - } else switch (sdata->vif.type) { - case NL80211_IFTYPE_STATION: - ieee80211_sta_rx_queued_mgmt(sdata, skb); - break; - case NL80211_IFTYPE_ADHOC: - ieee80211_ibss_rx_queued_mgmt(sdata, skb); - break; - case NL80211_IFTYPE_MESH_POINT: - if (!ieee80211_vif_is_mesh(&sdata->vif)) - break; - ieee80211_mesh_rx_queued_mgmt(sdata, skb); - break; - default: - WARN(1, "frame for unexpected interface type"); - break; - } + if (skb->protocol == cpu_to_be16(ETH_P_TDLS)) + ieee80211_process_tdls_channel_switch(sdata, skb); + else + ieee80211_iface_process_skb(local, sdata, skb); kfree_skb(skb); kcov_remote_stop(); @@ -1964,6 +1977,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, } } + for (i = 0; i < IEEE80211_NUM_ACS; i++) + init_airtime_info(&sdata->airtime[i], &local->airtime[i]); + ieee80211_set_default_queues(sdata); sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL; diff --git a/net/mac80211/led.c b/net/mac80211/led.c index b275c8853074..6de8d0ad5497 100644 --- a/net/mac80211/led.c +++ b/net/mac80211/led.c @@ -259,7 +259,6 @@ static void tpt_trig_timer(struct timer_list *t) { struct tpt_led_trigger *tpt_trig = from_timer(tpt_trig, t, timer); struct ieee80211_local *local = tpt_trig->local; - struct led_classdev *led_cdev; unsigned long on, off, tpt; int i; @@ -283,10 +282,7 @@ static void tpt_trig_timer(struct timer_list *t) } } - read_lock(&local->tpt_led.leddev_list_lock); - list_for_each_entry(led_cdev, &local->tpt_led.led_cdevs, trig_list) - led_blink_set(led_cdev, &on, &off); - read_unlock(&local->tpt_led.leddev_list_lock); + led_trigger_blink(&local->tpt_led, &on, &off); } const char * @@ -341,7 +337,6 @@ static void ieee80211_start_tpt_led_trig(struct ieee80211_local *local) static void ieee80211_stop_tpt_led_trig(struct ieee80211_local *local) { struct tpt_led_trigger *tpt_trig = local->tpt_led_trigger; - struct led_classdev *led_cdev; if (!tpt_trig->running) return; @@ -349,10 +344,7 @@ static void ieee80211_stop_tpt_led_trig(struct ieee80211_local *local) tpt_trig->running = false; del_timer_sync(&tpt_trig->timer); - read_lock(&local->tpt_led.leddev_list_lock); - list_for_each_entry(led_cdev, &local->tpt_led.led_cdevs, trig_list) - led_set_brightness(led_cdev, LED_OFF); - read_unlock(&local->tpt_led.leddev_list_lock); + led_trigger_event(&local->tpt_led, LED_OFF); } void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index f33a3acd7f96..05f4c3c72619 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -257,14 +257,13 @@ static void ieee80211_restart_work(struct work_struct *work) /* wait for scan work complete */ flush_workqueue(local->workqueue); flush_work(&local->sched_scan_stopped_work); + flush_work(&local->radar_detected_work); + + rtnl_lock(); WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), "%s called with hardware scan in progress\n", __func__); - flush_work(&local->radar_detected_work); - /* we might do interface manipulations, so need both */ - rtnl_lock(); - wiphy_lock(local->hw.wiphy); list_for_each_entry(sdata, &local->interfaces, list) { /* * XXX: there may be more work for other vif types and even @@ -706,10 +705,13 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, spin_lock_init(&local->queue_stop_reason_lock); for (i = 0; i < IEEE80211_NUM_ACS; i++) { - INIT_LIST_HEAD(&local->active_txqs[i]); - spin_lock_init(&local->active_txq_lock[i]); - local->aql_txq_limit_low[i] = IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L; - local->aql_txq_limit_high[i] = + struct airtime_sched_info *air_sched = &local->airtime[i]; + + air_sched->active_txqs = RB_ROOT_CACHED; + INIT_LIST_HEAD(&air_sched->active_list); + spin_lock_init(&air_sched->lock); + air_sched->aql_txq_limit_low = IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L; + air_sched->aql_txq_limit_high = IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H; } @@ -739,8 +741,6 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, INIT_WORK(&local->sched_scan_stopped_work, ieee80211_sched_scan_stopped_work); - INIT_WORK(&local->tdls_chsw_work, ieee80211_tdls_chsw_work); - spin_lock_init(&local->ack_status_lock); idr_init(&local->ack_status_frames); @@ -757,7 +757,6 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, skb_queue_head_init(&local->skb_queue); skb_queue_head_init(&local->skb_queue_unreliable); - skb_queue_head_init(&local->skb_queue_tdls_chsw); ieee80211_alloc_led_names(local); @@ -1014,8 +1013,13 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) supp_ht = supp_ht || sband->ht_cap.ht_supported; supp_vht = supp_vht || sband->vht_cap.vht_supported; - if (!supp_he) - supp_he = !!ieee80211_get_he_sta_cap(sband); + for (i = 0; i < sband->n_iftype_data; i++) { + const struct ieee80211_sband_iftype_data *iftd; + + iftd = &sband->iftype_data[i]; + + supp_he = supp_he || (iftd && iftd->he_cap.has_he); + } /* HT, VHT, HE require QoS, thus >= 4 queues */ if (WARN_ON(local->hw.queues < IEEE80211_NUM_ACS && @@ -1389,7 +1393,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) cancel_delayed_work_sync(&local->roc_work); cancel_work_sync(&local->restart_work); cancel_work_sync(&local->reconfig_filter); - cancel_work_sync(&local->tdls_chsw_work); flush_work(&local->sched_scan_stopped_work); flush_work(&local->radar_detected_work); @@ -1401,7 +1404,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) wiphy_warn(local->hw.wiphy, "skb_queue not empty\n"); skb_queue_purge(&local->skb_queue); skb_queue_purge(&local->skb_queue_unreliable); - skb_queue_purge(&local->skb_queue_tdls_chsw); wiphy_unregister(local->hw.wiphy); destroy_workqueue(local->workqueue); diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 40492d1bd8fd..77080b4f87b8 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -134,7 +134,7 @@ struct mesh_path { * gate's mpath may or may not be resolved and active. * @gates_lock: protects updates to known_gates * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr - * @walk_head: linked list containging all mesh_path objects + * @walk_head: linked list containing all mesh_path objects * @walk_lock: lock protecting walk_head * @entries: number of entries in the table */ diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 3db514c4c63a..a05b615deb51 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1124,7 +1124,7 @@ enddiscovery: * forwarding information is found. * * Returns: 0 if the next hop was found and -ENOENT if the frame was queued. - * skb is freeed here if no mpath could be allocated. + * skb is freed here if no mpath could be allocated. */ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 620ecf922408..efbefcbac3ac 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -122,7 +122,7 @@ static void prepare_for_gate(struct sk_buff *skb, char *dst_addr, hdr = (struct ieee80211_hdr *) skb->data; /* we preserve the previous mesh header and only add - * the new addreses */ + * the new addresses */ mshdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); mshdr->flags = MESH_FLAGS_AE_A5_A6; memcpy(mshdr->eaddr1, hdr->addr3, ETH_ALEN); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index aca26df7587d..a6915847d78a 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -150,7 +150,7 @@ out: * mesh STA in a MBSS. Three HT protection modes are supported for now, non-HT * mixed mode, 20MHz-protection and no-protection mode. non-HT mixed mode is * selected if any non-HT peers are present in our MBSS. 20MHz-protection mode - * is selected if all peers in our 20/40MHz MBSS support HT and atleast one + * is selected if all peers in our 20/40MHz MBSS support HT and at least one * HT20 peer is present. Otherwise no-protection mode is selected. */ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3f2aad2e7436..a00f11a33699 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2020 Intel Corporation + * Copyright (C) 2018 - 2021 Intel Corporation */ #include <linux/delay.h> @@ -371,7 +371,6 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, struct cfg80211_chan_def chandef; u16 ht_opmode; u32 flags; - enum ieee80211_sta_rx_bandwidth new_sta_bw; u32 vht_cap_info = 0; int ret; @@ -385,7 +384,9 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, /* don't check HE if we associated as non-HE station */ if (ifmgd->flags & IEEE80211_STA_DISABLE_HE || - !ieee80211_get_he_sta_cap(sband)) + !ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif))) + he_oper = NULL; if (WARN_ON_ONCE(!sta)) @@ -445,40 +446,13 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, IEEE80211_STA_DISABLE_160MHZ)) || !cfg80211_chandef_valid(&chandef)) { sdata_info(sdata, - "AP %pM changed bandwidth in a way we can't support - disconnect\n", - ifmgd->bssid); - return -EINVAL; - } - - switch (chandef.width) { - case NL80211_CHAN_WIDTH_20_NOHT: - case NL80211_CHAN_WIDTH_20: - new_sta_bw = IEEE80211_STA_RX_BW_20; - break; - case NL80211_CHAN_WIDTH_40: - new_sta_bw = IEEE80211_STA_RX_BW_40; - break; - case NL80211_CHAN_WIDTH_80: - new_sta_bw = IEEE80211_STA_RX_BW_80; - break; - case NL80211_CHAN_WIDTH_80P80: - case NL80211_CHAN_WIDTH_160: - new_sta_bw = IEEE80211_STA_RX_BW_160; - break; - default: + "AP %pM changed caps/bw in a way we can't support (0x%x/0x%x) - disconnect\n", + ifmgd->bssid, flags, ifmgd->flags); return -EINVAL; } - if (new_sta_bw > sta->cur_max_bandwidth) - new_sta_bw = sta->cur_max_bandwidth; - - if (new_sta_bw < sta->sta.bandwidth) { - sta->sta.bandwidth = new_sta_bw; - rate_control_rate_update(local, sband, sta, - IEEE80211_RC_BW_CHANGED); - } - ret = ieee80211_vif_change_bandwidth(sdata, &chandef, changed); + if (ret) { sdata_info(sdata, "AP %pM changed bandwidth to incompatible one - disconnect\n", @@ -486,12 +460,6 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, return ret; } - if (new_sta_bw > sta->sta.bandwidth) { - sta->sta.bandwidth = new_sta_bw; - rate_control_rate_update(local, sband, sta, - IEEE80211_RC_BW_CHANGED); - } - return 0; } @@ -617,7 +585,7 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, cap &= ~IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE; /* - * If some other vif is using the MU-MIMO capablity we cannot associate + * If some other vif is using the MU-MIMO capability we cannot associate * using MU-MIMO - this will lead to contradictions in the group-id * mechanism. * Ownership is defined since association request, in order to avoid @@ -676,7 +644,8 @@ static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); - he_cap = ieee80211_get_he_sta_cap(sband); + he_cap = ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); if (!he_cap || !reg_cap) return; @@ -712,6 +681,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) u32 rates = 0; __le16 listen_int; struct element *ext_capa = NULL; + enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); + const struct ieee80211_sband_iftype_data *iftd; + struct ieee80211_prep_tx_info info = {}; /* we know it's writable, cast away the const */ if (assoc_data->ie_len) @@ -756,6 +728,8 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) } } + iftd = ieee80211_get_sband_iftype_data(sband, iftype); + skb = alloc_skb(local->hw.extra_tx_headroom + sizeof(*mgmt) + /* bit too much but doesn't matter */ 2 + assoc_data->ssid_len + /* SSID */ @@ -770,7 +744,8 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) 2 + 1 + sizeof(struct ieee80211_he_6ghz_capa) + assoc_data->ie_len + /* extra IEs */ (assoc_data->fils_kek_len ? 16 /* AES-SIV */ : 0) + - 9, /* WMM */ + 9 + /* WMM */ + (iftd ? iftd->vendor_elems.len : 0), GFP_KERNEL); if (!skb) return; @@ -810,12 +785,14 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) mgmt->u.reassoc_req.listen_interval = listen_int; memcpy(mgmt->u.reassoc_req.current_ap, assoc_data->prev_bssid, ETH_ALEN); + info.subtype = IEEE80211_STYPE_REASSOC_REQ; } else { skb_put(skb, 4); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_REQ); mgmt->u.assoc_req.capab_info = cpu_to_le16(capab); mgmt->u.assoc_req.listen_interval = listen_int; + info.subtype = IEEE80211_STYPE_ASSOC_REQ; } /* SSID */ @@ -1043,6 +1020,9 @@ skip_rates: ieee80211_add_s1g_capab_ie(sdata, &sband->s1g_cap, skb); } + if (iftd && iftd->vendor_elems.data && iftd->vendor_elems.len) + skb_put_data(skb, iftd->vendor_elems.data, iftd->vendor_elems.len); + /* add any remaining custom (i.e. vendor specific here) IEs */ if (assoc_data->ie_len) { noffset = assoc_data->ie_len; @@ -1060,7 +1040,7 @@ skip_rates: ifmgd->assoc_req_ies = kmemdup(ie_start, pos - ie_start, GFP_ATOMIC); ifmgd->assoc_req_ies_len = pos - ie_start; - drv_mgd_prepare_tx(local, sdata, 0); + drv_mgd_prepare_tx(local, sdata, &info); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) @@ -1094,11 +1074,6 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_hdr_3addr *nullfunc; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - /* Don't send NDPs when STA is connected HE */ - if (sdata->vif.type == NL80211_IFTYPE_STATION && - !(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) - return; - skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, !ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP)); if (!skb) @@ -1130,10 +1105,6 @@ static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) return; - /* Don't send NDPs when connected HE */ - if (!(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE)) - return; - skb = dev_alloc_skb(local->hw.extra_tx_headroom + 30); if (!skb) return; @@ -1183,10 +1154,6 @@ static void ieee80211_chswitch_work(struct work_struct *work) */ if (sdata->reserved_chanctx) { - struct ieee80211_supported_band *sband = NULL; - struct sta_info *mgd_sta = NULL; - enum ieee80211_sta_rx_bandwidth bw = IEEE80211_STA_RX_BW_20; - /* * with multi-vif csa driver may call ieee80211_csa_finish() * many times while waiting for other interfaces to use their @@ -1195,48 +1162,6 @@ static void ieee80211_chswitch_work(struct work_struct *work) if (sdata->reserved_ready) goto out; - if (sdata->vif.bss_conf.chandef.width != - sdata->csa_chandef.width) { - /* - * For managed interface, we need to also update the AP - * station bandwidth and align the rate scale algorithm - * on the bandwidth change. Here we only consider the - * bandwidth of the new channel definition (as channel - * switch flow does not have the full HT/VHT/HE - * information), assuming that if additional changes are - * required they would be done as part of the processing - * of the next beacon from the AP. - */ - switch (sdata->csa_chandef.width) { - case NL80211_CHAN_WIDTH_20_NOHT: - case NL80211_CHAN_WIDTH_20: - default: - bw = IEEE80211_STA_RX_BW_20; - break; - case NL80211_CHAN_WIDTH_40: - bw = IEEE80211_STA_RX_BW_40; - break; - case NL80211_CHAN_WIDTH_80: - bw = IEEE80211_STA_RX_BW_80; - break; - case NL80211_CHAN_WIDTH_80P80: - case NL80211_CHAN_WIDTH_160: - bw = IEEE80211_STA_RX_BW_160; - break; - } - - mgd_sta = sta_info_get(sdata, ifmgd->bssid); - sband = - local->hw.wiphy->bands[sdata->csa_chandef.chan->band]; - } - - if (sdata->vif.bss_conf.chandef.width > - sdata->csa_chandef.width) { - mgd_sta->sta.bandwidth = bw; - rate_control_rate_update(local, sband, mgd_sta, - IEEE80211_RC_BW_CHANGED); - } - ret = ieee80211_vif_use_reserved_context(sdata); if (ret) { sdata_info(sdata, @@ -1247,13 +1172,6 @@ static void ieee80211_chswitch_work(struct work_struct *work) goto out; } - if (sdata->vif.bss_conf.chandef.width < - sdata->csa_chandef.width) { - mgd_sta->sta.bandwidth = bw; - rate_control_rate_update(local, sband, mgd_sta, - IEEE80211_RC_BW_CHANGED); - } - goto out; } @@ -2341,6 +2259,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; u32 changed = 0; + struct ieee80211_prep_tx_info info = { + .subtype = stype, + }; sdata_assert_lock(sdata); @@ -2390,8 +2311,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, * driver requested so. */ if (ieee80211_hw_check(&local->hw, DEAUTH_NEED_MGD_TX_PREP) && - !ifmgd->have_beacon) - drv_mgd_prepare_tx(sdata->local, sdata, 0); + !ifmgd->have_beacon) { + drv_mgd_prepare_tx(sdata->local, sdata, &info); + } ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, ifmgd->bssid, stype, reason, @@ -2402,6 +2324,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, if (tx) ieee80211_flush_queues(local, sdata, false); + drv_mgd_complete_tx(sdata->local, sdata, &info); + /* clear bssid only after building the needed mgmt frames */ eth_zero_addr(ifmgd->bssid); @@ -2617,10 +2541,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) if (ieee80211_hw_check(&sdata->local->hw, REPORTS_TX_ACK_STATUS)) { ifmgd->nullfunc_failed = false; - if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) - ifmgd->probe_send_count--; - else - ieee80211_send_nullfunc(sdata->local, sdata, false); + ieee80211_send_nullfunc(sdata->local, sdata, false); } else { int ssid_len; @@ -2952,6 +2873,9 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, u8 *pos; struct ieee802_11_elems elems; u32 tx_flags = 0; + struct ieee80211_prep_tx_info info = { + .subtype = IEEE80211_STYPE_AUTH, + }; pos = mgmt->u.auth.variable; ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, &elems, @@ -2959,7 +2883,7 @@ 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, 0); + drv_mgd_prepare_tx(sdata->local, sdata, &info); if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) tx_flags = IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_INTFL_MLME_CONN_TX; @@ -3012,6 +2936,9 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, .type = MLME_EVENT, .u.mlme.data = AUTH_EVENT, }; + struct ieee80211_prep_tx_info info = { + .subtype = IEEE80211_STYPE_AUTH, + }; sdata_assert_lock(sdata); @@ -3040,7 +2967,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, mgmt->sa, auth_alg, ifmgd->auth_data->algorithm, auth_transaction, ifmgd->auth_data->expected_transaction); - return; + goto notify_driver; } if (status_code != WLAN_STATUS_SUCCESS) { @@ -3051,7 +2978,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, (auth_transaction == 1 && (status_code == WLAN_STATUS_SAE_HASH_TO_ELEMENT || status_code == WLAN_STATUS_SAE_PK)))) - return; + goto notify_driver; sdata_info(sdata, "%pM denied authentication (status %d)\n", mgmt->sa, status_code); @@ -3059,7 +2986,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, event.u.mlme.status = MLME_DENIED; event.u.mlme.reason = status_code; drv_event_callback(sdata->local, sdata, &event); - return; + goto notify_driver; } switch (ifmgd->auth_data->algorithm) { @@ -3081,10 +3008,11 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, default: WARN_ONCE(1, "invalid auth alg %d", ifmgd->auth_data->algorithm); - return; + goto notify_driver; } event.u.mlme.status = MLME_SUCCESS; + info.success = 1; drv_event_callback(sdata->local, sdata, &event); if (ifmgd->auth_data->algorithm != WLAN_AUTH_SAE || (auth_transaction == 2 && @@ -3098,6 +3026,8 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, } cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); +notify_driver: + drv_mgd_complete_tx(sdata->local, sdata, &info); } #define case_WLAN(type) \ @@ -3314,6 +3244,23 @@ static int ieee80211_recalc_twt_req(struct ieee80211_sub_if_data *sdata, return 0; } +static bool ieee80211_twt_bcast_support(struct ieee80211_sub_if_data *sdata, + struct ieee80211_bss_conf *bss_conf, + struct ieee80211_supported_band *sband, + struct sta_info *sta) +{ + const struct ieee80211_sta_he_cap *own_he_cap = + ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); + + return bss_conf->he_support && + (sta->sta.he_cap.he_cap_elem.mac_cap_info[2] & + IEEE80211_HE_MAC_CAP2_BCAST_TWT) && + own_he_cap && + (own_he_cap->he_cap_elem.mac_cap_info[2] & + IEEE80211_HE_MAC_CAP2_BCAST_TWT); +} + static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, struct cfg80211_bss *cbss, struct ieee80211_mgmt *mgmt, size_t len, @@ -3529,6 +3476,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, bss_conf->twt_protected = false; } + bss_conf->twt_broadcast = + ieee80211_twt_bcast_support(sdata, bss_conf, sband, sta); + if (bss_conf->he_support) { bss_conf->he_bss_color.color = le32_get_bits(elems->he_operation->he_oper_params, @@ -3699,6 +3649,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, .type = MLME_EVENT, .u.mlme.data = ASSOC_EVENT, }; + struct ieee80211_prep_tx_info info = {}; sdata_assert_lock(sdata); @@ -3728,6 +3679,15 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, aid = 0; /* TODO */ } + /* + * Note: this may not be perfect, AP might misbehave - if + * anyone needs to rely on perfect complete notification + * with the exact right subtype, then we need to track what + * we actually transmitted. + */ + info.subtype = reassoc ? IEEE80211_STYPE_REASSOC_REQ : + IEEE80211_STYPE_ASSOC_REQ; + sdata_info(sdata, "RX %sssocResp from %pM (capab=0x%x status=%d aid=%d)\n", reassoc ? "Rea" : "A", mgmt->sa, @@ -3753,7 +3713,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, assoc_data->timeout_started = true; if (ms > IEEE80211_ASSOC_TIMEOUT) run_again(sdata, assoc_data->timeout); - return; + goto notify_driver; } if (status_code != WLAN_STATUS_SUCCESS) { @@ -3768,7 +3728,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, /* oops -- internal error -- send timeout for now */ ieee80211_destroy_assoc_data(sdata, false, false); cfg80211_assoc_timeout(sdata->dev, cbss); - return; + goto notify_driver; } event.u.mlme.status = MLME_SUCCESS; drv_event_callback(sdata->local, sdata, &event); @@ -3786,10 +3746,14 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) if (sdata->tx_conf[ac].uapsd) uapsd_queues |= ieee80211_ac_to_qos_mask[ac]; + + info.success = 1; } cfg80211_rx_assoc_resp(sdata->dev, cbss, (u8 *)mgmt, len, uapsd_queues, ifmgd->assoc_req_ies, ifmgd->assoc_req_ies_len); +notify_driver: + drv_mgd_complete_tx(sdata->local, sdata, &info); } static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, @@ -4408,7 +4372,9 @@ 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; + struct ieee80211_prep_tx_info info = { + .subtype = IEEE80211_STYPE_AUTH, + }; sdata_assert_lock(sdata); @@ -4431,10 +4397,9 @@ static int ieee80211_auth(struct ieee80211_sub_if_data *sdata) } if (auth_data->algorithm == WLAN_AUTH_SAE) - prepare_tx_duration = - jiffies_to_msecs(IEEE80211_AUTH_TIMEOUT_SAE); + info.duration = jiffies_to_msecs(IEEE80211_AUTH_TIMEOUT_SAE); - drv_mgd_prepare_tx(local, sdata, prepare_tx_duration); + drv_mgd_prepare_tx(local, sdata, &info); sdata_info(sdata, "send auth to %pM (try %d/%d)\n", auth_data->bss->bssid, auth_data->tries, @@ -4929,11 +4894,13 @@ static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata, } static bool -ieee80211_verify_sta_he_mcs_support(struct ieee80211_supported_band *sband, +ieee80211_verify_sta_he_mcs_support(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, const struct ieee80211_he_operation *he_op) { const struct ieee80211_sta_he_cap *sta_he_cap = - ieee80211_get_he_sta_cap(sband); + ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); u16 ap_min_req_set; int i; @@ -5027,7 +4994,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } - if (!ieee80211_get_he_sta_cap(sband)) + if (!ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif))) ifmgd->flags |= IEEE80211_STA_DISABLE_HE; rcu_read_lock(); @@ -5085,7 +5053,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, else he_oper = NULL; - if (!ieee80211_verify_sta_he_mcs_support(sband, he_oper)) + if (!ieee80211_verify_sta_he_mcs_support(sdata, sband, he_oper)) ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } @@ -5655,15 +5623,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, 2 * FILS_NONCE_LEN); assoc_data->bss = req->bss; - - if (ifmgd->req_smps == IEEE80211_SMPS_AUTOMATIC) { - if (ifmgd->powersave) - sdata->smps_mode = IEEE80211_SMPS_DYNAMIC; - else - sdata->smps_mode = IEEE80211_SMPS_OFF; - } else - sdata->smps_mode = ifmgd->req_smps; - assoc_data->capability = req->bss->capability; assoc_data->supp_rates = bss->supp_rates; assoc_data->supp_rates_len = bss->supp_rates_len; @@ -5770,6 +5729,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (err) goto err_clear; + if (ifmgd->req_smps == IEEE80211_SMPS_AUTOMATIC) { + if (ifmgd->powersave) + sdata->smps_mode = IEEE80211_SMPS_DYNAMIC; + else + sdata->smps_mode = IEEE80211_SMPS_OFF; + } else { + sdata->smps_mode = ifmgd->req_smps; + } + rcu_read_lock(); beacon_ies = rcu_dereference(req->bss->beacon_ies); @@ -5854,6 +5822,9 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; bool tx = !req->local_state_change; + struct ieee80211_prep_tx_info info = { + .subtype = IEEE80211_STYPE_DEAUTH, + }; if (ifmgd->auth_data && ether_addr_equal(ifmgd->auth_data->bss->bssid, req->bssid)) { @@ -5862,7 +5833,7 @@ 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, 0); + drv_mgd_prepare_tx(sdata->local, sdata, &info); ieee80211_send_deauth_disassoc(sdata, req->bssid, req->bssid, IEEE80211_STYPE_DEAUTH, req->reason_code, tx, @@ -5871,7 +5842,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, req->reason_code, false); - + drv_mgd_complete_tx(sdata->local, sdata, &info); return 0; } @@ -5882,7 +5853,7 @@ 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, 0); + drv_mgd_prepare_tx(sdata->local, sdata, &info); ieee80211_send_deauth_disassoc(sdata, req->bssid, req->bssid, IEEE80211_STYPE_DEAUTH, req->reason_code, tx, @@ -5906,6 +5877,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, req->reason_code, false); + drv_mgd_complete_tx(sdata->local, sdata, &info); return 0; } diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 63652c39c8e0..e5935e3d7a07 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -297,15 +297,11 @@ void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata) static bool rc_no_data_or_no_ack_use_min(struct ieee80211_tx_rate_control *txrc) { struct sk_buff *skb = txrc->skb; - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - __le16 fc; - - fc = hdr->frame_control; return (info->flags & (IEEE80211_TX_CTL_NO_ACK | IEEE80211_TX_CTL_USE_MINRATE)) || - !ieee80211_is_data(fc); + !ieee80211_is_tx_data(skb); } static void rc_send_low_basicrate(struct ieee80211_tx_rate *rate, @@ -396,6 +392,10 @@ static bool rate_control_send_low(struct ieee80211_sta *pubsta, int mcast_rate; bool use_basicrate = false; + if (ieee80211_is_tx_data(txrc->skb) && + info->flags & IEEE80211_TX_CTL_NO_ACK) + return false; + if (!pubsta || rc_no_data_or_no_ack_use_min(txrc)) { __rate_control_send_low(txrc->hw, sband, pubsta, info, txrc->rate_idx_mask); @@ -870,7 +870,6 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, int max_rates) { struct ieee80211_sub_if_data *sdata; - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_supported_band *sband; @@ -882,7 +881,7 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, sdata = vif_to_sdata(vif); sband = sdata->local->hw.wiphy->bands[info->band]; - if (ieee80211_is_data(hdr->frame_control)) + if (ieee80211_is_tx_data(skb)) rate_control_apply_mask(sdata, sta, sband, dest, max_rates); if (dest[0].idx < 0) diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index a6f3fb4a9197..72b44d4c42d0 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -434,7 +434,7 @@ minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, unsigned int nsecs = 0, overhead = mi->overhead; unsigned int ampdu_len = 1; - /* do not account throughput if sucess prob is below 10% */ + /* do not account throughput if success prob is below 10% */ if (prob_avg < MINSTREL_FRAC(10, 100)) return 0; @@ -1176,29 +1176,6 @@ minstrel_downgrade_rate(struct minstrel_ht_sta *mi, u16 *idx, bool primary) } static void -minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb) -{ - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - struct sta_info *sta = container_of(pubsta, struct sta_info, sta); - u16 tid; - - if (skb_get_queue_mapping(skb) == IEEE80211_AC_VO) - return; - - if (unlikely(!ieee80211_is_data_qos(hdr->frame_control))) - return; - - if (unlikely(skb->protocol == cpu_to_be16(ETH_P_PAE))) - return; - - tid = ieee80211_get_tid(hdr); - if (likely(sta->ampdu_mlme.tid_tx[tid])) - return; - - ieee80211_start_tx_ba_session(pubsta, tid, 0); -} - -static void minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, void *priv_sta, struct ieee80211_tx_status *st) { @@ -1211,6 +1188,10 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, bool last, update = false; int i; + /* Ignore packet that was sent with noAck flag */ + if (info->flags & IEEE80211_TX_CTL_NO_ACK) + return; + /* This packet was aggregated but doesn't carry status info */ if ((info->flags & IEEE80211_TX_CTL_AMPDU) && !(info->flags & IEEE80211_TX_STAT_AMPDU)) @@ -1498,10 +1479,6 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, struct minstrel_priv *mp = priv; u16 sample_idx; - if (!(info->flags & IEEE80211_TX_CTL_AMPDU) && - !minstrel_ht_is_legacy_group(MI_RATE_GROUP(mi->max_prob_rate))) - minstrel_aggr_check(sta, txrc->skb); - info->flags |= mi->tx_flags; #ifdef CONFIG_MAC80211_DEBUGFS @@ -1907,6 +1884,7 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta) static const struct rate_control_ops mac80211_minstrel_ht = { .name = "minstrel_ht", + .capa = RATE_CTRL_CAPA_AMPDU_TRIGGER, .tx_status_ext = minstrel_ht_tx_status, .get_rate = minstrel_ht_get_rate, .rate_init = minstrel_ht_rate_init, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index af0ef456eb0f..771921c057e8 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -214,6 +214,24 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, return len; } +static void __ieee80211_queue_skb_to_iface(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct sk_buff *skb) +{ + skb_queue_tail(&sdata->skb_queue, skb); + ieee80211_queue_work(&sdata->local->hw, &sdata->work); + if (sta) + sta->rx_stats.packets++; +} + +static void ieee80211_queue_skb_to_iface(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct sk_buff *skb) +{ + skb->protocol = 0; + __ieee80211_queue_skb_to_iface(sdata, sta, skb); +} + static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int rtap_space) @@ -254,8 +272,7 @@ static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, if (!skb) return; - skb_queue_tail(&sdata->skb_queue, skb); - ieee80211_queue_work(&sdata->local->hw, &sdata->work); + ieee80211_queue_skb_to_iface(sdata, NULL, skb); } /* @@ -1339,7 +1356,6 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, struct sk_buff_head *frames) { struct sk_buff *skb = rx->skb; - struct ieee80211_local *local = rx->local; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct sta_info *sta = rx->sta; struct tid_ampdu_rx *tid_agg_rx; @@ -1391,8 +1407,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, /* if this mpdu is fragmented - terminate rx aggregation session */ sc = le16_to_cpu(hdr->seq_ctrl); if (sc & IEEE80211_SCTL_FRAG) { - skb_queue_tail(&rx->sdata->skb_queue, skb); - ieee80211_queue_work(&local->hw, &rx->sdata->work); + ieee80211_queue_skb_to_iface(rx->sdata, NULL, skb); return; } @@ -1563,12 +1578,8 @@ static void sta_ps_start(struct sta_info *sta) for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) { struct ieee80211_txq *txq = sta->sta.txq[tid]; - struct txq_info *txqi = to_txq_info(txq); - spin_lock(&local->active_txq_lock[txq->ac]); - if (!list_empty(&txqi->schedule_order)) - list_del_init(&txqi->schedule_order); - spin_unlock(&local->active_txq_lock[txq->ac]); + ieee80211_unschedule_txq(&local->hw, txq, false); if (txq_has_queue(txq)) set_bit(tid, &sta->txq_buffered_tids); @@ -3009,11 +3020,8 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) tf->category == WLAN_CATEGORY_TDLS && (tf->action_code == WLAN_TDLS_CHANNEL_SWITCH_REQUEST || tf->action_code == WLAN_TDLS_CHANNEL_SWITCH_RESPONSE)) { - skb_queue_tail(&local->skb_queue_tdls_chsw, rx->skb); - schedule_work(&local->tdls_chsw_work); - if (rx->sta) - rx->sta->rx_stats.packets++; - + rx->skb->protocol = cpu_to_be16(ETH_P_TDLS); + __ieee80211_queue_skb_to_iface(sdata, rx->sta, rx->skb); return RX_QUEUED; } } @@ -3493,10 +3501,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) return RX_QUEUED; queue: - skb_queue_tail(&sdata->skb_queue, rx->skb); - ieee80211_queue_work(&local->hw, &sdata->work); - if (rx->sta) - rx->sta->rx_stats.packets++; + ieee80211_queue_skb_to_iface(sdata, rx->sta, rx->skb); return RX_QUEUED; } @@ -3644,10 +3649,7 @@ ieee80211_rx_h_ext(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; /* for now only beacons are ext, so queue them */ - skb_queue_tail(&sdata->skb_queue, rx->skb); - ieee80211_queue_work(&rx->local->hw, &sdata->work); - if (rx->sta) - rx->sta->rx_stats.packets++; + ieee80211_queue_skb_to_iface(sdata, rx->sta, rx->skb); return RX_QUEUED; } @@ -3704,11 +3706,7 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; } - /* queue up frame and kick off work to process it */ - skb_queue_tail(&sdata->skb_queue, rx->skb); - ieee80211_queue_work(&rx->local->hw, &sdata->work); - if (rx->sta) - rx->sta->rx_stats.packets++; + ieee80211_queue_skb_to_iface(sdata, rx->sta, rx->skb); return RX_QUEUED; } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f2fb69da9b6e..a5505ee51229 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -425,15 +425,11 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, if (sta_prepare_rate_control(local, sta, gfp)) goto free_txq; - sta->airtime_weight = IEEE80211_DEFAULT_AIRTIME_WEIGHT; for (i = 0; i < IEEE80211_NUM_ACS; i++) { skb_queue_head_init(&sta->ps_tx_buf[i]); skb_queue_head_init(&sta->tx_filtered[i]); - sta->airtime[i].deficit = sta->airtime_weight; - atomic_set(&sta->airtime[i].aql_tx_pending, 0); - sta->airtime[i].aql_limit_low = local->aql_txq_limit_low[i]; - sta->airtime[i].aql_limit_high = local->aql_txq_limit_high[i]; + init_airtime_info(&sta->airtime[i], &local->airtime[i]); } for (i = 0; i < IEEE80211_NUM_TIDS; i++) @@ -1398,11 +1394,6 @@ static void ieee80211_send_null_response(struct sta_info *sta, int tid, struct ieee80211_tx_info *info; struct ieee80211_chanctx_conf *chanctx_conf; - /* Don't send NDPs when STA is connected HE */ - if (sdata->vif.type == NL80211_IFTYPE_STATION && - !(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE)) - return; - if (qos) { fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC | @@ -1897,24 +1888,59 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, } EXPORT_SYMBOL(ieee80211_sta_set_buffered); -void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, - u32 tx_airtime, u32 rx_airtime) +void ieee80211_register_airtime(struct ieee80211_txq *txq, + u32 tx_airtime, u32 rx_airtime) { - struct sta_info *sta = container_of(pubsta, struct sta_info, sta); - struct ieee80211_local *local = sta->sdata->local; - u8 ac = ieee80211_ac_from_tid(tid); + struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif); + struct ieee80211_local *local = sdata->local; + u64 weight_sum, weight_sum_reciprocal; + struct airtime_sched_info *air_sched; + struct airtime_info *air_info; u32 airtime = 0; - if (sta->local->airtime_flags & AIRTIME_USE_TX) + air_sched = &local->airtime[txq->ac]; + air_info = to_airtime_info(txq); + + if (local->airtime_flags & AIRTIME_USE_TX) airtime += tx_airtime; - if (sta->local->airtime_flags & AIRTIME_USE_RX) + if (local->airtime_flags & AIRTIME_USE_RX) airtime += rx_airtime; - spin_lock_bh(&local->active_txq_lock[ac]); - sta->airtime[ac].tx_airtime += tx_airtime; - sta->airtime[ac].rx_airtime += rx_airtime; - sta->airtime[ac].deficit -= airtime; - spin_unlock_bh(&local->active_txq_lock[ac]); + /* Weights scale so the unit weight is 256 */ + airtime <<= 8; + + spin_lock_bh(&air_sched->lock); + + air_info->tx_airtime += tx_airtime; + air_info->rx_airtime += rx_airtime; + + if (air_sched->weight_sum) { + weight_sum = air_sched->weight_sum; + weight_sum_reciprocal = air_sched->weight_sum_reciprocal; + } else { + weight_sum = air_info->weight; + weight_sum_reciprocal = air_info->weight_reciprocal; + } + + /* Round the calculation of global vt */ + air_sched->v_t += (u64)((airtime + (weight_sum >> 1)) * + weight_sum_reciprocal) >> IEEE80211_RECIPROCAL_SHIFT_64; + air_info->v_t += (u32)((airtime + (air_info->weight >> 1)) * + air_info->weight_reciprocal) >> IEEE80211_RECIPROCAL_SHIFT_32; + ieee80211_resort_txq(&local->hw, txq); + + spin_unlock_bh(&air_sched->lock); +} + +void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, + u32 tx_airtime, u32 rx_airtime) +{ + struct ieee80211_txq *txq = pubsta->txq[tid]; + + if (!txq) + return; + + ieee80211_register_airtime(txq, tx_airtime, rx_airtime); } EXPORT_SYMBOL(ieee80211_sta_register_airtime); @@ -2093,10 +2119,9 @@ static struct ieee80211_sta_rx_stats * sta_get_last_rx_stats(struct sta_info *sta) { struct ieee80211_sta_rx_stats *stats = &sta->rx_stats; - struct ieee80211_local *local = sta->local; int cpu; - if (!ieee80211_hw_check(&local->hw, USES_RSS)) + if (!sta->pcpu_rx_stats) return stats; for_each_possible_cpu(cpu) { @@ -2196,9 +2221,7 @@ static void sta_set_tidstats(struct sta_info *sta, int cpu; if (!(tidstats->filled & BIT(NL80211_TID_STATS_RX_MSDU))) { - if (!ieee80211_hw_check(&local->hw, USES_RSS)) - tidstats->rx_msdu += - sta_get_tidstats_msdu(&sta->rx_stats, tid); + tidstats->rx_msdu += sta_get_tidstats_msdu(&sta->rx_stats, tid); if (sta->pcpu_rx_stats) { for_each_possible_cpu(cpu) { @@ -2277,7 +2300,6 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, sinfo->rx_beacon = sdata->u.mgd.count_beacon_signal; drv_sta_statistics(local, sdata, &sta->sta, sinfo); - sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME) | BIT_ULL(NL80211_STA_INFO_STA_FLAGS) | BIT_ULL(NL80211_STA_INFO_BSS_PARAM) | @@ -2312,8 +2334,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_RX_BYTES64) | BIT_ULL(NL80211_STA_INFO_RX_BYTES)))) { - if (!ieee80211_hw_check(&local->hw, USES_RSS)) - sinfo->rx_bytes += sta_get_stats_bytes(&sta->rx_stats); + sinfo->rx_bytes += sta_get_stats_bytes(&sta->rx_stats); if (sta->pcpu_rx_stats) { for_each_possible_cpu(cpu) { @@ -2363,7 +2384,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT))) { - sinfo->airtime_weight = sta->airtime_weight; + sinfo->airtime_weight = sta->airtime[0].weight; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT); } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 0333072ebd98..ba2796782008 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -135,18 +135,25 @@ enum ieee80211_agg_stop_reason { #define AIRTIME_USE_TX BIT(0) #define AIRTIME_USE_RX BIT(1) + struct airtime_info { u64 rx_airtime; u64 tx_airtime; - s64 deficit; + u64 v_t; + u64 last_scheduled; + struct list_head list; atomic_t aql_tx_pending; /* Estimated airtime for frames pending */ u32 aql_limit_low; u32 aql_limit_high; + u32 weight_reciprocal; + u16 weight; }; void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, struct sta_info *sta, u8 ac, u16 tx_airtime, bool tx_completed); +void ieee80211_register_airtime(struct ieee80211_txq *txq, + u32 tx_airtime, u32 rx_airtime); struct sta_info; @@ -515,7 +522,6 @@ struct ieee80211_fragment_cache { * @tid_seq: per-TID sequence numbers for sending to this STA * @airtime: per-AC struct airtime_info describing airtime statistics for this * station - * @airtime_weight: station weight for airtime fairness calculation purposes * @ampdu_mlme: A-MPDU state machine state * @mesh: mesh STA information * @debugfs_dir: debug filesystem directory dentry @@ -646,7 +652,6 @@ struct sta_info { u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; struct airtime_info airtime[IEEE80211_NUM_ACS]; - u16 airtime_weight; /* * Aggregation information, locked with lock. diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 9baf185ee4c7..bae321ff77f6 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -970,6 +970,25 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, if (!(info->flags & IEEE80211_TX_CTL_INJECTED) && acked) ieee80211_frame_acked(sta, skb); + } else if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) { + struct ieee80211_sub_if_data *sdata; + struct ieee80211_txq *txq; + u32 airtime; + + /* Account airtime to multicast queue */ + sdata = ieee80211_sdata_from_skb(local, skb); + + if (sdata && (txq = sdata->vif.txq)) { + airtime = info->status.tx_time ?: + ieee80211_calc_expected_tx_airtime(hw, + &sdata->vif, + NULL, + skb->len, + false); + + ieee80211_register_airtime(txq, airtime, 0); + } } /* SNMP counters @@ -1006,12 +1025,11 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) && !(info->flags & IEEE80211_TX_CTL_INJECTED) && local->ps_sdata && !(local->scanning)) { - if (info->flags & IEEE80211_TX_STAT_ACK) { + if (info->flags & IEEE80211_TX_STAT_ACK) local->ps_sdata->u.mgd.flags |= IEEE80211_STA_NULLFUNC_ACKED; - } else - mod_timer(&local->dynamic_ps_timer, jiffies + - msecs_to_jiffies(10)); + mod_timer(&local->dynamic_ps_timer, + jiffies + msecs_to_jiffies(10)); } ieee80211_report_used_skb(local, skb, false); diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index f91d02b81b92..45e532ad1215 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -1920,7 +1920,7 @@ out: return ret; } -static void +void ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { @@ -1971,32 +1971,6 @@ void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata) rcu_read_unlock(); } -void ieee80211_tdls_chsw_work(struct work_struct *wk) -{ - struct ieee80211_local *local = - container_of(wk, struct ieee80211_local, tdls_chsw_work); - struct ieee80211_sub_if_data *sdata; - struct sk_buff *skb; - struct ieee80211_tdls_data *tf; - - wiphy_lock(local->hw.wiphy); - while ((skb = skb_dequeue(&local->skb_queue_tdls_chsw))) { - tf = (struct ieee80211_tdls_data *)skb->data; - list_for_each_entry(sdata, &local->interfaces, list) { - if (!ieee80211_sdata_running(sdata) || - sdata->vif.type != NL80211_IFTYPE_STATION || - !ether_addr_equal(tf->da, sdata->vif.addr)) - continue; - - ieee80211_process_tdls_channel_switch(sdata, skb); - break; - } - - kfree_skb(skb); - } - wiphy_unlock(local->hw.wiphy); -} - void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata, const u8 *peer, u16 reason) { diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 8fcc39056402..f6ef15366938 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -2,7 +2,7 @@ /* * Portions of this file * Copyright(c) 2016-2017 Intel Deutschland GmbH -* Copyright (C) 2018 - 2020 Intel Corporation +* Copyright (C) 2018 - 2021 Intel Corporation */ #if !defined(__MAC80211_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) @@ -1461,31 +1461,52 @@ DEFINE_EVENT(release_evt, drv_allow_buffered_frames, TP_ARGS(local, sta, tids, num_frames, reason, more_data) ); -TRACE_EVENT(drv_mgd_prepare_tx, +DECLARE_EVENT_CLASS(mgd_prepare_complete_tx_evt, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - u16 duration), + u16 duration, u16 subtype, bool success), - TP_ARGS(local, sdata, duration), + TP_ARGS(local, sdata, duration, subtype, success), TP_STRUCT__entry( LOCAL_ENTRY VIF_ENTRY __field(u32, duration) + __field(u16, subtype) + __field(u8, success) ), TP_fast_assign( LOCAL_ASSIGN; VIF_ASSIGN; __entry->duration = duration; + __entry->subtype = subtype; + __entry->success = success; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT " duration: %u", - LOCAL_PR_ARG, VIF_PR_ARG, __entry->duration + LOCAL_PR_FMT VIF_PR_FMT " duration: %u, subtype:0x%x, success:%d", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->duration, + __entry->subtype, __entry->success ) ); +DEFINE_EVENT(mgd_prepare_complete_tx_evt, drv_mgd_prepare_tx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + u16 duration, u16 subtype, bool success), + + TP_ARGS(local, sdata, duration, subtype, success) +); + +DEFINE_EVENT(mgd_prepare_complete_tx_evt, drv_mgd_complete_tx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + u16 duration, u16 subtype, bool success), + + TP_ARGS(local, sdata, duration, subtype, success) +); + DEFINE_EVENT(local_sdata_evt, drv_mgd_protect_tdls_discover, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata), diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 2651498d05e8..e96981144358 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -18,6 +18,7 @@ #include <linux/bitmap.h> #include <linux/rcupdate.h> #include <linux/export.h> +#include <linux/timekeeping.h> #include <net/net_namespace.h> #include <net/ieee80211_radiotap.h> #include <net/cfg80211.h> @@ -666,6 +667,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) u32 len; struct ieee80211_tx_rate_control txrc; struct ieee80211_sta_rates *ratetbl = NULL; + bool encap = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP; bool assoc = false; memset(&txrc, 0, sizeof(txrc)); @@ -707,7 +709,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) * just wants a probe response. */ if (tx->sdata->vif.bss_conf.use_short_preamble && - (ieee80211_is_data(hdr->frame_control) || + (ieee80211_is_tx_data(tx->skb) || (tx->sta && test_sta_flag(tx->sta, WLAN_STA_SHORT_PREAMBLE)))) txrc.short_preamble = true; @@ -729,7 +731,8 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) "%s: Dropped data frame as no usable bitrate found while " "scanning and associated. Target station: " "%pM on %d GHz band\n", - tx->sdata->name, hdr->addr1, + tx->sdata->name, + encap ? ((struct ethhdr *)hdr)->h_dest : hdr->addr1, info->band ? 5 : 2)) return TX_DROP; @@ -763,7 +766,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) if (txrc.reported_rate.idx < 0) { txrc.reported_rate = tx->rate; - if (tx->sta && ieee80211_is_data(hdr->frame_control)) + if (tx->sta && ieee80211_is_tx_data(tx->skb)) tx->sta->tx_stats.last_rate = txrc.reported_rate; } else if (tx->sta) tx->sta->tx_stats.last_rate = txrc.reported_rate; @@ -1447,7 +1450,7 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, codel_vars_init(&txqi->def_cvars); codel_stats_init(&txqi->cstats); __skb_queue_head_init(&txqi->frags); - INIT_LIST_HEAD(&txqi->schedule_order); + RB_CLEAR_NODE(&txqi->schedule_order); txqi->txq.vif = &sdata->vif; @@ -1491,9 +1494,7 @@ void ieee80211_txq_purge(struct ieee80211_local *local, ieee80211_purge_tx_queue(&local->hw, &txqi->frags); spin_unlock_bh(&fq->lock); - spin_lock_bh(&local->active_txq_lock[txqi->txq.ac]); - list_del_init(&txqi->schedule_order); - spin_unlock_bh(&local->active_txq_lock[txqi->txq.ac]); + ieee80211_unschedule_txq(&local->hw, &txqi->txq, true); } void ieee80211_txq_set_params(struct ieee80211_local *local) @@ -1768,8 +1769,6 @@ static int invoke_tx_handlers_early(struct ieee80211_tx_data *tx) CALL_TXH(ieee80211_tx_h_ps_buf); CALL_TXH(ieee80211_tx_h_check_control_port_protocol); CALL_TXH(ieee80211_tx_h_select_key); - if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL)) - CALL_TXH(ieee80211_tx_h_rate_ctrl); txh_done: if (unlikely(res == TX_DROP)) { @@ -1802,6 +1801,9 @@ static int invoke_tx_handlers_late(struct ieee80211_tx_data *tx) goto txh_done; } + if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL)) + CALL_TXH(ieee80211_tx_h_rate_ctrl); + CALL_TXH(ieee80211_tx_h_michael_mic_add); CALL_TXH(ieee80211_tx_h_sequence); CALL_TXH(ieee80211_tx_h_fragment); @@ -3284,6 +3286,9 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (!ieee80211_hw_check(&local->hw, TX_AMSDU)) return false; + if (sdata->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_ENABLED) + return false; + if (skb_is_gso(skb)) return false; @@ -3389,15 +3394,21 @@ out: * Can be called while the sta lock is held. Anything that can cause packets to * be generated will cause deadlock! */ -static void ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, u8 pn_offs, - struct ieee80211_key *key, - struct sk_buff *skb) +static ieee80211_tx_result +ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, u8 pn_offs, + struct ieee80211_key *key, + struct ieee80211_tx_data *tx) { + struct sk_buff *skb = tx->skb; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *)skb->data; u8 tid = IEEE80211_NUM_TIDS; + if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL) && + ieee80211_tx_h_rate_ctrl(tx) != TX_CONTINUE) + return TX_DROP; + if (key) info->control.hw_key = &key->conf; @@ -3446,6 +3457,8 @@ static void ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata, break; } } + + return TX_CONTINUE; } static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, @@ -3549,24 +3562,17 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, tx.sta = sta; tx.key = fast_tx->key; - if (!ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { - tx.skb = skb; - r = ieee80211_tx_h_rate_ctrl(&tx); - skb = tx.skb; - tx.skb = NULL; - - if (r != TX_CONTINUE) { - if (r != TX_QUEUED) - kfree_skb(skb); - return true; - } - } - if (ieee80211_queue_skb(local, sdata, sta, skb)) return true; - ieee80211_xmit_fast_finish(sdata, sta, fast_tx->pn_offs, - fast_tx->key, skb); + tx.skb = skb; + r = ieee80211_xmit_fast_finish(sdata, sta, fast_tx->pn_offs, + fast_tx->key, &tx); + tx.skb = NULL; + if (r == TX_DROP) { + kfree_skb(skb); + return true; + } if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, @@ -3671,8 +3677,16 @@ begin: else info->flags &= ~IEEE80211_TX_CTL_AMPDU; - if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) + if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) { + if (!ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { + r = ieee80211_tx_h_rate_ctrl(&tx); + if (r != TX_CONTINUE) { + ieee80211_free_txskb(&local->hw, skb); + goto begin; + } + } goto encap_out; + } if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) { struct sta_info *sta = container_of(txq->sta, struct sta_info, @@ -3683,8 +3697,12 @@ begin: (tx.key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) pn_offs = ieee80211_hdrlen(hdr->frame_control); - ieee80211_xmit_fast_finish(sta->sdata, sta, pn_offs, - tx.key, skb); + r = ieee80211_xmit_fast_finish(sta->sdata, sta, pn_offs, + tx.key, &tx); + if (r != TX_CONTINUE) { + ieee80211_free_txskb(&local->hw, skb); + goto begin; + } } else { if (invoke_tx_handlers_late(&tx)) goto begin; @@ -3764,102 +3782,259 @@ EXPORT_SYMBOL(ieee80211_tx_dequeue); struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac) { struct ieee80211_local *local = hw_to_local(hw); + struct airtime_sched_info *air_sched; + u64 now = ktime_get_boottime_ns(); struct ieee80211_txq *ret = NULL; - struct txq_info *txqi = NULL, *head = NULL; - bool found_eligible_txq = false; + struct airtime_info *air_info; + struct txq_info *txqi = NULL; + struct rb_node *node; + bool first = false; - spin_lock_bh(&local->active_txq_lock[ac]); + air_sched = &local->airtime[ac]; + spin_lock_bh(&air_sched->lock); - begin: - txqi = list_first_entry_or_null(&local->active_txqs[ac], - struct txq_info, - schedule_order); - if (!txqi) + node = air_sched->schedule_pos; + +begin: + if (!node) { + node = rb_first_cached(&air_sched->active_txqs); + first = true; + } else { + node = rb_next(node); + } + + if (!node) goto out; - if (txqi == head) { - if (!found_eligible_txq) - goto out; - else - found_eligible_txq = false; + txqi = container_of(node, struct txq_info, schedule_order); + air_info = to_airtime_info(&txqi->txq); + + if (air_info->v_t > air_sched->v_t && + (!first || !airtime_catchup_v_t(air_sched, air_info->v_t, now))) + goto out; + + if (!ieee80211_txq_airtime_check(hw, &txqi->txq)) { + first = false; + goto begin; } - if (!head) - head = txqi; + air_sched->schedule_pos = node; + air_sched->last_schedule_activity = now; + ret = &txqi->txq; +out: + spin_unlock_bh(&air_sched->lock); + return ret; +} +EXPORT_SYMBOL(ieee80211_next_txq); - if (txqi->txq.sta) { - struct sta_info *sta = container_of(txqi->txq.sta, - struct sta_info, sta); - bool aql_check = ieee80211_txq_airtime_check(hw, &txqi->txq); - s64 deficit = sta->airtime[txqi->txq.ac].deficit; +static void __ieee80211_insert_txq(struct rb_root_cached *root, + struct txq_info *txqi) +{ + struct rb_node **new = &root->rb_root.rb_node; + struct airtime_info *old_air, *new_air; + struct rb_node *parent = NULL; + struct txq_info *__txqi; + bool leftmost = true; + + while (*new) { + parent = *new; + __txqi = rb_entry(parent, struct txq_info, schedule_order); + old_air = to_airtime_info(&__txqi->txq); + new_air = to_airtime_info(&txqi->txq); + + if (new_air->v_t <= old_air->v_t) { + new = &parent->rb_left; + } else { + new = &parent->rb_right; + leftmost = false; + } + } - if (aql_check) - found_eligible_txq = true; + rb_link_node(&txqi->schedule_order, parent, new); + rb_insert_color_cached(&txqi->schedule_order, root, leftmost); +} - if (deficit < 0) - sta->airtime[txqi->txq.ac].deficit += - sta->airtime_weight; +void ieee80211_resort_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct airtime_info *air_info = to_airtime_info(txq); + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = to_txq_info(txq); + struct airtime_sched_info *air_sched; - if (deficit < 0 || !aql_check) { - list_move_tail(&txqi->schedule_order, - &local->active_txqs[txqi->txq.ac]); - goto begin; + air_sched = &local->airtime[txq->ac]; + + lockdep_assert_held(&air_sched->lock); + + if (!RB_EMPTY_NODE(&txqi->schedule_order)) { + struct airtime_info *a_prev = NULL, *a_next = NULL; + struct txq_info *t_prev, *t_next; + struct rb_node *n_prev, *n_next; + + /* Erasing a node can cause an expensive rebalancing operation, + * so we check the previous and next nodes first and only remove + * and re-insert if the current node is not already in the + * correct position. + */ + if ((n_prev = rb_prev(&txqi->schedule_order)) != NULL) { + t_prev = container_of(n_prev, struct txq_info, + schedule_order); + a_prev = to_airtime_info(&t_prev->txq); + } + + if ((n_next = rb_next(&txqi->schedule_order)) != NULL) { + t_next = container_of(n_next, struct txq_info, + schedule_order); + a_next = to_airtime_info(&t_next->txq); } + + if ((!a_prev || a_prev->v_t <= air_info->v_t) && + (!a_next || a_next->v_t > air_info->v_t)) + return; + + if (air_sched->schedule_pos == &txqi->schedule_order) + air_sched->schedule_pos = n_prev; + + rb_erase_cached(&txqi->schedule_order, + &air_sched->active_txqs); + RB_CLEAR_NODE(&txqi->schedule_order); + __ieee80211_insert_txq(&air_sched->active_txqs, txqi); } +} +void ieee80211_update_airtime_weight(struct ieee80211_local *local, + struct airtime_sched_info *air_sched, + u64 now, bool force) +{ + struct airtime_info *air_info, *tmp; + u64 weight_sum = 0; + + if (unlikely(!now)) + now = ktime_get_boottime_ns(); - if (txqi->schedule_round == local->schedule_round[ac]) + lockdep_assert_held(&air_sched->lock); + + if (!force && (air_sched->last_weight_update < + now - AIRTIME_ACTIVE_DURATION)) + return; + + list_for_each_entry_safe(air_info, tmp, + &air_sched->active_list, list) { + if (airtime_is_active(air_info, now)) + weight_sum += air_info->weight; + else + list_del_init(&air_info->list); + } + airtime_weight_sum_set(air_sched, weight_sum); + air_sched->last_weight_update = now; +} + +void ieee80211_schedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) + __acquires(txq_lock) __releases(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = to_txq_info(txq); + struct airtime_sched_info *air_sched; + u64 now = ktime_get_boottime_ns(); + struct airtime_info *air_info; + u8 ac = txq->ac; + bool was_active; + + air_sched = &local->airtime[ac]; + air_info = to_airtime_info(txq); + + spin_lock_bh(&air_sched->lock); + was_active = airtime_is_active(air_info, now); + airtime_set_active(air_sched, air_info, now); + + if (!RB_EMPTY_NODE(&txqi->schedule_order)) goto out; - list_del_init(&txqi->schedule_order); - txqi->schedule_round = local->schedule_round[ac]; - ret = &txqi->txq; + /* If the station has been inactive for a while, catch up its v_t so it + * doesn't get indefinite priority; see comment above the definition of + * AIRTIME_MAX_BEHIND. + */ + if ((!was_active && air_info->v_t < air_sched->v_t) || + air_info->v_t < air_sched->v_t - AIRTIME_MAX_BEHIND) + air_info->v_t = air_sched->v_t; + + ieee80211_update_airtime_weight(local, air_sched, now, !was_active); + __ieee80211_insert_txq(&air_sched->active_txqs, txqi); out: - spin_unlock_bh(&local->active_txq_lock[ac]); - return ret; + spin_unlock_bh(&air_sched->lock); } -EXPORT_SYMBOL(ieee80211_next_txq); +EXPORT_SYMBOL(ieee80211_schedule_txq); -void __ieee80211_schedule_txq(struct ieee80211_hw *hw, - struct ieee80211_txq *txq, - bool force) +static void __ieee80211_unschedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, + bool purge) { struct ieee80211_local *local = hw_to_local(hw); struct txq_info *txqi = to_txq_info(txq); + struct airtime_sched_info *air_sched; + struct airtime_info *air_info; - spin_lock_bh(&local->active_txq_lock[txq->ac]); - - if (list_empty(&txqi->schedule_order) && - (force || !skb_queue_empty(&txqi->frags) || - txqi->tin.backlog_packets)) { - /* If airtime accounting is active, always enqueue STAs at the - * head of the list to ensure that they only get moved to the - * back by the airtime DRR scheduler once they have a negative - * deficit. A station that already has a negative deficit will - * get immediately moved to the back of the list on the next - * call to ieee80211_next_txq(). - */ - if (txqi->txq.sta && local->airtime_flags && - wiphy_ext_feature_isset(local->hw.wiphy, - NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) - list_add(&txqi->schedule_order, - &local->active_txqs[txq->ac]); - else - list_add_tail(&txqi->schedule_order, - &local->active_txqs[txq->ac]); + air_sched = &local->airtime[txq->ac]; + air_info = to_airtime_info(&txqi->txq); + + lockdep_assert_held(&air_sched->lock); + + if (purge) { + list_del_init(&air_info->list); + ieee80211_update_airtime_weight(local, air_sched, 0, true); } - spin_unlock_bh(&local->active_txq_lock[txq->ac]); + if (RB_EMPTY_NODE(&txqi->schedule_order)) + return; + + if (air_sched->schedule_pos == &txqi->schedule_order) + air_sched->schedule_pos = rb_prev(&txqi->schedule_order); + + if (!purge) + airtime_set_active(air_sched, air_info, + ktime_get_boottime_ns()); + + rb_erase_cached(&txqi->schedule_order, + &air_sched->active_txqs); + RB_CLEAR_NODE(&txqi->schedule_order); +} + +void ieee80211_unschedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, + bool purge) + __acquires(txq_lock) __releases(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + + spin_lock_bh(&local->airtime[txq->ac].lock); + __ieee80211_unschedule_txq(hw, txq, purge); + spin_unlock_bh(&local->airtime[txq->ac].lock); +} + +void ieee80211_return_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, bool force) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = to_txq_info(txq); + + spin_lock_bh(&local->airtime[txq->ac].lock); + + if (!RB_EMPTY_NODE(&txqi->schedule_order) && !force && + !txq_has_queue(txq)) + __ieee80211_unschedule_txq(hw, txq, false); + + spin_unlock_bh(&local->airtime[txq->ac].lock); } -EXPORT_SYMBOL(__ieee80211_schedule_txq); +EXPORT_SYMBOL(ieee80211_return_txq); DEFINE_STATIC_KEY_FALSE(aql_disable); bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq) { - struct sta_info *sta; + struct airtime_info *air_info = to_airtime_info(txq); struct ieee80211_local *local = hw_to_local(hw); if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) @@ -3874,15 +4049,12 @@ bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, if (unlikely(txq->tid == IEEE80211_NUM_TIDS)) return true; - sta = container_of(txq->sta, struct sta_info, sta); - if (atomic_read(&sta->airtime[txq->ac].aql_tx_pending) < - sta->airtime[txq->ac].aql_limit_low) + if (atomic_read(&air_info->aql_tx_pending) < air_info->aql_limit_low) return true; if (atomic_read(&local->aql_total_pending_airtime) < local->aql_threshold && - atomic_read(&sta->airtime[txq->ac].aql_tx_pending) < - sta->airtime[txq->ac].aql_limit_high) + atomic_read(&air_info->aql_tx_pending) < air_info->aql_limit_high) return true; return false; @@ -3892,63 +4064,85 @@ EXPORT_SYMBOL(ieee80211_txq_airtime_check); bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq) { + struct txq_info *first_txqi = NULL, *txqi = to_txq_info(txq); struct ieee80211_local *local = hw_to_local(hw); - struct txq_info *iter, *tmp, *txqi = to_txq_info(txq); - struct sta_info *sta; - u8 ac = txq->ac; + struct airtime_sched_info *air_sched; + struct airtime_info *air_info; + struct rb_node *node = NULL; + bool ret = false; + u64 now; - spin_lock_bh(&local->active_txq_lock[ac]); - if (!txqi->txq.sta) - goto out; + if (!ieee80211_txq_airtime_check(hw, txq)) + return false; - if (list_empty(&txqi->schedule_order)) + air_sched = &local->airtime[txq->ac]; + spin_lock_bh(&air_sched->lock); + + if (RB_EMPTY_NODE(&txqi->schedule_order)) goto out; - list_for_each_entry_safe(iter, tmp, &local->active_txqs[ac], - schedule_order) { - if (iter == txqi) - break; + now = ktime_get_boottime_ns(); - if (!iter->txq.sta) { - list_move_tail(&iter->schedule_order, - &local->active_txqs[ac]); - continue; - } - sta = container_of(iter->txq.sta, struct sta_info, sta); - if (sta->airtime[ac].deficit < 0) - sta->airtime[ac].deficit += sta->airtime_weight; - list_move_tail(&iter->schedule_order, &local->active_txqs[ac]); - } + /* Like in ieee80211_next_txq(), make sure the first station in the + * scheduling order is eligible for transmission to avoid starvation. + */ + node = rb_first_cached(&air_sched->active_txqs); + if (node) { + first_txqi = container_of(node, struct txq_info, + schedule_order); + air_info = to_airtime_info(&first_txqi->txq); - sta = container_of(txqi->txq.sta, struct sta_info, sta); - if (sta->airtime[ac].deficit >= 0) - goto out; + if (air_sched->v_t < air_info->v_t) + airtime_catchup_v_t(air_sched, air_info->v_t, now); + } - sta->airtime[ac].deficit += sta->airtime_weight; - list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]); - spin_unlock_bh(&local->active_txq_lock[ac]); + air_info = to_airtime_info(&txqi->txq); + if (air_info->v_t <= air_sched->v_t) { + air_sched->last_schedule_activity = now; + ret = true; + } - return false; out: - if (!list_empty(&txqi->schedule_order)) - list_del_init(&txqi->schedule_order); - spin_unlock_bh(&local->active_txq_lock[ac]); - - return true; + spin_unlock_bh(&air_sched->lock); + return ret; } EXPORT_SYMBOL(ieee80211_txq_may_transmit); void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) { struct ieee80211_local *local = hw_to_local(hw); + struct airtime_sched_info *air_sched = &local->airtime[ac]; - spin_lock_bh(&local->active_txq_lock[ac]); - local->schedule_round[ac]++; - spin_unlock_bh(&local->active_txq_lock[ac]); + spin_lock_bh(&air_sched->lock); + air_sched->schedule_pos = NULL; + spin_unlock_bh(&air_sched->lock); } EXPORT_SYMBOL(ieee80211_txq_schedule_start); +static void +ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct sk_buff *skb) +{ + struct rate_control_ref *ref = sdata->local->rate_ctrl; + u16 tid; + + if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER)) + return; + + if (!sta || !sta->sta.ht_cap.ht_supported || + !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO || + skb->protocol == sdata->control_port_protocol) + return; + + tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; + if (likely(sta->ampdu_mlme.tid_tx[tid])) + return; + + ieee80211_start_tx_ba_session(&sta->sta, tid, 0); +} + void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags, @@ -3979,6 +4173,8 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, skb_get_hash(skb); } + ieee80211_aggr_check(sdata, sta, skb); + if (sta) { struct ieee80211_fast_tx *fast_tx; @@ -4242,6 +4438,8 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, memset(info, 0, sizeof(*info)); + ieee80211_aggr_check(sdata, sta, skb); + tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); if (tid_tx) { diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 060059ef9668..05e96212b104 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -6,7 +6,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation * * utilities for mac80211 */ @@ -1693,7 +1693,10 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, if (auth_alg == WLAN_AUTH_SHARED_KEY && transaction == 3) { mgmt->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); err = ieee80211_wep_encrypt(local, skb, key, key_len, key_idx); - WARN_ON(err); + if (WARN_ON(err)) { + kfree_skb(skb); + return; + } } IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | @@ -1934,13 +1937,26 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, *offset = noffset; } - he_cap = ieee80211_get_he_sta_cap(sband); - if (he_cap) { + he_cap = ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); + if (he_cap && + cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band), + IEEE80211_CHAN_NO_HE)) { pos = ieee80211_ie_build_he_cap(pos, he_cap, end); if (!pos) goto out_err; + } + + if (cfg80211_any_usable_channels(local->hw.wiphy, + BIT(NL80211_BAND_6GHZ), + IEEE80211_CHAN_NO_HE)) { + struct ieee80211_supported_band *sband6; - if (sband->band == NL80211_BAND_6GHZ) { + sband6 = local->hw.wiphy->bands[NL80211_BAND_6GHZ]; + he_cap = ieee80211_get_he_iftype_cap(sband6, + ieee80211_vif_type_p2p(&sdata->vif)); + + if (he_cap) { enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); __le16 cap = ieee80211_get_he_6ghz_capa(sband, iftype); @@ -2944,12 +2960,15 @@ void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, u8 *pos; u16 cap; - sband = ieee80211_get_sband(sdata); - if (!sband) + if (!cfg80211_any_usable_channels(sdata->local->hw.wiphy, + BIT(NL80211_BAND_6GHZ), + IEEE80211_CHAN_NO_HE)) return; + sband = sdata->local->hw.wiphy->bands[NL80211_BAND_6GHZ]; + iftd = ieee80211_get_sband_iftype_data(sband, iftype); - if (WARN_ON(!iftd)) + if (!iftd) return; /* Check for device HE 6 GHz capability before adding element */ diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 96ba616f59bf..7d738bd06f2c 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -4,7 +4,9 @@ * Copyright (c) 2019, Tessares SA. */ +#ifdef CONFIG_SYSCTL #include <linux/sysctl.h> +#endif #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -15,10 +17,14 @@ static int mptcp_pernet_id; struct mptcp_pernet { +#ifdef CONFIG_SYSCTL struct ctl_table_header *ctl_table_hdr; +#endif - int mptcp_enabled; + u8 mptcp_enabled; unsigned int add_addr_timeout; + u8 checksum_enabled; + u8 allow_join_initial_addr_port; }; static struct mptcp_pernet *mptcp_get_pernet(struct net *net) @@ -36,15 +42,36 @@ unsigned int mptcp_get_add_addr_timeout(struct net *net) return mptcp_get_pernet(net)->add_addr_timeout; } +int mptcp_is_checksum_enabled(struct net *net) +{ + return mptcp_get_pernet(net)->checksum_enabled; +} + +int mptcp_allow_join_id0(struct net *net) +{ + return mptcp_get_pernet(net)->allow_join_initial_addr_port; +} + +static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) +{ + pernet->mptcp_enabled = 1; + pernet->add_addr_timeout = TCP_RTO_MAX; + pernet->checksum_enabled = 0; + pernet->allow_join_initial_addr_port = 1; +} + +#ifdef CONFIG_SYSCTL static struct ctl_table mptcp_sysctl_table[] = { { .procname = "enabled", - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, /* users with CAP_NET_ADMIN or root (not and) can change this * value, same as other sysctl or the 'net' tree. */ - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "add_addr_timeout", @@ -52,15 +79,25 @@ static struct ctl_table mptcp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "checksum_enabled", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, + { + .procname = "allow_join_initial_addr_port", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, {} }; -static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) -{ - pernet->mptcp_enabled = 1; - pernet->add_addr_timeout = TCP_RTO_MAX; -} - static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) { struct ctl_table_header *hdr; @@ -75,6 +112,8 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) table[0].data = &pernet->mptcp_enabled; table[1].data = &pernet->add_addr_timeout; + table[2].data = &pernet->checksum_enabled; + table[3].data = &pernet->allow_join_initial_addr_port; hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table); if (!hdr) @@ -100,6 +139,17 @@ static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) kfree(table); } +#else + +static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) +{ + return 0; +} + +static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) {} + +#endif /* CONFIG_SYSCTL */ + static int __net_init mptcp_net_init(struct net *net) { struct mptcp_pernet *pernet = mptcp_get_pernet(net); diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index eb2dc6dbe212..52ea2517e856 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -25,6 +25,8 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH), SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX), + SNMP_MIB_ITEM("DSSNoMatchTCP", MPTCP_MIB_DSSTCPMISMATCH), + SNMP_MIB_ITEM("DataCsumErr", MPTCP_MIB_DATACSUMERR), SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL), SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE), SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index f0da4f060fe1..193466c9b549 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -18,6 +18,8 @@ enum linux_mptcp_mib_field { MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ MPTCP_MIB_DSSNOMATCH, /* Received a new mapping that did not match the previous one */ MPTCP_MIB_INFINITEMAPRX, /* Received an infinite mapping */ + MPTCP_MIB_DSSTCPMISMATCH, /* DSS-mapping did not map with TCP's sequence numbers */ + MPTCP_MIB_DATACSUMERR, /* The data checksum fail */ MPTCP_MIB_OFOQUEUETAIL, /* Segments inserted into OoO queue tail */ MPTCP_MIB_OFOQUEUE, /* Segments inserted into OoO queue */ MPTCP_MIB_OFOMERGE, /* Segments merged in OoO queue */ diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index f16d9b5ee978..8f88ddeab6a2 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -144,6 +144,7 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, info->mptcpi_write_seq = READ_ONCE(msk->write_seq); info->mptcpi_snd_una = READ_ONCE(msk->snd_una); info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq); + info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); unlock_sock_fast(sk, slow); } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 9b263f27ce9b..b5850afea343 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -44,7 +44,20 @@ static void mptcp_parse_option(const struct sk_buff *skb, else expected_opsize = TCPOLEN_MPTCP_MPC_SYN; } - if (opsize != expected_opsize) + + /* Cfr RFC 8684 Section 3.3.0: + * If a checksum is present but its use had + * not been negotiated in the MP_CAPABLE handshake, the receiver MUST + * close the subflow with a RST, as it is not behaving as negotiated. + * If a checksum is not present when its use has been negotiated, the + * receiver MUST close the subflow with a RST, as it is considered + * broken + * We parse even option with mismatching csum presence, so that + * later in subflow_data_ready we can trigger the reset. + */ + if (opsize != expected_opsize && + (expected_opsize != TCPOLEN_MPTCP_MPC_ACK_DATA || + opsize != TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM)) break; /* try to be gentle vs future versions on the initial syn */ @@ -66,16 +79,12 @@ static void mptcp_parse_option(const struct sk_buff *skb, * host requires the use of checksums, checksums MUST be used. * In other words, the only way for checksums not to be used * is if both hosts in their SYNs set A=0." - * - * Section 3.3.0: - * "If a checksum is not present when its use has been - * negotiated, the receiver MUST close the subflow with a RST as - * it is considered broken." - * - * We don't implement DSS checksum - fall back to TCP. */ if (flags & MPTCP_CAP_CHECKSUM_REQD) - break; + mp_opt->csum_reqd = 1; + + if (flags & MPTCP_CAP_DENY_JOIN_ID0) + mp_opt->deny_join_id0 = 1; mp_opt->mp_capable = 1; if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) { @@ -86,7 +95,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->rcvr_key = get_unaligned_be64(ptr); ptr += 8; } - if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA) { + if (opsize >= TCPOLEN_MPTCP_MPC_ACK_DATA) { /* Section 3.1.: * "the data parameters in a MP_CAPABLE are semantically * equivalent to those in a DSS option and can be used @@ -98,9 +107,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; } - pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d", + if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) { + mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum_reqd = 1; + ptr += 2; + } + pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u", version, flags, opsize, mp_opt->sndr_key, - mp_opt->rcvr_key, mp_opt->data_len); + mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum); break; case MPTCPOPT_MP_JOIN: @@ -171,10 +185,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, expected_opsize += TCPOLEN_MPTCP_DSS_MAP32; } - /* RFC 6824, Section 3.3: - * If a checksum is present, but its use had - * not been negotiated in the MP_CAPABLE handshake, - * the checksum field MUST be ignored. + /* Always parse any csum presence combination, we will enforce + * RFC 8684 Section 3.3.0 checks later in subflow_data_ready */ if (opsize != expected_opsize && opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) @@ -209,9 +221,15 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; - pr_debug("data_seq=%llu subflow_seq=%u data_len=%u", + if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { + mp_opt->csum_reqd = 1; + mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + ptr += 2; + } + + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", mp_opt->data_seq, mp_opt->subflow_seq, - mp_opt->data_len); + mp_opt->data_len, mp_opt->csum_reqd, mp_opt->csum); } break; @@ -323,9 +341,12 @@ static void mptcp_parse_option(const struct sk_buff *skb, } } -void mptcp_get_options(const struct sk_buff *skb, +void mptcp_get_options(const struct sock *sk, + const struct sk_buff *skb, struct mptcp_options_received *mp_opt) { + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); const struct tcphdr *th = tcp_hdr(skb); const unsigned char *ptr; int length; @@ -341,6 +362,8 @@ void mptcp_get_options(const struct sk_buff *skb, mp_opt->dss = 0; mp_opt->mp_prio = 0; mp_opt->reset = 0; + mp_opt->csum_reqd = READ_ONCE(msk->csum_enabled); + mp_opt->deny_join_id0 = 0; length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); @@ -382,6 +405,8 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, subflow->snd_isn = TCP_SKB_CB(skb)->end_seq; if (subflow->request_mptcp) { opts->suboptions = OPTION_MPTCP_MPC_SYN; + opts->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk)); + opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk)); *size = TCPOLEN_MPTCP_MPC_SYN; return true; } else if (subflow->request_join) { @@ -437,8 +462,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct mptcp_ext *mpext; unsigned int data_len; + u8 len; /* When skb is not available, we better over-estimate the emitted * options len. A full DSS option (28 bytes) is longer than @@ -467,16 +494,27 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, opts->suboptions = OPTION_MPTCP_MPC_ACK; opts->sndr_key = subflow->local_key; opts->rcvr_key = subflow->remote_key; + opts->csum_reqd = READ_ONCE(msk->csum_enabled); + opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk)); /* Section 3.1. * The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK * packets that start the first subflow of an MPTCP connection, * as well as the first packet that carries data */ - if (data_len > 0) - *size = ALIGN(TCPOLEN_MPTCP_MPC_ACK_DATA, 4); - else + if (data_len > 0) { + len = TCPOLEN_MPTCP_MPC_ACK_DATA; + if (opts->csum_reqd) { + /* we need to propagate more info to csum the pseudo hdr */ + opts->ext_copy.data_seq = mpext->data_seq; + opts->ext_copy.subflow_seq = mpext->subflow_seq; + opts->ext_copy.csum = mpext->csum; + len += TCPOLEN_MPTCP_DSS_CHECKSUM; + } + *size = ALIGN(len, 4); + } else { *size = TCPOLEN_MPTCP_MPC_ACK; + } pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d", subflow, subflow->local_key, subflow->remote_key, @@ -537,18 +575,21 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, bool ret = false; u64 ack_seq; + opts->csum_reqd = READ_ONCE(msk->csum_enabled); mpext = skb ? mptcp_get_ext(skb) : NULL; if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) { - unsigned int map_size; + unsigned int map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64; - map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64; + if (mpext) { + if (opts->csum_reqd) + map_size += TCPOLEN_MPTCP_DSS_CHECKSUM; - remaining -= map_size; - dss_size = map_size; - if (mpext) opts->ext_copy = *mpext; + } + remaining -= map_size; + dss_size = map_size; if (skb && snd_data_fin_enable) mptcp_write_data_fin(subflow, skb, &opts->ext_copy); ret = true; @@ -791,6 +832,8 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, if (subflow_req->mp_capable) { opts->suboptions = OPTION_MPTCP_MPC_SYNACK; opts->sndr_key = subflow_req->local_key; + opts->csum_reqd = subflow_req->csum_reqd; + opts->allow_join_id0 = subflow_req->allow_join_id0; *size = TCPOLEN_MPTCP_MPC_SYNACK; pr_debug("subflow_req=%p, local_key=%llu", subflow_req, subflow_req->local_key); @@ -869,6 +912,9 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, return false; } + if (mp_opt->deny_join_id0) + WRITE_ONCE(msk->pm.remote_deny_join_id0, true); + if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); mptcp_subflow_fully_established(subflow, mp_opt); @@ -896,19 +942,20 @@ reset: return false; } -static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit) +u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq) { - u32 old_ack32, cur_ack32; - - if (use_64bit) - return cur_ack; - - old_ack32 = (u32)old_ack; - cur_ack32 = (u32)cur_ack; - cur_ack = (old_ack & GENMASK_ULL(63, 32)) + cur_ack32; - if (unlikely(before(cur_ack32, old_ack32))) - return cur_ack + (1LL << 32); - return cur_ack; + u32 old_seq32, cur_seq32; + + old_seq32 = (u32)old_seq; + cur_seq32 = (u32)cur_seq; + cur_seq = (old_seq & GENMASK_ULL(63, 32)) + cur_seq32; + if (unlikely(cur_seq32 < old_seq32 && before(old_seq32, cur_seq32))) + return cur_seq + (1LL << 32); + + /* reverse wrap could happen, too */ + if (unlikely(cur_seq32 > old_seq32 && after(old_seq32, cur_seq32))) + return cur_seq - (1LL << 32); + return cur_seq; } static void ack_update_msk(struct mptcp_sock *msk, @@ -926,7 +973,7 @@ static void ack_update_msk(struct mptcp_sock *msk, * more dangerous than missing an ack */ old_snd_una = msk->snd_una; - new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64); + new_snd_una = mptcp_expand_seq(old_snd_una, mp_opt->data_ack, mp_opt->ack64); /* ACK for data not even sent yet? Ignore. */ if (after64(new_snd_una, snd_nxt)) @@ -963,7 +1010,7 @@ bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool us return false; WRITE_ONCE(msk->rcv_data_fin_seq, - expand_ack(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit)); + mptcp_expand_seq(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit)); WRITE_ONCE(msk->rcv_data_fin, 1); return true; @@ -1009,7 +1056,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) return; } - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) return; @@ -1101,6 +1148,10 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) } mpext->data_len = mp_opt.data_len; mpext->use_map = 1; + mpext->csum_reqd = mp_opt.csum_reqd; + + if (mpext->csum_reqd) + mpext->csum = mp_opt.csum; } } @@ -1120,25 +1171,53 @@ static void mptcp_set_rwin(const struct tcp_sock *tp) WRITE_ONCE(msk->rcv_wnd_sent, ack_seq); } +static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +{ + struct csum_pseudo_header header; + __wsum csum; + + /* cfr RFC 8684 3.3.1.: + * the data sequence number used in the pseudo-header is + * always the 64-bit value, irrespective of what length is used in the + * DSS option itself. + */ + header.data_seq = cpu_to_be64(mpext->data_seq); + header.subflow_seq = htonl(mpext->subflow_seq); + header.data_len = htons(mpext->data_len); + header.csum = 0; + + csum = csum_partial(&header, sizeof(header), ~csum_unfold(mpext->csum)); + return (__force u16)csum_fold(csum); +} + void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) & opts->suboptions) { - u8 len; + u8 len, flag = MPTCP_CAP_HMAC_SHA256; - if (OPTION_MPTCP_MPC_SYN & opts->suboptions) + if (OPTION_MPTCP_MPC_SYN & opts->suboptions) { len = TCPOLEN_MPTCP_MPC_SYN; - else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) + } else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) { len = TCPOLEN_MPTCP_MPC_SYNACK; - else if (opts->ext_copy.data_len) + } else if (opts->ext_copy.data_len) { len = TCPOLEN_MPTCP_MPC_ACK_DATA; - else + if (opts->csum_reqd) + len += TCPOLEN_MPTCP_DSS_CHECKSUM; + } else { len = TCPOLEN_MPTCP_MPC_ACK; + } + + if (opts->csum_reqd) + flag |= MPTCP_CAP_CHECKSUM_REQD; + + if (!opts->allow_join_id0) + flag |= MPTCP_CAP_DENY_JOIN_ID0; *ptr++ = mptcp_option(MPTCPOPT_MP_CAPABLE, len, MPTCP_SUPPORTED_VERSION, - MPTCP_CAP_HMAC_SHA256); + flag); if (!((OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) & opts->suboptions)) @@ -1154,8 +1233,13 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, if (!opts->ext_copy.data_len) goto mp_capable_done; - put_unaligned_be32(opts->ext_copy.data_len << 16 | - TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + if (opts->csum_reqd) { + put_unaligned_be32(opts->ext_copy.data_len << 16 | + mptcp_make_csum(&opts->ext_copy), ptr); + } else { + put_unaligned_be32(opts->ext_copy.data_len << 16 | + TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + } ptr += 1; } @@ -1307,6 +1391,9 @@ mp_capable_done: flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64; if (mpext->data_fin) flags |= MPTCP_DSS_DATA_FIN; + + if (opts->csum_reqd) + len += TCPOLEN_MPTCP_DSS_CHECKSUM; } *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags); @@ -1326,8 +1413,13 @@ mp_capable_done: ptr += 2; put_unaligned_be32(mpext->subflow_seq, ptr); ptr += 1; - put_unaligned_be32(mpext->data_len << 16 | - TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + if (opts->csum_reqd) { + put_unaligned_be32(mpext->data_len << 16 | + mptcp_make_csum(mpext), ptr); + } else { + put_unaligned_be32(mpext->data_len << 16 | + TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + } } } diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 9d00fa6d22e9..639271e09604 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -320,6 +320,7 @@ void mptcp_pm_data_init(struct mptcp_sock *msk) WRITE_ONCE(msk->pm.addr_signal, 0); WRITE_ONCE(msk->pm.accept_addr, false); WRITE_ONCE(msk->pm.accept_subflow, false); + WRITE_ONCE(msk->pm.remote_deny_join_id0, false); msk->pm.status = 0; spin_lock_init(&msk->pm.lock); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 2469e06a3a9d..d2591ebf01d9 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -451,7 +451,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) /* check if should create a new subflow */ if (msk->pm.local_addr_used < local_addr_max && - msk->pm.subflows < subflows_max) { + msk->pm.subflows < subflows_max && + !READ_ONCE(msk->pm.remote_deny_join_id0)) { local = select_local_address(pernet, msk); if (local) { struct mptcp_addr_info remote = { 0 }; @@ -540,6 +541,7 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node); if (subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; spin_unlock_bh(&msk->pm.lock); pr_debug("send ack for %s%s%s", @@ -547,9 +549,9 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) mptcp_pm_should_add_signal_ipv6(msk) ? " [ipv6]" : "", mptcp_pm_should_add_signal_port(msk) ? " [port]" : ""); - lock_sock(ssk); + slow = lock_sock_fast(ssk); tcp_send_ack(ssk); - release_sock(ssk); + unlock_sock_fast(ssk, slow); spin_lock_bh(&msk->pm.lock); } } @@ -566,6 +568,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct sock *ssk = mptcp_subflow_tcp_sock(subflow); struct sock *sk = (struct sock *)msk; struct mptcp_addr_info local; + bool slow; local_address((struct sock_common *)ssk, &local); if (!addresses_equal(&local, addr, addr->port)) @@ -578,9 +581,9 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, spin_unlock_bh(&msk->pm.lock); pr_debug("send ack for mp_prio"); - lock_sock(ssk); + slow = lock_sock_fast(ssk); tcp_send_ack(ssk); - release_sock(ssk); + unlock_sock_fast(ssk, slow); spin_lock_bh(&msk->pm.lock); return 0; @@ -971,8 +974,14 @@ skip_family: if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); - if (tb[MPTCP_PM_ADDR_ATTR_PORT]) + if (tb[MPTCP_PM_ADDR_ATTR_PORT]) { + if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + NL_SET_ERR_MSG_ATTR(info->extack, attr, + "flags must have signal when using port"); + return -EINVAL; + } entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); + } return 0; } @@ -1913,10 +1922,13 @@ static int __net_init pm_nl_init_net(struct net *net) struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id); INIT_LIST_HEAD_RCU(&pernet->local_addr_list); - __reset_counters(pernet); pernet->next_id = 1; - bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1); spin_lock_init(&pernet->lock); + + /* No need to initialize other pernet fields, the struct is zeroed at + * allocation time. + */ + return 0; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 632350018fb6..7a5afa8c6866 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -39,10 +39,15 @@ struct mptcp_skb_cb { u64 map_seq; u64 end_seq; u32 offset; + u8 has_rxtstamp:1; }; #define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0])) +enum { + MPTCP_CMSG_TS = BIT(0), +}; + static struct percpu_counter mptcp_sockets_allocated; static void __mptcp_destroy_sock(struct sock *sk); @@ -272,6 +277,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; struct sk_buff *tail; + bool has_rxtstamp; __skb_unlink(skb, &ssk->sk_receive_queue); @@ -289,6 +295,8 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, sk->sk_forward_alloc += amount; } + has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; + /* the skb map_seq accounts for the skb offset: * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq * value @@ -296,6 +304,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow); MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len; MPTCP_SKB_CB(skb)->offset = offset; + MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp; if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { /* in sequence */ @@ -424,56 +433,55 @@ static void mptcp_send_ack(struct mptcp_sock *msk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; - lock_sock(ssk); + slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) tcp_send_ack(ssk); - release_sock(ssk); + unlock_sock_fast(ssk, slow); } } -static bool mptcp_subflow_cleanup_rbuf(struct sock *ssk) +static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) { - int ret; + bool slow; - lock_sock(ssk); - ret = tcp_can_send_ack(ssk); - if (ret) + slow = lock_sock_fast(ssk); + if (tcp_can_send_ack(ssk)) tcp_cleanup_rbuf(ssk, 1); - release_sock(ssk); - return ret; + unlock_sock_fast(ssk, slow); +} + +static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) +{ + const struct inet_connection_sock *icsk = inet_csk(ssk); + u8 ack_pending = READ_ONCE(icsk->icsk_ack.pending); + const struct tcp_sock *tp = tcp_sk(ssk); + + return (ack_pending & ICSK_ACK_SCHED) && + ((READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->rcv_wup) > + READ_ONCE(icsk->icsk_ack.rcv_mss)) || + (rx_empty && ack_pending & + (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) { - struct sock *ack_hint = READ_ONCE(msk->ack_hint); int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - bool cleanup; + int space = __mptcp_space(sk); + bool cleanup, rx_empty; - /* this is a simple superset of what tcp_cleanup_rbuf() implements - * so that we don't have to acquire the ssk socket lock most of the time - * to do actually nothing - */ - cleanup = __mptcp_space(sk) - old_space >= max(0, old_space); - if (!cleanup) - return; + cleanup = (space > 0) && (space >= (old_space << 1)); + rx_empty = !atomic_read(&sk->sk_rmem_alloc); - /* if the hinted ssk is still active, try to use it */ - if (likely(ack_hint)) { - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - if (ack_hint == ssk && mptcp_subflow_cleanup_rbuf(ssk)) - return; - } + if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) + mptcp_subflow_cleanup_rbuf(ssk); } - - /* otherwise pick the first active subflow */ - mptcp_for_each_subflow(msk, subflow) - if (mptcp_subflow_cleanup_rbuf(mptcp_subflow_tcp_sock(subflow))) - return; } static bool mptcp_check_data_fin(struct sock *sk) @@ -618,7 +626,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, break; } } while (more_data_avail); - WRITE_ONCE(msk->ack_hint, ssk); *bytes += moved; return done; @@ -675,9 +682,6 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) struct sock *sk = (struct sock *)msk; unsigned int moved = 0; - if (inet_sk_state_load(sk) == TCP_CLOSE) - return false; - __mptcp_move_skbs_from_subflow(msk, ssk, &moved); __mptcp_ofo_queue(msk); if (unlikely(ssk->sk_err)) { @@ -893,22 +897,14 @@ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, df->data_seq + df->data_len == msk->write_seq; } -static int mptcp_wmem_with_overhead(struct sock *sk, int size) +static int mptcp_wmem_with_overhead(int size) { - struct mptcp_sock *msk = mptcp_sk(sk); - int ret, skbs; - - ret = size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT); - skbs = (msk->tx_pending_data + size) / msk->size_goal_cache; - if (skbs < msk->skb_tx_cache.qlen) - return ret; - - return ret + (skbs - msk->skb_tx_cache.qlen) * SKB_TRUESIZE(MAX_TCP_HEADER); + return size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT); } static void __mptcp_wmem_reserve(struct sock *sk, int size) { - int amount = mptcp_wmem_with_overhead(sk, size); + int amount = mptcp_wmem_with_overhead(size); struct mptcp_sock *msk = mptcp_sk(sk); WARN_ON_ONCE(msk->wmem_reserved); @@ -1203,49 +1199,8 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp) return NULL; } -static bool mptcp_tx_cache_refill(struct sock *sk, int size, - struct sk_buff_head *skbs, int *total_ts) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - struct sk_buff *skb; - int space_needed; - - if (unlikely(tcp_under_memory_pressure(sk))) { - mptcp_mem_reclaim_partial(sk); - - /* under pressure pre-allocate at most a single skb */ - if (msk->skb_tx_cache.qlen) - return true; - space_needed = msk->size_goal_cache; - } else { - space_needed = msk->tx_pending_data + size - - msk->skb_tx_cache.qlen * msk->size_goal_cache; - } - - while (space_needed > 0) { - skb = __mptcp_do_alloc_tx_skb(sk, sk->sk_allocation); - if (unlikely(!skb)) { - /* under memory pressure, try to pass the caller a - * single skb to allow forward progress - */ - while (skbs->qlen > 1) { - skb = __skb_dequeue_tail(skbs); - *total_ts -= skb->truesize; - __kfree_skb(skb); - } - return skbs->qlen > 0; - } - - *total_ts += skb->truesize; - __skb_queue_tail(skbs, skb); - space_needed -= msk->size_goal_cache; - } - return true; -} - static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) { - struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb; if (ssk->sk_tx_skb_cache) { @@ -1256,22 +1211,6 @@ static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) return true; } - skb = skb_peek(&msk->skb_tx_cache); - if (skb) { - if (likely(sk_wmem_schedule(ssk, skb->truesize))) { - skb = __skb_dequeue(&msk->skb_tx_cache); - if (WARN_ON_ONCE(!skb)) - return false; - - mptcp_wmem_uncharge(sk, skb->truesize); - ssk->sk_tx_skb_cache = skb; - return true; - } - - /* over memory limit, no point to try to allocate a new skb */ - return false; - } - skb = __mptcp_do_alloc_tx_skb(sk, gfp); if (!skb) return false; @@ -1287,7 +1226,6 @@ static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) static bool mptcp_must_reclaim_memory(struct sock *sk, struct sock *ssk) { return !ssk->sk_tx_skb_cache && - !skb_peek(&mptcp_sk(sk)->skb_tx_cache) && tcp_under_memory_pressure(sk); } @@ -1298,6 +1236,18 @@ static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk) return __mptcp_alloc_tx_skb(sk, ssk, sk->sk_allocation); } +/* note: this always recompute the csum on the whole skb, even + * if we just appended a single frag. More status info needed + */ +static void mptcp_update_data_checksum(struct sk_buff *skb, int added) +{ + struct mptcp_ext *mpext = mptcp_get_ext(skb); + __wsum csum = ~csum_unfold(mpext->csum); + int offset = skb->len - added; + + mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset)); +} + static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, struct mptcp_data_frag *dfrag, struct mptcp_sendmsg_info *info) @@ -1318,7 +1268,6 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, /* compute send limit */ info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags); avail_size = info->size_goal; - msk->size_goal_cache = info->size_goal; skb = tcp_write_queue_tail(ssk); if (skb) { /* Limit the write to the size available in the @@ -1392,10 +1341,14 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, if (zero_window_probe) { mptcp_subflow_ctx(ssk)->rel_write_seq += ret; mpext->frozen = 1; - ret = 0; + if (READ_ONCE(msk->csum_enabled)) + mptcp_update_data_checksum(tail, ret); tcp_push_pending_frames(ssk); + return 0; } out: + if (READ_ONCE(msk->csum_enabled)) + mptcp_update_data_checksum(tail, ret); mptcp_subflow_ctx(ssk)->rel_write_seq += ret; return ret; } @@ -1663,7 +1616,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) while (msg_data_left(msg)) { int total_ts, frag_truesize = 0; struct mptcp_data_frag *dfrag; - struct sk_buff_head skbs; bool dfrag_collapsed; size_t psize, offset; @@ -1696,16 +1648,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) psize = pfrag->size - offset; psize = min_t(size_t, psize, msg_data_left(msg)); total_ts = psize + frag_truesize; - __skb_queue_head_init(&skbs); - if (!mptcp_tx_cache_refill(sk, psize, &skbs, &total_ts)) - goto wait_for_memory; - if (!mptcp_wmem_alloc(sk, total_ts)) { - __skb_queue_purge(&skbs); + if (!mptcp_wmem_alloc(sk, total_ts)) goto wait_for_memory; - } - skb_queue_splice_tail(&skbs, &msk->skb_tx_cache); if (copy_page_from_iter(dfrag->page, offset, psize, &msg->msg_iter) != psize) { mptcp_wmem_uncharge(sk, psize + frag_truesize); @@ -1762,7 +1708,7 @@ static void mptcp_wait_data(struct sock *sk, long *timeo) sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); sk_wait_event(sk, timeo, - test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait); + test_bit(MPTCP_DATA_READY, &msk->flags), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); @@ -1770,7 +1716,9 @@ static void mptcp_wait_data(struct sock *sk, long *timeo) static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, struct msghdr *msg, - size_t len, int flags) + size_t len, int flags, + struct scm_timestamping_internal *tss, + int *cmsg_flags) { struct sk_buff *skb, *tmp; int copied = 0; @@ -1790,6 +1738,11 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, } } + if (MPTCP_SKB_CB(skb)->has_rxtstamp) { + tcp_update_recv_tstamps(skb, tss); + *cmsg_flags |= MPTCP_CMSG_TS; + } + copied += count; if (count < data_len) { @@ -1953,7 +1906,6 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) __mptcp_update_rmem(sk); done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); mptcp_data_unlock(sk); - tcp_cleanup_rbuf(ssk, moved); if (unlikely(ssk->sk_err)) __mptcp_error_report(sk); @@ -1969,7 +1921,6 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) ret |= __mptcp_ofo_queue(msk); __mptcp_splice_receive_queue(sk); mptcp_data_unlock(sk); - mptcp_cleanup_rbuf(msk); } if (ret) mptcp_check_data_fin((struct sock *)msk); @@ -1980,7 +1931,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { struct mptcp_sock *msk = mptcp_sk(sk); - int copied = 0; + struct scm_timestamping_internal tss; + int copied = 0, cmsg_flags = 0; int target; long timeo; @@ -2002,7 +1954,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, while (copied < len) { int bytes_read; - bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags); + bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; @@ -2078,11 +2030,14 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, */ if (unlikely(__mptcp_move_skbs(msk))) set_bit(MPTCP_DATA_READY, &msk->flags); - } else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) { - /* data to read but mptcp_wait_data() cleared DATA_READY */ - set_bit(MPTCP_DATA_READY, &msk->flags); } + out_err: + if (cmsg_flags && copied >= 0) { + if (cmsg_flags & MPTCP_CMSG_TS) + tcp_recv_timestamp(msg, sk, &tss); + } + pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d", msk, test_bit(MPTCP_DATA_READY, &msk->flags), skb_queue_empty_lockless(&sk->sk_receive_queue), copied); @@ -2214,9 +2169,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (ssk == msk->last_snd) msk->last_snd = NULL; - if (ssk == msk->ack_hint) - msk->ack_hint = NULL; - if (ssk == msk->first) msk->first = NULL; @@ -2288,13 +2240,14 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + bool slow; - lock_sock(tcp_sk); + slow = lock_sock_fast(tcp_sk); if (tcp_sk->sk_state != TCP_CLOSE) { tcp_send_active_reset(tcp_sk, GFP_ATOMIC); tcp_set_state(tcp_sk, TCP_CLOSE); } - release_sock(tcp_sk); + unlock_sock_fast(tcp_sk, slow); } inet_sk_state_store(sk, TCP_CLOSE); @@ -2339,8 +2292,8 @@ static void __mptcp_retrans(struct sock *sk) /* limit retransmission to the bytes already sent on some subflows */ info.sent = 0; - info.limit = dfrag->already_sent; - while (info.sent < dfrag->already_sent) { + info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent; + while (info.sent < info.limit) { if (!mptcp_alloc_tx_skb(sk, ssk)) break; @@ -2352,9 +2305,11 @@ static void __mptcp_retrans(struct sock *sk) copied += ret; info.sent += ret; } - if (copied) + if (copied) { + dfrag->already_sent = max(dfrag->already_sent, info.sent); tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); + } mptcp_set_timeout(sk, ssk); release_sock(ssk); @@ -2422,17 +2377,15 @@ static int __mptcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&msk->rtx_queue); INIT_WORK(&msk->work, mptcp_worker); __skb_queue_head_init(&msk->receive_queue); - __skb_queue_head_init(&msk->skb_tx_cache); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; msk->wmem_reserved = 0; msk->rmem_released = 0; msk->tx_pending_data = 0; - msk->size_goal_cache = TCP_BASE_MSS; - msk->ack_hint = NULL; msk->first = NULL; inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; + WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_init(msk); @@ -2484,15 +2437,10 @@ static void __mptcp_clear_xmit(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; - struct sk_buff *skb; WRITE_ONCE(msk->first_pending, NULL); list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) dfrag_clear(sk, dfrag); - while ((skb = __skb_dequeue(&msk->skb_tx_cache)) != NULL) { - sk->sk_forward_alloc += skb->truesize; - kfree_skb(skb); - } } static void mptcp_cancel_work(struct sock *sk) @@ -2773,6 +2721,8 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->token = subflow_req->token; msk->subflow = NULL; WRITE_ONCE(msk->fully_established, false); + if (mp_opt->csum_reqd) + WRITE_ONCE(msk->csum_enabled, true); msk->write_seq = subflow_req->idsn + 1; msk->snd_nxt = msk->write_seq; @@ -2946,6 +2896,11 @@ static void mptcp_release_cb(struct sock *sk) spin_lock_bh(&sk->sk_lock.slock); } + /* be sure to set the current sk state before tacking actions + * depending on sk_state + */ + if (test_and_clear_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags)) + __mptcp_set_connected(sk); if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags)) __mptcp_clean_una_wakeup(sk); if (test_and_clear_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->flags)) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 385796f0ef19..426ed80fe72f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -68,6 +68,8 @@ #define TCPOLEN_MPTCP_FASTCLOSE 12 #define TCPOLEN_MPTCP_RST 4 +#define TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM (TCPOLEN_MPTCP_DSS_CHECKSUM + TCPOLEN_MPTCP_MPC_ACK_DATA) + /* MPTCP MP_JOIN flags */ #define MPTCPOPT_BACKUP BIT(0) #define MPTCPOPT_HMAC_LEN 20 @@ -77,8 +79,9 @@ #define MPTCP_VERSION_MASK (0x0F) #define MPTCP_CAP_CHECKSUM_REQD BIT(7) #define MPTCP_CAP_EXTENSIBILITY BIT(6) +#define MPTCP_CAP_DENY_JOIN_ID0 BIT(5) #define MPTCP_CAP_HMAC_SHA256 BIT(0) -#define MPTCP_CAP_FLAG_MASK (0x3F) +#define MPTCP_CAP_FLAG_MASK (0x1F) /* MPTCP DSS flags */ #define MPTCP_DSS_DATA_FIN BIT(4) @@ -109,6 +112,7 @@ #define MPTCP_ERROR_REPORT 8 #define MPTCP_RETRANSMIT 9 #define MPTCP_WORK_SYNC_SETSOCKOPT 10 +#define MPTCP_CONNECTED 11 static inline bool before64(__u64 seq1, __u64 seq2) { @@ -124,6 +128,7 @@ struct mptcp_options_received { u64 data_seq; u32 subflow_seq; u16 data_len; + __sum16 csum; u16 mp_capable : 1, mp_join : 1, fastclose : 1, @@ -133,7 +138,9 @@ struct mptcp_options_received { rm_addr : 1, mp_prio : 1, echo : 1, - backup : 1; + csum_reqd : 1, + backup : 1, + deny_join_id0 : 1; u32 token; u32 nonce; u64 thmac; @@ -188,6 +195,7 @@ struct mptcp_pm_data { bool work_pending; bool accept_addr; bool accept_subflow; + bool remote_deny_join_id0; u8 add_addr_signaled; u8 add_addr_accepted; u8 local_addr_used; @@ -234,15 +242,13 @@ struct mptcp_sock { bool snd_data_fin_enable; bool rcv_fastclose; bool use_64bit_ack; /* Set when we received a 64-bit DSN */ + bool csum_enabled; spinlock_t join_list_lock; - struct sock *ack_hint; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; struct sk_buff_head receive_queue; - struct sk_buff_head skb_tx_cache; /* this is wmem accounted */ int tx_pending_data; - int size_goal_cache; struct list_head conn_list; struct list_head rtx_queue; struct mptcp_data_frag *first_pending; @@ -335,11 +341,20 @@ static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk) return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list); } +struct csum_pseudo_header { + __be64 data_seq; + __be32 subflow_seq; + __be16 data_len; + __sum16 csum; +}; + struct mptcp_subflow_request_sock { struct tcp_request_sock sk; u16 mp_capable : 1, mp_join : 1, - backup : 1; + backup : 1, + csum_reqd : 1, + allow_join_id0 : 1; u8 local_id; u8 remote_id; u64 local_key; @@ -386,6 +401,8 @@ struct mptcp_subflow_context { u32 map_subflow_seq; u32 ssn_offset; u32 map_data_len; + __wsum map_data_csum; + u32 map_csum_len; u32 request_mptcp : 1, /* send MP_CAPABLE */ request_join : 1, /* send MP_JOIN */ request_bkup : 1, @@ -395,6 +412,8 @@ struct mptcp_subflow_context { pm_notified : 1, /* PM hook called for established status */ conn_finished : 1, map_valid : 1, + map_csum_reqd : 1, + map_data_fin : 1, mpc_map : 1, backup : 1, send_mp_prio : 1, @@ -524,6 +543,8 @@ static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *su int mptcp_is_enabled(struct net *net); unsigned int mptcp_get_add_addr_timeout(struct net *net); +int mptcp_is_checksum_enabled(struct net *net); +int mptcp_allow_join_id0(struct net *net); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, struct mptcp_options_received *mp_opt); bool mptcp_subflow_data_available(struct sock *sk); @@ -575,10 +596,12 @@ int __init mptcp_proto_v6_init(void); struct sock *mptcp_sk_clone(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct request_sock *req); -void mptcp_get_options(const struct sk_buff *skb, +void mptcp_get_options(const struct sock *sk, + const struct sk_buff *skb, struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); +void __mptcp_set_connected(struct sock *sk); static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && @@ -593,6 +616,14 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname, int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option); +u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq); +static inline u64 mptcp_expand_seq(u64 old_seq, u64 cur_seq, bool use_64bit) +{ + if (use_64bit) + return cur_seq; + + return __mptcp_expand_seq(old_seq, cur_seq); +} void __mptcp_check_push(struct sock *sk, struct sock *ssk); void __mptcp_data_acked(struct sock *sk); void __mptcp_error_report(struct sock *sk); @@ -626,6 +657,8 @@ static inline void mptcp_write_space(struct sock *sk) void mptcp_destroy_common(struct mptcp_sock *msk); +#define MPTCP_TOKEN_MAX_RETRIES 4 + void __init mptcp_token_init(void); static inline void mptcp_token_init_request(struct request_sock *req) { @@ -752,9 +785,6 @@ unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk); unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk); -int mptcp_setsockopt(struct sock *sk, int level, int optname, - sockptr_t optval, unsigned int optlen); - void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_all(struct mptcp_sock *msk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index a79798189599..092d1f635d27 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -140,6 +140,43 @@ static void mptcp_so_incoming_cpu(struct mptcp_sock *msk, int val) mptcp_sol_socket_sync_intval(msk, SO_INCOMING_CPU, val); } +static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optname, int val) +{ + sockptr_t optval = KERNEL_SOCKPTR(&val); + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + int ret; + + ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, + optval, sizeof(val)); + if (ret) + return ret; + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow = lock_sock_fast(ssk); + + switch (optname) { + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: + case SO_TIMESTAMPNS_OLD: + case SO_TIMESTAMPNS_NEW: + sock_set_timestamp(sk, optname, !!val); + break; + case SO_TIMESTAMPING_NEW: + case SO_TIMESTAMPING_OLD: + sock_set_timestamping(sk, optname, val); + break; + } + + unlock_sock_fast(ssk, slow); + } + + release_sock(sk); + return 0; +} + static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { @@ -164,6 +201,13 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, case SO_INCOMING_CPU: mptcp_so_incoming_cpu(msk, val); return 0; + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: + case SO_TIMESTAMPNS_OLD: + case SO_TIMESTAMPNS_NEW: + case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: + return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val); } return -ENOPROTOOPT; @@ -251,9 +295,23 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, case SO_MARK: case SO_INCOMING_CPU: case SO_DEBUG: + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: + case SO_TIMESTAMPNS_OLD: + case SO_TIMESTAMPNS_NEW: + case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen); case SO_LINGER: return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen); + case SO_RCVLOWAT: + case SO_RCVTIMEO_OLD: + case SO_RCVTIMEO_NEW: + case SO_BUSY_POLL: + case SO_PREFER_BUSY_POLL: + case SO_BUSY_POLL_BUDGET: + /* No need to copy: only relevant for msk */ + return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen); case SO_NO_CHECK: case SO_DONTROUTE: case SO_BROADCAST: @@ -267,7 +325,24 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, return 0; } - return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen); + /* SO_OOBINLINE is not supported, let's avoid the related mess + * SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF, + * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER, + * we must be careful with subflows + * + * SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks + * explicitly the sk_protocol field + * + * SO_PEEK_OFF is unsupported, as it is for plain TCP + * SO_MAX_PACING_RATE is unsupported, we must be careful with subflows + * SO_CNX_ADVICE is currently unsupported, could possibly be relevant, + * but likely needs careful design + * + * SO_ZEROCOPY is currently unsupported, TODO in sndmsg + * SO_TXTIME is currently unsupported + */ + + return -EOPNOTSUPP; } static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, @@ -299,72 +374,6 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, static bool mptcp_supported_sockopt(int level, int optname) { - if (level == SOL_SOCKET) { - switch (optname) { - case SO_DEBUG: - case SO_REUSEPORT: - case SO_REUSEADDR: - - /* the following ones need a better implementation, - * but are quite common we want to preserve them - */ - case SO_BINDTODEVICE: - case SO_SNDBUF: - case SO_SNDBUFFORCE: - case SO_RCVBUF: - case SO_RCVBUFFORCE: - case SO_KEEPALIVE: - case SO_PRIORITY: - case SO_LINGER: - case SO_TIMESTAMP_OLD: - case SO_TIMESTAMP_NEW: - case SO_TIMESTAMPNS_OLD: - case SO_TIMESTAMPNS_NEW: - case SO_TIMESTAMPING_OLD: - case SO_TIMESTAMPING_NEW: - case SO_RCVLOWAT: - case SO_RCVTIMEO_OLD: - case SO_RCVTIMEO_NEW: - case SO_SNDTIMEO_OLD: - case SO_SNDTIMEO_NEW: - case SO_MARK: - case SO_INCOMING_CPU: - case SO_BINDTOIFINDEX: - case SO_BUSY_POLL: - case SO_PREFER_BUSY_POLL: - case SO_BUSY_POLL_BUDGET: - - /* next ones are no-op for plain TCP */ - case SO_NO_CHECK: - case SO_DONTROUTE: - case SO_BROADCAST: - case SO_BSDCOMPAT: - case SO_PASSCRED: - case SO_PASSSEC: - case SO_RXQ_OVFL: - case SO_WIFI_STATUS: - case SO_NOFCS: - case SO_SELECT_ERR_QUEUE: - return true; - } - - /* SO_OOBINLINE is not supported, let's avoid the related mess */ - /* SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF, - * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER, - * we must be careful with subflows - */ - /* SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks - * explicitly the sk_protocol field - */ - /* SO_PEEK_OFF is unsupported, as it is for plain TCP */ - /* SO_MAX_PACING_RATE is unsupported, we must be careful with subflows */ - /* SO_CNX_ADVICE is currently unsupported, could possibly be relevant, - * but likely needs careful design - */ - /* SO_ZEROCOPY is currently unsupported, TODO in sndmsg */ - /* SO_TXTIME is currently unsupported */ - return false; - } if (level == SOL_IP) { switch (optname) { /* should work fine */ @@ -574,12 +583,12 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname, pr_debug("msk=%p", msk); - if (!mptcp_supported_sockopt(level, optname)) - return -ENOPROTOOPT; - if (level == SOL_SOCKET) return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen); + if (!mptcp_supported_sockopt(level, optname)) + return -ENOPROTOOPT; + /* @@ the meaning of setsockopt() when the socket is connected and * there are multiple subflows is not yet defined. It is up to the * MPTCP-level socket to configure the subflows until the subflow diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index be1de4084196..66d0b1893d26 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -108,6 +108,8 @@ static void subflow_init_req(struct request_sock *req, const struct sock *sk_lis subflow_req->mp_capable = 0; subflow_req->mp_join = 0; + subflow_req->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk_listener)); + subflow_req->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk_listener)); subflow_req->msk = NULL; mptcp_token_init_request(req); } @@ -150,7 +152,7 @@ static int subflow_check_req(struct request_sock *req, return -EINVAL; #endif - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk_listener, skb, &mp_opt); if (mp_opt.mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); @@ -162,7 +164,7 @@ static int subflow_check_req(struct request_sock *req, } if (mp_opt.mp_capable && listener->request_mptcp) { - int err, retries = 4; + int err, retries = MPTCP_TOKEN_MAX_RETRIES; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; again: @@ -247,7 +249,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, int err; subflow_init_req(req, sk_listener); - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk_listener, skb, &mp_opt); if (mp_opt.mp_capable && mp_opt.mp_join) return -EINVAL; @@ -371,6 +373,24 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport; } +void __mptcp_set_connected(struct sock *sk) +{ + if (sk->sk_state == TCP_SYN_SENT) { + inet_sk_state_store(sk, TCP_ESTABLISHED); + sk->sk_state_change(sk); + } +} + +static void mptcp_set_connected(struct sock *sk) +{ + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_set_connected(sk); + else + set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags); + mptcp_data_unlock(sk); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -379,10 +399,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); - if (inet_sk_state_load(parent) == TCP_SYN_SENT) { - inet_sk_state_store(parent, TCP_ESTABLISHED); - parent->sk_state_change(parent); - } /* be sure no special action on any packet other than syn-ack */ if (subflow->conn_finished) @@ -394,7 +410,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->ssn_offset = TCP_SKB_CB(skb)->seq; pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset); - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (subflow->request_mptcp) { if (!mp_opt.mp_capable) { MPTCP_INC_STATS(sock_net(sk), @@ -404,6 +420,10 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) goto fallback; } + if (mp_opt.csum_reqd) + WRITE_ONCE(mptcp_sk(parent)->csum_enabled, true); + if (mp_opt.deny_join_id0) + WRITE_ONCE(mptcp_sk(parent)->pm.remote_deny_join_id0, true); subflow->mp_capable = 1; subflow->can_ack = 1; subflow->remote_key = mp_opt.sndr_key; @@ -411,6 +431,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->remote_key); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); + mptcp_set_connected(parent); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -430,15 +451,15 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) goto do_reset; } + if (!mptcp_finish_join(sk)) + goto do_reset; + subflow_generate_hmac(subflow->local_key, subflow->remote_key, subflow->local_nonce, subflow->remote_nonce, hmac); memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN); - if (!mptcp_finish_join(sk)) - goto do_reset; - subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); @@ -451,6 +472,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } else if (mptcp_check_fallback(sk)) { fallback: mptcp_rcv_space_init(mptcp_sk(parent), sk); + mptcp_set_connected(parent); } return; @@ -558,6 +580,7 @@ static void mptcp_sock_destruct(struct sock *sk) static void mptcp_force_close(struct sock *sk) { + /* the msk is not yet exposed to user-space */ inet_sk_state_store(sk, TCP_CLOSE); sk_common_release(sk); } @@ -638,7 +661,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * reordered MPC will cause fallback, but we don't have other * options. */ - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!mp_opt.mp_capable) { fallback = true; goto create_child; @@ -648,7 +671,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); @@ -775,15 +798,6 @@ enum mapping_status { MAPPING_DUMMY }; -static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) -{ - if ((u32)seq == (u32)old_seq) - return old_seq; - - /* Assume map covers data not mapped yet. */ - return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32)); -} - static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", @@ -824,10 +838,92 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) return true; } +static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *skb, + bool csum_reqd) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct csum_pseudo_header header; + u32 offset, seq, delta; + __wsum csum; + int len; + + if (!csum_reqd) + return MAPPING_OK; + + /* mapping already validated on previous traversal */ + if (subflow->map_csum_len == subflow->map_data_len) + return MAPPING_OK; + + /* traverse the receive queue, ensuring it contains a full + * DSS mapping and accumulating the related csum. + * Preserve the accoumlate csum across multiple calls, to compute + * the csum only once + */ + delta = subflow->map_data_len - subflow->map_csum_len; + for (;;) { + seq = tcp_sk(ssk)->copied_seq + subflow->map_csum_len; + offset = seq - TCP_SKB_CB(skb)->seq; + + /* if the current skb has not been accounted yet, csum its contents + * up to the amount covered by the current DSS + */ + if (offset < skb->len) { + __wsum csum; + + len = min(skb->len - offset, delta); + csum = skb_checksum(skb, offset, len, 0); + subflow->map_data_csum = csum_block_add(subflow->map_data_csum, csum, + subflow->map_csum_len); + + delta -= len; + subflow->map_csum_len += len; + } + if (delta == 0) + break; + + if (skb_queue_is_last(&ssk->sk_receive_queue, skb)) { + /* if this subflow is closed, the partial mapping + * will be never completed; flush the pending skbs, so + * that subflow_sched_work_if_closed() can kick in + */ + if (unlikely(ssk->sk_state == TCP_CLOSE)) + while ((skb = skb_peek(&ssk->sk_receive_queue))) + sk_eat_skb(ssk, skb); + + /* not enough data to validate the csum */ + return MAPPING_EMPTY; + } + + /* the DSS mapping for next skbs will be validated later, + * when a get_mapping_status call will process such skb + */ + skb = skb->next; + } + + /* note that 'map_data_len' accounts only for the carried data, does + * not include the eventual seq increment due to the data fin, + * while the pseudo header requires the original DSS data len, + * including that + */ + header.data_seq = cpu_to_be64(subflow->map_seq); + header.subflow_seq = htonl(subflow->map_subflow_seq); + header.data_len = htons(subflow->map_data_len + subflow->map_data_fin); + header.csum = 0; + + csum = csum_partial(&header, sizeof(header), subflow->map_data_csum); + if (unlikely(csum_fold(csum))) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); + return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; + } + + return MAPPING_OK; +} + static enum mapping_status get_mapping_status(struct sock *ssk, struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + bool csum_reqd = READ_ONCE(msk->csum_enabled); struct mptcp_ext *mpext; struct sk_buff *skb; u16 data_len; @@ -907,22 +1003,17 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_len--; } - if (!mpext->dsn64) { - map_seq = expand_seq(subflow->map_seq, subflow->map_data_len, - mpext->data_seq); - pr_debug("expanded seq=%llu", subflow->map_seq); - } else { - map_seq = mpext->data_seq; - } + map_seq = mptcp_expand_seq(READ_ONCE(msk->ack_seq), mpext->data_seq, mpext->dsn64); WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64); if (subflow->map_valid) { /* Allow replacing only with an identical map */ if (subflow->map_seq == map_seq && subflow->map_subflow_seq == mpext->subflow_seq && - subflow->map_data_len == data_len) { + subflow->map_data_len == data_len && + subflow->map_csum_reqd == mpext->csum_reqd) { skb_ext_del(skb, SKB_EXT_MPTCP); - return MAPPING_OK; + goto validate_csum; } /* If this skb data are fully covered by the current mapping, @@ -934,27 +1025,41 @@ static enum mapping_status get_mapping_status(struct sock *ssk, } /* will validate the next map after consuming the current one */ - return MAPPING_OK; + goto validate_csum; } subflow->map_seq = map_seq; subflow->map_subflow_seq = mpext->subflow_seq; subflow->map_data_len = data_len; subflow->map_valid = 1; + subflow->map_data_fin = mpext->data_fin; subflow->mpc_map = mpext->mpc_map; - pr_debug("new map seq=%llu subflow_seq=%u data_len=%u", + subflow->map_csum_reqd = mpext->csum_reqd; + subflow->map_csum_len = 0; + subflow->map_data_csum = csum_unfold(mpext->csum); + + /* Cfr RFC 8684 Section 3.3.0 */ + if (unlikely(subflow->map_csum_reqd != csum_reqd)) + return MAPPING_INVALID; + + pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", subflow->map_seq, subflow->map_subflow_seq, - subflow->map_data_len); + subflow->map_data_len, subflow->map_csum_reqd, + subflow->map_data_csum); validate_seq: /* we revalidate valid mapping on new skb, because we must ensure * the current skb is completely covered by the available mapping */ - if (!validate_mapping(ssk, skb)) + if (!validate_mapping(ssk, skb)) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSTCPMISMATCH); return MAPPING_INVALID; + } skb_ext_del(skb, SKB_EXT_MPTCP); - return MAPPING_OK; + +validate_csum: + return validate_data_csum(ssk, skb, csum_reqd); } static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, @@ -1137,7 +1242,7 @@ void __mptcp_error_report(struct sock *sk) /* This barrier is coupled with smp_rmb() in mptcp_poll() */ smp_wmb(); - sk->sk_error_report(sk); + sk_error_report(sk); break; } } @@ -1489,10 +1594,7 @@ static void subflow_state_change(struct sock *sk) mptcp_rcv_space_init(mptcp_sk(parent), sk); pr_fallback(mptcp_sk(parent)); subflow->conn_finished = 1; - if (inet_sk_state_load(parent) == TCP_SYN_SENT) { - inet_sk_state_store(parent, TCP_ESTABLISHED); - parent->sk_state_change(parent); - } + mptcp_set_connected(parent); } /* as recvmsg() does not acquire the subflow socket for ssk selection diff --git a/net/mptcp/token.c b/net/mptcp/token.c index 8f0270a780ce..a98e554b034f 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -33,7 +33,6 @@ #include <net/mptcp.h> #include "protocol.h" -#define TOKEN_MAX_RETRIES 4 #define TOKEN_MAX_CHAIN_LEN 4 struct token_bucket { @@ -153,12 +152,9 @@ int mptcp_token_new_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - int retries = TOKEN_MAX_RETRIES; + int retries = MPTCP_TOKEN_MAX_RETRIES; struct token_bucket *bucket; - pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n", - sk, subflow->local_key, subflow->token, subflow->idsn); - again: mptcp_crypto_key_gen_sha(&subflow->local_key, &subflow->token, &subflow->idsn); @@ -172,6 +168,9 @@ again: goto again; } + pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n", + sk, subflow->local_key, subflow->token, subflow->idsn); + WRITE_ONCE(msk->token, subflow->token); __sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain); bucket->chain_len++; diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 49031f804276..cbbb0de4750a 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -238,7 +238,7 @@ struct ncsi_package { struct ncsi_dev_priv *ndp; /* NCSI device */ spinlock_t lock; /* Protect the package */ unsigned int channel_num; /* Number of channels */ - struct list_head channels; /* List of chanels */ + struct list_head channels; /* List of channels */ struct list_head node; /* Form list of packages */ bool multi_channel; /* Enable multiple channels */ @@ -339,7 +339,7 @@ struct ncsi_cmd_arg { unsigned char type; /* Command in the NCSI packet */ unsigned char id; /* Request ID (sequence number) */ unsigned char package; /* Destination package ID */ - unsigned char channel; /* Detination channel ID or 0x1f */ + unsigned char channel; /* Destination channel ID or 0x1f */ unsigned short payload; /* Command packet payload length */ unsigned int req_flags; /* NCSI request properties */ union { diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index ffff8da707b8..ca04b6df1341 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -627,7 +627,7 @@ static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, return 0; } -/* Find an outstanding VLAN tag and constuct a "Set VLAN Filter - Enable" +/* Find an outstanding VLAN tag and construct a "Set VLAN Filter - Enable" * packet. */ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 56a2531a3402..54395266339d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -19,6 +19,16 @@ config NETFILTER_FAMILY_BRIDGE config NETFILTER_FAMILY_ARP bool +config NETFILTER_NETLINK_HOOK + tristate "Netfilter base hook dump support" + depends on NETFILTER_ADVANCED + depends on NF_TABLES + select NETFILTER_NETLINK + help + If this option is enabled, the kernel will include support + to list the base netfilter hooks via NFNETLINK. + This is helpful for debugging. + config NETFILTER_NETLINK_ACCT tristate "Netfilter NFACCT over NFNETLINK interface" depends on NETFILTER_ADVANCED @@ -816,7 +826,7 @@ config NETFILTER_XT_TARGET_CLASSIFY the priority of a packet. Some qdiscs can use this value for classification, among these are: - atm, cbq, dsmark, pfifo_fast, htb, prio + atm, cbq, dsmark, pfifo_fast, htb, prio To compile it as a module, choose M here. If unsure, say N. diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index e80e010354b1..049890e00a3d 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o obj-$(CONFIG_NETFILTER_NETLINK_OSF) += nfnetlink_osf.o +obj-$(CONFIG_NETFILTER_NETLINK_HOOK) += nfnetlink_hook.o # connection tracking obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o @@ -73,7 +74,7 @@ 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_meta.o nft_rt.o nft_exthdr.o \ + nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o nft_last.o \ nft_chain_route.o nf_tables_offload.o \ nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o \ nft_set_pipapo.o diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index de2d20c37cda..16ae92054baa 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1685,8 +1685,8 @@ static const struct nla_policy ip_set_adt_policy[IPSET_ATTR_CMD_MAX + 1] = { }; static int -call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, - struct nlattr *tb[], enum ipset_adt adt, +call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb, + struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 flags, bool use_lineno) { int ret; @@ -1738,8 +1738,7 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, *errline = lineno; - netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); + nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); /* Signal netlink not to send its ACK/errmsg. */ return -EINTR; } @@ -1783,7 +1782,7 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; - ret = call_ad(ctnl, skb, set, tb, adt, flags, + ret = call_ad(net, ctnl, skb, set, tb, adt, flags, use_lineno); } else { int nla_rem; @@ -1794,7 +1793,7 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla, set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; - ret = call_ad(ctnl, skb, set, tb, adt, + ret = call_ad(net, ctnl, skb, set, tb, adt, flags, use_lineno); if (ret < 0) return ret; @@ -1859,7 +1858,6 @@ static int ip_set_header(struct sk_buff *skb, const struct nfnl_info *info, const struct ip_set *set; struct sk_buff *skb2; struct nlmsghdr *nlh2; - int ret = 0; if (unlikely(protocol_min_failed(attr) || !attr[IPSET_ATTR_SETNAME])) @@ -1885,12 +1883,7 @@ static int ip_set_header(struct sk_buff *skb, const struct nfnl_info *info, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret < 0) - return ret; - - return 0; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); nla_put_failure: nlmsg_cancel(skb2, nlh2); @@ -1945,12 +1938,7 @@ static int ip_set_type(struct sk_buff *skb, const struct nfnl_info *info, nlmsg_end(skb2, nlh2); pr_debug("Send TYPE, nlmsg_len: %u\n", nlh2->nlmsg_len); - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret < 0) - return ret; - - return 0; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); nla_put_failure: nlmsg_cancel(skb2, nlh2); @@ -1971,7 +1959,6 @@ static int ip_set_protocol(struct sk_buff *skb, const struct nfnl_info *info, { struct sk_buff *skb2; struct nlmsghdr *nlh2; - int ret = 0; if (unlikely(!attr[IPSET_ATTR_PROTOCOL])) return -IPSET_ERR_PROTOCOL; @@ -1990,12 +1977,7 @@ static int ip_set_protocol(struct sk_buff *skb, const struct nfnl_info *info, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret < 0) - return ret; - - return 0; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); nla_put_failure: nlmsg_cancel(skb2, nlh2); @@ -2014,7 +1996,6 @@ static int ip_set_byname(struct sk_buff *skb, const struct nfnl_info *info, struct nlmsghdr *nlh2; ip_set_id_t id = IPSET_INVALID_ID; const struct ip_set *set; - int ret = 0; if (unlikely(protocol_failed(attr) || !attr[IPSET_ATTR_SETNAME])) @@ -2038,12 +2019,7 @@ static int ip_set_byname(struct sk_buff *skb, const struct nfnl_info *info, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret < 0) - return ret; - - return 0; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); nla_put_failure: nlmsg_cancel(skb2, nlh2); @@ -2065,7 +2041,6 @@ static int ip_set_byindex(struct sk_buff *skb, const struct nfnl_info *info, struct nlmsghdr *nlh2; ip_set_id_t id = IPSET_INVALID_ID; const struct ip_set *set; - int ret = 0; if (unlikely(protocol_failed(attr) || !attr[IPSET_ATTR_INDEX])) @@ -2091,12 +2066,7 @@ static int ip_set_byindex(struct sk_buff *skb, const struct nfnl_info *info, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret < 0) - return ret; - - return 0; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); nla_put_failure: nlmsg_cancel(skb2, nlh2); diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index d61886874940..271da8447b29 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -318,7 +318,7 @@ config IP_VS_MH_TAB_INDEX comment 'IPVS application helper' config IP_VS_FTP - tristate "FTP protocol helper" + tristate "FTP protocol helper" depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT && \ NF_CONNTRACK_FTP select IP_VS_NFCT diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e0befcf8113a..96ba19fc8155 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -55,8 +55,6 @@ #include "nf_internals.h" -extern unsigned int nf_conntrack_net_id; - __cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; EXPORT_SYMBOL_GPL(nf_conntrack_locks); @@ -87,8 +85,6 @@ static __read_mostly bool nf_conntrack_locks_all; static struct conntrack_gc_work conntrack_gc_work; -extern unsigned int nf_conntrack_net_id; - void nf_conntrack_lock(spinlock_t *lock) __acquires(lock) { /* 1) Acquire the lock */ @@ -1404,7 +1400,7 @@ static void gc_worker(struct work_struct *work) continue; net = nf_ct_net(tmp); - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); if (atomic_read(&cnet->count) < nf_conntrack_max95) continue; @@ -1484,7 +1480,7 @@ __nf_conntrack_alloc(struct net *net, const struct nf_conntrack_tuple *repl, gfp_t gfp, u32 hash) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); unsigned int ct_count; struct nf_conn *ct; @@ -1556,7 +1552,7 @@ void nf_conntrack_free(struct nf_conn *ct) nf_ct_ext_destroy(ct); kmem_cache_free(nf_conntrack_cachep, ct); - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); smp_mb__before_atomic(); atomic_dec(&cnet->count); @@ -1614,7 +1610,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, GFP_ATOMIC); local_bh_disable(); - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); if (cnet->expect_count) { spin_lock(&nf_conntrack_expect_lock); exp = nf_ct_find_expectation(net, zone, tuple); @@ -2317,7 +2313,7 @@ __nf_ct_unconfirmed_destroy(struct net *net) void nf_ct_unconfirmed_destroy(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); might_sleep(); @@ -2333,7 +2329,7 @@ void nf_ct_iterate_cleanup_net(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data, u32 portid, int report) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct iter_data d; might_sleep(); @@ -2367,7 +2363,7 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data) down_read(&net_rwsem); for_each_net(net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); if (atomic_read(&cnet->count) == 0) continue; @@ -2449,7 +2445,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); nf_ct_iterate_cleanup(kill_all, net, 0, 0); if (atomic_read(&cnet->count) != 0) @@ -2733,7 +2729,7 @@ void nf_conntrack_init_end(void) int nf_conntrack_init_net(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); int ret = -ENOMEM; int cpu; diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 759d87aef95f..296e4a171bd1 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -27,8 +27,6 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_extend.h> -extern unsigned int nf_conntrack_net_id; - static DEFINE_MUTEX(nf_ct_ecache_mutex); #define ECACHE_RETRY_WAIT (HZ/10) @@ -348,7 +346,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); if (state == NFCT_ECACHE_DESTROY_FAIL && !delayed_work_pending(&cnet->ecache_dwork)) { @@ -371,7 +369,7 @@ static const struct nf_ct_ext_type event_extend = { void nf_conntrack_ecache_pernet_init(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); net->ct.sysctl_events = nf_ct_events; cnet->ct_net = &net->ct; @@ -380,7 +378,7 @@ void nf_conntrack_ecache_pernet_init(struct net *net) void nf_conntrack_ecache_pernet_fini(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); cancel_delayed_work_sync(&cnet->ecache_dwork); } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index efdd391b3f72..1e851bc2e61a 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -43,8 +43,6 @@ unsigned int nf_ct_expect_max __read_mostly; static struct kmem_cache *nf_ct_expect_cachep __read_mostly; static unsigned int nf_ct_expect_hashrnd __read_mostly; -extern unsigned int nf_conntrack_net_id; - /* nf_conntrack_expect helper functions */ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, u32 portid, int report) @@ -58,7 +56,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, hlist_del_rcu(&exp->hnode); - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); cnet->expect_count--; hlist_del_rcu(&exp->lnode); @@ -123,7 +121,7 @@ __nf_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_conntrack_expect *i; unsigned int h; @@ -164,7 +162,7 @@ nf_ct_find_expectation(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_conntrack_expect *i, *exp = NULL; unsigned int h; @@ -397,7 +395,7 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) master_help->expecting[exp->class]++; hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]); - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); cnet->expect_count++; NF_CT_STAT_INC(net, expect_create); @@ -468,7 +466,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, } } - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); if (cnet->expect_count >= nf_ct_expect_max) { net_warn_ratelimited("nf_conntrack: expectation table full\n"); ret = -EMFILE; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index aafaff00baf1..2eb31ffb3d14 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -194,7 +194,7 @@ static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff, if (tcpdatalen == 4) { /* Separate TPKT header */ /* Netmeeting sends TPKT header and data separately */ pr_debug("nf_ct_h323: separate TPKT header indicates " - "there will be TPKT data of %hu bytes\n", + "there will be TPKT data of %d bytes\n", tpktlen - 4); info->tpkt_len[dir] = tpktlen - 4; return 0; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index ac396cc8bfae..ae4488a13c70 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -43,8 +43,6 @@ MODULE_PARM_DESC(nf_conntrack_helper, static DEFINE_MUTEX(nf_ct_nat_helpers_mutex); static struct list_head nf_ct_nat_helpers __read_mostly; -extern unsigned int nf_conntrack_net_id; - /* Stupid hash, but collision free for the default registrations of the * helpers currently in the kernel. */ static unsigned int helper_hash(const struct nf_conntrack_tuple *tuple) @@ -214,7 +212,7 @@ EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add); static struct nf_conntrack_helper * nf_ct_lookup_helper(struct nf_conn *ct, struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); if (!cnet->sysctl_auto_assign_helper) { if (cnet->auto_assign_helper_warned) @@ -560,7 +558,7 @@ static const struct nf_ct_ext_type helper_extend = { void nf_conntrack_helper_pernet_init(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); cnet->sysctl_auto_assign_helper = nf_ct_auto_assign_helper; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 8690fc07030f..4e1a9dba7077 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1528,7 +1528,7 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + u8 family = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; @@ -1541,12 +1541,12 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb, if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, - nfmsg->nfgen_family, &zone); + family, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, - nfmsg->nfgen_family, &zone); + family, &zone); else { - u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC; + u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC; return ctnetlink_flush_conntrack(info->net, cda, NETLINK_CB(skb).portid, @@ -1586,8 +1586,7 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; @@ -1628,9 +1627,8 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb, ct = nf_ct_tuplehash_to_ctrack(h); - err = -ENOMEM; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) { + if (!skb2) { nf_ct_put(ct); return -ENOMEM; } @@ -1640,21 +1638,12 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb, NFNL_MSG_TYPE(info->nlh->nlmsg_type), ct, true, 0); nf_ct_put(ct); - if (err <= 0) - goto free; - - err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (err < 0) - goto out; - - return 0; + if (err <= 0) { + kfree_skb(skb2); + return -ENOMEM; + } -free: - kfree_skb(skb2); -out: - /* this avoids a loop in nfnetlink. */ - return err == -EAGAIN ? -ENOBUFS : err; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static int ctnetlink_done_list(struct netlink_callback *cb) @@ -2373,10 +2362,9 @@ static int ctnetlink_new_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_zone zone; struct nf_conn *ct; int err; @@ -2590,21 +2578,12 @@ static int ctnetlink_stat_ct(struct sk_buff *skb, const struct nfnl_info *info, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), sock_net(skb->sk)); - if (err <= 0) - goto free; - - err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (err < 0) - goto out; - - return 0; + if (err <= 0) { + kfree_skb(skb2); + return -ENOMEM; + } -free: - kfree_skb(skb2); -out: - /* this avoids a loop in nfnetlink. */ - return err == -EAGAIN ? -ENOBUFS : err; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { @@ -3278,8 +3257,7 @@ static int ctnetlink_get_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; @@ -3329,11 +3307,10 @@ static int ctnetlink_get_expect(struct sk_buff *skb, } } - err = -ENOMEM; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) { + if (!skb2) { nf_ct_expect_put(exp); - goto out; + return -ENOMEM; } rcu_read_lock(); @@ -3342,21 +3319,12 @@ static int ctnetlink_get_expect(struct sk_buff *skb, exp); rcu_read_unlock(); nf_ct_expect_put(exp); - if (err <= 0) - goto free; - - err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (err < 0) - goto out; - - return 0; + if (err <= 0) { + kfree_skb(skb2); + return -ENOMEM; + } -free: - kfree_skb(skb2); -out: - /* this avoids a loop in nfnetlink. */ - return err == -EAGAIN ? -ENOBUFS : err; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data) @@ -3378,8 +3346,7 @@ static int ctnetlink_del_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; @@ -3630,8 +3597,7 @@ static int ctnetlink_new_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index dc9ca12b0489..55647409a9be 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -42,17 +42,16 @@ #include <net/ipv6.h> #include <net/inet_frag.h> -extern unsigned int nf_conntrack_net_id; - static DEFINE_MUTEX(nf_ct_proto_mutex); #ifdef CONFIG_SYSCTL -__printf(5, 6) +__printf(4, 5) void nf_l4proto_log_invalid(const struct sk_buff *skb, - struct net *net, - u16 pf, u8 protonum, + const struct nf_hook_state *state, + u8 protonum, const char *fmt, ...) { + struct net *net = state->net; struct va_format vaf; va_list args; @@ -64,15 +63,16 @@ void nf_l4proto_log_invalid(const struct sk_buff *skb, vaf.fmt = fmt; vaf.va = &args; - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_proto_%d: %pV ", protonum, &vaf); + nf_log_packet(net, state->pf, 0, skb, state->in, state->out, + NULL, "nf_ct_proto_%d: %pV ", protonum, &vaf); va_end(args); } EXPORT_SYMBOL_GPL(nf_l4proto_log_invalid); -__printf(3, 4) +__printf(4, 5) void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, + const struct nf_hook_state *state, const char *fmt, ...) { struct va_format vaf; @@ -87,7 +87,7 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, vaf.fmt = fmt; vaf.va = &args; - nf_l4proto_log_invalid(skb, net, nf_ct_l3num(ct), + nf_l4proto_log_invalid(skb, state, nf_ct_protonum(ct), "%pV", &vaf); va_end(args); } @@ -446,7 +446,7 @@ static struct nf_ct_bridge_info *nf_ct_bridge_info; static int nf_ct_netns_do_get(struct net *net, u8 nfproto) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); bool fixup_needed = false, retry = true; int err = 0; retry: @@ -531,7 +531,7 @@ retry: static void nf_ct_netns_do_put(struct net *net, u8 nfproto) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); mutex_lock(&nf_ct_proto_mutex); switch (nfproto) { diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 4f33307fa3cf..c1557d47ccd1 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -382,7 +382,8 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = static noinline bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, - const struct dccp_hdr *dh) + const struct dccp_hdr *dh, + const struct nf_hook_state *hook_state) { struct net *net = nf_ct_net(ct); struct nf_dccp_net *dn; @@ -414,7 +415,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb, return true; out_invalid: - nf_ct_l4proto_log_invalid(skb, ct, "%s", msg); + nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", msg); return false; } @@ -464,8 +465,7 @@ static bool dccp_error(const struct dccp_hdr *dh, } return false; out_invalid: - nf_l4proto_log_invalid(skb, state->net, state->pf, - IPPROTO_DCCP, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_DCCP, "%s", msg); return true; } @@ -488,7 +488,7 @@ int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, return -NF_ACCEPT; type = dh->dccph_type; - if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh)) + if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh, state)) return -NF_ACCEPT; if (type == DCCP_PKT_RESET && @@ -543,11 +543,11 @@ int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, ct->proto.dccp.last_pkt = type; spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "%s", "invalid packet"); + nf_ct_l4proto_log_invalid(skb, ct, state, "%s", "invalid packet"); return NF_ACCEPT; case CT_DCCP_INVALID: spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "%s", "invalid state transition"); + nf_ct_l4proto_log_invalid(skb, ct, state, "%s", "invalid state transition"); return -NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 4efd8741c105..b38b7164acd5 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -170,12 +170,12 @@ int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, ct_daddr = &ct->tuplehash[dir].tuple.dst.u3; if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) { if (state->pf == AF_INET) { - nf_l4proto_log_invalid(skb, state->net, state->pf, + nf_l4proto_log_invalid(skb, state, l4proto, "outer daddr %pI4 != inner %pI4", &outer_daddr->ip, &ct_daddr->ip); } else if (state->pf == AF_INET6) { - nf_l4proto_log_invalid(skb, state->net, state->pf, + nf_l4proto_log_invalid(skb, state, l4proto, "outer daddr %pI6 != inner %pI6", &outer_daddr->ip6, &ct_daddr->ip6); @@ -197,8 +197,7 @@ static void icmp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { - nf_l4proto_log_invalid(skb, state->net, state->pf, - IPPROTO_ICMP, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_ICMP, "%s", msg); } /* Small and modified version of icmp_rcv */ diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index facd8c64ec4e..61e3b05cf02c 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -126,8 +126,7 @@ static void icmpv6_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { - nf_l4proto_log_invalid(skb, state->net, state->pf, - IPPROTO_ICMPV6, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_ICMPV6, "%s", msg); } int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index fb8dc02e502f..2394238d01c9 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -351,7 +351,7 @@ static bool sctp_error(struct sk_buff *skb, } return false; out_invalid: - nf_l4proto_log_invalid(skb, state->net, state->pf, IPPROTO_SCTP, "%s", logmsg); + nf_l4proto_log_invalid(skb, state, IPPROTO_SCTP, "%s", logmsg); return true; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 34e22416a721..f7e8baf59b51 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -446,14 +446,15 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, } } -static bool tcp_in_window(const struct nf_conn *ct, - struct ip_ct_tcp *state, +static bool tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, unsigned int index, const struct sk_buff *skb, unsigned int dataoff, - const struct tcphdr *tcph) + const struct tcphdr *tcph, + const struct nf_hook_state *hook_state) { + struct ip_ct_tcp *state = &ct->proto.tcp; struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = nf_tcp_pernet(net); struct ip_ct_tcp_state *sender = &state->seen[dir]; @@ -670,7 +671,7 @@ static bool tcp_in_window(const struct nf_conn *ct, tn->tcp_be_liberal) res = true; if (!res) { - nf_ct_l4proto_log_invalid(skb, ct, + nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", before(seq, sender->td_maxend + 1) ? in_recv_win ? @@ -710,7 +711,7 @@ static void tcp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { - nf_l4proto_log_invalid(skb, state->net, state->pf, IPPROTO_TCP, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_TCP, "%s", msg); } /* Protect conntrack agaist broken packets. Code taken from ipt_unclean.c. */ @@ -970,7 +971,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, IP_CT_EXP_CHALLENGE_ACK; } spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, + nf_ct_l4proto_log_invalid(skb, ct, state, "packet (index %d) in dir %d ignored, state %s", index, dir, tcp_conntrack_names[old_state]); @@ -995,7 +996,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n", dir, get_conntrack_index(th), old_state); spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "invalid state"); + nf_ct_l4proto_log_invalid(skb, ct, state, "invalid state"); return -NF_ACCEPT; case TCP_CONNTRACK_TIME_WAIT: /* RFC5961 compliance cause stack to send "challenge-ACK" @@ -1010,7 +1011,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, /* Detected RFC5961 challenge ACK */ ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "challenge-ack ignored"); + nf_ct_l4proto_log_invalid(skb, ct, state, "challenge-ack ignored"); return NF_ACCEPT; /* Don't change state */ } break; @@ -1035,7 +1036,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) { /* Invalid RST */ spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "invalid rst"); + nf_ct_l4proto_log_invalid(skb, ct, state, "invalid rst"); return -NF_ACCEPT; } @@ -1079,8 +1080,8 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, break; } - if (!tcp_in_window(ct, &ct->proto.tcp, dir, index, - skb, dataoff, th)) { + if (!tcp_in_window(ct, dir, index, + skb, dataoff, th, state)) { spin_unlock_bh(&ct->lock); return -NF_ACCEPT; } @@ -1441,6 +1442,11 @@ void nf_conntrack_tcp_init_net(struct net *net) * will be started. */ tn->tcp_max_retrans = 3; + +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + tn->offload_timeout = 30 * HZ; + tn->offload_pickup = 120 * HZ; +#endif } const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp = diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index af402f458ee0..698fee49e732 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -38,8 +38,7 @@ static void udp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { - nf_l4proto_log_invalid(skb, state->net, state->pf, - IPPROTO_UDP, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_UDP, "%s", msg); } static bool udp_error(struct sk_buff *skb, @@ -130,8 +129,7 @@ static void udplite_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { - nf_l4proto_log_invalid(skb, state->net, state->pf, - IPPROTO_UDPLITE, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_UDPLITE, "%s", msg); } static bool udplite_error(struct sk_buff *skb, @@ -270,6 +268,11 @@ void nf_conntrack_udp_init_net(struct net *net) for (i = 0; i < UDP_CT_MAX; i++) un->timeouts[i] = udp_timeouts[i]; + +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + un->offload_timeout = 30 * HZ; + un->offload_pickup = 30 * HZ; +#endif } const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp = diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index aaa55246d0ca..f57a951c9b5e 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -512,9 +512,7 @@ static void nf_conntrack_standalone_fini_proc(struct net *net) u32 nf_conntrack_count(const struct net *net) { - const struct nf_conntrack_net *cnet; - - cnet = net_generic(net, nf_conntrack_net_id); + const struct nf_conntrack_net *cnet = nf_ct_pernet(net); return atomic_read(&cnet->count); } @@ -575,11 +573,19 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK, +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP, +#endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD, + NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP, +#endif NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP, NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6, #ifdef CONFIG_NF_CT_PROTO_SCTP @@ -762,6 +768,20 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD] = { + .procname = "nf_flowtable_tcp_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = { + .procname = "nf_flowtable_tcp_pickup", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, +#endif [NF_SYSCTL_CT_PROTO_TCP_LOOSE] = { .procname = "nf_conntrack_tcp_loose", .maxlen = sizeof(u8), @@ -796,6 +816,20 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, +#if IS_ENABLED(CONFIG_NFT_FLOW_OFFLOAD) + [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = { + .procname = "nf_flowtable_udp_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = { + .procname = "nf_flowtable_udp_pickup", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, +#endif [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = { .procname = "nf_conntrack_icmp_timeout", .maxlen = sizeof(unsigned int), @@ -971,6 +1005,12 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, XASSIGN(LIBERAL, &tn->tcp_be_liberal); XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans); #undef XASSIGN + +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout; + table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup; +#endif + } static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, @@ -1032,7 +1072,7 @@ static void nf_conntrack_standalone_init_gre_sysctl(struct net *net, static int nf_conntrack_standalone_init_sysctl(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_udp_net *un = nf_udp_pernet(net); struct ctl_table *table; @@ -1059,6 +1099,10 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP].data = &un->timeouts[UDP_CT_UNREPLIED]; table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED]; +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout; + table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup; +#endif nf_conntrack_standalone_init_tcp_sysctl(net, table); nf_conntrack_standalone_init_sctp_sysctl(net, table); @@ -1085,7 +1129,7 @@ out_unregister_netfilter: static void nf_conntrack_standalone_fini_sysctl(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct ctl_table *table; table = cnet->sysctl_header->ctl_table_arg; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 1d02650dd715..1e50908b1b7e 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -178,12 +178,10 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) tcp->seen[1].td_maxwin = 0; } -#define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT (120 * HZ) -#define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT (30 * HZ) - static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; + struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); unsigned int timeout; @@ -191,12 +189,17 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (!l4proto) return; - if (l4num == IPPROTO_TCP) - timeout = NF_FLOWTABLE_TCP_PICKUP_TIMEOUT; - else if (l4num == IPPROTO_UDP) - timeout = NF_FLOWTABLE_UDP_PICKUP_TIMEOUT; - else + if (l4num == IPPROTO_TCP) { + struct nf_tcp_net *tn = nf_tcp_pernet(net); + + timeout = tn->offload_pickup; + } else if (l4num == IPPROTO_UDP) { + struct nf_udp_net *tn = nf_udp_pernet(net); + + timeout = tn->offload_pickup; + } else { return; + } if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout) ct->timeout = nfct_time_stamp + timeout; @@ -268,11 +271,35 @@ static const struct rhashtable_params nf_flow_offload_rhash_params = { .automatic_shrinking = true, }; +unsigned long flow_offload_get_timeout(struct flow_offload *flow) +{ + const struct nf_conntrack_l4proto *l4proto; + unsigned long timeout = NF_FLOW_TIMEOUT; + struct net *net = nf_ct_net(flow->ct); + int l4num = nf_ct_protonum(flow->ct); + + l4proto = nf_ct_l4proto_find(l4num); + if (!l4proto) + return timeout; + + if (l4num == IPPROTO_TCP) { + struct nf_tcp_net *tn = nf_tcp_pernet(net); + + timeout = tn->offload_timeout; + } else if (l4num == IPPROTO_UDP) { + struct nf_udp_net *tn = nf_udp_pernet(net); + + timeout = tn->offload_timeout; + } + + return timeout; +} + int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) { int err; - flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; + flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); err = rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[0].node, @@ -304,7 +331,7 @@ EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, struct flow_offload *flow) { - flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; + flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); if (likely(!nf_flowtable_hw_offload(flow_table))) return; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 528b2f172684..f92006cec94c 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -937,7 +937,7 @@ static void flow_offload_work_stats(struct flow_offload_work *offload) lastused = max_t(u64, stats[0].lastused, stats[1].lastused); offload->flow->timeout = max_t(u64, offload->flow->timeout, - lastused + NF_FLOW_TIMEOUT); + lastused + flow_offload_get_timeout(offload->flow)); if (offload->flowtable->flags & NF_FLOWTABLE_COUNTER) { if (stats[0].pkts) @@ -1041,7 +1041,7 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable, __s32 delta; delta = nf_flow_timeout_delta(flow->timeout); - if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10)) + if ((delta >= (9 * flow_offload_get_timeout(flow)) / 10)) return; offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_STATS); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index bf4d6ec9fc55..390d4466567f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -571,7 +571,7 @@ static struct nft_table *nft_table_lookup(const struct net *net, table->family == family && nft_active_genmask(table, genmask)) { if (nft_table_has_owner(table) && - table->nlpid != nlpid) + nlpid && table->nlpid != nlpid) return ERR_PTR(-EPERM); return table; @@ -583,7 +583,7 @@ static struct nft_table *nft_table_lookup(const struct net *net, static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, - u8 genmask) + u8 genmask, u32 nlpid) { struct nftables_pernet *nft_net; struct nft_table *table; @@ -591,8 +591,13 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, nft_net = nft_pernet(net); list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && - nft_active_genmask(table, genmask)) + nft_active_genmask(table, genmask)) { + if (nft_table_has_owner(table) && + nlpid && table->nlpid != nlpid) + return ERR_PTR(-EPERM); + return table; + } } return ERR_PTR(-ENOENT); @@ -862,10 +867,9 @@ static int nft_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb, static int nf_tables_gettable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; struct net *net = info->net; struct sk_buff *skb2; @@ -1068,10 +1072,9 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -1263,10 +1266,9 @@ out: static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -1279,7 +1281,8 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_TABLE_HANDLE]) { attr = nla[NFTA_TABLE_HANDLE]; - table = nft_table_lookup_byhandle(net, attr, genmask); + table = nft_table_lookup_byhandle(net, attr, genmask, + NETLINK_CB(skb).portid); } else { attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask, @@ -1636,10 +1639,9 @@ done: static int nf_tables_getchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; struct net *net = info->net; struct nft_table *table; @@ -2015,11 +2017,12 @@ static void nft_basechain_hook_init(struct nf_hook_ops *ops, u8 family, const struct nft_chain_hook *hook, struct nft_chain *chain) { - ops->pf = family; - ops->hooknum = hook->num; - ops->priority = hook->priority; - ops->priv = chain; - ops->hook = hook->type->hooks[ops->hooknum]; + ops->pf = family; + ops->hooknum = hook->num; + ops->priority = hook->priority; + ops->priv = chain; + ops->hook = hook->type->hooks[ops->hooknum]; + ops->hook_ops_type = NF_HOOK_OP_NF_TABLES; } static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, @@ -2371,10 +2374,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; struct net *net = info->net; const struct nlattr *attr; @@ -2469,10 +2471,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -3096,10 +3097,9 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; const struct nft_rule *rule; struct net *net = info->net; @@ -3237,15 +3237,14 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; unsigned int size, i, n, ulen = 0, usize = 0; u8 genmask = nft_genmask_next(info->net); struct nft_rule *rule, *old_rule = NULL; struct nft_expr_info *expr_info = NULL; - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; + struct nft_flow_rule *flow = NULL; struct net *net = info->net; - struct nft_flow_rule *flow; struct nft_userdata *udata; struct nft_table *table; struct nft_chain *chain; @@ -3340,13 +3339,13 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) { err = -EINVAL; if (nla_type(tmp) != NFTA_LIST_ELEM) - goto err1; + goto err_release_expr; if (n == NFT_RULE_MAXEXPRS) - goto err1; + goto err_release_expr; err = nf_tables_expr_parse(&ctx, tmp, &expr_info[n]); if (err < 0) { NL_SET_BAD_ATTR(extack, tmp); - goto err1; + goto err_release_expr; } size += expr_info[n].ops->size; n++; @@ -3355,7 +3354,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, /* Check for overflow of dlen field */ err = -EFBIG; if (size >= 1 << 12) - goto err1; + goto err_release_expr; if (nla[NFTA_RULE_USERDATA]) { ulen = nla_len(nla[NFTA_RULE_USERDATA]); @@ -3366,7 +3365,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, err = -ENOMEM; rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL); if (rule == NULL) - goto err1; + goto err_release_expr; nft_activate_next(net, rule); @@ -3385,7 +3384,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_newexpr(&ctx, &expr_info[i], expr); if (err < 0) { NL_SET_BAD_ATTR(extack, expr_info[i].attr); - goto err2; + goto err_release_rule; } if (expr_info[i].ops->validate) @@ -3395,16 +3394,24 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, expr = nft_expr_next(expr); } + if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { + flow = nft_flow_rule_create(net, rule); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto err_release_rule; + } + } + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; - goto err2; + goto err_destroy_flow_rule; } err = nft_delrule(&ctx, old_rule); if (err < 0) { nft_trans_destroy(trans); - goto err2; + goto err_destroy_flow_rule; } list_add_tail_rcu(&rule->list, &old_rule->list); @@ -3412,7 +3419,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (!trans) { err = -ENOMEM; - goto err2; + goto err_destroy_flow_rule; } if (info->nlh->nlmsg_flags & NLM_F_APPEND) { @@ -3430,21 +3437,19 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, kvfree(expr_info); chain->use++; + if (flow) + nft_trans_flow_rule(trans) = flow; + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); - if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { - flow = nft_flow_rule_create(net, rule); - if (IS_ERR(flow)) - return PTR_ERR(flow); - - nft_trans_flow_rule(trans) = flow; - } - return 0; -err2: + +err_destroy_flow_rule: + nft_flow_rule_destroy(flow); +err_release_rule: nf_tables_rule_release(&ctx, rule); -err1: +err_release_expr: for (i = 0; i < n; i++) { if (expr_info[i].ops) { module_put(expr_info[i].ops->type->owner); @@ -3477,15 +3482,15 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; - int family = nfmsg->nfgen_family, err = 0; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; struct net *net = info->net; struct nft_table *table; struct nft_rule *rule; struct nft_ctx ctx; + int err = 0; table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, NETLINK_CB(skb).portid); @@ -3665,30 +3670,6 @@ static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { [NFTA_SET_DESC_CONCAT] = { .type = NLA_NESTED }, }; -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, u32 nlpid) -{ - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - int family = nfmsg->nfgen_family; - struct nft_table *table = NULL; - - if (nla[NFTA_SET_TABLE] != NULL) { - table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, - genmask, nlpid); - 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 *nft_set_lookup(const struct nft_table *table, const struct nlattr *nla, u8 genmask) { @@ -4068,20 +4049,26 @@ static int nf_tables_dump_sets_done(struct netlink_callback *cb) static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; + struct nft_table *table = NULL; struct net *net = info->net; const struct nft_set *set; struct sk_buff *skb2; struct nft_ctx ctx; int err; - /* Verify existence before starting dump */ - err = nft_ctx_init_from_setattr(&ctx, net, skb, info->nlh, nla, extack, - genmask, 0); - if (err < 0) - return err; + if (nla[NFTA_SET_TABLE]) { + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, + genmask, 0); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); + return PTR_ERR(table); + } + } + + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -4096,12 +4083,12 @@ static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, } /* Only accept unspec with dump */ - if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; if (!nla[NFTA_SET_TABLE]) return -EINVAL; - set = nft_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); + set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) return PTR_ERR(set); @@ -4189,11 +4176,10 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc, static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); u32 ktype, dtype, flags, policy, gc_int, objtype; struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_set_ops *ops; struct nft_expr *expr = NULL; struct net *net = info->net; @@ -4494,31 +4480,31 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; + struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; - int err; - if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; - if (nla[NFTA_SET_TABLE] == NULL) - return -EINVAL; - err = nft_ctx_init_from_setattr(&ctx, net, skb, info->nlh, nla, extack, - genmask, NETLINK_CB(skb).portid); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); + return PTR_ERR(table); + } if (nla[NFTA_SET_HANDLE]) { attr = nla[NFTA_SET_HANDLE]; - set = nft_set_lookup_byhandle(ctx.table, attr, genmask); + set = nft_set_lookup_byhandle(table, attr, genmask); } else { attr = nla[NFTA_SET_NAME]; - set = nft_set_lookup(ctx.table, attr, genmask); + set = nft_set_lookup(table, attr, genmask); } if (IS_ERR(set)) { @@ -4532,6 +4518,8 @@ static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, return -EBUSY; } + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + return nft_delset(&ctx, set); } @@ -4733,28 +4721,6 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + [NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 }, }; -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, u32 nlpid) -{ - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - int family = nfmsg->nfgen_family; - struct nft_table *table; - - table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, - genmask, nlpid); - 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; -} - static int nft_set_elem_expr_dump(struct sk_buff *skb, const struct nft_set *set, const struct nft_set_ext *ext) @@ -5212,21 +5178,27 @@ static int nf_tables_getsetelem(struct sk_buff *skb, { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; + struct nft_table *table; struct nft_set *set; struct nlattr *attr; struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack, - genmask, NETLINK_CB(skb).portid); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); + return PTR_ERR(table); + } - set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); + set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_set_start, @@ -5995,8 +5967,10 @@ static int nf_tables_newsetelem(struct sk_buff *skb, struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; + struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; int rem, err; @@ -6004,12 +5978,14 @@ static int nf_tables_newsetelem(struct sk_buff *skb, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack, - genmask, NETLINK_CB(skb).portid); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); + return PTR_ERR(table); + } - set = nft_set_lookup_global(net, ctx.table, nla[NFTA_SET_ELEM_LIST_SET], + set = nft_set_lookup_global(net, table, nla[NFTA_SET_ELEM_LIST_SET], nla[NFTA_SET_ELEM_LIST_SET_ID], genmask); if (IS_ERR(set)) return PTR_ERR(set); @@ -6017,6 +5993,8 @@ static int nf_tables_newsetelem(struct sk_buff *skb, if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) return -EBUSY; + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags); if (err < 0) @@ -6024,7 +6002,7 @@ static int nf_tables_newsetelem(struct sk_buff *skb, } if (nft_net->validate_state == NFT_VALIDATE_DO) - return nft_table_validate(net, ctx.table); + return nft_table_validate(net, table); return 0; } @@ -6262,23 +6240,29 @@ static int nf_tables_delsetelem(struct sk_buff *skb, { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; + struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack, - genmask, NETLINK_CB(skb).portid); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); + return PTR_ERR(table); + } - set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); + set = nft_set_lookup(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) return -EBUSY; + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return nft_set_flush(&ctx, set, genmask); @@ -6546,11 +6530,10 @@ err_free_trans: static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nft_object_type *type; - int family = nfmsg->nfgen_family; struct net *net = info->net; struct nft_table *table; struct nft_object *obj; @@ -6802,10 +6785,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; struct net *net = info->net; struct nft_object *obj; @@ -6892,10 +6874,9 @@ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -7323,12 +7304,11 @@ static int nf_tables_newflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; struct nft_flowtable_hook flowtable_hook; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; - int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct nft_hook *hook, *next; struct net *net = info->net; @@ -7512,10 +7492,9 @@ static int nf_tables_delflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct net *net = info->net; const struct nlattr *attr; @@ -7707,9 +7686,8 @@ static int nf_tables_getflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; const struct nft_table *table; struct net *net = info->net; @@ -8839,11 +8817,16 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_ABORT); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index dbc2e945c98e..866cfba04d6c 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -81,7 +81,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr, else { if (!pkt->tprot_set) return false; - ptr = skb_network_header(skb) + pkt->xt.thoff; + ptr = skb_network_header(skb) + nft_thoff(pkt); } ptr += priv->offset; @@ -268,6 +268,7 @@ static struct nft_expr_type *nft_basic_types[] = { &nft_meta_type, &nft_rt_type, &nft_exthdr_type, + &nft_last_type, }; static struct nft_object_type *nft_basic_objects[] = { diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index a48c5fd53a80..b58d73a96523 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -54,15 +54,10 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow) { struct nft_flow_match *match = &flow->match; - struct nft_offload_ethertype ethertype; - - if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL) && - match->key.basic.n_proto != htons(ETH_P_8021Q) && - match->key.basic.n_proto != htons(ETH_P_8021AD)) - return; - - ethertype.value = match->key.basic.n_proto; - ethertype.mask = match->mask.basic.n_proto; + struct nft_offload_ethertype ethertype = { + .value = match->key.basic.n_proto, + .mask = match->mask.basic.n_proto, + }; if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || @@ -76,7 +71,9 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN); - } else { + } else if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC) && + (match->key.basic.n_proto == htons(ETH_P_8021Q) || + match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; @@ -594,23 +591,6 @@ int nft_flow_rule_offload_commit(struct net *net) } } - list_for_each_entry(trans, &nft_net->commit_list, list) { - if (trans->ctx.family != NFPROTO_NETDEV) - continue; - - switch (trans->msg_type) { - case NFT_MSG_NEWRULE: - case NFT_MSG_DELRULE: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) - continue; - - nft_flow_rule_destroy(nft_trans_flow_rule(trans)); - break; - default: - break; - } - } - return err; } diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 0cf3278007ba..e4fe2f0780eb 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -113,17 +113,17 @@ static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, int off = skb_network_offset(skb); unsigned int len, nh_end; - nh_end = pkt->tprot_set ? pkt->xt.thoff : skb->len; + nh_end = pkt->tprot_set ? nft_thoff(pkt) : skb->len; len = min_t(unsigned int, nh_end - skb_network_offset(skb), NFT_TRACETYPE_NETWORK_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len)) return -1; if (pkt->tprot_set) { - len = min_t(unsigned int, skb->len - pkt->xt.thoff, + len = min_t(unsigned int, skb->len - nft_thoff(pkt), NFT_TRACETYPE_TRANSPORT_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb, - pkt->xt.thoff, len)) + nft_thoff(pkt), len)) return -1; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index e8dbd8379027..7e2c8dd01408 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -68,6 +68,7 @@ static const char *const nfnl_lockdep_names[NFNL_SUBSYS_COUNT] = { [NFNL_SUBSYS_CTHELPER] = "nfnl_subsys_cthelper", [NFNL_SUBSYS_NFTABLES] = "nfnl_subsys_nftables", [NFNL_SUBSYS_NFT_COMPAT] = "nfnl_subsys_nftcompat", + [NFNL_SUBSYS_HOOK] = "nfnl_subsys_hook", }; static const int nfnl_group2type[NFNLGRP_MAX+1] = { @@ -256,6 +257,7 @@ replay: .net = net, .sk = nfnlnet->nfnl, .nlh = nlh, + .nfmsg = nlmsg_data(nlh), .extack = extack, }; @@ -491,6 +493,7 @@ replay_abort: .net = net, .sk = nfnlnet->nfnl, .nlh = nlh, + .nfmsg = nlmsg_data(nlh), .extack = &extack, }; diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 3c8cf8748cfb..505f46a32173 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -314,14 +314,11 @@ static int nfnl_acct_get(struct sk_buff *skb, const struct nfnl_info *info, kfree_skb(skb2); break; } - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret > 0) - ret = 0; - /* this avoids a loop in nfnetlink. */ - return ret == -EAGAIN ? -ENOBUFS : ret; + ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); + break; } + return ret; } diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 752b10cae524..5c622f55c9d6 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -667,14 +667,10 @@ static int nfnl_cthelper_get(struct sk_buff *skb, const struct nfnl_info *info, break; } - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret > 0) - ret = 0; - - /* this avoids a loop in nfnetlink. */ - return ret == -EAGAIN ? -ENOBUFS : ret; + ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); + break; } + return ret; } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 38848ad68899..c57673d499be 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -287,14 +287,11 @@ static int cttimeout_get_timeout(struct sk_buff *skb, kfree_skb(skb2); break; } - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret > 0) - ret = 0; - /* this avoids a loop in nfnetlink. */ - return ret == -EAGAIN ? -ENOBUFS : ret; + ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); + break; } + return ret; } @@ -427,9 +424,9 @@ static int cttimeout_default_get(struct sk_buff *skb, const struct nf_conntrack_l4proto *l4proto; unsigned int *timeouts = NULL; struct sk_buff *skb2; - int ret, err; __u16 l3num; __u8 l4num; + int ret; if (!cda[CTA_TIMEOUT_L3PROTO] || !cda[CTA_TIMEOUT_L4PROTO]) return -EINVAL; @@ -438,9 +435,8 @@ static int cttimeout_default_get(struct sk_buff *skb, l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find(l4num); - err = -EOPNOTSUPP; if (l4proto->l4proto != l4num) - goto err; + return -EOPNOTSUPP; switch (l4proto->l4proto) { case IPPROTO_ICMP: @@ -480,13 +476,11 @@ static int cttimeout_default_get(struct sk_buff *skb, } if (!timeouts) - goto err; + return -EOPNOTSUPP; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) { - err = -ENOMEM; - goto err; - } + if (!skb2) + return -ENOMEM; ret = cttimeout_default_fill_info(info->net, skb2, NETLINK_CB(skb).portid, @@ -496,18 +490,10 @@ static int cttimeout_default_get(struct sk_buff *skb, l3num, l4proto, timeouts); if (ret <= 0) { kfree_skb(skb2); - err = -ENOMEM; - goto err; + return -ENOMEM; } - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret > 0) - ret = 0; - /* this avoids a loop in nfnetlink. */ - return ret == -EAGAIN ? -ENOBUFS : ret; -err: - return err; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net, diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c new file mode 100644 index 000000000000..50b4e3c9347a --- /dev/null +++ b/net/netfilter/nfnetlink_hook.c @@ -0,0 +1,377 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021 Red Hat GmbH + * + * Author: Florian Westphal <fw@strlen.de> + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/netlink.h> +#include <linux/slab.h> + +#include <linux/netfilter.h> + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/nfnetlink_hook.h> + +#include <net/netfilter/nf_tables.h> +#include <net/sock.h> + +static const struct nla_policy nfnl_hook_nla_policy[NFNLA_HOOK_MAX + 1] = { + [NFNLA_HOOK_HOOKNUM] = { .type = NLA_U32 }, + [NFNLA_HOOK_PRIORITY] = { .type = NLA_U32 }, + [NFNLA_HOOK_DEV] = { .type = NLA_STRING, + .len = IFNAMSIZ - 1 }, + [NFNLA_HOOK_FUNCTION_NAME] = { .type = NLA_NUL_STRING, + .len = KSYM_NAME_LEN, }, + [NFNLA_HOOK_MODULE_NAME] = { .type = NLA_NUL_STRING, + .len = MODULE_NAME_LEN, }, + [NFNLA_HOOK_CHAIN_INFO] = { .type = NLA_NESTED, }, +}; + +static int nf_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; +} + +struct nfnl_dump_hook_data { + char devname[IFNAMSIZ]; + unsigned long headv; + u8 hook; +}; + +static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb, + const struct nfnl_dump_hook_data *ctx, + unsigned int seq, + const struct nf_hook_ops *ops) +{ + struct net *net = sock_net(nlskb->sk); + struct nlattr *nest, *nest2; + struct nft_chain *chain; + int ret = 0; + + if (ops->hook_ops_type != NF_HOOK_OP_NF_TABLES) + return 0; + + chain = ops->priv; + if (WARN_ON_ONCE(!chain)) + return 0; + + if (!nft_is_active(net, chain)) + return 0; + + nest = nla_nest_start(nlskb, NFNLA_HOOK_CHAIN_INFO); + if (!nest) + return -EMSGSIZE; + + ret = nla_put_be32(nlskb, NFNLA_HOOK_INFO_TYPE, + htonl(NFNL_HOOK_TYPE_NFTABLES)); + if (ret) + goto cancel_nest; + + nest2 = nla_nest_start(nlskb, NFNLA_HOOK_INFO_DESC); + if (!nest2) + goto cancel_nest; + + ret = nla_put_string(nlskb, NFTA_CHAIN_TABLE, chain->table->name); + if (ret) + goto cancel_nest; + + ret = nla_put_string(nlskb, NFTA_CHAIN_NAME, chain->name); + if (ret) + goto cancel_nest; + + nla_nest_end(nlskb, nest2); + nla_nest_end(nlskb, nest); + return ret; + +cancel_nest: + nla_nest_cancel(nlskb, nest); + return -EMSGSIZE; +} + +static int nfnl_hook_dump_one(struct sk_buff *nlskb, + const struct nfnl_dump_hook_data *ctx, + const struct nf_hook_ops *ops, + unsigned int seq) +{ + u16 event = nfnl_msg_type(NFNL_SUBSYS_HOOK, NFNL_MSG_HOOK_GET); + unsigned int portid = NETLINK_CB(nlskb).portid; + struct nlmsghdr *nlh; + int ret = -EMSGSIZE; +#ifdef CONFIG_KALLSYMS + char sym[KSYM_SYMBOL_LEN]; + char *module_name; +#endif + nlh = nfnl_msg_put(nlskb, portid, seq, event, + NLM_F_MULTI, ops->pf, NFNETLINK_V0, 0); + if (!nlh) + goto nla_put_failure; + +#ifdef CONFIG_KALLSYMS + ret = snprintf(sym, sizeof(sym), "%ps", ops->hook); + if (ret >= sizeof(sym)) { + ret = -EINVAL; + goto nla_put_failure; + } + + module_name = strstr(sym, " ["); + if (module_name) { + char *end; + + module_name += 2; + end = strchr(module_name, ']'); + if (end) { + *end = 0; + + ret = nla_put_string(nlskb, NFNLA_HOOK_MODULE_NAME, module_name); + if (ret) + goto nla_put_failure; + } + } + + ret = nla_put_string(nlskb, NFNLA_HOOK_FUNCTION_NAME, sym); + if (ret) + goto nla_put_failure; +#endif + + ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(ops->hooknum)); + if (ret) + goto nla_put_failure; + + ret = nla_put_be32(nlskb, NFNLA_HOOK_PRIORITY, htonl(ops->priority)); + if (ret) + goto nla_put_failure; + + ret = nfnl_hook_put_nft_chain_info(nlskb, ctx, seq, ops); + if (ret) + goto nla_put_failure; + + nlmsg_end(nlskb, nlh); + return 0; +nla_put_failure: + nlmsg_trim(nlskb, nlh); + return ret; +} + +static const struct nf_hook_entries * +nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) +{ + const struct nf_hook_entries *hook_head = NULL; + struct net_device *netdev; + + switch (pf) { + case NFPROTO_IPV4: + if (hook >= ARRAY_SIZE(net->nf.hooks_ipv4)) + return ERR_PTR(-EINVAL); + hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); + break; + case NFPROTO_IPV6: + if (hook >= ARRAY_SIZE(net->nf.hooks_ipv6)) + return ERR_PTR(-EINVAL); + hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); + break; + case NFPROTO_ARP: +#ifdef CONFIG_NETFILTER_FAMILY_ARP + if (hook >= ARRAY_SIZE(net->nf.hooks_arp)) + return ERR_PTR(-EINVAL); + hook_head = rcu_dereference(net->nf.hooks_arp[hook]); +#endif + break; + case NFPROTO_BRIDGE: +#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE + if (hook >= ARRAY_SIZE(net->nf.hooks_bridge)) + return ERR_PTR(-EINVAL); + hook_head = rcu_dereference(net->nf.hooks_bridge[hook]); +#endif + break; +#if IS_ENABLED(CONFIG_DECNET) + case NFPROTO_DECNET: + if (hook >= ARRAY_SIZE(net->nf.hooks_decnet)) + return ERR_PTR(-EINVAL); + hook_head = rcu_dereference(net->nf.hooks_decnet[hook]); + break; +#endif +#ifdef CONFIG_NETFILTER_INGRESS + case NFPROTO_NETDEV: + if (hook != NF_NETDEV_INGRESS) + return ERR_PTR(-EOPNOTSUPP); + + if (!dev) + return ERR_PTR(-ENODEV); + + netdev = dev_get_by_name_rcu(net, dev); + if (!netdev) + return ERR_PTR(-ENODEV); + + return rcu_dereference(netdev->nf_hooks_ingress); +#endif + default: + return ERR_PTR(-EPROTONOSUPPORT); + } + + return hook_head; +} + +static int nfnl_hook_dump(struct sk_buff *nlskb, + struct netlink_callback *cb) +{ + struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + struct nfnl_dump_hook_data *ctx = cb->data; + int err, family = nfmsg->nfgen_family; + struct net *net = sock_net(nlskb->sk); + struct nf_hook_ops * const *ops; + const struct nf_hook_entries *e; + unsigned int i = cb->args[0]; + + rcu_read_lock(); + + e = nfnl_hook_entries_head(family, ctx->hook, net, ctx->devname); + if (!e) + goto done; + + if (IS_ERR(e)) { + cb->seq++; + goto done; + } + + if ((unsigned long)e != ctx->headv || i >= e->num_hook_entries) + cb->seq++; + + ops = nf_hook_entries_get_hook_ops(e); + + for (; i < e->num_hook_entries; i++) { + err = nfnl_hook_dump_one(nlskb, ctx, ops[i], cb->seq); + if (err) + break; + } + +done: + nl_dump_check_consistent(cb, nlmsg_hdr(nlskb)); + rcu_read_unlock(); + cb->args[0] = i; + return nlskb->len; +} + +static int nfnl_hook_dump_start(struct netlink_callback *cb) +{ + const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + const struct nlattr * const *nla = cb->data; + struct nfnl_dump_hook_data *ctx = NULL; + struct net *net = sock_net(cb->skb->sk); + u8 family = nfmsg->nfgen_family; + char name[IFNAMSIZ] = ""; + const void *head; + u32 hooknum; + + hooknum = ntohl(nla_get_be32(nla[NFNLA_HOOK_HOOKNUM])); + if (hooknum > 255) + return -EINVAL; + + if (family == NFPROTO_NETDEV) { + if (!nla[NFNLA_HOOK_DEV]) + return -EINVAL; + + nla_strscpy(name, nla[NFNLA_HOOK_DEV], sizeof(name)); + } + + rcu_read_lock(); + /* Not dereferenced; for consistency check only */ + head = nfnl_hook_entries_head(family, hooknum, net, name); + rcu_read_unlock(); + + if (head && IS_ERR(head)) + return PTR_ERR(head); + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + strscpy(ctx->devname, name, sizeof(ctx->devname)); + ctx->headv = (unsigned long)head; + ctx->hook = hooknum; + + cb->seq = 1; + cb->data = ctx; + + return 0; +} + +static int nfnl_hook_dump_stop(struct netlink_callback *cb) +{ + kfree(cb->data); + return 0; +} + +static int nfnl_hook_get(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + if (!nla[NFNLA_HOOK_HOOKNUM]) + return -EINVAL; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nfnl_hook_dump_start, + .done = nfnl_hook_dump_stop, + .dump = nfnl_hook_dump, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nf_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + return -EOPNOTSUPP; +} + +static const struct nfnl_callback nfnl_hook_cb[NFNL_MSG_HOOK_MAX] = { + [NFNL_MSG_HOOK_GET] = { + .call = nfnl_hook_get, + .type = NFNL_CB_RCU, + .attr_count = NFNLA_HOOK_MAX, + .policy = nfnl_hook_nla_policy + }, +}; + +static const struct nfnetlink_subsystem nfhook_subsys = { + .name = "nfhook", + .subsys_id = NFNL_SUBSYS_HOOK, + .cb_count = NFNL_MSG_HOOK_MAX, + .cb = nfnl_hook_cb, +}; + +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_HOOK); + +static int __init nfnetlink_hook_init(void) +{ + return nfnetlink_subsys_register(&nfhook_subsys); +} + +static void __exit nfnetlink_hook_exit(void) +{ + nfnetlink_subsys_unregister(&nfhook_subsys); +} + +module_init(nfnetlink_hook_init); +module_exit(nfnetlink_hook_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); +MODULE_DESCRIPTION("nfnetlink_hook: list registered netfilter hooks"); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 587086b18c36..691ef4cffdd9 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -871,15 +871,14 @@ static int nfulnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfula[]) { struct nfnl_log_net *log = nfnl_log_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int16_t group_num = ntohs(nfmsg->res_id); + u_int16_t group_num = ntohs(info->nfmsg->res_id); struct nfulnl_msg_config_cmd *cmd = NULL; struct nfulnl_instance *inst; u16 flags = 0; int ret = 0; if (nfula[NFULA_CFG_CMD]) { - u_int8_t pf = nfmsg->nfgen_family; + u_int8_t pf = info->nfmsg->nfgen_family; cmd = nla_data(nfula[NFULA_CFG_CMD]); /* Commands without queue context */ diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index f37a575ebd7f..f774de0fc24f 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1051,8 +1051,7 @@ static int nfqnl_recv_verdict_batch(struct sk_buff *skb, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u16 queue_num = ntohs(nfmsg->res_id); + u16 queue_num = ntohs(info->nfmsg->res_id); struct nf_queue_entry *entry, *tmp; struct nfqnl_msg_verdict_hdr *vhdr; struct nfqnl_instance *queue; @@ -1160,8 +1159,7 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int16_t queue_num = ntohs(nfmsg->res_id); + u_int16_t queue_num = ntohs(info->nfmsg->res_id); struct nfqnl_msg_verdict_hdr *vhdr; enum ip_conntrack_info ctinfo; struct nfqnl_instance *queue; @@ -1243,8 +1241,7 @@ static int nfqnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int16_t queue_num = ntohs(nfmsg->res_id); + u_int16_t queue_num = ntohs(info->nfmsg->res_id); struct nfqnl_msg_config_cmd *cmd = NULL; struct nfqnl_instance *queue; __u32 flags = 0, mask = 0; diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 363bdd7044ec..5b02408a920b 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -18,7 +18,7 @@ static unsigned int nft_do_chain_ipv4(void *priv, struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv4(&pkt, skb); + nft_set_pktinfo_ipv4(&pkt); return nft_do_chain(&pkt, priv); } @@ -62,7 +62,7 @@ static unsigned int nft_do_chain_arp(void *priv, struct sk_buff *skb, struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_unspec(&pkt, skb); + nft_set_pktinfo_unspec(&pkt); return nft_do_chain(&pkt, priv); } @@ -102,7 +102,7 @@ static unsigned int nft_do_chain_ipv6(void *priv, struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv6(&pkt, skb); + nft_set_pktinfo_ipv6(&pkt); return nft_do_chain(&pkt, priv); } @@ -149,10 +149,10 @@ static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb, switch (state->pf) { case NFPROTO_IPV4: - nft_set_pktinfo_ipv4(&pkt, skb); + nft_set_pktinfo_ipv4(&pkt); break; case NFPROTO_IPV6: - nft_set_pktinfo_ipv6(&pkt, skb); + nft_set_pktinfo_ipv6(&pkt); break; default: break; @@ -174,7 +174,7 @@ static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb, ingress_state.hook = NF_INET_INGRESS; nft_set_pktinfo(&pkt, skb, &ingress_state); - if (nft_set_pktinfo_ipv4_ingress(&pkt, skb) < 0) + if (nft_set_pktinfo_ipv4_ingress(&pkt) < 0) return NF_DROP; break; case htons(ETH_P_IPV6): @@ -182,7 +182,7 @@ static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb, ingress_state.hook = NF_INET_INGRESS; nft_set_pktinfo(&pkt, skb, &ingress_state); - if (nft_set_pktinfo_ipv6_ingress(&pkt, skb) < 0) + if (nft_set_pktinfo_ipv6_ingress(&pkt) < 0) return NF_DROP; break; default: @@ -238,13 +238,13 @@ nft_do_chain_bridge(void *priv, switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): - nft_set_pktinfo_ipv4_validate(&pkt, skb); + nft_set_pktinfo_ipv4_validate(&pkt); break; case htons(ETH_P_IPV6): - nft_set_pktinfo_ipv6_validate(&pkt, skb); + nft_set_pktinfo_ipv6_validate(&pkt); break; default: - nft_set_pktinfo_unspec(&pkt, skb); + nft_set_pktinfo_unspec(&pkt); break; } @@ -293,13 +293,13 @@ static unsigned int nft_do_chain_netdev(void *priv, struct sk_buff *skb, switch (skb->protocol) { case htons(ETH_P_IP): - nft_set_pktinfo_ipv4_validate(&pkt, skb); + nft_set_pktinfo_ipv4_validate(&pkt); break; case htons(ETH_P_IPV6): - nft_set_pktinfo_ipv6_validate(&pkt, skb); + nft_set_pktinfo_ipv6_validate(&pkt); break; default: - nft_set_pktinfo_unspec(&pkt, skb); + nft_set_pktinfo_unspec(&pkt); break; } diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c index eac4a901233f..98e4946100c5 100644 --- a/net/netfilter/nft_chain_nat.c +++ b/net/netfilter/nft_chain_nat.c @@ -17,12 +17,12 @@ static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, switch (state->pf) { #ifdef CONFIG_NF_TABLES_IPV4 case NFPROTO_IPV4: - nft_set_pktinfo_ipv4(&pkt, skb); + nft_set_pktinfo_ipv4(&pkt); break; #endif #ifdef CONFIG_NF_TABLES_IPV6 case NFPROTO_IPV6: - nft_set_pktinfo_ipv6(&pkt, skb); + nft_set_pktinfo_ipv6(&pkt); break; #endif default: diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c index edd02cda57fc..925db0dce48d 100644 --- a/net/netfilter/nft_chain_route.c +++ b/net/netfilter/nft_chain_route.c @@ -26,7 +26,7 @@ static unsigned int nf_route_table_hook4(void *priv, u8 tos; nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv4(&pkt, skb); + nft_set_pktinfo_ipv4(&pkt); mark = skb->mark; iph = ip_hdr(skb); @@ -74,7 +74,7 @@ static unsigned int nf_route_table_hook6(void *priv, int err; nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv6(&pkt, skb); + nft_set_pktinfo_ipv6(&pkt); /* save source/dest address, mark, hoplimit, flowlabel, priority */ memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr)); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 5415ab14400d..639c337c885b 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -57,8 +57,13 @@ union nft_entry { }; static inline void -nft_compat_set_par(struct xt_action_param *par, void *xt, const void *xt_info) +nft_compat_set_par(struct xt_action_param *par, + const struct nft_pktinfo *pkt, + const void *xt, const void *xt_info) { + par->state = pkt->state; + par->thoff = nft_thoff(pkt); + par->fragoff = pkt->fragoff; par->target = xt; par->targinfo = xt_info; par->hotdrop = false; @@ -71,13 +76,14 @@ static void nft_target_eval_xt(const struct nft_expr *expr, void *info = nft_expr_priv(expr); struct xt_target *target = expr->ops->data; struct sk_buff *skb = pkt->skb; + struct xt_action_param xt; int ret; - nft_compat_set_par((struct xt_action_param *)&pkt->xt, target, info); + nft_compat_set_par(&xt, pkt, target, info); - ret = target->target(skb, &pkt->xt); + ret = target->target(skb, &xt); - if (pkt->xt.hotdrop) + if (xt.hotdrop) ret = NF_DROP; switch (ret) { @@ -97,13 +103,14 @@ static void nft_target_eval_bridge(const struct nft_expr *expr, void *info = nft_expr_priv(expr); struct xt_target *target = expr->ops->data; struct sk_buff *skb = pkt->skb; + struct xt_action_param xt; int ret; - nft_compat_set_par((struct xt_action_param *)&pkt->xt, target, info); + nft_compat_set_par(&xt, pkt, target, info); - ret = target->target(skb, &pkt->xt); + ret = target->target(skb, &xt); - if (pkt->xt.hotdrop) + if (xt.hotdrop) ret = NF_DROP; switch (ret) { @@ -350,13 +357,14 @@ static void __nft_match_eval(const struct nft_expr *expr, { struct xt_match *match = expr->ops->data; struct sk_buff *skb = pkt->skb; + struct xt_action_param xt; bool ret; - nft_compat_set_par((struct xt_action_param *)&pkt->xt, match, info); + nft_compat_set_par(&xt, pkt, match, info); - ret = match->match(skb, (struct xt_action_param *)&pkt->xt); + ret = match->match(skb, &xt); - if (pkt->xt.hotdrop) { + if (xt.hotdrop) { regs->verdict.code = NF_DROP; return; } @@ -617,7 +625,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const tb[]) { - struct nfgenmsg *nfmsg; + u8 family = info->nfmsg->nfgen_family; const char *name, *fmt; struct sk_buff *skb2; int ret = 0, target; @@ -632,9 +640,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, rev = ntohl(nla_get_be32(tb[NFTA_COMPAT_REV])); target = ntohl(nla_get_be32(tb[NFTA_COMPAT_TYPE])); - nfmsg = nlmsg_data(info->nlh); - - switch(nfmsg->nfgen_family) { + switch(family) { case AF_INET: fmt = "ipt_%s"; break; @@ -648,8 +654,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, fmt = "arpt_%s"; break; default: - pr_err("nft_compat: unsupported protocol %d\n", - nfmsg->nfgen_family); + pr_err("nft_compat: unsupported protocol %d\n", family); return -EINVAL; } @@ -657,9 +662,8 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, return -EINVAL; rcu_read_unlock(); - try_then_request_module(xt_find_revision(nfmsg->nfgen_family, name, - rev, target, &ret), - fmt, name); + try_then_request_module(xt_find_revision(family, name, rev, target, &ret), + fmt, name); if (ret < 0) goto out_put; @@ -674,8 +678,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), NFNL_MSG_COMPAT_GET, - nfmsg->nfgen_family, - name, ret, target) <= 0) { + family, name, ret, target) <= 0) { kfree_skb(skb2); goto out_put; } diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index f64f0017e9a5..af4ee874a067 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -10,8 +10,10 @@ #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> +#include <linux/sctp.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> +#include <net/sctp/sctp.h> #include <net/tcp.h> struct nft_exthdr { @@ -42,6 +44,9 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, unsigned int offset = 0; int err; + if (pkt->skb->protocol != htons(ETH_P_IPV6)) + goto err; + err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); if (priv->flags & NFT_EXTHDR_F_PRESENT) { nft_reg_store8(dest, err >= 0); @@ -162,10 +167,10 @@ nft_tcp_header_pointer(const struct nft_pktinfo *pkt, { struct tcphdr *tcph; - if (!pkt->tprot_set || pkt->tprot != IPPROTO_TCP) + if (pkt->tprot != IPPROTO_TCP) return NULL; - tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, sizeof(*tcph), buffer); + tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(*tcph), buffer); if (!tcph) return NULL; @@ -173,7 +178,7 @@ nft_tcp_header_pointer(const struct nft_pktinfo *pkt, if (*tcphdr_len < sizeof(*tcph) || *tcphdr_len > len) return NULL; - return skb_header_pointer(pkt->skb, pkt->xt.thoff, *tcphdr_len, buffer); + return skb_header_pointer(pkt->skb, nft_thoff(pkt), *tcphdr_len, buffer); } static void nft_exthdr_tcp_eval(const struct nft_expr *expr, @@ -249,7 +254,7 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, return; if (skb_ensure_writable(pkt->skb, - pkt->xt.thoff + i + priv->len)) + nft_thoff(pkt) + i + priv->len)) return; tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, @@ -300,6 +305,48 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, } } +static void nft_exthdr_sctp_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + unsigned int offset = nft_thoff(pkt) + sizeof(struct sctphdr); + struct nft_exthdr *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + const struct sctp_chunkhdr *sch; + struct sctp_chunkhdr _sch; + + if (pkt->tprot != IPPROTO_SCTP) + goto err; + + do { + sch = skb_header_pointer(pkt->skb, offset, sizeof(_sch), &_sch); + if (!sch || !sch->length) + break; + + if (sch->type == priv->type) { + if (priv->flags & NFT_EXTHDR_F_PRESENT) { + nft_reg_store8(dest, true); + return; + } + if (priv->offset + priv->len > ntohs(sch->length) || + offset + ntohs(sch->length) > pkt->skb->len) + break; + + dest[priv->len / NFT_REG32_SIZE] = 0; + if (skb_copy_bits(pkt->skb, offset + priv->offset, + dest, priv->len) < 0) + break; + return; + } + offset += SCTP_PAD4(ntohs(sch->length)); + } while (offset < pkt->skb->len); +err: + if (priv->flags & NFT_EXTHDR_F_PRESENT) + nft_reg_store8(dest, false); + else + regs->verdict.code = NFT_BREAK; +} + static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_DREG] = { .type = NLA_U32 }, [NFTA_EXTHDR_TYPE] = { .type = NLA_U8 }, @@ -499,6 +546,14 @@ static const struct nft_expr_ops nft_exthdr_tcp_set_ops = { .dump = nft_exthdr_dump_set, }; +static const struct nft_expr_ops nft_exthdr_sctp_ops = { + .type = &nft_exthdr_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), + .eval = nft_exthdr_sctp_eval, + .init = nft_exthdr_init, + .dump = nft_exthdr_dump, +}; + static const struct nft_expr_ops * nft_exthdr_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -529,6 +584,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx, return &nft_exthdr_ipv4_ops; } break; + case NFT_EXTHDR_OP_SCTP: + if (tb[NFTA_EXTHDR_DREG]) + return &nft_exthdr_sctp_ops; + break; } return ERR_PTR(-EOPNOTSUPP); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 4843dd2b410c..0af34ad41479 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -291,7 +291,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) { case IPPROTO_TCP: - tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, + tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); if (unlikely(!tcph || tcph->fin || tcph->rst)) goto out; diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c new file mode 100644 index 000000000000..913ac45167f2 --- /dev/null +++ b/net/netfilter/nft_last.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0-only +#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> + +struct nft_last_priv { + unsigned long last_jiffies; + unsigned int last_set; +}; + +static const struct nla_policy nft_last_policy[NFTA_LAST_MAX + 1] = { + [NFTA_LAST_SET] = { .type = NLA_U32 }, + [NFTA_LAST_MSECS] = { .type = NLA_U64 }, +}; + +static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_last_priv *priv = nft_expr_priv(expr); + u64 last_jiffies; + int err; + + if (tb[NFTA_LAST_MSECS]) { + err = nf_msecs_to_jiffies64(tb[NFTA_LAST_MSECS], &last_jiffies); + if (err < 0) + return err; + + priv->last_jiffies = jiffies + (unsigned long)last_jiffies; + priv->last_set = 1; + } + + return 0; +} + +static void nft_last_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt) +{ + struct nft_last_priv *priv = nft_expr_priv(expr); + + priv->last_jiffies = jiffies; + priv->last_set = 1; +} + +static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + struct nft_last_priv *priv = nft_expr_priv(expr); + __be64 msecs; + + if (time_before(jiffies, priv->last_jiffies)) + priv->last_set = 0; + + if (priv->last_set) + msecs = nf_jiffies64_to_msecs(jiffies - priv->last_jiffies); + else + msecs = 0; + + if (nla_put_be32(skb, NFTA_LAST_SET, htonl(priv->last_set)) || + nla_put_be64(skb, NFTA_LAST_MSECS, msecs, NFTA_LAST_PAD)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static const struct nft_expr_ops nft_last_ops = { + .type = &nft_last_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_last_priv)), + .eval = nft_last_eval, + .init = nft_last_init, + .dump = nft_last_dump, +}; + +struct nft_expr_type nft_last_type __read_mostly = { + .name = "last", + .ops = &nft_last_ops, + .policy = nft_last_policy, + .maxattr = NFTA_LAST_MAX, + .flags = NFT_EXPR_STATEFUL, + .owner = THIS_MODULE, +}; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index a479f8a1270c..90becbf5bff3 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -23,6 +23,37 @@ struct nft_lookup { struct nft_set_binding binding; }; +#ifdef CONFIG_RETPOLINE +bool nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) +{ + if (set->ops == &nft_set_hash_fast_type.ops) + return nft_hash_lookup_fast(net, set, key, ext); + if (set->ops == &nft_set_hash_type.ops) + return nft_hash_lookup(net, set, key, ext); + + if (set->ops == &nft_set_rhash_type.ops) + return nft_rhash_lookup(net, set, key, ext); + + if (set->ops == &nft_set_bitmap_type.ops) + return nft_bitmap_lookup(net, set, key, ext); + + if (set->ops == &nft_set_pipapo_type.ops) + return nft_pipapo_lookup(net, set, key, ext); +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) + if (set->ops == &nft_set_pipapo_avx2_type.ops) + return nft_pipapo_avx2_lookup(net, set, key, ext); +#endif + + if (set->ops == &nft_set_rbtree_type.ops) + return nft_rbtree_lookup(net, set, key, ext); + + WARN_ON_ONCE(1); + return set->ops->lookup(net, set, key, ext); +} +EXPORT_SYMBOL_GPL(nft_set_do_lookup); +#endif + void nft_lookup_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -33,8 +64,8 @@ void nft_lookup_eval(const struct nft_expr *expr, const struct net *net = nft_net(pkt); bool found; - found = set->ops->lookup(net, set, ®s->data[priv->sreg], &ext) ^ - priv->invert; + found = nft_set_do_lookup(net, set, ®s->data[priv->sreg], &ext) ^ + priv->invert; if (!found) { ext = nft_set_catchall_lookup(net, set); if (!ext) { diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 7e47edee88ee..94b2327e71dc 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -9,7 +9,7 @@ #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> #define nft_objref_priv(expr) *((struct nft_object **)nft_expr_priv(expr)) @@ -110,7 +110,7 @@ static void nft_objref_map_eval(const struct nft_expr *expr, struct nft_object *obj; bool found; - found = set->ops->lookup(net, set, ®s->data[priv->sreg], &ext); + found = nft_set_do_lookup(net, set, ®s->data[priv->sreg], &ext); if (!found) { ext = nft_set_catchall_lookup(net, set); if (!ext) { diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index ac61f708b82d..d82677e83400 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -28,6 +28,11 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nf_osf_data data; struct tcphdr _tcph; + if (pkt->tprot != IPPROTO_TCP) { + regs->verdict.code = NFT_BREAK; + return; + } + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); if (!tcp) { diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 501c5b24cc39..a44b14f6c0dc 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -110,7 +110,7 @@ void nft_payload_eval(const struct nft_expr *expr, case NFT_PAYLOAD_TRANSPORT_HEADER: if (!pkt->tprot_set) goto err; - offset = pkt->xt.thoff; + offset = nft_thoff(pkt); break; default: BUG(); @@ -507,7 +507,7 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt, *l4csum_offset = offsetof(struct tcphdr, check); break; case IPPROTO_UDP: - if (!nft_payload_udp_checksum(skb, pkt->xt.thoff)) + if (!nft_payload_udp_checksum(skb, nft_thoff(pkt))) return -1; fallthrough; case IPPROTO_UDPLITE: @@ -520,7 +520,7 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt, return -1; } - *l4csum_offset += pkt->xt.thoff; + *l4csum_offset += nft_thoff(pkt); return 0; } @@ -612,7 +612,7 @@ static void nft_payload_set_eval(const struct nft_expr *expr, case NFT_PAYLOAD_TRANSPORT_HEADER: if (!pkt->tprot_set) goto err; - offset = pkt->xt.thoff; + offset = nft_thoff(pkt); break; default: BUG(); @@ -643,7 +643,7 @@ static void nft_payload_set_eval(const struct nft_expr *expr, if (priv->csum_type == NFT_PAYLOAD_CSUM_SCTP && pkt->tprot == IPPROTO_SCTP && skb->ip_summed != CHECKSUM_PARTIAL) { - if (nft_payload_csum_sctp(skb, pkt->xt.thoff)) + if (nft_payload_csum_sctp(skb, nft_thoff(pkt))) goto err; } diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 95090186ee90..554caf967baa 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -28,7 +28,7 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, nft_hook(pkt)); break; case NFT_REJECT_TCP_RST: - nf_send_reset(nft_net(pkt), pkt->xt.state->sk, + nf_send_reset(nft_net(pkt), nft_sk(pkt), pkt->skb, nft_hook(pkt)); break; case NFT_REJECT_ICMPX_UNREACH: @@ -45,7 +45,7 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, priv->icmp_code, nft_hook(pkt)); break; case NFT_REJECT_TCP_RST: - nf_send_reset6(nft_net(pkt), pkt->xt.state->sk, + nf_send_reset6(nft_net(pkt), nft_sk(pkt), pkt->skb, nft_hook(pkt)); break; case NFT_REJECT_ICMPX_UNREACH: diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 2a81ea421819..e7ae5914971e 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -73,8 +73,9 @@ nft_bitmap_active(const u8 *bitmap, u32 idx, u32 off, u8 genmask) return (bitmap[idx] & (0x3 << off)) & (genmask << off); } -static bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +INDIRECT_CALLABLE_SCOPE +bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { const struct nft_bitmap *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 7b3d0a78c569..df40314de21f 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -74,8 +74,9 @@ static const struct rhashtable_params nft_rhash_params = { .automatic_shrinking = true, }; -static bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +INDIRECT_CALLABLE_SCOPE +bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_rhash *priv = nft_set_priv(set); const struct nft_rhash_elem *he; @@ -446,8 +447,9 @@ struct nft_hash_elem { struct nft_set_ext ext; }; -static bool nft_hash_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +INDIRECT_CALLABLE_SCOPE +bool nft_hash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); @@ -484,9 +486,10 @@ static void *nft_hash_get(const struct net *net, const struct nft_set *set, return ERR_PTR(-ENOENT); } -static bool nft_hash_lookup_fast(const struct net *net, - const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +INDIRECT_CALLABLE_SCOPE +bool nft_hash_lookup_fast(const struct net *net, + const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index d84afb8fa79a..25a75591583e 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -178,8 +178,6 @@ struct nft_pipapo_elem { int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, union nft_pipapo_map_bucket *mt, bool match_only); -bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); /** * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index eabdb8d552ee..e517663e0cd1 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -142,7 +142,6 @@ static void nft_pipapo_avx2_fill(unsigned long *data, int start, int len) * @map: Bitmap to be scanned for set bits * @dst: Destination bitmap * @mt: Mapping table containing bit set specifiers - * @len: Length of bitmap in longs * @last: Return index of first set bit, if this is the last field * * This is an alternative implementation of pipapo_refill() suitable for usage @@ -1109,7 +1108,7 @@ bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features, * nft_pipapo_avx2_lookup() - Lookup function for AVX2 implementation * @net: Network namespace * @set: nftables API set representation - * @elem: nftables API element representation containing key data + * @key: nftables API element representation containing key data * @ext: nftables API extension pointer, filled with matching reference * * For more details, see DOC: Theory of Operation in nft_set_pipapo.c. @@ -1136,8 +1135,13 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, m = rcu_dereference(priv->match); - /* This also protects access to all data related to scratch maps */ - kernel_fpu_begin(); + /* This also protects access to all data related to scratch maps. + * + * Note that we don't need a valid MXCSR state for any of the + * operations we use here, so pass 0 as mask and spare a LDMXCSR + * instruction. + */ + kernel_fpu_begin_mask(0); scratch = *raw_cpu_ptr(m->scratch_aligned); if (unlikely(!scratch)) { diff --git a/net/netfilter/nft_set_pipapo_avx2.h b/net/netfilter/nft_set_pipapo_avx2.h index 394bcb704db7..dbb6aaca8a7a 100644 --- a/net/netfilter/nft_set_pipapo_avx2.h +++ b/net/netfilter/nft_set_pipapo_avx2.h @@ -5,8 +5,6 @@ #include <asm/fpu/xstate.h> #define NFT_PIPAPO_ALIGN (XSAVE_YMM_SIZE / BITS_PER_BYTE) -bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est); #endif /* defined(CONFIG_X86_64) && !defined(CONFIG_UML) */ diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 9e36eb4a7429..d600a566da32 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -107,8 +107,9 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set return false; } -static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +INDIRECT_CALLABLE_SCOPE +bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 4fda8b3f1762..a0109fa1e92d 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -109,7 +109,7 @@ static void nft_synproxy_do_eval(const struct nft_synproxy *priv, { struct synproxy_options opts = {}; struct sk_buff *skb = pkt->skb; - int thoff = pkt->xt.thoff; + int thoff = nft_thoff(pkt); const struct tcphdr *tcp; struct tcphdr _tcph; @@ -123,7 +123,7 @@ static void nft_synproxy_do_eval(const struct nft_synproxy *priv, return; } - tcp = skb_header_pointer(skb, pkt->xt.thoff, + tcp = skb_header_pointer(skb, thoff, sizeof(struct tcphdr), &_tcph); if (!tcp) { diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index accef672088c..b5b09a902c7a 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -30,6 +30,12 @@ static void nft_tproxy_eval_v4(const struct nft_expr *expr, __be16 tport = 0; struct sock *sk; + if (pkt->tprot != IPPROTO_TCP && + pkt->tprot != IPPROTO_UDP) { + regs->verdict.code = NFT_BREAK; + return; + } + hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (!hp) { regs->verdict.code = NFT_BREAK; @@ -82,16 +88,17 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr, const struct nft_tproxy *priv = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; const struct ipv6hdr *iph = ipv6_hdr(skb); - struct in6_addr taddr; - int thoff = pkt->xt.thoff; + int thoff = nft_thoff(pkt); struct udphdr _hdr, *hp; + struct in6_addr taddr; __be16 tport = 0; struct sock *sk; int l4proto; memset(&taddr, 0, sizeof(taddr)); - if (!pkt->tprot_set) { + if (pkt->tprot != IPPROTO_TCP && + pkt->tprot != IPPROTO_UDP) { regs->verdict.code = NFT_BREAK; return; } diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c index 9cdc16b0d0d8..b6a015aee0ce 100644 --- a/net/netfilter/xt_AUDIT.c +++ b/net/netfilter/xt_AUDIT.c @@ -117,7 +117,7 @@ static int audit_tg_check(const struct xt_tgchk_param *par) const struct xt_audit_info *info = par->targinfo; if (info->type > XT_AUDIT_TYPE_MAX) { - pr_info_ratelimited("Audit type out of range (valid range: 0..%hhu)\n", + pr_info_ratelimited("Audit type out of range (valid range: 0..%u)\n", XT_AUDIT_TYPE_MAX); return -ERANGE; } diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index d4deee39158b..12404d221026 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -172,7 +172,6 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, goto err2; } - ret = 0; if ((info->ct_events || info->exp_events) && !nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events, GFP_KERNEL)) { diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index 24d4afb9988d..8b4fd27857f2 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -8,16 +8,14 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/skbuff.h> -#include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_limit.h> struct xt_limit_priv { - spinlock_t lock; unsigned long prev; - uint32_t credit; + u32 credit; }; MODULE_LICENSE("GPL"); @@ -66,22 +64,31 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rateinfo *r = par->matchinfo; struct xt_limit_priv *priv = r->master; - unsigned long now = jiffies; - - spin_lock_bh(&priv->lock); - priv->credit += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY; - if (priv->credit > r->credit_cap) - priv->credit = r->credit_cap; - - if (priv->credit >= r->cost) { - /* We're not limited. */ - priv->credit -= r->cost; - spin_unlock_bh(&priv->lock); - return true; - } - - spin_unlock_bh(&priv->lock); - return false; + unsigned long now; + u32 old_credit, new_credit, credit_increase = 0; + bool ret; + + /* fastpath if there is nothing to update */ + if ((READ_ONCE(priv->credit) < r->cost) && (READ_ONCE(priv->prev) == jiffies)) + return false; + + do { + now = jiffies; + credit_increase += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY; + old_credit = READ_ONCE(priv->credit); + new_credit = old_credit; + new_credit += credit_increase; + if (new_credit > r->credit_cap) + new_credit = r->credit_cap; + if (new_credit >= r->cost) { + ret = true; + new_credit -= r->cost; + } else { + ret = false; + } + } while (cmpxchg(&priv->credit, old_credit, new_credit) != old_credit); + + return ret; } /* Precision saver. */ @@ -122,7 +129,6 @@ static int limit_mt_check(const struct xt_mtchk_param *par) r->credit_cap = priv->credit; /* Credits full. */ r->cost = user2credits(r->avg); } - spin_lock_init(&priv->lock); return 0; } diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index f28c8947c730..91a19c3ea1a3 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -105,7 +105,7 @@ static int netlbl_calipso_add(struct sk_buff *skb, struct genl_info *info) !info->attrs[NLBL_CALIPSO_A_MTYPE]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CALIPSO_A_MTYPE])) { case CALIPSO_MAP_PASS: ret_val = netlbl_calipso_add_pass(info, &audit_info); @@ -287,7 +287,7 @@ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NLBL_CALIPSO_A_DOI]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); cb_arg.doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); cb_arg.audit_info = &audit_info; ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain, diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 4f50a64315cf..baf235721c43 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -410,7 +410,7 @@ static int netlbl_cipsov4_add(struct sk_buff *skb, struct genl_info *info) !info->attrs[NLBL_CIPSOV4_A_MTYPE]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CIPSOV4_A_MTYPE])) { case CIPSO_V4_MAP_TRANS: ret_val = netlbl_cipsov4_add_std(info, &audit_info); @@ -709,7 +709,7 @@ static int netlbl_cipsov4_remove(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NLBL_CIPSOV4_A_DOI]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); cb_arg.doi = nla_get_u32(info->attrs[NLBL_CIPSOV4_A_DOI]); cb_arg.audit_info = &audit_info; ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain, diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index dc8c39f51f7d..8158a25972b4 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -929,7 +929,7 @@ struct netlbl_dommap_def *netlbl_domhsh_getentry_af6(const char *domain, * @cb_arg: argument for the callback function * * Description: - * Interate over the domain mapping hash table, skipping the first @skip_bkt + * Iterate over the domain mapping hash table, skipping the first @skip_bkt * buckets and @skip_chain entries. For each entry in the table call * @callback, if @callback returns a negative value stop 'walking' through the * table and return. Updates the values in @skip_bkt and @skip_chain on diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 5e1239cef000..beb0e573266d 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -719,7 +719,7 @@ int netlbl_catmap_walkrng(struct netlbl_lsm_catmap *catmap, u32 offset) * it in @bitmap. The @offset must be aligned to an unsigned long and will be * updated on return if different from what was requested; if the catmap is * empty at the requested offset and beyond, the @offset is set to (u32)-1. - * Returns zero on sucess, negative values on failure. + * Returns zero on success, negative values on failure. * */ int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap, diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index ca52f5085989..032b7d7b32c7 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -76,6 +76,7 @@ static const struct nla_policy netlbl_mgmt_genl_policy[NLBL_MGMT_A_MAX + 1] = { static int netlbl_mgmt_add_common(struct genl_info *info, struct netlbl_audit *audit_info) { + void *pmap = NULL; int ret_val = -EINVAL; struct netlbl_domaddr_map *addrmap = NULL; struct cipso_v4_doi *cipsov4 = NULL; @@ -175,6 +176,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = -ENOMEM; goto add_free_addrmap; } + pmap = map; map->list.addr = addr->s_addr & mask->s_addr; map->list.mask = mask->s_addr; map->list.valid = 1; @@ -183,10 +185,8 @@ static int netlbl_mgmt_add_common(struct genl_info *info, map->def.cipso = cipsov4; ret_val = netlbl_af4list_add(&map->list, &addrmap->list4); - if (ret_val != 0) { - kfree(map); - goto add_free_addrmap; - } + if (ret_val != 0) + goto add_free_map; entry->family = AF_INET; entry->def.type = NETLBL_NLTYPE_ADDRSELECT; @@ -223,6 +223,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = -ENOMEM; goto add_free_addrmap; } + pmap = map; map->list.addr = *addr; map->list.addr.s6_addr32[0] &= mask->s6_addr32[0]; map->list.addr.s6_addr32[1] &= mask->s6_addr32[1]; @@ -235,10 +236,8 @@ static int netlbl_mgmt_add_common(struct genl_info *info, map->def.calipso = calipso; ret_val = netlbl_af6list_add(&map->list, &addrmap->list6); - if (ret_val != 0) { - kfree(map); - goto add_free_addrmap; - } + if (ret_val != 0) + goto add_free_map; entry->family = AF_INET6; entry->def.type = NETLBL_NLTYPE_ADDRSELECT; @@ -248,10 +247,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = netlbl_domhsh_add(entry, audit_info); if (ret_val != 0) - goto add_free_addrmap; + goto add_free_map; return 0; +add_free_map: + kfree(pmap); add_free_addrmap: kfree(addrmap); add_doi_put_def: @@ -434,7 +435,7 @@ static int netlbl_mgmt_add(struct sk_buff *skb, struct genl_info *info) (info->attrs[NLBL_MGMT_A_IPV6MASK] != NULL))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); return netlbl_mgmt_add_common(info, &audit_info); } @@ -457,7 +458,7 @@ static int netlbl_mgmt_remove(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NLBL_MGMT_A_DOMAIN]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); domain = nla_data(info->attrs[NLBL_MGMT_A_DOMAIN]); return netlbl_domhsh_remove(domain, AF_UNSPEC, &audit_info); @@ -557,7 +558,7 @@ static int netlbl_mgmt_adddef(struct sk_buff *skb, struct genl_info *info) (info->attrs[NLBL_MGMT_A_IPV6MASK] != NULL))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); return netlbl_mgmt_add_common(info, &audit_info); } @@ -576,7 +577,7 @@ static int netlbl_mgmt_removedef(struct sk_buff *skb, struct genl_info *info) { struct netlbl_audit audit_info; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); return netlbl_domhsh_remove_default(AF_UNSPEC, &audit_info); } diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 3e6ac9b790b1..2483df0bbd7c 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -814,7 +814,7 @@ static int netlbl_unlabel_accept(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NLBL_UNLABEL_A_ACPTFLG]) { value = nla_get_u8(info->attrs[NLBL_UNLABEL_A_ACPTFLG]); if (value == 1 || value == 0) { - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); netlbl_unlabel_acceptflg_set(value, &audit_info); return 0; } @@ -897,7 +897,7 @@ static int netlbl_unlabel_staticadd(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) @@ -947,7 +947,7 @@ static int netlbl_unlabel_staticadddef(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) @@ -994,7 +994,7 @@ static int netlbl_unlabel_staticremove(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) @@ -1034,7 +1034,7 @@ static int netlbl_unlabel_staticremovedef(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h index b9ba8112b3c5..6190cbf94bf0 100644 --- a/net/netlabel/netlabel_user.h +++ b/net/netlabel/netlabel_user.h @@ -28,11 +28,9 @@ /** * netlbl_netlink_auditinfo - Fetch the audit information from a NETLINK msg - * @skb: the packet * @audit_info: NetLabel audit information */ -static inline void netlbl_netlink_auditinfo(struct sk_buff *skb, - struct netlbl_audit *audit_info) +static inline void netlbl_netlink_auditinfo(struct netlbl_audit *audit_info) { security_task_getsecid_subj(current, &audit_info->secid); audit_info->loginuid = audit_get_loginuid(current); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6133e412b948..d233ac4a91b6 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -351,7 +351,7 @@ static void netlink_overrun(struct sock *sk) if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { sk->sk_err = ENOBUFS; - sk->sk_error_report(sk); + sk_error_report(sk); } } atomic_inc(&sk->sk_drops); @@ -1576,7 +1576,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) } sk->sk_err = p->code; - sk->sk_error_report(sk); + sk_error_report(sk); out: return ret; } @@ -2012,7 +2012,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, ret = netlink_dump(sk); if (ret) { sk->sk_err = -ret; - sk->sk_error_report(sk); + sk_error_report(sk); } } @@ -2439,7 +2439,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) { NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; - NETLINK_CB(in_skb).sk->sk_error_report(NETLINK_CB(in_skb).sk); + sk_error_report(NETLINK_CB(in_skb).sk); return; } diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c index e02b9befce0b..3a89bd9b89fc 100644 --- a/net/nfc/hci/command.c +++ b/net/nfc/hci/command.c @@ -34,7 +34,7 @@ static int nfc_hci_execute_cmd_async(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, * HCI command execution completion callback. * err will be a standard linux error (may be converted from HCI response) * skb contains the response data and must be disposed, or may be NULL if - * an error occured + * an error occurred */ static void nfc_hci_execute_cb(void *context, struct sk_buff *skb, int err) { diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 43811b5219b5..3481941be70b 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -705,7 +705,7 @@ static void hci_transceive_cb(void *context, struct sk_buff *skb, int err) /* * TODO: Check RF Error indicator to make sure data is valid. * It seems that HCI cmd can complete without error, but data - * can be invalid if an RF error occured? Ignore for now. + * can be invalid if an RF error occurred? Ignore for now. */ if (err == 0) skb_trim(skb, skb->len - 1); /* RF Err ind */ diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index c0c8fea3a186..1e3a90049da9 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -406,7 +406,7 @@ static void llc_shdlc_rcv_u_frame(struct llc_shdlc *shdlc, case SHDLC_NEGOTIATING: case SHDLC_CONNECTING: /* - * We sent RSET, but chip wants to negociate or we + * We sent RSET, but chip wants to negotiate or we * got RSET before we managed to send out our. */ if (skb->len > 0) diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 96865142104f..d6732e5e8958 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -161,8 +161,6 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, *(u8 *)skb_push(skb, 1) = data_type; do { - len = conn_info->max_pkt_payload_len; - /* If last packet add NCI_HFP_NO_CHAINING */ if (i + conn_info->max_pkt_payload_len - (skb->len + 1) >= data_len) { diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 5f1d438a0a23..5e39640becdb 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -49,7 +49,7 @@ static void rawsock_report_error(struct sock *sk, int err) sk->sk_shutdown = SHUTDOWN_MASK; sk->sk_err = -err; - sk->sk_error_report(sk); + sk_error_report(sk); rawsock_write_queue_purge(sk); } diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile index 41109c326f3a..28982630bef3 100644 --- a/net/openvswitch/Makefile +++ b/net/openvswitch/Makefile @@ -13,6 +13,7 @@ openvswitch-y := \ flow_netlink.o \ flow_table.o \ meter.o \ + openvswitch_trace.o \ vport.o \ vport-internal_dev.o \ vport-netdev.o @@ -24,3 +25,5 @@ endif obj-$(CONFIG_OPENVSWITCH_VXLAN)+= vport-vxlan.o obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o obj-$(CONFIG_OPENVSWITCH_GRE) += vport-gre.o + +CFLAGS_openvswitch_trace.o = -I$(src) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 77d924ab8cdb..ef15d9eb4774 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -30,6 +30,7 @@ #include "conntrack.h" #include "vport.h" #include "flow_netlink.h" +#include "openvswitch_trace.h" struct deferred_action { struct sk_buff *skb; @@ -1242,6 +1243,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, a = nla_next(a, &rem)) { int err = 0; + if (trace_ovs_do_execute_action_enabled()) + trace_ovs_do_execute_action(dp, skb, key, a, rem); + switch (nla_type(a)) { case OVS_ACTION_ATTR_OUTPUT: { int port = nla_get_u32(a); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index cadb6a29b285..1b5eae57bc90 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -967,8 +967,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, /* Associate skb with specified zone. */ if (tmpl) { - if (skb_nfct(skb)) - nf_conntrack_put(skb_nfct(skb)); + nf_conntrack_put(skb_nfct(skb)); nf_conntrack_get(&tmpl->ct_general); nf_ct_set(skb, tmpl, IP_CT_NEW); } @@ -1329,11 +1328,9 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) { - if (skb_nfct(skb)) { - nf_conntrack_put(skb_nfct(skb)); - nf_ct_set(skb, NULL, IP_CT_UNTRACKED); - ovs_ct_fill_key(skb, key, false); - } + nf_conntrack_put(skb_nfct(skb)); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + ovs_ct_fill_key(skb, key, false); return 0; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 9d6ef6cb9b26..bc164b35e67d 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -43,6 +43,7 @@ #include "flow_table.h" #include "flow_netlink.h" #include "meter.h" +#include "openvswitch_trace.h" #include "vport-internal_dev.h" #include "vport-netdev.h" @@ -275,6 +276,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, struct dp_stats_percpu *stats; int err; + if (trace_ovs_dp_upcall_enabled()) + trace_ovs_dp_upcall(dp, skb, key, upcall_info); + if (upcall_info->portid == 0) { err = -ENOTCONN; goto err; diff --git a/net/openvswitch/openvswitch_trace.c b/net/openvswitch/openvswitch_trace.c new file mode 100644 index 000000000000..62c5f7d6f023 --- /dev/null +++ b/net/openvswitch/openvswitch_trace.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +/* bug in tracepoint.h, it should include this */ +#include <linux/module.h> + +/* sparse isn't too happy with all macros... */ +#ifndef __CHECKER__ +#define CREATE_TRACE_POINTS +#include "openvswitch_trace.h" + +#endif diff --git a/net/openvswitch/openvswitch_trace.h b/net/openvswitch/openvswitch_trace.h new file mode 100644 index 000000000000..3eb35d9eb700 --- /dev/null +++ b/net/openvswitch/openvswitch_trace.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM openvswitch + +#if !defined(_TRACE_OPENVSWITCH_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_OPENVSWITCH_H + +#include <linux/tracepoint.h> + +#include "datapath.h" + +TRACE_EVENT(ovs_do_execute_action, + + TP_PROTO(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, const struct nlattr *a, int rem), + + TP_ARGS(dp, skb, key, a, rem), + + TP_STRUCT__entry( + __field( void *, dpaddr ) + __string( dp_name, ovs_dp_name(dp) ) + __string( dev_name, skb->dev->name ) + __field( void *, skbaddr ) + __field( unsigned int, len ) + __field( unsigned int, data_len ) + __field( unsigned int, truesize ) + __field( u8, nr_frags ) + __field( u16, gso_size ) + __field( u16, gso_type ) + __field( u32, ovs_flow_hash ) + __field( u32, recirc_id ) + __field( void *, keyaddr ) + __field( u16, key_eth_type ) + __field( u8, key_ct_state ) + __field( u8, key_ct_orig_proto ) + __field( u16, key_ct_zone ) + __field( unsigned int, flow_key_valid ) + __field( u8, action_type ) + __field( unsigned int, action_len ) + __field( void *, action_data ) + __field( u8, is_last ) + ), + + TP_fast_assign( + __entry->dpaddr = dp; + __assign_str(dp_name, ovs_dp_name(dp)); + __assign_str(dev_name, skb->dev->name); + __entry->skbaddr = skb; + __entry->len = skb->len; + __entry->data_len = skb->data_len; + __entry->truesize = skb->truesize; + __entry->nr_frags = skb_shinfo(skb)->nr_frags; + __entry->gso_size = skb_shinfo(skb)->gso_size; + __entry->gso_type = skb_shinfo(skb)->gso_type; + __entry->ovs_flow_hash = key->ovs_flow_hash; + __entry->recirc_id = key->recirc_id; + __entry->keyaddr = key; + __entry->key_eth_type = key->eth.type; + __entry->key_ct_state = key->ct_state; + __entry->key_ct_orig_proto = key->ct_orig_proto; + __entry->key_ct_zone = key->ct_zone; + __entry->flow_key_valid = !(key->mac_proto & SW_FLOW_KEY_INVALID); + __entry->action_type = nla_type(a); + __entry->action_len = nla_len(a); + __entry->action_data = nla_data(a); + __entry->is_last = nla_is_last(a, rem); + ), + + TP_printk("dpaddr=%p dp_name=%s dev=%s skbaddr=%p len=%u data_len=%u truesize=%u nr_frags=%d gso_size=%d gso_type=%#x ovs_flow_hash=0x%08x recirc_id=0x%08x keyaddr=%p eth_type=0x%04x ct_state=%02x ct_orig_proto=%02x ct_Zone=%04x flow_key_valid=%d action_type=%u action_len=%u action_data=%p is_last=%d", + __entry->dpaddr, __get_str(dp_name), __get_str(dev_name), + __entry->skbaddr, __entry->len, __entry->data_len, + __entry->truesize, __entry->nr_frags, __entry->gso_size, + __entry->gso_type, __entry->ovs_flow_hash, + __entry->recirc_id, __entry->keyaddr, __entry->key_eth_type, + __entry->key_ct_state, __entry->key_ct_orig_proto, + __entry->key_ct_zone, + __entry->flow_key_valid, + __entry->action_type, __entry->action_len, + __entry->action_data, __entry->is_last) +); + +TRACE_EVENT(ovs_dp_upcall, + + TP_PROTO(struct datapath *dp, struct sk_buff *skb, + const struct sw_flow_key *key, + const struct dp_upcall_info *upcall_info), + + TP_ARGS(dp, skb, key, upcall_info), + + TP_STRUCT__entry( + __field( void *, dpaddr ) + __string( dp_name, ovs_dp_name(dp) ) + __string( dev_name, skb->dev->name ) + __field( void *, skbaddr ) + __field( unsigned int, len ) + __field( unsigned int, data_len ) + __field( unsigned int, truesize ) + __field( u8, nr_frags ) + __field( u16, gso_size ) + __field( u16, gso_type ) + __field( u32, ovs_flow_hash ) + __field( u32, recirc_id ) + __field( const void *, keyaddr ) + __field( u16, key_eth_type ) + __field( u8, key_ct_state ) + __field( u8, key_ct_orig_proto ) + __field( u16, key_ct_zone ) + __field( unsigned int, flow_key_valid ) + __field( u8, upcall_cmd ) + __field( u32, upcall_port ) + __field( u16, upcall_mru ) + ), + + TP_fast_assign( + __entry->dpaddr = dp; + __assign_str(dp_name, ovs_dp_name(dp)); + __assign_str(dev_name, skb->dev->name); + __entry->skbaddr = skb; + __entry->len = skb->len; + __entry->data_len = skb->data_len; + __entry->truesize = skb->truesize; + __entry->nr_frags = skb_shinfo(skb)->nr_frags; + __entry->gso_size = skb_shinfo(skb)->gso_size; + __entry->gso_type = skb_shinfo(skb)->gso_type; + __entry->ovs_flow_hash = key->ovs_flow_hash; + __entry->recirc_id = key->recirc_id; + __entry->keyaddr = key; + __entry->key_eth_type = key->eth.type; + __entry->key_ct_state = key->ct_state; + __entry->key_ct_orig_proto = key->ct_orig_proto; + __entry->key_ct_zone = key->ct_zone; + __entry->flow_key_valid = !(key->mac_proto & SW_FLOW_KEY_INVALID); + __entry->upcall_cmd = upcall_info->cmd; + __entry->upcall_port = upcall_info->portid; + __entry->upcall_mru = upcall_info->mru; + ), + + TP_printk("dpaddr=%p dp_name=%s dev=%s skbaddr=%p len=%u data_len=%u truesize=%u nr_frags=%d gso_size=%d gso_type=%#x ovs_flow_hash=0x%08x recirc_id=0x%08x keyaddr=%p eth_type=0x%04x ct_state=%02x ct_orig_proto=%02x ct_zone=%04x flow_key_valid=%d upcall_cmd=%u upcall_port=%u upcall_mru=%u", + __entry->dpaddr, __get_str(dp_name), __get_str(dev_name), + __entry->skbaddr, __entry->len, __entry->data_len, + __entry->truesize, __entry->nr_frags, __entry->gso_size, + __entry->gso_type, __entry->ovs_flow_hash, + __entry->recirc_id, __entry->keyaddr, __entry->key_eth_type, + __entry->key_ct_state, __entry->key_ct_orig_proto, + __entry->key_ct_zone, + __entry->flow_key_valid, + __entry->upcall_cmd, __entry->upcall_port, + __entry->upcall_mru) +); + +#endif /* _TRACE_OPENVSWITCH_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE openvswitch_trace +#include <trace/define_trace.h> diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d56941d51e20..57a1971f29e5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3207,7 +3207,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } out_unlock: @@ -3935,12 +3935,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, return -EFAULT; lock_sock(sk); - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { - ret = -EBUSY; - } else { + if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec) po->tp_tx_has_off = !!val; - ret = 0; - } + release_sock(sk); return 0; } @@ -4107,7 +4104,7 @@ static int packet_notifier(struct notifier_block *this, __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 8d00dfe8139e..1990d496fcfc 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -775,8 +775,10 @@ int qrtr_ns_init(void) } qrtr_ns.workqueue = alloc_workqueue("qrtr_ns_handler", WQ_UNBOUND, 1); - if (!qrtr_ns.workqueue) + if (!qrtr_ns.workqueue) { + ret = -ENOMEM; goto err_sock; + } qrtr_ns.sock->sk->sk_data_ready = qrtr_ns_data_ready; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index f2efaa4225f9..e6f4a6202f82 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -751,7 +751,7 @@ static void qrtr_reset_ports(void) xa_for_each_start(&qrtr_ports, index, ipc, 1) { sock_hold(&ipc->sk); ipc->sk.sk_err = ENETRESET; - ipc->sk.sk_error_report(&ipc->sk); + sk_error_report(&ipc->sk); sock_put(&ipc->sk); } rcu_read_unlock(); diff --git a/net/rds/ib_ring.c b/net/rds/ib_ring.c index ff97e8eda858..006b2e441418 100644 --- a/net/rds/ib_ring.c +++ b/net/rds/ib_ring.c @@ -141,7 +141,7 @@ int rds_ib_ring_low(struct rds_ib_work_ring *ring) } /* - * returns the oldest alloced ring entry. This will be the next one + * returns the oldest allocated ring entry. This will be the next one * freed. This can't be called if there are none allocated. */ u32 rds_ib_ring_oldest(struct rds_ib_work_ring *ring) diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index 42c5ff1eda95..f4ee13da90c7 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -177,7 +177,7 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb, goto out; } tc->t_tinc = tinc; - rdsdebug("alloced tinc %p\n", tinc); + rdsdebug("allocated tinc %p\n", tinc); rds_inc_path_init(&tinc->ti_inc, cp, &cp->cp_conn->c_faddr); tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] = diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 3ce6d628cd75..19e929c7c38b 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -77,7 +77,7 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, } /* - * Process event packets targetted at a local endpoint. + * Process event packets targeted at a local endpoint. */ void rxrpc_process_local_events(struct rxrpc_local *local) { diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f6d5755d669e..d17a66aab8ee 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -381,7 +381,8 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, } mutex_unlock(&idrinfo->lock); - if (nla_put_u32(skb, TCA_FCNT, n_i)) + ret = nla_put_u32(skb, TCA_FCNT, n_i); + if (ret) goto nla_put_failure; nla_nest_end(skb, nest); diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index e48e980c3b93..e409a0005717 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -43,7 +43,6 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, tcf_lastuse_update(&prog->tcf_tm); bstats_cpu_update(this_cpu_ptr(prog->common.cpu_bstats), skb); - rcu_read_lock(); filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); @@ -56,7 +55,6 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, } if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) skb_orphan(skb); - rcu_read_unlock(); /* A BPF program may overwrite the default action opcode. * Similarly as in cls_bpf, if filter_res == -1 we use the diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 1cac3c6fbb49..71f2015c70ca 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -70,7 +70,7 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a, /* replace the vid */ tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid; /* replace prio bits, if tcfv_push_prio specified */ - if (p->tcfv_push_prio) { + if (p->tcfv_push_prio_exists) { tci &= ~VLAN_PRIO_MASK; tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT; } @@ -121,6 +121,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, vlan_net_id); struct nlattr *tb[TCA_VLAN_MAX + 1]; struct tcf_chain *goto_ch = NULL; + bool push_prio_exists = false; struct tcf_vlan_params *p; struct tc_vlan *parm; struct tcf_vlan *v; @@ -189,7 +190,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, push_proto = htons(ETH_P_8021Q); } - if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY]) + push_prio_exists = !!tb[TCA_VLAN_PUSH_VLAN_PRIORITY]; + if (push_prio_exists) push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]); break; case TCA_VLAN_ACT_POP_ETH: @@ -241,6 +243,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, p->tcfv_action = action; p->tcfv_push_vid = push_vid; p->tcfv_push_prio = push_prio; + p->tcfv_push_prio_exists = push_prio_exists || action == TCA_VLAN_ACT_PUSH; p->tcfv_push_proto = push_proto; if (action == TCA_VLAN_ACT_PUSH_ETH) { @@ -304,8 +307,8 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, p->tcfv_push_proto) || - (nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, - p->tcfv_push_prio)))) + (p->tcfv_push_prio_exists && + nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, p->tcfv_push_prio)))) goto nla_put_failure; if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 279f9e2a2319..d73b5c5514a9 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1531,7 +1531,7 @@ static inline int __tcf_classify(struct sk_buff *skb, u32 *last_executed_chain) { #ifdef CONFIG_NET_CLS_ACT - const int max_reclassify_loop = 4; + const int max_reclassify_loop = 16; const struct tcf_proto *first_tp; int limit = 0; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 6e3e63db0e01..fa739efa59f4 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -85,8 +85,6 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_bpf_prog *prog; int ret = -1; - /* Needed here for accessing maps. */ - rcu_read_lock(); list_for_each_entry_rcu(prog, &head->plist, link) { int filter_res; @@ -131,7 +129,6 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, break; } - rcu_read_unlock(); return ret; } diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 2e288f88ff02..27a4b6dbcf57 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -7,7 +7,7 @@ /* Comparing to general packet classification problem, - RSVP needs only sevaral relatively simple rules: + RSVP needs only several relatively simple rules: * (dst, protocol) are always specified, so that we are able to hash them. diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index c4007b9cd16d..5b274534264c 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -304,7 +304,7 @@ static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) int i, err = 0; cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!cp->perfect) return -ENOMEM; diff --git a/net/sched/ematch.c b/net/sched/ematch.c index f885bea5b452..4ce681361851 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -141,7 +141,7 @@ errout: EXPORT_SYMBOL(tcf_em_register); /** - * tcf_em_unregister - unregster and extended match + * tcf_em_unregister - unregister and extended match * * @ops: ematch operations lookup table * diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index fc8b56bcabf3..d9ac60ffe927 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -52,6 +52,8 @@ static void qdisc_maybe_clear_missed(struct Qdisc *q, */ if (!netif_xmit_frozen_or_stopped(txq)) set_bit(__QDISC_STATE_MISSED, &q->state); + else + set_bit(__QDISC_STATE_DRAINING, &q->state); } /* Main transmission queue. */ @@ -164,9 +166,13 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) skb = next; } - if (lock) + + if (lock) { spin_unlock(lock); - __netif_schedule(q); + set_bit(__QDISC_STATE_MISSED, &q->state); + } else { + __netif_schedule(q); + } } static void try_bulk_dequeue_skb(struct Qdisc *q, @@ -409,7 +415,11 @@ void __qdisc_run(struct Qdisc *q) while (qdisc_restart(q, &packets)) { quota -= packets; if (quota <= 0) { - __netif_schedule(q); + if (q->flags & TCQ_F_NOLOCK) + set_bit(__QDISC_STATE_MISSED, &q->state); + else + __netif_schedule(q); + break; } } @@ -540,6 +550,24 @@ void netif_carrier_off(struct net_device *dev) } EXPORT_SYMBOL(netif_carrier_off); +/** + * netif_carrier_event - report carrier state event + * @dev: network device + * + * Device has detected a carrier event but the carrier state wasn't changed. + * Use in drivers when querying carrier state asynchronously, to avoid missing + * events (link flaps) if link recovers before it's queried. + */ +void netif_carrier_event(struct net_device *dev) +{ + if (dev->reg_state == NETREG_UNINITIALIZED) + return; + atomic_inc(&dev->carrier_up_count); + atomic_inc(&dev->carrier_down_count); + linkwatch_fire_event(dev); +} +EXPORT_SYMBOL_GPL(netif_carrier_event); + /* "NOOP" scheduler: the best scheduler, recommended for all interfaces under all circumstances. It is difficult to invent anything faster or cheaper. @@ -680,13 +708,14 @@ retry: if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); } else if (need_retry && - test_bit(__QDISC_STATE_MISSED, &qdisc->state)) { + READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY) { /* Delay clearing the STATE_MISSED here to reduce * the overhead of the second spin_trylock() in * qdisc_run_begin() and __netif_schedule() calling * in qdisc_run_end(). */ clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); /* Make sure dequeuing happens after clearing * STATE_MISSED. @@ -696,8 +725,6 @@ retry: need_retry = false; goto retry; - } else { - WRITE_ONCE(qdisc->empty, true); } return skb; @@ -898,7 +925,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; - sch->empty = true; dev_hold(dev); refcount_set(&sch->refcnt, 1); @@ -1204,6 +1230,7 @@ static void dev_reset_queue(struct net_device *dev, spin_unlock_bh(qdisc_lock(qdisc)); if (nolock) { clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); } } diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index f4132dc25ac0..621dc6afde8f 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -6,7 +6,7 @@ * * 991129: - Bug fix with grio mode * - a better sing. AvgQ mode with Grio(WRED) - * - A finer grained VQ dequeue based on sugestion + * - A finer grained VQ dequeue based on suggestion * from Ren Liu * - More error checks * diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 8827987ba903..5f7ac27a5264 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -52,7 +52,7 @@ */ static int htb_hysteresis __read_mostly = 0; /* whether to use mode hysteresis for speedup */ -#define HTB_VER 0x30011 /* major must be matched with number suplied by TC as version */ +#define HTB_VER 0x30011 /* major must be matched with number supplied by TC as version */ #if HTB_VER >> 16 != TC_HTB_PROTOVER #error "Mismatched sch_htb.c and pkt_sch.h" @@ -273,6 +273,9 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, /** * htb_add_to_id_tree - adds class to the round robin list + * @root: the root of the tree + * @cl: the class to add + * @prio: the give prio in class * * Routine adds class to the list (actually tree) sorted by classid. * Make sure that class is not already on such list for given prio. @@ -298,6 +301,9 @@ static void htb_add_to_id_tree(struct rb_root *root, /** * htb_add_to_wait_tree - adds class to the event queue with delay + * @q: the priority event queue + * @cl: the class to add + * @delay: delay in microseconds * * The class is added to priority event queue to indicate that class will * change its mode in cl->pq_key microseconds. Make sure that class is not @@ -331,6 +337,7 @@ static void htb_add_to_wait_tree(struct htb_sched *q, /** * htb_next_rb_node - finds next node in binary tree + * @n: the current node in binary tree * * When we are past last key we return NULL. * Average complexity is 2 steps per call. @@ -342,6 +349,9 @@ static inline void htb_next_rb_node(struct rb_node **n) /** * htb_add_class_to_row - add class to its row + * @q: the priority event queue + * @cl: the class to add + * @mask: the given priorities in class in bitmap * * The class is added to row at priorities marked in mask. * It does nothing if mask == 0. @@ -371,6 +381,9 @@ static void htb_safe_rb_erase(struct rb_node *rb, struct rb_root *root) /** * htb_remove_class_from_row - removes class from its row + * @q: the priority event queue + * @cl: the class to add + * @mask: the given priorities in class in bitmap * * The class is removed from row at priorities marked in mask. * It does nothing if mask == 0. @@ -398,6 +411,8 @@ static inline void htb_remove_class_from_row(struct htb_sched *q, /** * htb_activate_prios - creates active classe's feed chain + * @q: the priority event queue + * @cl: the class to activate * * The class is connected to ancestors and/or appropriate rows * for priorities it is participating on. cl->cmode must be new @@ -433,6 +448,8 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) /** * htb_deactivate_prios - remove class from feed chain + * @q: the priority event queue + * @cl: the class to deactivate * * cl->cmode must represent old mode (before deactivation). It does * nothing if cl->prio_activity == 0. Class is removed from all feed @@ -493,6 +510,8 @@ static inline s64 htb_hiwater(const struct htb_class *cl) /** * htb_class_mode - computes and returns current class mode + * @cl: the target class + * @diff: diff time in microseconds * * It computes cl's mode at time cl->t_c+diff and returns it. If mode * is not HTB_CAN_SEND then cl->pq_key is updated to time difference @@ -521,9 +540,12 @@ htb_class_mode(struct htb_class *cl, s64 *diff) /** * htb_change_class_mode - changes classe's mode + * @q: the priority event queue + * @cl: the target class + * @diff: diff time in microseconds * * This should be the only way how to change classe's mode under normal - * cirsumstances. Routine will update feed lists linkage, change mode + * circumstances. Routine will update feed lists linkage, change mode * and add class to the wait event queue if appropriate. New mode should * be different from old one and cl->pq_key has to be valid if changing * to mode other than HTB_CAN_SEND (see htb_add_to_wait_tree). @@ -553,6 +575,8 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) /** * htb_activate - inserts leaf cl into appropriate active feeds + * @q: the priority event queue + * @cl: the target class * * Routine learns (new) priority of leaf and activates feed chain * for the prio. It can be called on already active leaf safely. @@ -570,6 +594,8 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) /** * htb_deactivate - remove leaf cl from active feeds + * @q: the priority event queue + * @cl: the target class * * Make sure that leaf is active. In the other words it can't be called * with non-active leaf. It also removes class from the drop list. @@ -649,6 +675,10 @@ static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, s64 diff) /** * htb_charge_class - charges amount "bytes" to leaf and ancestors + * @q: the priority event queue + * @cl: the class to start iterate + * @level: the minimum level to account + * @skb: the socket buffer * * Routine assumes that packet "bytes" long was dequeued from leaf cl * borrowing from "level". It accounts bytes to ceil leaky bucket for @@ -698,6 +728,9 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl, /** * htb_do_events - make mode changes to classes at the level + * @q: the priority event queue + * @level: which wait_pq in 'q->hlevel' + * @start: start jiffies * * Scans event queue for pending events and applies them. Returns time of * next pending event (0 for no event in pq, q->now for too many events). @@ -766,6 +799,8 @@ static struct rb_node *htb_id_find_next_upper(int prio, struct rb_node *n, /** * htb_lookup_leaf - returns next leaf class in DRR order + * @hprio: the current one + * @prio: which prio in class * * Find leaf where current feed pointers points to. */ diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 1db9d4a2ef5e..b692a0de1ad5 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -485,11 +485,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl->qdisc != &noop_qdisc) qdisc_hash_add(cl->qdisc, true); - sch_tree_lock(sch); - qdisc_class_hash_insert(&q->clhash, &cl->common); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); set_change_agg: sch_tree_lock(sch); @@ -507,8 +502,11 @@ set_change_agg: } if (existing) qfq_deact_rm_from_agg(q, cl); + else + qdisc_class_hash_insert(&q->clhash, &cl->common); qfq_add_to_agg(q, new_agg, cl); sch_tree_unlock(sch); + qdisc_class_hash_grow(sch, &q->clhash); *arg = (unsigned long)cl; return 0; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 5c91df52b8c2..66fe2b82af9a 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -114,9 +114,6 @@ static void taprio_free_sched_cb(struct rcu_head *head) struct sched_gate_list *sched = container_of(head, struct sched_gate_list, rcu); struct sched_entry *entry, *n; - if (!sched) - return; - list_for_each_entry_safe(entry, n, &sched->entries, list) { list_del(&entry->list); kfree(entry); @@ -438,6 +435,11 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct Qdisc *child; int queue; + if (unlikely(FULL_OFFLOAD_IS_ENABLED(q->flags))) { + WARN_ONCE(1, "Trying to enqueue skb into the root of a taprio qdisc configured with full offload\n"); + return qdisc_drop(skb, sch, to_free); + } + queue = skb_get_queue_mapping(skb); child = q->qdiscs[queue]; @@ -529,23 +531,7 @@ static struct sk_buff *taprio_peek_soft(struct Qdisc *sch) static struct sk_buff *taprio_peek_offload(struct Qdisc *sch) { - struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); - struct sk_buff *skb; - int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct Qdisc *child = q->qdiscs[i]; - - if (unlikely(!child)) - continue; - - skb = child->ops->peek(child); - if (!skb) - continue; - - return skb; - } + WARN_ONCE(1, "Trying to peek into the root of a taprio qdisc configured with full offload\n"); return NULL; } @@ -654,27 +640,7 @@ done: static struct sk_buff *taprio_dequeue_offload(struct Qdisc *sch) { - struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); - struct sk_buff *skb; - int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct Qdisc *child = q->qdiscs[i]; - - if (unlikely(!child)) - continue; - - skb = child->ops->dequeue(child); - if (unlikely(!skb)) - continue; - - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - return skb; - } + WARN_ONCE(1, "Trying to dequeue from the root of a taprio qdisc configured with full offload\n"); return NULL; } @@ -1759,6 +1725,37 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, return taprio_change(sch, opt, extack); } +static void taprio_attach(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx; + + /* Attach underlying qdisc */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + struct Qdisc *qdisc = q->qdiscs[ntx]; + struct Qdisc *old; + + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + old = dev_graft_qdisc(qdisc->dev_queue, qdisc); + if (ntx < dev->real_num_tx_queues) + qdisc_hash_add(qdisc, false); + } else { + old = dev_graft_qdisc(qdisc->dev_queue, sch); + qdisc_refcount_inc(sch); + } + if (old) + qdisc_put(old); + } + + /* access to the child qdiscs is not needed in offload mode */ + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + kfree(q->qdiscs); + q->qdiscs = NULL; + } +} + static struct netdev_queue *taprio_queue_get(struct Qdisc *sch, unsigned long cl) { @@ -1785,8 +1782,12 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl, if (dev->flags & IFF_UP) dev_deactivate(dev); - *old = q->qdiscs[cl - 1]; - q->qdiscs[cl - 1] = new; + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + *old = dev_graft_qdisc(dev_queue, new); + } else { + *old = q->qdiscs[cl - 1]; + q->qdiscs[cl - 1] = new; + } if (new) new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; @@ -2020,6 +2021,7 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { .change = taprio_change, .destroy = taprio_destroy, .reset = taprio_reset, + .attach = taprio_attach, .peek = taprio_peek, .dequeue = taprio_dequeue, .enqueue = taprio_enqueue, diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 336df4b36655..be29da09cc7a 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -98,6 +98,7 @@ static struct sctp_association *sctp_association_init( * sock configured value. */ asoc->hbinterval = msecs_to_jiffies(sp->hbinterval); + asoc->probe_interval = msecs_to_jiffies(sp->probe_interval); asoc->encap_port = sp->encap_port; @@ -625,6 +626,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, * association configured value. */ peer->hbinterval = asoc->hbinterval; + peer->probe_interval = asoc->probe_interval; peer->encap_port = asoc->encap_port; @@ -714,6 +716,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, return NULL; } + sctp_transport_pl_reset(peer); + /* Attach the remote transport to our asoc. */ list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list); asoc->peer.transport_count++; @@ -812,6 +816,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, spc_state = SCTP_ADDR_CONFIRMED; transport->state = SCTP_ACTIVE; + sctp_transport_pl_reset(transport); break; case SCTP_TRANSPORT_DOWN: @@ -821,6 +826,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, */ if (transport->state != SCTP_UNCONFIRMED) { transport->state = SCTP_INACTIVE; + sctp_transport_pl_reset(transport); spc_state = SCTP_ADDR_UNREACHABLE; } else { sctp_transport_dst_release(transport); diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 53e5ed79f63f..59e653b528b1 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -270,22 +270,19 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list, rawaddr = (union sctp_addr_param *)raw_addr_list; af = sctp_get_af_specific(param_type2af(param->type)); - if (unlikely(!af)) { + if (unlikely(!af) || + !af->from_addr_param(&addr, rawaddr, htons(port), 0)) { retval = -EINVAL; - sctp_bind_addr_clean(bp); - break; + goto out_err; } - af->from_addr_param(&addr, rawaddr, htons(port), 0); if (sctp_bind_addr_state(bp, &addr) != -1) goto next; retval = sctp_add_bind_addr(bp, &addr, sizeof(addr), SCTP_ADDR_SRC, gfp); - if (retval) { + if (retval) /* Can't finish building the list, clean up. */ - sctp_bind_addr_clean(bp); - break; - } + goto out_err; next: len = ntohs(param->length); @@ -294,6 +291,12 @@ next: } return retval; + +out_err: + if (retval) + sctp_bind_addr_clean(bp); + + return retval; } /******************************************************************** diff --git a/net/sctp/debug.c b/net/sctp/debug.c index c4d9c7feffb9..ccd773e4c371 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -154,6 +154,7 @@ static const char *const sctp_timer_tbl[] = { "TIMEOUT_T5_SHUTDOWN_GUARD", "TIMEOUT_HEARTBEAT", "TIMEOUT_RECONF", + "TIMEOUT_PROBE", "TIMEOUT_SACK", "TIMEOUT_AUTOCLOSE", }; diff --git a/net/sctp/input.c b/net/sctp/input.c index 5ceaf75105ba..eb3c2a34a31c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -385,7 +385,9 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t, __u32 pmtu) { - if (!t || (t->pathmtu <= pmtu)) + if (!t || + (t->pathmtu <= pmtu && + t->pl.probe_size + sctp_transport_pl_hlen(t) <= pmtu)) return; if (sock_owned_by_user(sk)) { @@ -554,6 +556,50 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t) sctp_transport_put(t); } +static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb, + __u8 type, __u8 code, __u32 info) +{ + struct sctp_association *asoc = t->asoc; + struct sock *sk = asoc->base.sk; + int err = 0; + + switch (type) { + case ICMP_PARAMETERPROB: + err = EPROTO; + break; + case ICMP_DEST_UNREACH: + if (code > NR_ICMP_UNREACH) + return; + if (code == ICMP_FRAG_NEEDED) { + sctp_icmp_frag_needed(sk, asoc, t, SCTP_TRUNC4(info)); + return; + } + if (code == ICMP_PROT_UNREACH) { + sctp_icmp_proto_unreachable(sk, asoc, t); + return; + } + err = icmp_err_convert[code].errno; + break; + case ICMP_TIME_EXCEEDED: + if (code == ICMP_EXC_FRAGTIME) + return; + + err = EHOSTUNREACH; + break; + case ICMP_REDIRECT: + sctp_icmp_redirect(sk, t, skb); + return; + default: + return; + } + if (!sock_owned_by_user(sk) && inet_sk(sk)->recverr) { + sk->sk_err = err; + sk_error_report(sk); + } else { /* Only an error on timeout */ + sk->sk_err_soft = err; + } +} + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -572,22 +618,19 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t) int sctp_v4_err(struct sk_buff *skb, __u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; - const int ihlen = iph->ihl * 4; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; - struct sock *sk; - struct sctp_association *asoc = NULL; + struct net *net = dev_net(skb->dev); struct sctp_transport *transport; - struct inet_sock *inet; + struct sctp_association *asoc; __u16 saveip, savesctp; - int err; - struct net *net = dev_net(skb->dev); + struct sock *sk; /* Fix up skb to look at the embedded net header. */ saveip = skb->network_header; savesctp = skb->transport_header; skb_reset_network_header(skb); - skb_set_transport_header(skb, ihlen); + skb_set_transport_header(skb, iph->ihl * 4); sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &transport); /* Put back, the original values. */ skb->network_header = saveip; @@ -596,59 +639,41 @@ int sctp_v4_err(struct sk_buff *skb, __u32 info) __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; } - /* Warning: The sock lock is held. Remember to call - * sctp_err_finish! - */ - switch (type) { - case ICMP_PARAMETERPROB: - err = EPROTO; - break; - case ICMP_DEST_UNREACH: - if (code > NR_ICMP_UNREACH) - goto out_unlock; + sctp_v4_err_handle(transport, skb, type, code, info); + sctp_err_finish(sk, transport); - /* PMTU discovery (RFC1191) */ - if (ICMP_FRAG_NEEDED == code) { - sctp_icmp_frag_needed(sk, asoc, transport, - SCTP_TRUNC4(info)); - goto out_unlock; - } else { - if (ICMP_PROT_UNREACH == code) { - sctp_icmp_proto_unreachable(sk, asoc, - transport); - goto out_unlock; - } - } - err = icmp_err_convert[code].errno; - break; - case ICMP_TIME_EXCEEDED: - /* Ignore any time exceeded errors due to fragment reassembly - * timeouts. - */ - if (ICMP_EXC_FRAGTIME == code) - goto out_unlock; + return 0; +} - err = EHOSTUNREACH; - break; - case ICMP_REDIRECT: - sctp_icmp_redirect(sk, transport, skb); - goto out_unlock; - default: - goto out_unlock; +int sctp_udp_v4_err(struct sock *sk, struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + struct sctp_association *asoc; + struct sctp_transport *t; + struct icmphdr *hdr; + __u32 info = 0; + + skb->transport_header += sizeof(struct udphdr); + sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &t); + if (!sk) { + __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); + return -ENOENT; } - inet = inet_sk(sk); - if (!sock_owned_by_user(sk) && inet->recverr) { - sk->sk_err = err; - sk->sk_error_report(sk); - } else { /* Only an error on timeout */ - sk->sk_err_soft = err; + skb->transport_header -= sizeof(struct udphdr); + hdr = (struct icmphdr *)(skb_network_header(skb) - sizeof(struct icmphdr)); + if (hdr->type == ICMP_REDIRECT) { + /* can't be handled without outer iphdr known, leave it to udp_err */ + sctp_err_finish(sk, t); + return 0; } + if (hdr->type == ICMP_DEST_UNREACH && hdr->code == ICMP_FRAG_NEEDED) + info = ntohs(hdr->un.frag.mtu); + sctp_v4_err_handle(t, skb, hdr->type, hdr->code, info); -out_unlock: - sctp_err_finish(sk, transport); - return 0; + sctp_err_finish(sk, t); + return 1; } /* @@ -1131,7 +1156,8 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, if (!af) continue; - af->from_addr_param(paddr, params.addr, sh->source, 0); + if (!af->from_addr_param(paddr, params.addr, sh->source, 0)) + continue; asoc = __sctp_lookup_association(net, laddr, paddr, transportp); if (asoc) @@ -1167,6 +1193,9 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( union sctp_addr_param *param; union sctp_addr paddr; + if (ntohs(ch->length) < sizeof(*asconf) + sizeof(struct sctp_paramhdr)) + return NULL; + /* Skip over the ADDIP header and find the Address parameter */ param = (union sctp_addr_param *)(asconf + 1); @@ -1174,7 +1203,8 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( if (unlikely(!af)) return NULL; - af->from_addr_param(&paddr, param, peer_port, 0); + if (af->from_addr_param(&paddr, param, peer_port, 0)) + return NULL; return __sctp_lookup_association(net, laddr, &paddr, transportp); } @@ -1246,7 +1276,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, ch = (struct sctp_chunkhdr *)ch_end; chunk_num++; - } while (ch_end < skb_tail_pointer(skb)); + } while (ch_end + sizeof(*ch) < skb_tail_pointer(skb)); return asoc; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index bd08807c9e44..e48dd909dee5 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -122,54 +122,28 @@ static struct notifier_block sctp_inet6addr_notifier = { .notifier_call = sctp_inet6addr_event, }; -/* ICMP error handler. */ -static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) +static void sctp_v6_err_handle(struct sctp_transport *t, struct sk_buff *skb, + __u8 type, __u8 code, __u32 info) { - struct inet6_dev *idev; - struct sock *sk; - struct sctp_association *asoc; - struct sctp_transport *transport; + struct sctp_association *asoc = t->asoc; + struct sock *sk = asoc->base.sk; struct ipv6_pinfo *np; - __u16 saveip, savesctp; - int err, ret = 0; - struct net *net = dev_net(skb->dev); - - idev = in6_dev_get(skb->dev); - - /* Fix up skb to look at the embedded net header. */ - saveip = skb->network_header; - savesctp = skb->transport_header; - skb_reset_network_header(skb); - skb_set_transport_header(skb, offset); - sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &transport); - /* Put back, the original pointers. */ - skb->network_header = saveip; - skb->transport_header = savesctp; - if (!sk) { - __ICMP6_INC_STATS(net, idev, ICMP6_MIB_INERRORS); - ret = -ENOENT; - goto out; - } - - /* Warning: The sock lock is held. Remember to call - * sctp_err_finish! - */ + int err = 0; switch (type) { case ICMPV6_PKT_TOOBIG: if (ip6_sk_accept_pmtu(sk)) - sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info)); - goto out_unlock; + sctp_icmp_frag_needed(sk, asoc, t, info); + return; case ICMPV6_PARAMPROB: if (ICMPV6_UNK_NEXTHDR == code) { - sctp_icmp_proto_unreachable(sk, asoc, transport); - goto out_unlock; + sctp_icmp_proto_unreachable(sk, asoc, t); + return; } break; case NDISC_REDIRECT: - sctp_icmp_redirect(sk, transport, skb); - goto out_unlock; + sctp_icmp_redirect(sk, t, skb); + return; default: break; } @@ -178,18 +152,70 @@ static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, icmpv6_err_convert(type, code, &err); if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); - } else { /* Only an error on timeout */ + sk_error_report(sk); + } else { sk->sk_err_soft = err; } +} + +/* ICMP error handler. */ +static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct net *net = dev_net(skb->dev); + struct sctp_transport *transport; + struct sctp_association *asoc; + __u16 saveip, savesctp; + struct sock *sk; + + /* Fix up skb to look at the embedded net header. */ + saveip = skb->network_header; + savesctp = skb->transport_header; + skb_reset_network_header(skb); + skb_set_transport_header(skb, offset); + sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &transport); + /* Put back, the original pointers. */ + skb->network_header = saveip; + skb->transport_header = savesctp; + if (!sk) { + __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + return -ENOENT; + } -out_unlock: + sctp_v6_err_handle(transport, skb, type, code, ntohl(info)); sctp_err_finish(sk, transport); -out: - if (likely(idev != NULL)) - in6_dev_put(idev); - return ret; + return 0; +} + +int sctp_udp_v6_err(struct sock *sk, struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + struct sctp_association *asoc; + struct sctp_transport *t; + struct icmp6hdr *hdr; + __u32 info = 0; + + skb->transport_header += sizeof(struct udphdr); + sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &t); + if (!sk) { + __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + return -ENOENT; + } + + skb->transport_header -= sizeof(struct udphdr); + hdr = (struct icmp6hdr *)(skb_network_header(skb) - sizeof(struct icmp6hdr)); + if (hdr->icmp6_type == NDISC_REDIRECT) { + /* can't be handled without outer ip6hdr known, leave it to udpv6_err */ + sctp_err_finish(sk, t); + return 0; + } + if (hdr->icmp6_type == ICMPV6_PKT_TOOBIG) + info = ntohl(hdr->icmp6_mtu); + sctp_v6_err_handle(t, skb, hdr->icmp6_type, hdr->icmp6_code, info); + + sctp_err_finish(sk, t); + return 1; } static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t) @@ -551,15 +577,20 @@ static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk) } /* Initialize a sctp_addr from an address parameter. */ -static void sctp_v6_from_addr_param(union sctp_addr *addr, +static bool sctp_v6_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, __be16 port, int iif) { + if (ntohs(param->v6.param_hdr.length) < sizeof(struct sctp_ipv6addr_param)) + return false; + addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = port; addr->v6.sin6_flowinfo = 0; /* BUG */ addr->v6.sin6_addr = param->v6.addr; addr->v6.sin6_scope_id = iif; + + return true; } /* Initialize an address parameter from a sctp_addr and return the length diff --git a/net/sctp/output.c b/net/sctp/output.c index a6aa17df09ef..9032ce60d50e 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -103,7 +103,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, sctp_transport_route(tp, NULL, sp); if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); - } else if (!sctp_transport_pmtu_check(tp)) { + } else if (!sctp_transport_pl_enabled(tp) && + !sctp_transport_pmtu_check(tp)) { if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); } @@ -211,6 +212,30 @@ enum sctp_xmit sctp_packet_transmit_chunk(struct sctp_packet *packet, return retval; } +/* Try to bundle a pad chunk into a packet with a heartbeat chunk for PLPMTUTD probe */ +static enum sctp_xmit sctp_packet_bundle_pad(struct sctp_packet *pkt, struct sctp_chunk *chunk) +{ + struct sctp_transport *t = pkt->transport; + struct sctp_chunk *pad; + int overhead = 0; + + if (!chunk->pmtu_probe) + return SCTP_XMIT_OK; + + /* calculate the Padding Data size for the pad chunk */ + overhead += sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr); + overhead += sizeof(struct sctp_sender_hb_info) + sizeof(struct sctp_pad_chunk); + pad = sctp_make_pad(t->asoc, t->pl.probe_size - overhead); + if (!pad) + return SCTP_XMIT_DELAY; + + list_add_tail(&pad->list, &pkt->chunk_list); + pkt->size += SCTP_PAD4(ntohs(pad->chunk_hdr->length)); + chunk->transport = t; + + return SCTP_XMIT_OK; +} + /* Try to bundle an auth chunk into the packet. */ static enum sctp_xmit sctp_packet_bundle_auth(struct sctp_packet *pkt, struct sctp_chunk *chunk) @@ -382,6 +407,10 @@ enum sctp_xmit sctp_packet_append_chunk(struct sctp_packet *packet, goto finish; retval = __sctp_packet_append_chunk(packet, chunk); + if (retval != SCTP_XMIT_OK) + goto finish; + + retval = sctp_packet_bundle_pad(packet, chunk); finish: return retval; @@ -553,7 +582,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) sk = chunk->skb->sk; /* check gso */ - if (packet->size > tp->pathmtu && !packet->ipfragok) { + if (packet->size > tp->pathmtu && !packet->ipfragok && !chunk->pmtu_probe) { if (!sk_can_gso(sk)) { pr_err_once("Trying to GSO but underlying device doesn't support it."); goto out; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 5cb1aa5f067b..ff47091c385e 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -769,7 +769,11 @@ static int sctp_packet_singleton(struct sctp_transport *transport, sctp_packet_init(&singleton, transport, sport, dport); sctp_packet_config(&singleton, vtag, 0); - sctp_packet_append_chunk(&singleton, chunk); + if (sctp_packet_append_chunk(&singleton, chunk) != SCTP_XMIT_OK) { + list_del_init(&chunk->list); + sctp_chunk_free(chunk); + return -ENOMEM; + } return sctp_packet_transmit(&singleton, gfp); } @@ -929,8 +933,13 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) one_packet = 1; fallthrough; - case SCTP_CID_SACK: case SCTP_CID_HEARTBEAT: + if (chunk->pmtu_probe) { + sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); + break; + } + fallthrough; + case SCTP_CID_SACK: case SCTP_CID_SHUTDOWN: case SCTP_CID_ECN_ECNE: case SCTP_CID_ASCONF: diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 6f2bbfeec3a4..3c1fbf38f4f7 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -254,14 +254,19 @@ static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk) } /* Initialize a sctp_addr from an address parameter. */ -static void sctp_v4_from_addr_param(union sctp_addr *addr, +static bool sctp_v4_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, __be16 port, int iif) { + if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param)) + return false; + addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); + + return true; } /* Initialize an address parameter from a sctp_addr and return the length @@ -850,23 +855,6 @@ static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb) return 0; } -static int sctp_udp_err_lookup(struct sock *sk, struct sk_buff *skb) -{ - struct sctp_association *asoc; - struct sctp_transport *t; - int family; - - skb->transport_header += sizeof(struct udphdr); - family = (ip_hdr(skb)->version == 4) ? AF_INET : AF_INET6; - sk = sctp_err_lookup(dev_net(skb->dev), family, skb, sctp_hdr(skb), - &asoc, &t); - if (!sk) - return -ENOENT; - - sctp_err_finish(sk, t); - return 0; -} - int sctp_udp_sock_start(struct net *net) { struct udp_tunnel_sock_cfg tuncfg = {NULL}; @@ -885,7 +873,7 @@ int sctp_udp_sock_start(struct net *net) tuncfg.encap_type = 1; tuncfg.encap_rcv = sctp_udp_rcv; - tuncfg.encap_err_lookup = sctp_udp_err_lookup; + tuncfg.encap_err_lookup = sctp_udp_v4_err; setup_udp_tunnel_sock(net, sock, &tuncfg); net->sctp.udp4_sock = sock->sk; @@ -907,7 +895,7 @@ int sctp_udp_sock_start(struct net *net) tuncfg.encap_type = 1; tuncfg.encap_rcv = sctp_udp_rcv; - tuncfg.encap_err_lookup = sctp_udp_err_lookup; + tuncfg.encap_err_lookup = sctp_udp_v6_err; setup_udp_tunnel_sock(net, sock, &tuncfg); net->sctp.udp6_sock = sock->sk; #endif @@ -1171,7 +1159,6 @@ static const struct net_protocol sctp_protocol = { .handler = sctp4_rcv, .err_handler = sctp_v4_err, .no_policy = 1, - .netns_ok = 1, .icmp_strict_tag_validation = 1, }; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5b44d228b6ca..6c08e5048d38 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1160,7 +1160,8 @@ nodata: /* Make a HEARTBEAT chunk. */ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, - const struct sctp_transport *transport) + const struct sctp_transport *transport, + __u32 probe_size) { struct sctp_sender_hb_info hbinfo; struct sctp_chunk *retval; @@ -1176,6 +1177,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, hbinfo.daddr = transport->ipaddr; hbinfo.sent_at = jiffies; hbinfo.hb_nonce = transport->hb_nonce; + hbinfo.probe_size = probe_size; /* Cast away the 'const', as this is just telling the chunk * what transport it belongs to. @@ -1183,6 +1185,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, retval->transport = (struct sctp_transport *) transport; retval->subh.hbs_hdr = sctp_addto_chunk(retval, sizeof(hbinfo), &hbinfo); + retval->pmtu_probe = !!probe_size; nodata: return retval; @@ -1218,6 +1221,32 @@ nodata: return retval; } +/* RFC4820 3. Padding Chunk (PAD) + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Type = 0x84 | Flags=0 | Length | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | | + * \ Padding Data / + * / \ + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + */ +struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len) +{ + struct sctp_chunk *retval; + + retval = sctp_make_control(asoc, SCTP_CID_PAD, 0, len, GFP_ATOMIC); + if (!retval) + return NULL; + + skb_put_zero(retval->skb, len); + retval->chunk_hdr->length = htons(ntohs(retval->chunk_hdr->length) + len); + retval->chunk_end = skb_tail_pointer(retval->skb); + + return retval; +} + /* Create an Operation Error chunk with the specified space reserved. * This routine can be used for containing multiple causes in the chunk. */ @@ -2166,9 +2195,16 @@ static enum sctp_ierror sctp_verify_param(struct net *net, break; case SCTP_PARAM_SET_PRIMARY: - if (ep->asconf_enable) - break; - goto unhandled; + if (!ep->asconf_enable) + goto unhandled; + + if (ntohs(param.p->length) < sizeof(struct sctp_addip_param) + + sizeof(struct sctp_paramhdr)) { + sctp_process_inv_paramlength(asoc, param.p, + chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + } + break; case SCTP_PARAM_HOST_NAME_ADDRESS: /* Tell the peer, we won't support this param. */ @@ -2346,11 +2382,13 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, /* Process the initialization parameters. */ sctp_walk_params(param, peer_init, init_hdr.params) { - if (!src_match && (param.p->type == SCTP_PARAM_IPV4_ADDRESS || - param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { + if (!src_match && + (param.p->type == SCTP_PARAM_IPV4_ADDRESS || + param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { af = sctp_get_af_specific(param_type2af(param.p->type)); - af->from_addr_param(&addr, param.addr, - chunk->sctp_hdr->source, 0); + if (!af->from_addr_param(&addr, param.addr, + chunk->sctp_hdr->source, 0)) + continue; if (sctp_cmp_addr_exact(sctp_source(chunk), &addr)) src_match = 1; } @@ -2531,7 +2569,8 @@ static int sctp_process_param(struct sctp_association *asoc, break; do_addr_param: af = sctp_get_af_specific(param_type2af(param.p->type)); - af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0)) + break; scope = sctp_scope(peer_addr); if (sctp_in_scope(net, &addr, scope)) if (!sctp_assoc_add_peer(asoc, &addr, gfp, SCTP_UNCONFIRMED)) @@ -2632,15 +2671,13 @@ do_addr_param: addr_param = param.v + sizeof(struct sctp_addip_param); af = sctp_get_af_specific(param_type2af(addr_param->p.type)); - if (af == NULL) + if (!af) break; - af->from_addr_param(&addr, addr_param, - htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, addr_param, + htons(asoc->peer.port), 0)) + break; - /* if the address is invalid, we can't process it. - * XXX: see spec for what to do. - */ if (!af->addr_valid(&addr, NULL, NULL)) break; @@ -3054,7 +3091,8 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, if (unlikely(!af)) return SCTP_ERROR_DNS_FAILED; - af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0)) + return SCTP_ERROR_DNS_FAILED; /* ADDIP 4.2.1 This parameter MUST NOT contain a broadcast * or multicast address. @@ -3331,7 +3369,8 @@ static void sctp_asconf_param_success(struct sctp_association *asoc, /* We have checked the packet before, so we do not check again. */ af = sctp_get_af_specific(param_type2af(addr_param->p.type)); - af->from_addr_param(&addr, addr_param, htons(bp->port), 0); + if (!af->from_addr_param(&addr, addr_param, htons(bp->port), 0)) + return; switch (asconf_param->param_hdr.type) { case SCTP_PARAM_ADD_IP: diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index ce15d590a615..b3815b568e8e 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -471,6 +471,38 @@ out_unlock: sctp_transport_put(transport); } +/* Handle the timeout of the probe timer. */ +void sctp_generate_probe_event(struct timer_list *t) +{ + struct sctp_transport *transport = from_timer(transport, t, probe_timer); + struct sctp_association *asoc = transport->asoc; + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); + int error = 0; + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + pr_debug("%s: sock is busy\n", __func__); + + /* Try again later. */ + if (!mod_timer(&transport->probe_timer, jiffies + (HZ / 20))) + sctp_transport_hold(transport); + goto out_unlock; + } + + error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, + SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_PROBE), + asoc->state, asoc->ep, asoc, + transport, GFP_ATOMIC); + + if (error) + sk->sk_err = -error; + +out_unlock: + bh_unlock_sock(sk); + sctp_transport_put(transport); +} + /* Inject a SACK Timeout event into the state machine. */ static void sctp_generate_sack_event(struct timer_list *t) { @@ -1641,6 +1673,11 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, sctp_cmd_hb_timers_stop(commands, asoc); break; + case SCTP_CMD_PROBE_TIMER_UPDATE: + t = cmd->obj.transport; + sctp_transport_reset_probe_timer(t); + break; + case SCTP_CMD_REPORT_ERROR: error = cmd->obj.error; break; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index fd1e319eda00..09a8f23ec709 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -361,7 +361,7 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, /* If the INIT is coming toward a closing socket, we'll send back * and ABORT. Essentially, this catches the race of INIT being - * backloged to the socket at the same time as the user isses close(). + * backloged to the socket at the same time as the user issues close(). * Since the socket and all its associations are going away, we * can treat this OOTB */ @@ -608,8 +608,8 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_COOKIE_ECHOED)); - /* SCTP-AUTH: genereate the assocition shared keys so that - * we can potentially signe the COOKIE-ECHO. + /* SCTP-AUTH: generate the association shared keys so that + * we can potentially sign the COOKIE-ECHO. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL()); @@ -787,7 +787,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, goto nomem_init; /* SCTP-AUTH: Now that we've populate required fields in - * sctp_process_init, set up the assocaition shared keys as + * sctp_process_init, set up the association shared keys as * necessary so that we can potentially authenticate the ACK */ error = sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC); @@ -838,7 +838,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, /* Add all the state machine commands now since we've created * everything. This way we don't introduce memory corruptions - * during side-effect processing and correclty count established + * during side-effect processing and correctly count established * associations. */ sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); @@ -923,7 +923,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, commands); /* Reset init error count upon receipt of COOKIE-ACK, - * to avoid problems with the managemement of this + * to avoid problems with the management of this * counter in stale cookie situations when a transition back * from the COOKIE-ECHOED state to the COOKIE-WAIT * state is performed. @@ -1004,7 +1004,7 @@ static enum sctp_disposition sctp_sf_heartbeat( struct sctp_chunk *reply; /* Send a heartbeat to our peer. */ - reply = sctp_make_heartbeat(asoc, transport); + reply = sctp_make_heartbeat(asoc, transport, 0); if (!reply) return SCTP_DISPOSITION_NOMEM; @@ -1095,6 +1095,32 @@ enum sctp_disposition sctp_sf_send_reconf(struct net *net, return SCTP_DISPOSITION_CONSUME; } +/* send hb chunk with padding for PLPMUTD. */ +enum sctp_disposition sctp_sf_send_probe(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) +{ + struct sctp_transport *transport = (struct sctp_transport *)arg; + struct sctp_chunk *reply; + + if (!sctp_transport_pl_enabled(transport)) + return SCTP_DISPOSITION_CONSUME; + + sctp_transport_pl_send(transport); + + reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); + if (!reply) + return SCTP_DISPOSITION_NOMEM; + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE, + SCTP_TRANSPORT(transport)); + + return SCTP_DISPOSITION_CONSUME; +} + /* * Process an heartbeat request. * @@ -1243,6 +1269,18 @@ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net, if (hbinfo->hb_nonce != link->hb_nonce) return SCTP_DISPOSITION_DISCARD; + if (hbinfo->probe_size) { + if (hbinfo->probe_size != link->pl.probe_size || + !sctp_transport_pl_enabled(link)) + return SCTP_DISPOSITION_DISCARD; + + sctp_transport_pl_recv(link); + if (link->pl.state == SCTP_PL_COMPLETE) + return SCTP_DISPOSITION_CONSUME; + + return sctp_sf_send_probe(net, ep, asoc, type, link, commands); + } + max_interval = link->hbinterval + link->rto; /* Check if the timestamp looks valid. */ @@ -2950,7 +2988,7 @@ enum sctp_disposition sctp_sf_do_9_2_reshutack( commands); /* Since we are not going to really process this INIT, there - * is no point in verifying chunk boundries. Just generate + * is no point in verifying chunk boundaries. Just generate * the SHUTDOWN ACK. */ reply = sctp_make_shutdown_ack(asoc, chunk); @@ -3560,7 +3598,7 @@ enum sctp_disposition sctp_sf_do_9_2_final(struct net *net, goto nomem_chunk; /* Do all the commands now (after allocation), so that we - * have consistent state if memory allocation failes + * have consistent state if memory allocation fails */ sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); @@ -3747,7 +3785,7 @@ static enum sctp_disposition sctp_sf_shut_8_4_5( return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* We need to discard the rest of the packet to prevent - * potential bomming attacks from additional bundled chunks. + * potential boomming attacks from additional bundled chunks. * This is documented in SCTP Threats ID. */ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -4257,7 +4295,7 @@ gen_shutdown: } /* - * SCTP-AUTH Section 6.3 Receiving authenticated chukns + * SCTP-AUTH Section 6.3 Receiving authenticated chunks * * The receiver MUST use the HMAC algorithm indicated in the HMAC * Identifier field. If this algorithm was not specified by the @@ -4812,7 +4850,7 @@ static enum sctp_disposition sctp_sf_violation_ctsn( /* Handle protocol violation of an invalid chunk bundling. For example, * when we have an association and we receive bundled INIT-ACK, or - * SHUDOWN-COMPLETE, our peer is clearly violationg the "MUST NOT bundle" + * SHUTDOWN-COMPLETE, our peer is clearly violating the "MUST NOT bundle" * statement from the specs. Additionally, there might be an attacker * on the path and we may not want to continue this communication. */ @@ -5208,7 +5246,7 @@ enum sctp_disposition sctp_sf_cookie_wait_prm_shutdown( * Inputs * (endpoint, asoc) * - * The RFC does not explcitly address this issue, but is the route through the + * The RFC does not explicitly address this issue, but is the route through the * state table when someone issues a shutdown while in COOKIE_ECHOED state. * * Outputs @@ -5932,7 +5970,7 @@ enum sctp_disposition sctp_sf_t1_cookie_timer_expire( /* RFC2960 9.2 If the timer expires, the endpoint must re-send the SHUTDOWN * with the updated last sequential TSN received from its peer. * - * An endpoint should limit the number of retransmissions of the + * An endpoint should limit the number of retransmission of the * SHUTDOWN chunk to the protocol parameter 'Association.Max.Retrans'. * If this threshold is exceeded the endpoint should destroy the TCB and * MUST report the peer endpoint unreachable to the upper layer (and @@ -6010,7 +6048,7 @@ nomem: } /* - * ADDIP Section 4.1 ASCONF CHunk Procedures + * ADDIP Section 4.1 ASCONF Chunk Procedures * If the T4 RTO timer expires the endpoint should do B1 to B5 */ enum sctp_disposition sctp_sf_t4_timer_expire( @@ -6441,7 +6479,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, chunk->ecn_ce_done = 1; if (af->is_ce(sctp_gso_headskb(chunk->skb))) { - /* Do real work as sideffect. */ + /* Do real work as side effect. */ sctp_add_cmd_sf(commands, SCTP_CMD_ECN_CE, SCTP_U32(tsn)); } diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 88ea87f4f0e7..1816a4410b2b 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -527,6 +527,26 @@ auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { }; /*state_fn_t auth_chunk_event_table[][] */ static const struct sctp_sm_table_entry +pad_chunk_event_table[SCTP_STATE_NUM_STATES] = { + /* SCTP_STATE_CLOSED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_COOKIE_WAIT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_COOKIE_ECHOED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_ESTABLISHED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_PENDING */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_SENT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_RECEIVED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_ACK_SENT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), +}; /* chunk pad */ + +static const struct sctp_sm_table_entry chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ TYPE_SCTP_FUNC(sctp_sf_ootb), @@ -947,6 +967,25 @@ other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } +#define TYPE_SCTP_EVENT_TIMEOUT_PROBE { \ + /* SCTP_STATE_CLOSED */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_COOKIE_WAIT */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_COOKIE_ECHOED */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_ESTABLISHED */ \ + TYPE_SCTP_FUNC(sctp_sf_send_probe), \ + /* SCTP_STATE_SHUTDOWN_PENDING */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_SHUTDOWN_SENT */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ +} + static const struct sctp_sm_table_entry timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_EVENT_TIMEOUT_NONE, @@ -958,6 +997,7 @@ timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD, TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT, TYPE_SCTP_EVENT_TIMEOUT_RECONF, + TYPE_SCTP_EVENT_TIMEOUT_PROBE, TYPE_SCTP_EVENT_TIMEOUT_SACK, TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE, }; @@ -992,6 +1032,9 @@ static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( case SCTP_CID_AUTH: return &auth_chunk_event_table[0][state]; + + case SCTP_CID_PAD: + return &pad_chunk_event_table[state]; } return &chunk_event_table_unknown[state]; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index a79d193ff872..e64e01f61b11 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2496,6 +2496,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, sctp_transport_pmtu(trans, sctp_opt2sk(sp)); sctp_assoc_sync_pmtu(asoc); } + sctp_transport_pl_reset(trans); } else if (asoc) { asoc->param_flags = (asoc->param_flags & ~SPP_PMTUD) | pmtud_change; @@ -4481,6 +4482,61 @@ static int sctp_setsockopt_encap_port(struct sock *sk, return 0; } +static int sctp_setsockopt_probe_interval(struct sock *sk, + struct sctp_probeinterval *params, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_transport *t; + __u32 probe_interval; + + if (optlen != sizeof(*params)) + return -EINVAL; + + probe_interval = params->spi_interval; + if (probe_interval && probe_interval < SCTP_PROBE_TIMER_MIN) + return -EINVAL; + + /* If an address other than INADDR_ANY is specified, and + * no transport is found, then the request is invalid. + */ + if (!sctp_is_any(sk, (union sctp_addr *)¶ms->spi_address)) { + t = sctp_addr_id2transport(sk, ¶ms->spi_address, + params->spi_assoc_id); + if (!t) + return -EINVAL; + + t->probe_interval = msecs_to_jiffies(probe_interval); + sctp_transport_pl_reset(t); + return 0; + } + + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. + */ + asoc = sctp_id2assoc(sk, params->spi_assoc_id); + if (!asoc && params->spi_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + /* If changes are for association, also apply probe_interval to + * each transport. + */ + if (asoc) { + list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { + t->probe_interval = msecs_to_jiffies(probe_interval); + sctp_transport_pl_reset(t); + } + + asoc->probe_interval = msecs_to_jiffies(probe_interval); + return 0; + } + + sctp_sk(sk)->probe_interval = probe_interval; + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4703,6 +4759,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_REMOTE_UDP_ENCAPS_PORT: retval = sctp_setsockopt_encap_port(sk, kopt, optlen); break; + case SCTP_PLPMTUD_PROBE_INTERVAL: + retval = sctp_setsockopt_probe_interval(sk, kopt, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -4989,6 +5048,7 @@ static int sctp_init_sock(struct sock *sk) atomic_set(&sp->pd_mode, 0); skb_queue_head_init(&sp->pd_lobby); sp->frag_interleave = 0; + sp->probe_interval = net->sctp.probe_interval; /* Create a per socket endpoint structure. Even if we * change the data structure relationships, this may still @@ -7905,6 +7965,66 @@ out: return 0; } +static int sctp_getsockopt_probe_interval(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_probeinterval params; + struct sctp_association *asoc; + struct sctp_transport *t; + __u32 probe_interval; + + if (len < sizeof(params)) + return -EINVAL; + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + return -EFAULT; + + /* If an address other than INADDR_ANY is specified, and + * no transport is found, then the request is invalid. + */ + if (!sctp_is_any(sk, (union sctp_addr *)¶ms.spi_address)) { + t = sctp_addr_id2transport(sk, ¶ms.spi_address, + params.spi_assoc_id); + if (!t) { + pr_debug("%s: failed no transport\n", __func__); + return -EINVAL; + } + + probe_interval = jiffies_to_msecs(t->probe_interval); + goto out; + } + + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. + */ + asoc = sctp_id2assoc(sk, params.spi_assoc_id); + if (!asoc && params.spi_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { + pr_debug("%s: failed no association\n", __func__); + return -EINVAL; + } + + if (asoc) { + probe_interval = jiffies_to_msecs(asoc->probe_interval); + goto out; + } + + probe_interval = sctp_sk(sk)->probe_interval; + +out: + params.spi_interval = probe_interval; + if (copy_to_user(optval, ¶ms, len)) + return -EFAULT; + + if (put_user(len, optlen)) + return -EFAULT; + + return 0; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -8128,6 +8248,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_REMOTE_UDP_ENCAPS_PORT: retval = sctp_getsockopt_encap_port(sk, len, optval, optlen); break; + case SCTP_PLPMTUD_PROBE_INTERVAL: + retval = sctp_getsockopt_probe_interval(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 55871b277f47..b46a416787ec 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -55,6 +55,8 @@ static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_auth(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); +static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table sctp_table[] = { { @@ -294,6 +296,13 @@ static struct ctl_table sctp_net_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "plpmtud_probe_interval", + .data = &init_net.sctp.probe_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_sctp_do_probe_interval, + }, + { .procname = "udp_port", .data = &init_net.sctp.udp_port, .maxlen = sizeof(int), @@ -539,6 +548,32 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, return ret; } +static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + struct ctl_table tbl; + int ret, new_value; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.probe_interval; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + if (new_value && new_value < SCTP_PROBE_TIMER_MIN) + return -EINVAL; + + net->sctp.probe_interval = new_value; + } + + return ret; +} + int sctp_sysctl_net_register(struct net *net) { struct ctl_table *table; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index bf0ac467e757..5f23804f21c7 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -75,6 +75,7 @@ static struct sctp_transport *sctp_transport_init(struct net *net, timer_setup(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event, 0); timer_setup(&peer->hb_timer, sctp_generate_heartbeat_event, 0); timer_setup(&peer->reconf_timer, sctp_generate_reconf_event, 0); + timer_setup(&peer->probe_timer, sctp_generate_probe_event, 0); timer_setup(&peer->proto_unreach_timer, sctp_generate_proto_unreach_event, 0); @@ -131,6 +132,9 @@ void sctp_transport_free(struct sctp_transport *transport) if (del_timer(&transport->reconf_timer)) sctp_transport_put(transport); + if (del_timer(&transport->probe_timer)) + sctp_transport_put(transport); + /* Delete the ICMP proto unreachable timer if it's active. */ if (del_timer(&transport->proto_unreach_timer)) sctp_transport_put(transport); @@ -207,6 +211,15 @@ void sctp_transport_reset_reconf_timer(struct sctp_transport *transport) sctp_transport_hold(transport); } +void sctp_transport_reset_probe_timer(struct sctp_transport *transport) +{ + if (timer_pending(&transport->probe_timer)) + return; + if (!mod_timer(&transport->probe_timer, + jiffies + transport->probe_interval)) + sctp_transport_hold(transport); +} + /* This transport has been assigned to an association. * Initialize fields from the association or from the sock itself. * Register the reference count in the association. @@ -241,12 +254,143 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) transport->pathmtu = sctp_dst_mtu(transport->dst); else transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; + + sctp_transport_pl_update(transport); +} + +void sctp_transport_pl_send(struct sctp_transport *t) +{ + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + + if (t->pl.probe_count < SCTP_MAX_PROBES) { + t->pl.probe_count++; + return; + } + + if (t->pl.state == SCTP_PL_BASE) { + if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */ + t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ + + t->pl.pmtu = SCTP_MIN_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } + } else if (t->pl.state == SCTP_PL_SEARCH) { + if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */ + t->pl.state = SCTP_PL_BASE; /* Search -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + t->pl.probe_high = 0; + + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } else { /* Normal probe failure. */ + t->pl.probe_high = t->pl.probe_size; + t->pl.probe_size = t->pl.pmtu; + } + } else if (t->pl.state == SCTP_PL_COMPLETE) { + if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */ + t->pl.state = SCTP_PL_BASE; /* Search Complete -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } + } + t->pl.probe_count = 1; +} + +void sctp_transport_pl_recv(struct sctp_transport *t) +{ + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + + t->pl.pmtu = t->pl.probe_size; + t->pl.probe_count = 0; + if (t->pl.state == SCTP_PL_BASE) { + t->pl.state = SCTP_PL_SEARCH; /* Base -> Search */ + t->pl.probe_size += SCTP_PL_BIG_STEP; + } else if (t->pl.state == SCTP_PL_ERROR) { + t->pl.state = SCTP_PL_SEARCH; /* Error -> Search */ + + t->pl.pmtu = t->pl.probe_size; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + t->pl.probe_size += SCTP_PL_BIG_STEP; + } else if (t->pl.state == SCTP_PL_SEARCH) { + if (!t->pl.probe_high) { + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, + SCTP_MAX_PLPMTU); + return; + } + t->pl.probe_size += SCTP_PL_MIN_STEP; + if (t->pl.probe_size >= t->pl.probe_high) { + t->pl.probe_high = 0; + t->pl.raise_count = 0; + t->pl.state = SCTP_PL_COMPLETE; /* Search -> Search Complete */ + + t->pl.probe_size = t->pl.pmtu; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } + } else if (t->pl.state == SCTP_PL_COMPLETE && ++t->pl.raise_count == 30) { + /* Raise probe_size again after 30 * interval in Search Complete */ + t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ + t->pl.probe_size += SCTP_PL_MIN_STEP; + } +} + +static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu) +{ + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, ptb: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, pmtu); + + if (pmtu < SCTP_MIN_PLPMTU || pmtu >= t->pl.probe_size) + return false; + + if (t->pl.state == SCTP_PL_BASE) { + if (pmtu >= SCTP_MIN_PLPMTU && pmtu < SCTP_BASE_PLPMTU) { + t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ + + t->pl.pmtu = SCTP_MIN_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + } + } else if (t->pl.state == SCTP_PL_SEARCH) { + if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) { + t->pl.state = SCTP_PL_BASE; /* Search -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + t->pl.probe_count = 0; + + t->pl.probe_high = 0; + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + } else if (pmtu > t->pl.pmtu && pmtu < t->pl.probe_size) { + t->pl.probe_size = pmtu; + t->pl.probe_count = 0; + + return false; + } + } else if (t->pl.state == SCTP_PL_COMPLETE) { + if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) { + t->pl.state = SCTP_PL_BASE; /* Complete -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + t->pl.probe_count = 0; + + t->pl.probe_high = 0; + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + } + } + + return true; } bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) { - struct dst_entry *dst = sctp_transport_dst_check(t); struct sock *sk = t->asoc->base.sk; + struct dst_entry *dst; bool change = true; if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) { @@ -257,6 +401,10 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) } pmtu = SCTP_TRUNC4(pmtu); + if (sctp_transport_pl_enabled(t)) + return sctp_transport_pl_toobig(t, pmtu - sctp_transport_pl_hlen(t)); + + dst = sctp_transport_dst_check(t); if (dst) { struct sctp_pf *pf = sctp_get_pf_specific(dst->ops->family); union sctp_addr addr; diff --git a/net/smc/Makefile b/net/smc/Makefile index 77e54fe42b1c..99a0186cba5b 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -2,4 +2,4 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o -smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o +smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5eff7cccceff..898389611ae8 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -49,6 +49,7 @@ #include "smc_tx.h" #include "smc_rx.h" #include "smc_close.h" +#include "smc_stats.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@ -508,9 +509,44 @@ static void smc_link_save_peer_info(struct smc_link *link, link->peer_mtu = clc->r0.qp_mtu; } -static void smc_switch_to_fallback(struct smc_sock *smc) +static void smc_stat_inc_fback_rsn_cnt(struct smc_sock *smc, + struct smc_stats_fback *fback_arr) +{ + int cnt; + + for (cnt = 0; cnt < SMC_MAX_FBACK_RSN_CNT; cnt++) { + if (fback_arr[cnt].fback_code == smc->fallback_rsn) { + fback_arr[cnt].count++; + break; + } + if (!fback_arr[cnt].fback_code) { + fback_arr[cnt].fback_code = smc->fallback_rsn; + fback_arr[cnt].count++; + break; + } + } +} + +static void smc_stat_fallback(struct smc_sock *smc) +{ + struct net *net = sock_net(&smc->sk); + + mutex_lock(&net->smc.mutex_fback_rsn); + if (smc->listen_smc) { + smc_stat_inc_fback_rsn_cnt(smc, net->smc.fback_rsn->srv); + net->smc.fback_rsn->srv_fback_cnt++; + } else { + smc_stat_inc_fback_rsn_cnt(smc, net->smc.fback_rsn->clnt); + net->smc.fback_rsn->clnt_fback_cnt++; + } + mutex_unlock(&net->smc.mutex_fback_rsn); +} + +static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { smc->use_fallback = true; + smc->fallback_rsn = reason_code; + smc_stat_fallback(smc); if (smc->sk.sk_socket && smc->sk.sk_socket->file) { smc->clcsock->file = smc->sk.sk_socket->file; smc->clcsock->file->private_data = smc->clcsock; @@ -522,8 +558,7 @@ static void smc_switch_to_fallback(struct smc_sock *smc) /* fall back during connect */ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) { - smc_switch_to_fallback(smc); - smc->fallback_rsn = reason_code; + smc_switch_to_fallback(smc, reason_code); smc_copy_sock_settings_to_clc(smc); smc->connect_nonblock = 0; if (smc->sk.sk_state == SMC_INIT) @@ -535,9 +570,11 @@ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code, u8 version) { + struct net *net = sock_net(&smc->sk); int rc; if (reason_code < 0) { /* error, fallback is not possible */ + this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt); if (smc->sk.sk_state == SMC_INIT) sock_put(&smc->sk); /* passive closing */ return reason_code; @@ -545,6 +582,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code, if (reason_code != SMC_CLC_DECL_PEERDECL) { rc = smc_clc_send_decline(smc, reason_code, version); if (rc < 0) { + this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt); if (smc->sk.sk_state == SMC_INIT) sock_put(&smc->sk); /* passive closing */ return rc; @@ -992,6 +1030,7 @@ static int __smc_connect(struct smc_sock *smc) if (rc) goto vlan_cleanup; + SMC_STAT_CLNT_SUCC_INC(sock_net(smc->clcsock->sk), aclc); smc_connect_ism_vlan_cleanup(smc, ini); kfree(buf); kfree(ini); @@ -1307,7 +1346,9 @@ static void smc_listen_out_connected(struct smc_sock *new_smc) static void smc_listen_out_err(struct smc_sock *new_smc) { struct sock *newsmcsk = &new_smc->sk; + struct net *net = sock_net(newsmcsk); + this_cpu_inc(net->smc.smc_stats->srv_hshake_err_cnt); if (newsmcsk->sk_state == SMC_INIT) sock_put(&new_smc->sk); /* passive closing */ newsmcsk->sk_state = SMC_CLOSED; @@ -1325,8 +1366,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, smc_listen_out_err(new_smc); return; } - smc_switch_to_fallback(new_smc); - new_smc->fallback_rsn = reason_code; + smc_switch_to_fallback(new_smc, reason_code); if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { if (smc_clc_send_decline(new_smc, reason_code, version) < 0) { smc_listen_out_err(new_smc); @@ -1699,8 +1739,7 @@ static void smc_listen_work(struct work_struct *work) /* check if peer is smc capable */ if (!tcp_sk(newclcsock->sk)->syn_smc) { - smc_switch_to_fallback(new_smc); - new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC; + smc_switch_to_fallback(new_smc, SMC_CLC_DECL_PEERNOSMC); smc_listen_out_connected(new_smc); return; } @@ -1778,6 +1817,7 @@ static void smc_listen_work(struct work_struct *work) } smc_conn_save_peer_info(new_smc, cclc); smc_listen_out_connected(new_smc); + SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini); goto out_free; out_unlock: @@ -1984,18 +2024,19 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_FASTOPEN) { if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { - smc_switch_to_fallback(smc); - smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; + smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); } else { rc = -EINVAL; goto out; } } - if (smc->use_fallback) + if (smc->use_fallback) { rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len); - else + } else { rc = smc_tx_sendmsg(smc, msg, len); + SMC_STAT_TX_PAYLOAD(smc, len, rc); + } out: release_sock(sk); return rc; @@ -2030,6 +2071,7 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, } else { msg->msg_namelen = 0; rc = smc_rx_recvmsg(smc, msg, NULL, len, flags); + SMC_STAT_RX_PAYLOAD(smc, rc, rc); } out: @@ -2176,7 +2218,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, optval, optlen); if (smc->clcsock->sk->sk_err) { sk->sk_err = smc->clcsock->sk->sk_err; - sk->sk_error_report(sk); + sk_error_report(sk); } if (optlen < sizeof(int)) @@ -2194,8 +2236,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { - smc_switch_to_fallback(smc); - smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; + smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); } else { rc = -EINVAL; } @@ -2204,18 +2245,22 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (val) + if (val) { + SMC_STAT_INC(smc, ndly_cnt); mod_delayed_work(smc->conn.lgr->tx_wq, &smc->conn.tx_work, 0); + } } break; case TCP_CORK: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (!val) + if (!val) { + SMC_STAT_INC(smc, cork_cnt); mod_delayed_work(smc->conn.lgr->tx_wq, &smc->conn.tx_work, 0); + } } break; case TCP_DEFER_ACCEPT: @@ -2338,11 +2383,13 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page, goto out; } release_sock(sk); - if (smc->use_fallback) + if (smc->use_fallback) { rc = kernel_sendpage(smc->clcsock, page, offset, size, flags); - else + } else { + SMC_STAT_INC(smc, sendpage_cnt); rc = sock_no_sendpage(sock, page, offset, size, flags); + } out: return rc; @@ -2391,6 +2438,7 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, flags = MSG_DONTWAIT; else flags = 0; + SMC_STAT_INC(smc, splice_cnt); rc = smc_rx_recvmsg(smc, NULL, pipe, len, flags); } out: @@ -2479,6 +2527,16 @@ static void __net_exit smc_net_exit(struct net *net) smc_pnet_net_exit(net); } +static __net_init int smc_net_stat_init(struct net *net) +{ + return smc_stats_init(net); +} + +static void __net_exit smc_net_stat_exit(struct net *net) +{ + smc_stats_exit(net); +} + static struct pernet_operations smc_net_ops = { .init = smc_net_init, .exit = smc_net_exit, @@ -2486,6 +2544,11 @@ static struct pernet_operations smc_net_ops = { .size = sizeof(struct smc_net), }; +static struct pernet_operations smc_net_stat_ops = { + .init = smc_net_stat_init, + .exit = smc_net_stat_exit, +}; + static int __init smc_init(void) { int rc; @@ -2494,6 +2557,10 @@ static int __init smc_init(void) if (rc) return rc; + rc = register_pernet_subsys(&smc_net_stat_ops); + if (rc) + return rc; + smc_ism_init(); smc_clc_init(); @@ -2595,6 +2662,7 @@ static void __exit smc_exit(void) proto_unregister(&smc_proto); smc_pnet_exit(); smc_nl_exit(); + unregister_pernet_subsys(&smc_net_stat_ops); unregister_pernet_subsys(&smc_net_ops); rcu_barrier(); } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 0df85a12651e..cd0d7c908b2a 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -33,6 +33,7 @@ #include "smc_close.h" #include "smc_ism.h" #include "smc_netlink.h" +#include "smc_stats.h" #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) @@ -1235,20 +1236,6 @@ static void smc_lgr_free(struct smc_link_group *lgr) kfree(lgr); } -static void smcd_unregister_all_dmbs(struct smc_link_group *lgr) -{ - int i; - - for (i = 0; i < SMC_RMBE_SIZES; i++) { - struct smc_buf_desc *buf_desc; - - list_for_each_entry(buf_desc, &lgr->rmbs[i], list) { - buf_desc->len += sizeof(struct smcd_cdc_msg); - smc_ism_unregister_dmb(lgr->smcd, buf_desc); - } - } -} - static void smc_sk_wake_ups(struct smc_sock *smc) { smc->sk.sk_write_space(&smc->sk); @@ -1285,7 +1272,6 @@ static void smc_lgr_cleanup(struct smc_link_group *lgr) { if (lgr->is_smcd) { smc_ism_signal_shutdown(lgr); - smcd_unregister_all_dmbs(lgr); } else { u32 rsn = lgr->llc_termination_rsn; @@ -2044,6 +2030,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; int bufsize, bufsize_short; + bool is_dgraded = false; struct mutex *lock; /* lock buffer list */ int sk_buf_size; @@ -2071,6 +2058,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) /* check for reusable slot in the link group */ buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); if (buf_desc) { + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); + SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb); memset(buf_desc->cpu_addr, 0, bufsize); break; /* found reusable slot */ } @@ -2082,9 +2071,16 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (PTR_ERR(buf_desc) == -ENOMEM) break; - if (IS_ERR(buf_desc)) + if (IS_ERR(buf_desc)) { + if (!is_dgraded) { + is_dgraded = true; + SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rmb); + } continue; + } + SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; mutex_lock(lock); list_add(&buf_desc->list, buf_list); diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 967712ba52a0..9cb2df289963 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -470,7 +470,6 @@ void smcd_unregister_dev(struct smcd_dev *smcd) mutex_unlock(&smcd_dev_list.mutex); smcd->going_away = 1; smc_smcd_terminate_all(smcd); - flush_workqueue(smcd->event_wq); destroy_workqueue(smcd->event_wq); device_del(&smcd->dev); diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 140419a19dbf..6fb6f96c1d17 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -19,6 +19,7 @@ #include "smc_core.h" #include "smc_ism.h" #include "smc_ib.h" +#include "smc_stats.h" #include "smc_netlink.h" #define SMC_CMD_MAX_ATTR 1 @@ -55,6 +56,16 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smcr_nl_get_device, }, + { + .cmd = SMC_NETLINK_GET_STATS, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_get_stats, + }, + { + .cmd = SMC_NETLINK_GET_FBACK_STATS, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_get_fback_stats, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h index 3477265cba6c..5ce2c0a89ccd 100644 --- a/net/smc/smc_netlink.h +++ b/net/smc/smc_netlink.h @@ -18,7 +18,7 @@ extern struct genl_family smc_gen_nl_family; struct smc_nl_dmp_ctx { - int pos[2]; + int pos[3]; }; static inline struct smc_nl_dmp_ctx *smc_nl_dmp_ctx(struct netlink_callback *c) diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index fcfac59f8b72..170b733bc736 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -21,6 +21,7 @@ #include "smc_cdc.h" #include "smc_tx.h" /* smc_tx_consumer_update() */ #include "smc_rx.h" +#include "smc_stats.h" /* callback implementation to wakeup consumers blocked with smc_rx_wait(). * indirectly called by smc_cdc_msg_recv_action(). @@ -227,6 +228,7 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len, conn->urg_state == SMC_URG_READ) return -EINVAL; + SMC_STAT_INC(smc, urg_data_cnt); if (conn->urg_state == SMC_URG_VALID) { if (!(flags & MSG_PEEK)) smc->conn.urg_state = SMC_URG_READ; @@ -303,6 +305,12 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + readable = atomic_read(&conn->bytes_to_rcv); + if (readable >= conn->rmb_desc->len) + SMC_STAT_RMB_RX_FULL(smc, !conn->lnk); + + if (len < readable) + SMC_STAT_RMB_RX_SIZE_SMALL(smc, !conn->lnk); /* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */ rcvbuf_base = conn->rx_off + conn->rmb_desc->cpu_addr; diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c new file mode 100644 index 000000000000..e80e34f7ac15 --- /dev/null +++ b/net/smc/smc_stats.c @@ -0,0 +1,413 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * SMC statistics netlink routines + * + * Copyright IBM Corp. 2021 + * + * Author(s): Guvenc Gulce + */ +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/percpu.h> +#include <linux/ctype.h> +#include <linux/smc.h> +#include <net/genetlink.h> +#include <net/sock.h> +#include "smc_netlink.h" +#include "smc_stats.h" + +int smc_stats_init(struct net *net) +{ + net->smc.fback_rsn = kzalloc(sizeof(*net->smc.fback_rsn), GFP_KERNEL); + if (!net->smc.fback_rsn) + goto err_fback; + net->smc.smc_stats = alloc_percpu(struct smc_stats); + if (!net->smc.smc_stats) + goto err_stats; + mutex_init(&net->smc.mutex_fback_rsn); + return 0; + +err_stats: + kfree(net->smc.fback_rsn); +err_fback: + return -ENOMEM; +} + +void smc_stats_exit(struct net *net) +{ + kfree(net->smc.fback_rsn); + if (net->smc.smc_stats) + free_percpu(net->smc.smc_stats); +} + +static int smc_nl_fill_stats_rmb_data(struct sk_buff *skb, + struct smc_stats *stats, int tech, + int type) +{ + struct smc_stats_rmbcnt *stats_rmb_cnt; + struct nlattr *attrs; + + if (type == SMC_NLA_STATS_T_TX_RMB_STATS) + stats_rmb_cnt = &stats->smc[tech].rmb_tx; + else + stats_rmb_cnt = &stats->smc[tech].rmb_rx; + + attrs = nla_nest_start(skb, type); + if (!attrs) + goto errout; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_REUSE_CNT, + stats_rmb_cnt->reuse_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_SIZE_SM_PEER_CNT, + stats_rmb_cnt->buf_size_small_peer_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_SIZE_SM_CNT, + stats_rmb_cnt->buf_size_small_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_FULL_PEER_CNT, + stats_rmb_cnt->buf_full_peer_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_FULL_CNT, + stats_rmb_cnt->buf_full_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_ALLOC_CNT, + stats_rmb_cnt->alloc_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_DGRADE_CNT, + stats_rmb_cnt->dgrade_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +static int smc_nl_fill_stats_bufsize_data(struct sk_buff *skb, + struct smc_stats *stats, int tech, + int type) +{ + struct smc_stats_memsize *stats_pload; + struct nlattr *attrs; + + if (type == SMC_NLA_STATS_T_TXPLOAD_SIZE) + stats_pload = &stats->smc[tech].tx_pd; + else if (type == SMC_NLA_STATS_T_RXPLOAD_SIZE) + stats_pload = &stats->smc[tech].rx_pd; + else if (type == SMC_NLA_STATS_T_TX_RMB_SIZE) + stats_pload = &stats->smc[tech].tx_rmbsize; + else if (type == SMC_NLA_STATS_T_RX_RMB_SIZE) + stats_pload = &stats->smc[tech].rx_rmbsize; + else + goto errout; + + attrs = nla_nest_start(skb, type); + if (!attrs) + goto errout; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_8K, + stats_pload->buf[SMC_BUF_8K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_16K, + stats_pload->buf[SMC_BUF_16K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_32K, + stats_pload->buf[SMC_BUF_32K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_64K, + stats_pload->buf[SMC_BUF_64K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_128K, + stats_pload->buf[SMC_BUF_128K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_256K, + stats_pload->buf[SMC_BUF_256K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_512K, + stats_pload->buf[SMC_BUF_512K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_1024K, + stats_pload->buf[SMC_BUF_1024K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_G_1024K, + stats_pload->buf[SMC_BUF_G_1024K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +static int smc_nl_fill_stats_tech_data(struct sk_buff *skb, + struct smc_stats *stats, int tech) +{ + struct smc_stats_tech *smc_tech; + struct nlattr *attrs; + + smc_tech = &stats->smc[tech]; + if (tech == SMC_TYPE_D) + attrs = nla_nest_start(skb, SMC_NLA_STATS_SMCD_TECH); + else + attrs = nla_nest_start(skb, SMC_NLA_STATS_SMCR_TECH); + + if (!attrs) + goto errout; + if (smc_nl_fill_stats_rmb_data(skb, stats, tech, + SMC_NLA_STATS_T_TX_RMB_STATS)) + goto errattr; + if (smc_nl_fill_stats_rmb_data(skb, stats, tech, + SMC_NLA_STATS_T_RX_RMB_STATS)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_TXPLOAD_SIZE)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_RXPLOAD_SIZE)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_TX_RMB_SIZE)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_RX_RMB_SIZE)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CLNT_V1_SUCC, + smc_tech->clnt_v1_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CLNT_V2_SUCC, + smc_tech->clnt_v2_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SRV_V1_SUCC, + smc_tech->srv_v1_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SRV_V2_SUCC, + smc_tech->srv_v2_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_BYTES, + smc_tech->rx_bytes, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_TX_BYTES, + smc_tech->tx_bytes, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_CNT, + smc_tech->rx_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_TX_CNT, + smc_tech->tx_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SENDPAGE_CNT, + smc_tech->sendpage_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CORK_CNT, + smc_tech->cork_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_NDLY_CNT, + smc_tech->ndly_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SPLICE_CNT, + smc_tech->splice_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_URG_DATA_CNT, + smc_tech->urg_data_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +int smc_nl_get_stats(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct net *net = sock_net(skb->sk); + struct smc_stats *stats; + struct nlattr *attrs; + int cpu, i, size; + void *nlh; + u64 *src; + u64 *sum; + + if (cb_ctx->pos[0]) + goto errmsg; + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_STATS); + if (!nlh) + goto errmsg; + + attrs = nla_nest_start(skb, SMC_GEN_STATS); + if (!attrs) + goto errnest; + stats = kzalloc(sizeof(*stats), GFP_KERNEL); + if (!stats) + goto erralloc; + size = sizeof(*stats) / sizeof(u64); + for_each_possible_cpu(cpu) { + src = (u64 *)per_cpu_ptr(net->smc.smc_stats, cpu); + sum = (u64 *)stats; + for (i = 0; i < size; i++) + *(sum++) += *(src++); + } + if (smc_nl_fill_stats_tech_data(skb, stats, SMC_TYPE_D)) + goto errattr; + if (smc_nl_fill_stats_tech_data(skb, stats, SMC_TYPE_R)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_CLNT_HS_ERR_CNT, + stats->clnt_hshake_err_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_SRV_HS_ERR_CNT, + stats->srv_hshake_err_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + cb_ctx->pos[0] = 1; + kfree(stats); + return skb->len; + +errattr: + kfree(stats); +erralloc: + nla_nest_cancel(skb, attrs); +errnest: + genlmsg_cancel(skb, nlh); +errmsg: + return skb->len; +} + +static int smc_nl_get_fback_details(struct sk_buff *skb, + struct netlink_callback *cb, int pos, + bool is_srv) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct net *net = sock_net(skb->sk); + int cnt_reported = cb_ctx->pos[2]; + struct smc_stats_fback *trgt_arr; + struct nlattr *attrs; + int rc = 0; + void *nlh; + + if (is_srv) + trgt_arr = &net->smc.fback_rsn->srv[0]; + else + trgt_arr = &net->smc.fback_rsn->clnt[0]; + if (!trgt_arr[pos].fback_code) + return -ENODATA; + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_FBACK_STATS); + if (!nlh) + goto errmsg; + attrs = nla_nest_start(skb, SMC_GEN_FBACK_STATS); + if (!attrs) + goto errout; + if (nla_put_u8(skb, SMC_NLA_FBACK_STATS_TYPE, is_srv)) + goto errattr; + if (!cnt_reported) { + if (nla_put_u64_64bit(skb, SMC_NLA_FBACK_STATS_SRV_CNT, + net->smc.fback_rsn->srv_fback_cnt, + SMC_NLA_FBACK_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_FBACK_STATS_CLNT_CNT, + net->smc.fback_rsn->clnt_fback_cnt, + SMC_NLA_FBACK_STATS_PAD)) + goto errattr; + cnt_reported = 1; + } + + if (nla_put_u32(skb, SMC_NLA_FBACK_STATS_RSN_CODE, + trgt_arr[pos].fback_code)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_FBACK_STATS_RSN_CNT, + trgt_arr[pos].count)) + goto errattr; + + cb_ctx->pos[2] = cnt_reported; + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + return rc; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + +int smc_nl_get_fback_stats(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct net *net = sock_net(skb->sk); + int rc_srv = 0, rc_clnt = 0, k; + int skip_serv = cb_ctx->pos[1]; + int snum = cb_ctx->pos[0]; + bool is_srv = true; + + mutex_lock(&net->smc.mutex_fback_rsn); + for (k = 0; k < SMC_MAX_FBACK_RSN_CNT; k++) { + if (k < snum) + continue; + if (!skip_serv) { + rc_srv = smc_nl_get_fback_details(skb, cb, k, is_srv); + if (rc_srv && rc_srv != -ENODATA) + break; + } else { + skip_serv = 0; + } + rc_clnt = smc_nl_get_fback_details(skb, cb, k, !is_srv); + if (rc_clnt && rc_clnt != -ENODATA) { + skip_serv = 1; + break; + } + if (rc_clnt == -ENODATA && rc_srv == -ENODATA) + break; + } + mutex_unlock(&net->smc.mutex_fback_rsn); + cb_ctx->pos[1] = skip_serv; + cb_ctx->pos[0] = k; + return skb->len; +} diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h new file mode 100644 index 000000000000..84b7ecd8c05c --- /dev/null +++ b/net/smc/smc_stats.h @@ -0,0 +1,266 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Macros for SMC statistics + * + * Copyright IBM Corp. 2021 + * + * Author(s): Guvenc Gulce + */ + +#ifndef NET_SMC_SMC_STATS_H_ +#define NET_SMC_SMC_STATS_H_ +#include <linux/init.h> +#include <linux/mutex.h> +#include <linux/percpu.h> +#include <linux/ctype.h> +#include <linux/smc.h> + +#include "smc_clc.h" + +#define SMC_MAX_FBACK_RSN_CNT 30 + +enum { + SMC_BUF_8K, + SMC_BUF_16K, + SMC_BUF_32K, + SMC_BUF_64K, + SMC_BUF_128K, + SMC_BUF_256K, + SMC_BUF_512K, + SMC_BUF_1024K, + SMC_BUF_G_1024K, + SMC_BUF_MAX, +}; + +struct smc_stats_fback { + int fback_code; + u16 count; +}; + +struct smc_stats_rsn { + struct smc_stats_fback srv[SMC_MAX_FBACK_RSN_CNT]; + struct smc_stats_fback clnt[SMC_MAX_FBACK_RSN_CNT]; + u64 srv_fback_cnt; + u64 clnt_fback_cnt; +}; + +struct smc_stats_rmbcnt { + u64 buf_size_small_peer_cnt; + u64 buf_size_small_cnt; + u64 buf_full_peer_cnt; + u64 buf_full_cnt; + u64 reuse_cnt; + u64 alloc_cnt; + u64 dgrade_cnt; +}; + +struct smc_stats_memsize { + u64 buf[SMC_BUF_MAX]; +}; + +struct smc_stats_tech { + struct smc_stats_memsize tx_rmbsize; + struct smc_stats_memsize rx_rmbsize; + struct smc_stats_memsize tx_pd; + struct smc_stats_memsize rx_pd; + struct smc_stats_rmbcnt rmb_tx; + struct smc_stats_rmbcnt rmb_rx; + u64 clnt_v1_succ_cnt; + u64 clnt_v2_succ_cnt; + u64 srv_v1_succ_cnt; + u64 srv_v2_succ_cnt; + u64 sendpage_cnt; + u64 urg_data_cnt; + u64 splice_cnt; + u64 cork_cnt; + u64 ndly_cnt; + u64 rx_bytes; + u64 tx_bytes; + u64 rx_cnt; + u64 tx_cnt; +}; + +struct smc_stats { + struct smc_stats_tech smc[2]; + u64 clnt_hshake_err_cnt; + u64 srv_hshake_err_cnt; +}; + +#define SMC_STAT_PAYLOAD_SUB(_smc_stats, _tech, key, _len, _rc) \ +do { \ + typeof(_smc_stats) stats = (_smc_stats); \ + typeof(_tech) t = (_tech); \ + typeof(_len) l = (_len); \ + int _pos = fls64((l) >> 13); \ + typeof(_rc) r = (_rc); \ + int m = SMC_BUF_MAX - 1; \ + this_cpu_inc((*stats).smc[t].key ## _cnt); \ + if (r <= 0) \ + break; \ + _pos = (_pos < m) ? ((l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m; \ + this_cpu_inc((*stats).smc[t].key ## _pd.buf[_pos]); \ + this_cpu_add((*stats).smc[t].key ## _bytes, r); \ +} \ +while (0) + +#define SMC_STAT_TX_PAYLOAD(_smc, length, rcode) \ +do { \ + typeof(_smc) __smc = _smc; \ + struct net *_net = sock_net(&__smc->sk); \ + struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(length) _len = (length); \ + typeof(rcode) _rc = (rcode); \ + bool is_smcd = !__smc->conn.lnk; \ + if (is_smcd) \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_D, tx, _len, _rc); \ + else \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_R, tx, _len, _rc); \ +} \ +while (0) + +#define SMC_STAT_RX_PAYLOAD(_smc, length, rcode) \ +do { \ + typeof(_smc) __smc = _smc; \ + struct net *_net = sock_net(&__smc->sk); \ + struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(length) _len = (length); \ + typeof(rcode) _rc = (rcode); \ + bool is_smcd = !__smc->conn.lnk; \ + if (is_smcd) \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_D, rx, _len, _rc); \ + else \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_R, rx, _len, _rc); \ +} \ +while (0) + +#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _len) \ +do { \ + typeof(_len) _l = (_len); \ + typeof(_tech) t = (_tech); \ + int _pos = fls((_l) >> 13); \ + int m = SMC_BUF_MAX - 1; \ + _pos = (_pos < m) ? ((_l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m; \ + this_cpu_inc((*(_smc_stats)).smc[t].k ## _rmbsize.buf[_pos]); \ +} \ +while (0) + +#define SMC_STAT_RMB_SUB(_smc_stats, type, t, key) \ + this_cpu_inc((*(_smc_stats)).smc[t].rmb ## _ ## key.type ## _cnt) + +#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _len) \ +do { \ + struct net *_net = sock_net(&(_smc)->sk); \ + struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(_is_smcd) is_d = (_is_smcd); \ + typeof(_is_rx) is_r = (_is_rx); \ + typeof(_len) l = (_len); \ + if ((is_d) && (is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, l); \ + if ((is_d) && !(is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, l); \ + if (!(is_d) && (is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, l); \ + if (!(is_d) && !(is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, l); \ +} \ +while (0) + +#define SMC_STAT_RMB(_smc, type, _is_smcd, _is_rx) \ +do { \ + struct net *net = sock_net(&(_smc)->sk); \ + struct smc_stats __percpu *_smc_stats = net->smc.smc_stats; \ + typeof(_is_smcd) is_d = (_is_smcd); \ + typeof(_is_rx) is_r = (_is_rx); \ + if ((is_d) && (is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_D, rx); \ + if ((is_d) && !(is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_D, tx); \ + if (!(is_d) && (is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_R, rx); \ + if (!(is_d) && !(is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_R, tx); \ +} \ +while (0) + +#define SMC_STAT_BUF_REUSE(smc, is_smcd, is_rx) \ + SMC_STAT_RMB(smc, reuse, is_smcd, is_rx) + +#define SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rx) \ + SMC_STAT_RMB(smc, alloc, is_smcd, is_rx) + +#define SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rx) \ + SMC_STAT_RMB(smc, dgrade, is_smcd, is_rx) + +#define SMC_STAT_RMB_TX_PEER_FULL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_full_peer, is_smcd, false) + +#define SMC_STAT_RMB_TX_FULL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_full, is_smcd, false) + +#define SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_size_small_peer, is_smcd, false) + +#define SMC_STAT_RMB_TX_SIZE_SMALL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_size_small, is_smcd, false) + +#define SMC_STAT_RMB_RX_SIZE_SMALL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_size_small, is_smcd, true) + +#define SMC_STAT_RMB_RX_FULL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_full, is_smcd, true) + +#define SMC_STAT_INC(_smc, type) \ +do { \ + typeof(_smc) __smc = _smc; \ + bool is_smcd = !(__smc)->conn.lnk; \ + struct net *net = sock_net(&(__smc)->sk); \ + struct smc_stats __percpu *smc_stats = net->smc.smc_stats; \ + if ((is_smcd)) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].type); \ + else \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].type); \ +} \ +while (0) + +#define SMC_STAT_CLNT_SUCC_INC(net, _aclc) \ +do { \ + typeof(_aclc) acl = (_aclc); \ + bool is_v2 = (acl->hdr.version == SMC_V2); \ + bool is_smcd = (acl->hdr.typev1 == SMC_TYPE_D); \ + struct smc_stats __percpu *smc_stats = (net)->smc.smc_stats; \ + if (is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].clnt_v2_succ_cnt); \ + else if (is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].clnt_v2_succ_cnt); \ + else if (!is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].clnt_v1_succ_cnt); \ + else if (!is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].clnt_v1_succ_cnt); \ +} \ +while (0) + +#define SMC_STAT_SERV_SUCC_INC(net, _ini) \ +do { \ + typeof(_ini) i = (_ini); \ + bool is_v2 = (i->smcd_version & SMC_V2); \ + bool is_smcd = (i->is_smcd); \ + typeof(net->smc.smc_stats) smc_stats = (net)->smc.smc_stats; \ + if (is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].srv_v2_succ_cnt); \ + else if (is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].srv_v2_succ_cnt); \ + else if (!is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].srv_v1_succ_cnt); \ + else if (!is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].srv_v1_succ_cnt); \ +} \ +while (0) + +int smc_nl_get_stats(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_get_fback_stats(struct sk_buff *skb, struct netlink_callback *cb); +int smc_stats_init(struct net *net); +void smc_stats_exit(struct net *net); + +#endif /* NET_SMC_SMC_STATS_H_ */ diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 4532c16bf85e..289025cd545a 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -27,6 +27,7 @@ #include "smc_close.h" #include "smc_ism.h" #include "smc_tx.h" +#include "smc_stats.h" #define SMC_TX_WORK_DELAY 0 #define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */ @@ -45,6 +46,8 @@ static void smc_tx_write_space(struct sock *sk) /* similar to sk_stream_write_space */ if (atomic_read(&smc->conn.sndbuf_space) && sock) { + if (test_bit(SOCK_NOSPACE, &sock->flags)) + SMC_STAT_RMB_TX_FULL(smc, !smc->conn.lnk); clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); @@ -151,9 +154,19 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) goto out_err; } + if (sk->sk_state == SMC_INIT) + return -ENOTCONN; + + if (len > conn->sndbuf_desc->len) + SMC_STAT_RMB_TX_SIZE_SMALL(smc, !conn->lnk); + + if (len > conn->peer_rmbe_size) + SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, !conn->lnk); + + if (msg->msg_flags & MSG_OOB) + SMC_STAT_INC(smc, urg_data_cnt); + while (msg_data_left(msg)) { - if (sk->sk_state == SMC_INIT) - return -ENOTCONN; if (smc->sk.sk_shutdown & SEND_SHUTDOWN || (smc->sk.sk_err == ECONNABORTED) || conn->killed) @@ -419,8 +432,12 @@ static int smc_tx_rdma_writes(struct smc_connection *conn, /* destination: RMBE */ /* cf. snd_wnd */ rmbespace = atomic_read(&conn->peer_rmbe_space); - if (rmbespace <= 0) + if (rmbespace <= 0) { + struct smc_sock *smc = container_of(conn, struct smc_sock, + conn); + SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk); return 0; + } smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); diff --git a/net/socket.c b/net/socket.c index 4f2c6d2795d0..bd9233da2497 100644 --- a/net/socket.c +++ b/net/socket.c @@ -165,6 +165,54 @@ static const struct file_operations socket_file_ops = { .show_fdinfo = sock_show_fdinfo, }; +static const char * const pf_family_names[] = { + [PF_UNSPEC] = "PF_UNSPEC", + [PF_UNIX] = "PF_UNIX/PF_LOCAL", + [PF_INET] = "PF_INET", + [PF_AX25] = "PF_AX25", + [PF_IPX] = "PF_IPX", + [PF_APPLETALK] = "PF_APPLETALK", + [PF_NETROM] = "PF_NETROM", + [PF_BRIDGE] = "PF_BRIDGE", + [PF_ATMPVC] = "PF_ATMPVC", + [PF_X25] = "PF_X25", + [PF_INET6] = "PF_INET6", + [PF_ROSE] = "PF_ROSE", + [PF_DECnet] = "PF_DECnet", + [PF_NETBEUI] = "PF_NETBEUI", + [PF_SECURITY] = "PF_SECURITY", + [PF_KEY] = "PF_KEY", + [PF_NETLINK] = "PF_NETLINK/PF_ROUTE", + [PF_PACKET] = "PF_PACKET", + [PF_ASH] = "PF_ASH", + [PF_ECONET] = "PF_ECONET", + [PF_ATMSVC] = "PF_ATMSVC", + [PF_RDS] = "PF_RDS", + [PF_SNA] = "PF_SNA", + [PF_IRDA] = "PF_IRDA", + [PF_PPPOX] = "PF_PPPOX", + [PF_WANPIPE] = "PF_WANPIPE", + [PF_LLC] = "PF_LLC", + [PF_IB] = "PF_IB", + [PF_MPLS] = "PF_MPLS", + [PF_CAN] = "PF_CAN", + [PF_TIPC] = "PF_TIPC", + [PF_BLUETOOTH] = "PF_BLUETOOTH", + [PF_IUCV] = "PF_IUCV", + [PF_RXRPC] = "PF_RXRPC", + [PF_ISDN] = "PF_ISDN", + [PF_PHONET] = "PF_PHONET", + [PF_IEEE802154] = "PF_IEEE802154", + [PF_CAIF] = "PF_CAIF", + [PF_ALG] = "PF_ALG", + [PF_NFC] = "PF_NFC", + [PF_VSOCK] = "PF_VSOCK", + [PF_KCM] = "PF_KCM", + [PF_QIPCRTR] = "PF_QIPCRTR", + [PF_SMC] = "PF_SMC", + [PF_XDP] = "PF_XDP", +}; + /* * The protocol list. Each protocol is registered in here. */ @@ -2975,7 +3023,7 @@ int sock_register(const struct net_proto_family *ops) } spin_unlock(&net_family_lock); - pr_info("NET: Registered protocol family %d\n", ops->family); + pr_info("NET: Registered %s protocol family\n", pf_family_names[ops->family]); return err; } EXPORT_SYMBOL(sock_register); @@ -3003,7 +3051,7 @@ void sock_unregister(int family) synchronize_rcu(); - pr_info("NET: Unregistered protocol family %d\n", family); + pr_info("NET: Unregistered %s protocol family\n", pf_family_names[family]); } EXPORT_SYMBOL(sock_unregister); diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index b3815c1e8f2e..9c0343568d2a 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -58,7 +58,7 @@ static void strp_abort_strp(struct strparser *strp, int err) /* Report an error on the lower socket */ sk->sk_err = -err; - sk->sk_error_report(sk); + sk_error_report(sk); } } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 89a36db47ab4..070698dd19bc 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -381,19 +381,20 @@ EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers); static int __switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*add_cb)(struct net_device *dev, + int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)) { + struct switchdev_notifier_info *info = &port_obj_info->info; struct netlink_ext_ack *extack; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; - extack = switchdev_notifier_info_to_extack(&port_obj_info->info); + extack = switchdev_notifier_info_to_extack(info); if (check_cb(dev)) { - err = add_cb(dev, port_obj_info->obj, extack); + err = add_cb(dev, info->ctx, port_obj_info->obj, extack); if (err != -EOPNOTSUPP) port_obj_info->handled = true; return err; @@ -422,7 +423,7 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev, int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*add_cb)(struct net_device *dev, + int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)) { @@ -439,15 +440,16 @@ EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_add); static int __switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*del_cb)(struct net_device *dev, + int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)) { + struct switchdev_notifier_info *info = &port_obj_info->info; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; if (check_cb(dev)) { - err = del_cb(dev, port_obj_info->obj); + err = del_cb(dev, info->ctx, port_obj_info->obj); if (err != -EOPNOTSUPP) port_obj_info->handled = true; return err; @@ -476,7 +478,7 @@ static int __switchdev_handle_port_obj_del(struct net_device *dev, int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*del_cb)(struct net_device *dev, + int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)) { int err; @@ -492,19 +494,20 @@ EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del); static int __switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), - int (*set_cb)(struct net_device *dev, + int (*set_cb)(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack)) { + struct switchdev_notifier_info *info = &port_attr_info->info; struct netlink_ext_ack *extack; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; - extack = switchdev_notifier_info_to_extack(&port_attr_info->info); + extack = switchdev_notifier_info_to_extack(info); if (check_cb(dev)) { - err = set_cb(dev, port_attr_info->attr, extack); + err = set_cb(dev, info->ctx, port_attr_info->attr, extack); if (err != -EOPNOTSUPP) port_attr_info->handled = true; return err; @@ -533,7 +536,7 @@ static int __switchdev_handle_port_attr_set(struct net_device *dev, int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), - int (*set_cb)(struct net_device *dev, + int (*set_cb)(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack)) { diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index d4beca895992..593846d25214 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -699,7 +699,7 @@ int tipc_bcast_init(struct net *net) spin_lock_init(&tipc_net(net)->bclock); if (!tipc_link_bc_create(net, 0, 0, NULL, - FB_MTU, + one_page_mtu, BCLINK_WIN_DEFAULT, BCLINK_WIN_DEFAULT, 0, diff --git a/net/tipc/link.c b/net/tipc/link.c index 1b7a487c8841..cf586840caeb 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -913,7 +913,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, dnode, l->addr, dport, 0, 0); if (!skb) - return -ENOBUFS; + return -ENOMEM; msg_set_dest_droppable(buf_msg(skb), true); TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr); skb_queue_tail(&l->wakeupq, skb); @@ -1031,7 +1031,7 @@ void tipc_link_reset(struct tipc_link *l) * * Consumes the buffer chain. * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted - * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS + * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS or -ENOMEM */ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq) @@ -1089,7 +1089,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, if (!_skb) { kfree_skb(skb); __skb_queue_purge(list); - return -ENOBUFS; + return -ENOMEM; } __skb_queue_tail(transmq, skb); tipc_link_set_skb_retransmit_time(skb, l); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index ce6ab54822d8..5c9fd4791c4b 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -41,19 +41,18 @@ #include "name_table.h" #include "crypto.h" +#define BUF_ALIGN(x) ALIGN(x, 4) #define MAX_FORWARD_SIZE 1024 #ifdef CONFIG_TIPC_CRYPTO #define BUF_HEADROOM ALIGN(((LL_MAX_HEADER + 48) + EHDR_MAX_SIZE), 16) -#define BUF_TAILROOM (TIPC_AES_GCM_TAG_SIZE) +#define BUF_OVERHEAD (BUF_HEADROOM + TIPC_AES_GCM_TAG_SIZE) #else #define BUF_HEADROOM (LL_MAX_HEADER + 48) -#define BUF_TAILROOM 16 +#define BUF_OVERHEAD BUF_HEADROOM #endif -static unsigned int align(unsigned int i) -{ - return (i + 3) & ~3u; -} +const int one_page_mtu = PAGE_SIZE - SKB_DATA_ALIGN(BUF_OVERHEAD) - + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); /** * tipc_buf_acquire - creates a TIPC message buffer @@ -69,13 +68,8 @@ static unsigned int align(unsigned int i) struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp) { struct sk_buff *skb; -#ifdef CONFIG_TIPC_CRYPTO - unsigned int buf_size = (BUF_HEADROOM + size + BUF_TAILROOM + 3) & ~3u; -#else - unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u; -#endif - skb = alloc_skb_fclone(buf_size, gfp); + skb = alloc_skb_fclone(BUF_OVERHEAD + size, gfp); if (skb) { skb_reserve(skb, BUF_HEADROOM); skb_put(skb, size); @@ -395,7 +389,8 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, if (unlikely(!skb)) { if (pktmax != MAX_MSG_SIZE) return -ENOMEM; - rc = tipc_msg_build(mhdr, m, offset, dsz, FB_MTU, list); + rc = tipc_msg_build(mhdr, m, offset, dsz, + one_page_mtu, list); if (rc != dsz) return rc; if (tipc_msg_assemble(list)) @@ -490,7 +485,7 @@ static bool tipc_msg_bundle(struct sk_buff *bskb, struct tipc_msg *msg, msz = msg_size(msg); bsz = msg_size(bmsg); - offset = align(bsz); + offset = BUF_ALIGN(bsz); pad = offset - bsz; if (unlikely(skb_tailroom(bskb) < (pad + msz))) @@ -547,7 +542,7 @@ bool tipc_msg_try_bundle(struct sk_buff *tskb, struct sk_buff **skb, u32 mss, /* Make a new bundle of the two messages if possible */ tsz = msg_size(buf_msg(tskb)); - if (unlikely(mss < align(INT_H_SIZE + tsz) + msg_size(msg))) + if (unlikely(mss < BUF_ALIGN(INT_H_SIZE + tsz) + msg_size(msg))) return true; if (unlikely(pskb_expand_head(tskb, INT_H_SIZE, mss - tsz - INT_H_SIZE, GFP_ATOMIC))) @@ -606,7 +601,7 @@ bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos) if (unlikely(!tipc_msg_validate(iskb))) goto none; - *pos += align(imsz); + *pos += BUF_ALIGN(imsz); return true; none: kfree_skb(skb); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 5d64596ba987..64ae4c4c44f8 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -99,9 +99,10 @@ struct plist; #define MAX_H_SIZE 60 /* Largest possible TIPC header size */ #define MAX_MSG_SIZE (MAX_H_SIZE + TIPC_MAX_USER_MSG_SIZE) -#define FB_MTU 3744 #define TIPC_MEDIA_INFO_OFFSET 5 +extern const int one_page_mtu; + struct tipc_skb_cb { union { struct { diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index fecab516bf41..01396dd1c899 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -673,12 +673,12 @@ exit: * Returns a list of local sockets */ void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua, - bool exact, struct list_head *dports) + struct list_head *dports) { struct service_range *sr; struct tipc_service *sc; struct publication *p; - u32 scope = ua->scope; + u8 scope = ua->scope; rcu_read_lock(); sc = tipc_service_find(net, ua); @@ -688,7 +688,7 @@ void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua, spin_lock_bh(&sc->lock); service_range_foreach_match(sr, sc, ua->sr.lower, ua->sr.upper) { list_for_each_entry(p, &sr->local_publ, local_publ) { - if (p->scope == scope || (!exact && p->scope < scope)) + if (scope == p->scope || scope == TIPC_ANY_SCOPE) tipc_dest_push(dports, 0, p->sk.ref); } } diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index c7c9a3ddd420..259f95e3d99c 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -51,6 +51,8 @@ struct tipc_uaddr; #define TIPC_PUBL_SCOPE_NUM (TIPC_NODE_SCOPE + 1) #define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */ +#define TIPC_ANY_SCOPE 10 /* Both node and cluster scope will match */ + /** * struct publication - info about a published service address or range * @sr: service range represented by this publication @@ -113,7 +115,7 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb); bool tipc_nametbl_lookup_anycast(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk); void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua, - bool exact, struct list_head *dports); + struct list_head *dports); void tipc_nametbl_lookup_mcast_nodes(struct net *net, struct tipc_uaddr *ua, struct tipc_nlist *nodes); bool tipc_nametbl_lookup_group(struct net *net, struct tipc_uaddr *ua, diff --git a/net/tipc/node.c b/net/tipc/node.c index 81af92954c6c..9947b7dfe1d2 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1214,7 +1214,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, /* Peer has changed i/f address without rebooting. * If so, the link will reset soon, and the next * discovery will be accepted. So we can ignore it. - * It may also be an cloned or malicious peer having + * It may also be a cloned or malicious peer having * chosen the same node address and signature as an * existing one. * Ignore requests until the link goes down, if ever. diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 53af72824c9c..34a97ea36cc8 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -73,9 +73,6 @@ struct sockaddr_pair { /** * struct tipc_sock - TIPC socket structure * @sk: socket - interacts with 'port' and with user via the socket API - * @conn_type: TIPC type used when connection was established - * @conn_instance: TIPC instance used when connection was established - * @published: non-zero if port has one or more associated names * @max_pkt: maximum packet size "hint" used when building messages sent by port * @maxnagle: maximum size of msg which can be subject to nagle * @portid: unique port identity in TIPC socket hash table @@ -106,11 +103,11 @@ struct sockaddr_pair { * @expect_ack: whether this TIPC socket is expecting an ack * @nodelay: setsockopt() TIPC_NODELAY setting * @group_is_open: TIPC socket group is fully open (FIXME) + * @published: true if port has one or more associated names + * @conn_addrtype: address type used when establishing connection */ struct tipc_sock { struct sock sk; - u32 conn_type; - u32 conn_instance; u32 max_pkt; u32 maxnagle; u32 portid; @@ -141,6 +138,7 @@ struct tipc_sock { bool nodelay; bool group_is_open; bool published; + u8 conn_addrtype; }; static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); @@ -664,7 +662,7 @@ static int tipc_release(struct socket *sock) * @skaddr: socket address describing name(s) and desired operation * @alen: size of socket address data structure * - * Name and name sequence binding is indicated using a positive scope value; + * Name and name sequence binding are indicated using a positive scope value; * a negative scope value unbinds the specified name. Specifying no name * (i.e. a socket address length of 0) unbinds all names from the socket. * @@ -1202,12 +1200,12 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct tipc_msg *hdr; struct tipc_uaddr ua; int user, mtyp, hlen; - bool exact; __skb_queue_head_init(&tmpq); INIT_LIST_HEAD(&dports); ua.addrtype = TIPC_SERVICE_RANGE; + /* tipc_skb_peek() increments the head skb's reference counter */ skb = tipc_skb_peek(arrvq, &inputq->lock); for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) { hdr = buf_msg(skb); @@ -1216,6 +1214,12 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, hlen = skb_headroom(skb) + msg_hdr_sz(hdr); onode = msg_orignode(hdr); ua.sr.type = msg_nametype(hdr); + ua.sr.lower = msg_namelower(hdr); + ua.sr.upper = msg_nameupper(hdr); + if (onode == self) + ua.scope = TIPC_ANY_SCOPE; + else + ua.scope = TIPC_CLUSTER_SCOPE; if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) { spin_lock_bh(&inputq->lock); @@ -1233,20 +1237,10 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, ua.sr.lower = 0; ua.sr.upper = ~0; ua.scope = msg_lookup_scope(hdr); - exact = true; - } else { - /* TIPC_NODE_SCOPE means "any scope" in this context */ - if (onode == self) - ua.scope = TIPC_NODE_SCOPE; - else - ua.scope = TIPC_CLUSTER_SCOPE; - exact = false; - ua.sr.lower = msg_namelower(hdr); - ua.sr.upper = msg_nameupper(hdr); } /* Create destination port list: */ - tipc_nametbl_lookup_mcast_sockets(net, &ua, exact, &dports); + tipc_nametbl_lookup_mcast_sockets(net, &ua, &dports); /* Clone message per destination */ while (tipc_dest_pop(&dports, NULL, &portid)) { @@ -1258,13 +1252,11 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, } pr_warn("Failed to clone mcast rcv buffer\n"); } - /* Append to inputq if not already done by other thread */ + /* Append clones to inputq only if skb is still head of arrvq */ spin_lock_bh(&inputq->lock); if (skb_peek(arrvq) == skb) { skb_queue_splice_tail_init(&tmpq, inputq); - /* Decrease the skb's refcnt as increasing in the - * function tipc_skb_peek - */ + /* Decrement the skb's refcnt */ kfree_skb(__skb_dequeue(arrvq)); } spin_unlock_bh(&inputq->lock); @@ -1463,10 +1455,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) return -EISCONN; if (tsk->published) return -EOPNOTSUPP; - if (atype == TIPC_SERVICE_ADDR) { - tsk->conn_type = ua->sa.type; - tsk->conn_instance = ua->sa.instance; - } + if (atype == TIPC_SERVICE_ADDR) + tsk->conn_addrtype = atype; msg_set_syn(hdr, 1); } @@ -1737,67 +1727,58 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb, struct tipc_sock *tsk) { - struct tipc_msg *msg; - u32 anc_data[3]; - u32 err; - u32 dest_type; - int has_name; - int res; + struct tipc_msg *hdr; + u32 data[3] = {0,}; + bool has_addr; + int dlen, rc; if (likely(m->msg_controllen == 0)) return 0; - msg = buf_msg(skb); - /* Optionally capture errored message object(s) */ - err = msg ? msg_errcode(msg) : 0; - if (unlikely(err)) { - anc_data[0] = err; - anc_data[1] = msg_data_sz(msg); - res = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, anc_data); - if (res) - return res; - if (anc_data[1]) { - if (skb_linearize(skb)) - return -ENOMEM; - msg = buf_msg(skb); - res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1], - msg_data(msg)); - if (res) - return res; - } + hdr = buf_msg(skb); + dlen = msg_data_sz(hdr); + + /* Capture errored message object, if any */ + if (msg_errcode(hdr)) { + if (skb_linearize(skb)) + return -ENOMEM; + hdr = buf_msg(skb); + data[0] = msg_errcode(hdr); + data[1] = dlen; + rc = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, data); + if (rc || !dlen) + return rc; + rc = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, dlen, msg_data(hdr)); + if (rc) + return rc; } - /* Optionally capture message destination object */ - dest_type = msg ? msg_type(msg) : TIPC_DIRECT_MSG; - switch (dest_type) { + /* Capture TIPC_SERVICE_ADDR/RANGE destination address, if any */ + switch (msg_type(hdr)) { case TIPC_NAMED_MSG: - has_name = 1; - anc_data[0] = msg_nametype(msg); - anc_data[1] = msg_namelower(msg); - anc_data[2] = msg_namelower(msg); + has_addr = true; + data[0] = msg_nametype(hdr); + data[1] = msg_namelower(hdr); + data[2] = data[1]; break; case TIPC_MCAST_MSG: - has_name = 1; - anc_data[0] = msg_nametype(msg); - anc_data[1] = msg_namelower(msg); - anc_data[2] = msg_nameupper(msg); + has_addr = true; + data[0] = msg_nametype(hdr); + data[1] = msg_namelower(hdr); + data[2] = msg_nameupper(hdr); break; case TIPC_CONN_MSG: - has_name = (tsk->conn_type != 0); - anc_data[0] = tsk->conn_type; - anc_data[1] = tsk->conn_instance; - anc_data[2] = tsk->conn_instance; + has_addr = !!tsk->conn_addrtype; + data[0] = msg_nametype(&tsk->phdr); + data[1] = msg_nameinst(&tsk->phdr); + data[2] = data[1]; break; default: - has_name = 0; + has_addr = false; } - if (has_name) { - res = put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, anc_data); - if (res) - return res; - } - - return 0; + if (!has_addr) + return 0; + return put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, data); } static struct sk_buff *tipc_sk_build_ack(struct tipc_sock *tsk) @@ -2750,8 +2731,9 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, tsk_set_importance(new_sk, msg_importance(msg)); if (msg_named(msg)) { - new_tsock->conn_type = msg_nametype(msg); - new_tsock->conn_instance = msg_nameinst(msg); + new_tsock->conn_addrtype = TIPC_SERVICE_ADDR; + msg_set_nametype(&new_tsock->phdr, msg_nametype(msg)); + msg_set_nameinst(&new_tsock->phdr, msg_nameinst(msg)); } /* @@ -3455,13 +3437,14 @@ void tipc_socket_stop(void) /* Caller should hold socket lock for the passed tipc socket. */ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk) { - u32 peer_node; - u32 peer_port; + u32 peer_node, peer_port; + u32 conn_type, conn_instance; struct nlattr *nest; peer_node = tsk_peer_node(tsk); peer_port = tsk_peer_port(tsk); - + conn_type = msg_nametype(&tsk->phdr); + conn_instance = msg_nameinst(&tsk->phdr); nest = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_CON); if (!nest) return -EMSGSIZE; @@ -3471,12 +3454,12 @@ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk) if (nla_put_u32(skb, TIPC_NLA_CON_SOCK, peer_port)) goto msg_full; - if (tsk->conn_type != 0) { + if (tsk->conn_addrtype != 0) { if (nla_put_flag(skb, TIPC_NLA_CON_FLAG)) goto msg_full; - if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, tsk->conn_type)) + if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, conn_type)) goto msg_full; - if (nla_put_u32(skb, TIPC_NLA_CON_INST, tsk->conn_instance)) + if (nla_put_u32(skb, TIPC_NLA_CON_INST, conn_instance)) goto msg_full; } nla_nest_end(skb, nest); @@ -3866,9 +3849,9 @@ bool tipc_sk_filtering(struct sock *sk) } if (!tipc_sk_type_connectionless(sk)) { - type = tsk->conn_type; - lower = tsk->conn_instance; - upper = tsk->conn_instance; + type = msg_nametype(&tsk->phdr); + lower = msg_nameinst(&tsk->phdr); + upper = lower; } if ((_type && _type != type) || (_lower && _lower != lower) || @@ -3933,6 +3916,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf) { int i = 0; size_t sz = (dqueues) ? SK_LMAX : SK_LMIN; + u32 conn_type, conn_instance; struct tipc_sock *tsk; struct publication *p; bool tsk_connected; @@ -3953,8 +3937,10 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf) if (tsk_connected) { i += scnprintf(buf + i, sz - i, " %x", tsk_peer_node(tsk)); i += scnprintf(buf + i, sz - i, " %u", tsk_peer_port(tsk)); - i += scnprintf(buf + i, sz - i, " %u", tsk->conn_type); - i += scnprintf(buf + i, sz - i, " %u", tsk->conn_instance); + conn_type = msg_nametype(&tsk->phdr); + conn_instance = msg_nameinst(&tsk->phdr); + i += scnprintf(buf + i, sz - i, " %u", conn_type); + i += scnprintf(buf + i, sz - i, " %u", conn_instance); } i += scnprintf(buf + i, sz - i, " | %u", tsk->published); if (tsk->published) { diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 8e00d739f03a..05d49ad81290 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -66,7 +66,7 @@ static void tipc_sub_send_event(struct tipc_subscription *sub, /** * tipc_sub_check_overlap - test for subscription overlap with the given values * @subscribed: the service range subscribed for - * @found: the service range we are checning for match + * @found: the service range we are checking for match * * Returns true if there is overlap, otherwise false. */ diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index bd9f1567aa39..b932469ee69c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -128,7 +128,7 @@ static void destroy_record(struct tls_record_info *record) int i; for (i = 0; i < record->num_frags; i++) - __skb_frag_unref(&record->frags[i]); + __skb_frag_unref(&record->frags[i], false); kfree(record); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 694de024d0ee..4feb95e34b64 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1153,7 +1153,7 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page, int ret = 0; bool eor; - eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST)); + eor = !(flags & MSG_SENDPAGE_NOTLAST); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* Call the sk_stream functions to manage the sndbuf mem. */ @@ -2019,8 +2019,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (copied < 0) goto splice_read_end; - if (likely(!(flags & MSG_PEEK))) - tls_sw_advance_skb(sk, skb, copied); + tls_sw_advance_skb(sk, skb, copied); splice_read_end: release_sock(sk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5d1192ceb139..23c92ad15c61 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -262,6 +262,14 @@ static void __unix_insert_socket(struct hlist_head *list, struct sock *sk) sk_add_node(sk, list); } +static void __unix_set_addr(struct sock *sk, struct unix_address *addr, + unsigned hash) +{ + __unix_remove_socket(sk); + smp_store_release(&unix_sk(sk)->addr, addr); + __unix_insert_socket(&unix_socket_table[hash], sk); +} + static inline void unix_remove_socket(struct sock *sk) { spin_lock(&unix_table_lock); @@ -278,11 +286,11 @@ static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk) static struct sock *__unix_find_socket_byname(struct net *net, struct sockaddr_un *sunname, - int len, int type, unsigned int hash) + int len, unsigned int hash) { struct sock *s; - sk_for_each(s, &unix_socket_table[hash ^ type]) { + sk_for_each(s, &unix_socket_table[hash]) { struct unix_sock *u = unix_sk(s); if (!net_eq(sock_net(s), net)) @@ -297,13 +305,12 @@ static struct sock *__unix_find_socket_byname(struct net *net, static inline struct sock *unix_find_socket_byname(struct net *net, struct sockaddr_un *sunname, - int len, int type, - unsigned int hash) + int len, unsigned int hash) { struct sock *s; spin_lock(&unix_table_lock); - s = __unix_find_socket_byname(net, sunname, len, type, hash); + s = __unix_find_socket_byname(net, sunname, len, hash); if (s) sock_hold(s); spin_unlock(&unix_table_lock); @@ -484,7 +491,7 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other) */ if (!sock_flag(other, SOCK_DEAD) && unix_peer(other) == sk) { other->sk_err = ECONNRESET; - other->sk_error_report(other); + sk_error_report(other); } } } @@ -891,12 +898,12 @@ static int unix_autobind(struct socket *sock) retry: addr->len = sprintf(addr->name->sun_path+1, "%05x", ordernum) + 1 + sizeof(short); addr->hash = unix_hash_fold(csum_partial(addr->name, addr->len, 0)); + addr->hash ^= sk->sk_type; spin_lock(&unix_table_lock); ordernum = (ordernum+1)&0xFFFFF; - if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type, - addr->hash)) { + if (__unix_find_socket_byname(net, addr->name, addr->len, addr->hash)) { spin_unlock(&unix_table_lock); /* * __unix_find_socket_byname() may take long time if many names @@ -911,11 +918,8 @@ retry: } goto retry; } - addr->hash ^= sk->sk_type; - __unix_remove_socket(sk); - smp_store_release(&u->addr, addr); - __unix_insert_socket(&unix_socket_table[addr->hash], sk); + __unix_set_addr(sk, addr, addr->hash); spin_unlock(&unix_table_lock); err = 0; @@ -960,7 +964,7 @@ static struct sock *unix_find_other(struct net *net, } } else { err = -ECONNREFUSED; - u = unix_find_socket_byname(net, sunname, len, type, hash); + u = unix_find_socket_byname(net, sunname, len, type ^ hash); if (u) { struct dentry *dentry; dentry = unix_sk(u)->path.dentry; @@ -978,125 +982,125 @@ fail: return NULL; } -static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) +static int unix_bind_bsd(struct sock *sk, struct unix_address *addr) { + struct unix_sock *u = unix_sk(sk); + umode_t mode = S_IFSOCK | + (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask()); + struct user_namespace *ns; // barf... + struct path parent; struct dentry *dentry; - struct path path; - int err = 0; + unsigned int hash; + int err; + /* * Get the parent directory, calculate the hash for last * component. */ - dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); - err = PTR_ERR(dentry); + dentry = kern_path_create(AT_FDCWD, addr->name->sun_path, &parent, 0); if (IS_ERR(dentry)) - return err; + return PTR_ERR(dentry); + ns = mnt_user_ns(parent.mnt); /* * All right, let's create it. */ - err = security_path_mknod(&path, dentry, mode, 0); - if (!err) { - err = vfs_mknod(mnt_user_ns(path.mnt), d_inode(path.dentry), - dentry, mode, 0); - if (!err) { - res->mnt = mntget(path.mnt); - res->dentry = dget(dentry); - } - } - done_path_create(&path, dentry); + err = security_path_mknod(&parent, dentry, mode, 0); + if (!err) + err = vfs_mknod(ns, d_inode(parent.dentry), dentry, mode, 0); + if (err) + goto out; + err = mutex_lock_interruptible(&u->bindlock); + if (err) + goto out_unlink; + if (u->addr) + goto out_unlock; + + addr->hash = UNIX_HASH_SIZE; + hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); + spin_lock(&unix_table_lock); + u->path.mnt = mntget(parent.mnt); + u->path.dentry = dget(dentry); + __unix_set_addr(sk, addr, hash); + spin_unlock(&unix_table_lock); + mutex_unlock(&u->bindlock); + done_path_create(&parent, dentry); + return 0; + +out_unlock: + mutex_unlock(&u->bindlock); + err = -EINVAL; +out_unlink: + /* failed after successful mknod? unlink what we'd created... */ + vfs_unlink(ns, d_inode(parent.dentry), dentry, NULL); +out: + done_path_create(&parent, dentry); return err; } +static int unix_bind_abstract(struct sock *sk, struct unix_address *addr) +{ + struct unix_sock *u = unix_sk(sk); + int err; + + err = mutex_lock_interruptible(&u->bindlock); + if (err) + return err; + + if (u->addr) { + mutex_unlock(&u->bindlock); + return -EINVAL; + } + + spin_lock(&unix_table_lock); + if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len, + addr->hash)) { + spin_unlock(&unix_table_lock); + mutex_unlock(&u->bindlock); + return -EADDRINUSE; + } + __unix_set_addr(sk, addr, addr->hash); + spin_unlock(&unix_table_lock); + mutex_unlock(&u->bindlock); + return 0; +} + static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - struct net *net = sock_net(sk); - struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; char *sun_path = sunaddr->sun_path; int err; unsigned int hash; struct unix_address *addr; - struct hlist_head *list; - struct path path = { }; - err = -EINVAL; if (addr_len < offsetofend(struct sockaddr_un, sun_family) || sunaddr->sun_family != AF_UNIX) - goto out; + return -EINVAL; - if (addr_len == sizeof(short)) { - err = unix_autobind(sock); - goto out; - } + if (addr_len == sizeof(short)) + return unix_autobind(sock); err = unix_mkname(sunaddr, addr_len, &hash); if (err < 0) - goto out; + return err; addr_len = err; - - if (sun_path[0]) { - umode_t mode = S_IFSOCK | - (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(sun_path, mode, &path); - if (err) { - if (err == -EEXIST) - err = -EADDRINUSE; - goto out; - } - } - - err = mutex_lock_interruptible(&u->bindlock); - if (err) - goto out_put; - - err = -EINVAL; - if (u->addr) - goto out_up; - - err = -ENOMEM; addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL); if (!addr) - goto out_up; + return -ENOMEM; memcpy(addr->name, sunaddr, addr_len); addr->len = addr_len; addr->hash = hash ^ sk->sk_type; refcount_set(&addr->refcnt, 1); - if (sun_path[0]) { - addr->hash = UNIX_HASH_SIZE; - hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); - spin_lock(&unix_table_lock); - u->path = path; - list = &unix_socket_table[hash]; - } else { - spin_lock(&unix_table_lock); - err = -EADDRINUSE; - if (__unix_find_socket_byname(net, sunaddr, addr_len, - sk->sk_type, hash)) { - unix_release_addr(addr); - goto out_unlock; - } - - list = &unix_socket_table[addr->hash]; - } - - err = 0; - __unix_remove_socket(sk); - smp_store_release(&u->addr, addr); - __unix_insert_socket(list, sk); - -out_unlock: - spin_unlock(&unix_table_lock); -out_up: - mutex_unlock(&u->bindlock); -out_put: + if (sun_path[0]) + err = unix_bind_bsd(sk, addr); + else + err = unix_bind_abstract(sk, addr); if (err) - path_put(&path); -out: - return err; + unix_release_addr(addr); + return err == -EEXIST ? -EADDRINUSE : err; } static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) @@ -1393,7 +1397,7 @@ restart: unix_state_unlock(sk); - /* take ten and and send info to listening sock */ + /* take ten and send info to listening sock */ spin_lock(&other->sk_receive_queue.lock); __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 92a72f0e0d94..3e02cc3b24f8 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -415,8 +415,8 @@ static void vsock_deassign_transport(struct vsock_sock *vsk) /* Assign a transport to a socket and call the .init transport callback. * - * Note: for stream socket this must be called when vsk->remote_addr is set - * (e.g. during the connect() or when a connection request on a listener + * Note: for connection oriented socket this must be called when vsk->remote_addr + * is set (e.g. during the connect() or when a connection request on a listener * socket is received). * The vsk->remote_addr is used to decide which transport to use: * - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if @@ -452,6 +452,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) new_transport = transport_dgram; break; case SOCK_STREAM: + case SOCK_SEQPACKET: if (vsock_use_local_transport(remote_cid)) new_transport = transport_local; else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g || @@ -469,10 +470,10 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) return 0; /* transport->release() must be called with sock lock acquired. - * This path can only be taken during vsock_stream_connect(), - * where we have already held the sock lock. - * In the other cases, this function is called on a new socket - * which is not assigned to any transport. + * This path can only be taken during vsock_connect(), where we + * have already held the sock lock. In the other cases, this + * function is called on a new socket which is not assigned to + * any transport. */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); @@ -484,6 +485,14 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) if (!new_transport || !try_module_get(new_transport->module)) return -ENODEV; + if (sk->sk_type == SOCK_SEQPACKET) { + if (!new_transport->seqpacket_allow || + !new_transport->seqpacket_allow(remote_cid)) { + module_put(new_transport->module); + return -ESOCKTNOSUPPORT; + } + } + ret = new_transport->init(vsk, psk); if (ret) { module_put(new_transport->module); @@ -604,8 +613,8 @@ out: /**** SOCKET OPERATIONS ****/ -static int __vsock_bind_stream(struct vsock_sock *vsk, - struct sockaddr_vm *addr) +static int __vsock_bind_connectible(struct vsock_sock *vsk, + struct sockaddr_vm *addr) { static u32 port; struct sockaddr_vm new_addr; @@ -649,9 +658,10 @@ static int __vsock_bind_stream(struct vsock_sock *vsk, vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port); - /* Remove stream sockets from the unbound list and add them to the hash - * table for easy lookup by its address. The unbound list is simply an - * extra entry at the end of the hash table, a trick used by AF_UNIX. + /* Remove connection oriented sockets from the unbound list and add them + * to the hash table for easy lookup by its address. The unbound list + * is simply an extra entry at the end of the hash table, a trick used + * by AF_UNIX. */ __vsock_remove_bound(vsk); __vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk); @@ -684,8 +694,9 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) switch (sk->sk_socket->type) { case SOCK_STREAM: + case SOCK_SEQPACKET: spin_lock_bh(&vsock_table_lock); - retval = __vsock_bind_stream(vsk, addr); + retval = __vsock_bind_connectible(vsk, addr); spin_unlock_bh(&vsock_table_lock); break; @@ -768,6 +779,11 @@ static struct sock *__vsock_create(struct net *net, return sk; } +static bool sock_type_connectible(u16 type) +{ + return (type == SOCK_STREAM) || (type == SOCK_SEQPACKET); +} + static void __vsock_release(struct sock *sk, int level) { if (sk) { @@ -786,7 +802,7 @@ static void __vsock_release(struct sock *sk, int level) if (vsk->transport) vsk->transport->release(vsk); - else if (sk->sk_type == SOCK_STREAM) + else if (sock_type_connectible(sk->sk_type)) vsock_remove_sock(vsk); sock_orphan(sk); @@ -844,6 +860,16 @@ s64 vsock_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(vsock_stream_has_data); +static s64 vsock_connectible_has_data(struct vsock_sock *vsk) +{ + struct sock *sk = sk_vsock(vsk); + + if (sk->sk_type == SOCK_SEQPACKET) + return vsk->transport->seqpacket_has_data(vsk); + else + return vsock_stream_has_data(vsk); +} + s64 vsock_stream_has_space(struct vsock_sock *vsk) { return vsk->transport->stream_has_space(vsk); @@ -937,10 +963,10 @@ static int vsock_shutdown(struct socket *sock, int mode) if ((mode & ~SHUTDOWN_MASK) || !mode) return -EINVAL; - /* If this is a STREAM socket and it is not connected then bail out - * immediately. If it is a DGRAM socket then we must first kick the - * socket so that it wakes up from any sleeping calls, for example - * recv(), and then afterwards return the error. + /* If this is a connection oriented socket and it is not connected then + * bail out immediately. If it is a DGRAM socket then we must first + * kick the socket so that it wakes up from any sleeping calls, for + * example recv(), and then afterwards return the error. */ sk = sock->sk; @@ -948,7 +974,7 @@ static int vsock_shutdown(struct socket *sock, int mode) lock_sock(sk); if (sock->state == SS_UNCONNECTED) { err = -ENOTCONN; - if (sk->sk_type == SOCK_STREAM) + if (sock_type_connectible(sk->sk_type)) goto out; } else { sock->state = SS_DISCONNECTING; @@ -961,7 +987,7 @@ static int vsock_shutdown(struct socket *sock, int mode) sk->sk_shutdown |= mode; sk->sk_state_change(sk); - if (sk->sk_type == SOCK_STREAM) { + if (sock_type_connectible(sk->sk_type)) { sock_reset_flag(sk, SOCK_DONE); vsock_send_shutdown(sk, mode); } @@ -1016,7 +1042,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; - } else if (sock->type == SOCK_STREAM) { + } else if (sock_type_connectible(sk->sk_type)) { const struct vsock_transport *transport; lock_sock(sk); @@ -1255,7 +1281,7 @@ static void vsock_connect_timeout(struct work_struct *work) (sk->sk_shutdown != SHUTDOWN_MASK)) { sk->sk_state = TCP_CLOSE; sk->sk_err = ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); vsock_transport_cancel_pkt(vsk); } release_sock(sk); @@ -1263,8 +1289,8 @@ static void vsock_connect_timeout(struct work_struct *work) sock_put(sk); } -static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, - int addr_len, int flags) +static int vsock_connect(struct socket *sock, struct sockaddr *addr, + int addr_len, int flags) { int err; struct sock *sk; @@ -1369,7 +1395,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (signal_pending(current)) { err = sock_intr_errno(timeout); - sk->sk_state = TCP_CLOSE; + sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); goto out_wait; @@ -1414,7 +1440,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, lock_sock(listener); - if (sock->type != SOCK_STREAM) { + if (!sock_type_connectible(sock->type)) { err = -EOPNOTSUPP; goto out; } @@ -1491,7 +1517,7 @@ static int vsock_listen(struct socket *sock, int backlog) lock_sock(sk); - if (sock->type != SOCK_STREAM) { + if (!sock_type_connectible(sk->sk_type)) { err = -EOPNOTSUPP; goto out; } @@ -1535,11 +1561,11 @@ static void vsock_update_buffer_size(struct vsock_sock *vsk, vsk->buffer_size = val; } -static int vsock_stream_setsockopt(struct socket *sock, - int level, - int optname, - sockptr_t optval, - unsigned int optlen) +static int vsock_connectible_setsockopt(struct socket *sock, + int level, + int optname, + sockptr_t optval, + unsigned int optlen) { int err; struct sock *sk; @@ -1617,10 +1643,10 @@ exit: return err; } -static int vsock_stream_getsockopt(struct socket *sock, - int level, int optname, - char __user *optval, - int __user *optlen) +static int vsock_connectible_getsockopt(struct socket *sock, + int level, int optname, + char __user *optval, + int __user *optlen) { int err; int len; @@ -1688,8 +1714,8 @@ static int vsock_stream_getsockopt(struct socket *sock, return 0; } -static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, - size_t len) +static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk; struct vsock_sock *vsk; @@ -1712,7 +1738,9 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, transport = vsk->transport; - /* Callers should not provide a destination with stream sockets. */ + /* Callers should not provide a destination with connection oriented + * sockets. + */ if (msg->msg_namelen) { err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out; @@ -1803,9 +1831,13 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, * responsibility to check how many bytes we were able to send. */ - written = transport->stream_enqueue( - vsk, msg, - len - total_written); + if (sk->sk_type == SOCK_SEQPACKET) { + written = transport->seqpacket_enqueue(vsk, + msg, len - total_written); + } else { + written = transport->stream_enqueue(vsk, + msg, len - total_written); + } if (written < 0) { err = -ENOMEM; goto out_err; @@ -1821,72 +1853,98 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, } out_err: - if (total_written > 0) - err = total_written; + if (total_written > 0) { + /* Return number of written bytes only if: + * 1) SOCK_STREAM socket. + * 2) SOCK_SEQPACKET socket when whole buffer is sent. + */ + if (sk->sk_type == SOCK_STREAM || total_written == len) + err = total_written; + } out: release_sock(sk); return err; } - -static int -vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +static int vsock_connectible_wait_data(struct sock *sk, + struct wait_queue_entry *wait, + long timeout, + struct vsock_transport_recv_notify_data *recv_data, + size_t target) { - struct sock *sk; - struct vsock_sock *vsk; const struct vsock_transport *transport; + struct vsock_sock *vsk; + s64 data; int err; - size_t target; - ssize_t copied; - long timeout; - struct vsock_transport_recv_notify_data recv_data; - DEFINE_WAIT(wait); - - sk = sock->sk; vsk = vsock_sk(sk); err = 0; + transport = vsk->transport; - lock_sock(sk); + while ((data = vsock_connectible_has_data(vsk)) == 0) { + prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); - transport = vsk->transport; + if (sk->sk_err != 0 || + (sk->sk_shutdown & RCV_SHUTDOWN) || + (vsk->peer_shutdown & SEND_SHUTDOWN)) { + break; + } - if (!transport || sk->sk_state != TCP_ESTABLISHED) { - /* Recvmsg is supposed to return 0 if a peer performs an - * orderly shutdown. Differentiate between that case and when a - * peer has not connected or a local shutdown occurred with the - * SOCK_DONE flag. - */ - if (sock_flag(sk, SOCK_DONE)) - err = 0; - else - err = -ENOTCONN; + /* Don't wait for non-blocking sockets. */ + if (timeout == 0) { + err = -EAGAIN; + break; + } - goto out; - } + if (recv_data) { + err = transport->notify_recv_pre_block(vsk, target, recv_data); + if (err < 0) + break; + } - if (flags & MSG_OOB) { - err = -EOPNOTSUPP; - goto out; - } + release_sock(sk); + timeout = schedule_timeout(timeout); + lock_sock(sk); - /* We don't check peer_shutdown flag here since peer may actually shut - * down, but there can be data in the queue that a local socket can - * receive. - */ - if (sk->sk_shutdown & RCV_SHUTDOWN) { - err = 0; - goto out; + if (signal_pending(current)) { + err = sock_intr_errno(timeout); + break; + } else if (timeout == 0) { + err = -EAGAIN; + break; + } } - /* It is valid on Linux to pass in a zero-length receive buffer. This - * is not an error. We may as well bail out now. + finish_wait(sk_sleep(sk), wait); + + if (err) + return err; + + /* Internal transport error when checking for available + * data. XXX This should be changed to a connection + * reset in a later change. */ - if (!len) { - err = 0; - goto out; - } + if (data < 0) + return -ENOMEM; + + return data; +} + +static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int flags) +{ + struct vsock_transport_recv_notify_data recv_data; + const struct vsock_transport *transport; + struct vsock_sock *vsk; + ssize_t copied; + size_t target; + long timeout; + int err; + + DEFINE_WAIT(wait); + + vsk = vsock_sk(sk); + transport = vsk->transport; /* We must not copy less than target bytes into the user's buffer * before returning successfully, so we wait for the consume queue to @@ -1908,94 +1966,158 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, while (1) { - s64 ready; + ssize_t read; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - ready = vsock_stream_has_data(vsk); + err = vsock_connectible_wait_data(sk, &wait, timeout, + &recv_data, target); + if (err <= 0) + break; - if (ready == 0) { - if (sk->sk_err != 0 || - (sk->sk_shutdown & RCV_SHUTDOWN) || - (vsk->peer_shutdown & SEND_SHUTDOWN)) { - finish_wait(sk_sleep(sk), &wait); - break; - } - /* Don't wait for non-blocking sockets. */ - if (timeout == 0) { - err = -EAGAIN; - finish_wait(sk_sleep(sk), &wait); - break; - } + err = transport->notify_recv_pre_dequeue(vsk, target, + &recv_data); + if (err < 0) + break; - err = transport->notify_recv_pre_block( - vsk, target, &recv_data); - if (err < 0) { - finish_wait(sk_sleep(sk), &wait); - break; - } - release_sock(sk); - timeout = schedule_timeout(timeout); - lock_sock(sk); + read = transport->stream_dequeue(vsk, msg, len - copied, flags); + if (read < 0) { + err = -ENOMEM; + break; + } - if (signal_pending(current)) { - err = sock_intr_errno(timeout); - finish_wait(sk_sleep(sk), &wait); - break; - } else if (timeout == 0) { - err = -EAGAIN; - finish_wait(sk_sleep(sk), &wait); - break; - } - } else { - ssize_t read; + copied += read; - finish_wait(sk_sleep(sk), &wait); + err = transport->notify_recv_post_dequeue(vsk, target, read, + !(flags & MSG_PEEK), &recv_data); + if (err < 0) + goto out; - if (ready < 0) { - /* Invalid queue pair content. XXX This should - * be changed to a connection reset in a later - * change. - */ + if (read >= target || flags & MSG_PEEK) + break; - err = -ENOMEM; - goto out; - } + target -= read; + } - err = transport->notify_recv_pre_dequeue( - vsk, target, &recv_data); - if (err < 0) - break; + if (sk->sk_err) + err = -sk->sk_err; + else if (sk->sk_shutdown & RCV_SHUTDOWN) + err = 0; - read = transport->stream_dequeue( - vsk, msg, - len - copied, flags); - if (read < 0) { - err = -ENOMEM; - break; - } + if (copied > 0) + err = copied; + +out: + return err; +} - copied += read; +static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int flags) +{ + const struct vsock_transport *transport; + struct vsock_sock *vsk; + ssize_t record_len; + long timeout; + int err = 0; + DEFINE_WAIT(wait); - err = transport->notify_recv_post_dequeue( - vsk, target, read, - !(flags & MSG_PEEK), &recv_data); - if (err < 0) - goto out; + vsk = vsock_sk(sk); + transport = vsk->transport; - if (read >= target || flags & MSG_PEEK) - break; + timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - target -= read; - } + err = vsock_connectible_wait_data(sk, &wait, timeout, NULL, 0); + if (err <= 0) + goto out; + + record_len = transport->seqpacket_dequeue(vsk, msg, flags); + + if (record_len < 0) { + err = -ENOMEM; + goto out; } - if (sk->sk_err) + if (sk->sk_err) { err = -sk->sk_err; - else if (sk->sk_shutdown & RCV_SHUTDOWN) + } else if (sk->sk_shutdown & RCV_SHUTDOWN) { err = 0; + } else { + /* User sets MSG_TRUNC, so return real length of + * packet. + */ + if (flags & MSG_TRUNC) + err = record_len; + else + err = len - msg_data_left(msg); - if (copied > 0) - err = copied; + /* Always set MSG_TRUNC if real length of packet is + * bigger than user's buffer. + */ + if (record_len > len) + msg->msg_flags |= MSG_TRUNC; + } + +out: + return err; +} + +static int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ + struct sock *sk; + struct vsock_sock *vsk; + const struct vsock_transport *transport; + int err; + + DEFINE_WAIT(wait); + + sk = sock->sk; + vsk = vsock_sk(sk); + err = 0; + + lock_sock(sk); + + transport = vsk->transport; + + if (!transport || sk->sk_state != TCP_ESTABLISHED) { + /* Recvmsg is supposed to return 0 if a peer performs an + * orderly shutdown. Differentiate between that case and when a + * peer has not connected or a local shutdown occurred with the + * SOCK_DONE flag. + */ + if (sock_flag(sk, SOCK_DONE)) + err = 0; + else + err = -ENOTCONN; + + goto out; + } + + if (flags & MSG_OOB) { + err = -EOPNOTSUPP; + goto out; + } + + /* We don't check peer_shutdown flag here since peer may actually shut + * down, but there can be data in the queue that a local socket can + * receive. + */ + if (sk->sk_shutdown & RCV_SHUTDOWN) { + err = 0; + goto out; + } + + /* It is valid on Linux to pass in a zero-length receive buffer. This + * is not an error. We may as well bail out now. + */ + if (!len) { + err = 0; + goto out; + } + + if (sk->sk_type == SOCK_STREAM) + err = __vsock_stream_recvmsg(sk, msg, len, flags); + else + err = __vsock_seqpacket_recvmsg(sk, msg, len, flags); out: release_sock(sk); @@ -2007,7 +2129,7 @@ static const struct proto_ops vsock_stream_ops = { .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, - .connect = vsock_stream_connect, + .connect = vsock_connect, .socketpair = sock_no_socketpair, .accept = vsock_accept, .getname = vsock_getname, @@ -2015,10 +2137,31 @@ static const struct proto_ops vsock_stream_ops = { .ioctl = sock_no_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, - .setsockopt = vsock_stream_setsockopt, - .getsockopt = vsock_stream_getsockopt, - .sendmsg = vsock_stream_sendmsg, - .recvmsg = vsock_stream_recvmsg, + .setsockopt = vsock_connectible_setsockopt, + .getsockopt = vsock_connectible_getsockopt, + .sendmsg = vsock_connectible_sendmsg, + .recvmsg = vsock_connectible_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +static const struct proto_ops vsock_seqpacket_ops = { + .family = PF_VSOCK, + .owner = THIS_MODULE, + .release = vsock_release, + .bind = vsock_bind, + .connect = vsock_connect, + .socketpair = sock_no_socketpair, + .accept = vsock_accept, + .getname = vsock_getname, + .poll = vsock_poll, + .ioctl = sock_no_ioctl, + .listen = vsock_listen, + .shutdown = vsock_shutdown, + .setsockopt = vsock_connectible_setsockopt, + .getsockopt = vsock_connectible_getsockopt, + .sendmsg = vsock_connectible_sendmsg, + .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; @@ -2043,6 +2186,9 @@ static int vsock_create(struct net *net, struct socket *sock, case SOCK_STREAM: sock->ops = &vsock_stream_ops; break; + case SOCK_SEQPACKET: + sock->ops = &vsock_seqpacket_ops; + break; default: return -ESOCKTNOSUPPORT; } diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 2700a63ab095..e0c2c992ad9c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -62,6 +62,7 @@ struct virtio_vsock { struct virtio_vsock_event event_list[8]; u32 guest_cid; + bool seqpacket_allow; }; static u32 virtio_transport_get_local_cid(void) @@ -359,7 +360,7 @@ static void virtio_vsock_reset_sock(struct sock *sk) lock_sock(sk); sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; - sk->sk_error_report(sk); + sk_error_report(sk); release_sock(sk); } @@ -443,6 +444,8 @@ static void virtio_vsock_rx_done(struct virtqueue *vq) queue_work(virtio_vsock_workqueue, &vsock->rx_work); } +static bool virtio_transport_seqpacket_allow(u32 remote_cid); + static struct virtio_transport virtio_transport = { .transport = { .module = THIS_MODULE, @@ -469,6 +472,11 @@ static struct virtio_transport virtio_transport = { .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, + .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, + .seqpacket_allow = virtio_transport_seqpacket_allow, + .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, @@ -485,6 +493,21 @@ static struct virtio_transport virtio_transport = { .send_pkt = virtio_transport_send_pkt, }; +static bool virtio_transport_seqpacket_allow(u32 remote_cid) +{ + struct virtio_vsock *vsock; + bool seqpacket_allow; + + seqpacket_allow = false; + rcu_read_lock(); + vsock = rcu_dereference(the_virtio_vsock); + if (vsock) + seqpacket_allow = vsock->seqpacket_allow; + rcu_read_unlock(); + + return seqpacket_allow; +} + static void virtio_transport_rx_work(struct work_struct *work) { struct virtio_vsock *vsock = @@ -608,10 +631,14 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->event_run = true; mutex_unlock(&vsock->event_lock); + if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_SEQPACKET)) + vsock->seqpacket_allow = true; + vdev->priv = vsock; rcu_assign_pointer(the_virtio_vsock, vsock); mutex_unlock(&the_virtio_vsock_mutex); + return 0; out: @@ -695,6 +722,7 @@ static struct virtio_device_id id_table[] = { }; static unsigned int features[] = { + VIRTIO_VSOCK_F_SEQPACKET }; static struct virtio_driver virtio_vsock_driver = { diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 902cb6dd710b..169ba8b72a63 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -74,6 +74,10 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, err = memcpy_from_msg(pkt->buf, info->msg, len); if (err) goto out; + + if (msg_data_left(info->msg) == 0 && + info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) + pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); } trace_virtio_transport_alloc_pkt(src_cid, src_port, @@ -165,6 +169,14 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); +static u16 virtio_transport_get_type(struct sock *sk) +{ + if (sk->sk_type == SOCK_STREAM) + return VIRTIO_VSOCK_TYPE_STREAM; + else + return VIRTIO_VSOCK_TYPE_SEQPACKET; +} + /* This function can only be used on connecting/connected sockets, * since a socket assigned to a transport is required. * @@ -179,6 +191,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; + info->type = virtio_transport_get_type(sk_vsock(vsk)); + t_ops = virtio_transport_get_ops(vsk); if (unlikely(!t_ops)) return -EFAULT; @@ -269,13 +283,10 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) } EXPORT_SYMBOL_GPL(virtio_transport_put_credit); -static int virtio_transport_send_credit_update(struct vsock_sock *vsk, - int type, - struct virtio_vsock_hdr *hdr) +static int virtio_transport_send_credit_update(struct vsock_sock *vsk) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, - .type = type, .vsk = vsk, }; @@ -383,11 +394,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, * messages, we set the limit to a high value. TODO: experiment * with different values. */ - if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { - virtio_transport_send_credit_update(vsk, - VIRTIO_VSOCK_TYPE_STREAM, - NULL); - } + if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) + virtio_transport_send_credit_update(vsk); return total; @@ -397,6 +405,75 @@ out: return err; } +static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + struct virtio_vsock_pkt *pkt; + int dequeued_len = 0; + size_t user_buf_len = msg_data_left(msg); + bool msg_ready = false; + + spin_lock_bh(&vvs->rx_lock); + + if (vvs->msg_count == 0) { + spin_unlock_bh(&vvs->rx_lock); + return 0; + } + + while (!msg_ready) { + pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list); + + if (dequeued_len >= 0) { + size_t pkt_len; + size_t bytes_to_copy; + + pkt_len = (size_t)le32_to_cpu(pkt->hdr.len); + bytes_to_copy = min(user_buf_len, pkt_len); + + if (bytes_to_copy) { + int err; + + /* sk_lock is held by caller so no one else can dequeue. + * Unlock rx_lock since memcpy_to_msg() may sleep. + */ + spin_unlock_bh(&vvs->rx_lock); + + err = memcpy_to_msg(msg, pkt->buf, bytes_to_copy); + if (err) { + /* Copy of message failed. Rest of + * fragments will be freed without copy. + */ + dequeued_len = err; + } else { + user_buf_len -= bytes_to_copy; + } + + spin_lock_bh(&vvs->rx_lock); + } + + if (dequeued_len >= 0) + dequeued_len += pkt_len; + } + + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) { + msg_ready = true; + vvs->msg_count--; + } + + virtio_transport_dec_rx_pkt(vvs, pkt); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + + spin_unlock_bh(&vvs->rx_lock); + + virtio_transport_send_credit_update(vsk); + + return dequeued_len; +} + ssize_t virtio_transport_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg, @@ -409,6 +486,38 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue); +ssize_t +virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags) +{ + if (flags & MSG_PEEK) + return -EOPNOTSUPP; + + return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags); +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); + +int +virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + spin_lock_bh(&vvs->tx_lock); + + if (len > vvs->peer_buf_alloc) { + spin_unlock_bh(&vvs->tx_lock); + return -EMSGSIZE; + } + + spin_unlock_bh(&vvs->tx_lock); + + return virtio_transport_stream_enqueue(vsk, msg, len); +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_enqueue); + int virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, @@ -431,6 +540,19 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data); +u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + u32 msg_count; + + spin_lock_bh(&vvs->rx_lock); + msg_count = vvs->msg_count; + spin_unlock_bh(&vvs->rx_lock); + + return msg_count; +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_has_data); + static s64 virtio_transport_has_space(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; @@ -496,8 +618,7 @@ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val) vvs->buf_alloc = *val; - virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, - NULL); + virtio_transport_send_credit_update(vsk); } EXPORT_SYMBOL_GPL(virtio_transport_notify_buffer_size); @@ -624,7 +745,6 @@ int virtio_transport_connect(struct vsock_sock *vsk) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_REQUEST, - .type = VIRTIO_VSOCK_TYPE_STREAM, .vsk = vsk, }; @@ -636,7 +756,6 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_SHUTDOWN, - .type = VIRTIO_VSOCK_TYPE_STREAM, .flags = (mode & RCV_SHUTDOWN ? VIRTIO_VSOCK_SHUTDOWN_RCV : 0) | (mode & SEND_SHUTDOWN ? @@ -665,7 +784,6 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RW, - .type = VIRTIO_VSOCK_TYPE_STREAM, .msg = msg, .pkt_len = len, .vsk = vsk, @@ -688,7 +806,6 @@ static int virtio_transport_reset(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, - .type = VIRTIO_VSOCK_TYPE_STREAM, .reply = !!pkt, .vsk = vsk, }; @@ -848,7 +965,7 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - if (sk->sk_type == SOCK_STREAM) + if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) remove_sock = virtio_transport_close(vsk); if (remove_sock) { @@ -890,7 +1007,7 @@ destroy: virtio_transport_reset(vsk, pkt); sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; - sk->sk_error_report(sk); + sk_error_report(sk); return err; } @@ -912,6 +1029,9 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, goto out; } + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) + vvs->msg_count++; + /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small * payload. @@ -923,13 +1043,18 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, struct virtio_vsock_pkt, list); /* If there is space in the last packet queued, we copy the - * new packet in its buffer. + * new packet in its buffer. We avoid this if the last packet + * queued has VIRTIO_VSOCK_SEQ_EOR set, because this is + * delimiter of SEQPACKET record, so 'pkt' is the first packet + * of a new record. */ - if (pkt->len <= last_pkt->buf_len - last_pkt->len) { + if ((pkt->len <= last_pkt->buf_len - last_pkt->len) && + !(le32_to_cpu(last_pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR)) { memcpy(last_pkt->buf + last_pkt->len, pkt->buf, pkt->len); last_pkt->len += pkt->len; free_pkt = true; + last_pkt->hdr.flags |= pkt->hdr.flags; goto out; } } @@ -1000,7 +1125,6 @@ virtio_transport_send_response(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RESPONSE, - .type = VIRTIO_VSOCK_TYPE_STREAM, .remote_cid = le64_to_cpu(pkt->hdr.src_cid), .remote_port = le32_to_cpu(pkt->hdr.src_port), .reply = true, @@ -1096,6 +1220,12 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, return 0; } +static bool virtio_transport_valid_type(u16 type) +{ + return (type == VIRTIO_VSOCK_TYPE_STREAM) || + (type == VIRTIO_VSOCK_TYPE_SEQPACKET); +} + /* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex * lock. */ @@ -1121,7 +1251,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, le32_to_cpu(pkt->hdr.buf_alloc), le32_to_cpu(pkt->hdr.fwd_cnt)); - if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) { + if (!virtio_transport_valid_type(le16_to_cpu(pkt->hdr.type))) { (void)virtio_transport_reset_no_sock(t, pkt); goto free_pkt; } @@ -1138,6 +1268,12 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, } } + if (virtio_transport_get_type(sk) != le16_to_cpu(pkt->hdr.type)) { + (void)virtio_transport_reset_no_sock(t, pkt); + sock_put(sk); + goto free_pkt; + } + vsk = vsock_sk(sk); lock_sock(sk); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index c99bc4ce78e2..7aef34e32bdf 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -831,7 +831,7 @@ static void vmci_transport_handle_detach(struct sock *sk) sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; - sk->sk_error_report(sk); + sk_error_report(sk); return; } sk->sk_state = TCP_CLOSE; @@ -1248,7 +1248,7 @@ vmci_transport_recv_connecting_server(struct sock *listener, vsock_remove_pending(listener, pending); vsock_enqueue_accept(listener, pending); - /* Callers of accept() will be be waiting on the listening socket, not + /* Callers of accept() will be waiting on the listening socket, not * the pending socket. */ listener->sk_data_ready(listener); @@ -1365,7 +1365,7 @@ destroy: sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; - sk->sk_error_report(sk); + sk_error_report(sk); return err; } diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index a45f7ffca8c5..169a8cf65b39 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -63,6 +63,8 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk) return 0; } +static bool vsock_loopback_seqpacket_allow(u32 remote_cid); + static struct virtio_transport loopback_transport = { .transport = { .module = THIS_MODULE, @@ -89,6 +91,11 @@ static struct virtio_transport loopback_transport = { .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, + .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, + .seqpacket_allow = vsock_loopback_seqpacket_allow, + .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, @@ -105,6 +112,11 @@ static struct virtio_transport loopback_transport = { .send_pkt = vsock_loopback_send_pkt, }; +static bool vsock_loopback_seqpacket_allow(u32 remote_cid) +{ + return true; +} + static void vsock_loopback_work(struct work_struct *work) { struct vsock_loopback *vsock = diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 285b8076054b..869c43d4414c 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -6,7 +6,7 @@ * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright 2018-2020 Intel Corporation + * Copyright 2018-2021 Intel Corporation */ #include <linux/export.h> @@ -942,7 +942,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, struct ieee80211_sta_vht_cap *vht_cap; struct ieee80211_edmg *edmg_cap; u32 width, control_freq, cap; - bool support_80_80 = false; + bool ext_nss_cap, support_80_80 = false; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -950,6 +950,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, ht_cap = &wiphy->bands[chandef->chan->band]->ht_cap; vht_cap = &wiphy->bands[chandef->chan->band]->vht_cap; edmg_cap = &wiphy->bands[chandef->chan->band]->edmg_cap; + ext_nss_cap = __le16_to_cpu(vht_cap->vht_mcs.tx_highest) & + IEEE80211_VHT_EXT_NSS_BW_CAPABLE; if (edmg_cap->channels && !cfg80211_edmg_usable(wiphy, @@ -1015,7 +1017,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) || (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) || - u32_get_bits(cap, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) > 1; + (ext_nss_cap && + u32_get_bits(cap, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) > 1); if (chandef->chan->band != NL80211_BAND_6GHZ && !support_80_80) return false; fallthrough; @@ -1037,7 +1040,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ && - !(vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK)) + !(ext_nss_cap && + (vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK))) return false; break; default: @@ -1335,3 +1339,34 @@ cfg80211_get_chan_state(struct wireless_dev *wdev, WARN_ON(1); } } + +bool cfg80211_any_usable_channels(struct wiphy *wiphy, + unsigned long sband_mask, + u32 prohibited_flags) +{ + int idx; + + prohibited_flags |= IEEE80211_CHAN_DISABLED; + + for_each_set_bit(idx, &sband_mask, NUM_NL80211_BANDS) { + struct ieee80211_supported_band *sband = wiphy->bands[idx]; + int chanidx; + + if (!sband) + continue; + + for (chanidx = 0; chanidx < sband->n_channels; chanidx++) { + struct ieee80211_channel *chan; + + chan = &sband->channels[chanidx]; + + if (chan->flags & prohibited_flags) + continue; + + return true; + } + } + + return false; +} +EXPORT_SYMBOL(cfg80211_any_usable_channels); diff --git a/net/wireless/core.c b/net/wireless/core.c index 8d0883e81093..03323121ca50 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -5,7 +5,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -532,11 +532,11 @@ use_default_name: wiphy_net_set(&rdev->wiphy, &init_net); rdev->rfkill_ops.set_block = cfg80211_rfkill_set_block; - rdev->rfkill = rfkill_alloc(dev_name(&rdev->wiphy.dev), - &rdev->wiphy.dev, RFKILL_TYPE_WLAN, - &rdev->rfkill_ops, rdev); + rdev->wiphy.rfkill = rfkill_alloc(dev_name(&rdev->wiphy.dev), + &rdev->wiphy.dev, RFKILL_TYPE_WLAN, + &rdev->rfkill_ops, rdev); - if (!rdev->rfkill) { + if (!rdev->wiphy.rfkill) { wiphy_free(&rdev->wiphy); return NULL; } @@ -589,14 +589,6 @@ static int wiphy_verify_combinations(struct wiphy *wiphy) if (WARN_ON(!c->num_different_channels)) return -EINVAL; - /* - * Put a sane limit on maximum number of different - * channels to simplify channel accounting code. - */ - if (WARN_ON(c->num_different_channels > - CFG80211_MAX_NUM_DIFFERENT_CHANNELS)) - return -EINVAL; - /* DFS only works on one channel. */ if (WARN_ON(c->radar_detect_widths && (c->num_different_channels > 1))) @@ -936,9 +928,6 @@ int wiphy_register(struct wiphy *wiphy) return res; } - /* set up regulatory info */ - wiphy_regulatory_register(wiphy); - list_add_rcu(&rdev->list, &cfg80211_rdev_list); cfg80211_rdev_list_generation++; @@ -949,6 +938,9 @@ int wiphy_register(struct wiphy *wiphy) cfg80211_debugfs_rdev_add(rdev); nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); + /* set up regulatory info */ + wiphy_regulatory_register(wiphy); + if (wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) { struct regulatory_request request; @@ -993,10 +985,10 @@ int wiphy_register(struct wiphy *wiphy) rdev->wiphy.registered = true; rtnl_unlock(); - res = rfkill_register(rdev->rfkill); + res = rfkill_register(rdev->wiphy.rfkill); if (res) { - rfkill_destroy(rdev->rfkill); - rdev->rfkill = NULL; + rfkill_destroy(rdev->wiphy.rfkill); + rdev->wiphy.rfkill = NULL; wiphy_unregister(&rdev->wiphy); return res; } @@ -1012,18 +1004,10 @@ void wiphy_rfkill_start_polling(struct wiphy *wiphy) if (!rdev->ops->rfkill_poll) return; rdev->rfkill_ops.poll = cfg80211_rfkill_poll; - rfkill_resume_polling(rdev->rfkill); + rfkill_resume_polling(wiphy->rfkill); } EXPORT_SYMBOL(wiphy_rfkill_start_polling); -void wiphy_rfkill_stop_polling(struct wiphy *wiphy) -{ - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - - rfkill_pause_polling(rdev->rfkill); -} -EXPORT_SYMBOL(wiphy_rfkill_stop_polling); - void wiphy_unregister(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); @@ -1035,8 +1019,8 @@ void wiphy_unregister(struct wiphy *wiphy) wiphy_unlock(&rdev->wiphy); __count == 0; })); - if (rdev->rfkill) - rfkill_unregister(rdev->rfkill); + if (rdev->wiphy.rfkill) + rfkill_unregister(rdev->wiphy.rfkill); rtnl_lock(); wiphy_lock(&rdev->wiphy); @@ -1088,7 +1072,7 @@ void cfg80211_dev_free(struct cfg80211_registered_device *rdev) { struct cfg80211_internal_bss *scan, *tmp; struct cfg80211_beacon_registration *reg, *treg; - rfkill_destroy(rdev->rfkill); + rfkill_destroy(rdev->wiphy.rfkill); list_for_each_entry_safe(reg, treg, &rdev->beacon_registrations, list) { list_del(®->list); kfree(reg); @@ -1110,7 +1094,7 @@ void wiphy_rfkill_set_hw_state_reason(struct wiphy *wiphy, bool blocked, { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - if (rfkill_set_hw_state_reason(rdev->rfkill, blocked, reason)) + if (rfkill_set_hw_state_reason(wiphy->rfkill, blocked, reason)) schedule_work(&rdev->rfkill_block); } EXPORT_SYMBOL(wiphy_rfkill_set_hw_state_reason); @@ -1503,7 +1487,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, wdev->use_4addr, 0)) return notifier_from_errno(-EOPNOTSUPP); - if (rfkill_blocked(rdev->rfkill)) + if (rfkill_blocked(rdev->wiphy.rfkill)) return notifier_from_errno(-ERFKILL); break; default: diff --git a/net/wireless/core.h b/net/wireless/core.h index a7d19b4b40ac..b35d0db12f1d 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -3,7 +3,7 @@ * Wireless configuration interface internals. * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #ifndef __NET_WIRELESS_CORE_H #define __NET_WIRELESS_CORE_H @@ -27,7 +27,6 @@ struct cfg80211_registered_device { /* rfkill support */ struct rfkill_ops rfkill_ops; - struct rfkill *rfkill; struct work_struct rfkill_block; /* ISO / IEC 3166 alpha2 for which this device is receiving diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fc9286afe3c9..50eb405b0690 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -330,7 +330,7 @@ nl80211_pmsr_req_attr_policy[NL80211_PMSR_REQ_ATTR_MAX + 1] = { }; static const struct nla_policy -nl80211_psmr_peer_attr_policy[NL80211_PMSR_PEER_ATTR_MAX + 1] = { +nl80211_pmsr_peer_attr_policy[NL80211_PMSR_PEER_ATTR_MAX + 1] = { [NL80211_PMSR_PEER_ATTR_ADDR] = NLA_POLICY_ETH_ADDR, [NL80211_PMSR_PEER_ATTR_CHAN] = NLA_POLICY_NESTED(nl80211_policy), [NL80211_PMSR_PEER_ATTR_REQ] = @@ -345,7 +345,7 @@ nl80211_pmsr_attr_policy[NL80211_PMSR_ATTR_MAX + 1] = { [NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_TYPE_CAPA] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_PEERS] = - NLA_POLICY_NESTED_ARRAY(nl80211_psmr_peer_attr_policy), + NLA_POLICY_NESTED_ARRAY(nl80211_pmsr_peer_attr_policy), }; static const struct nla_policy @@ -1731,6 +1731,11 @@ nl80211_send_iftype_data(struct sk_buff *msg, &iftdata->he_6ghz_capa)) return -ENOBUFS; + if (iftdata->vendor_elems.data && iftdata->vendor_elems.len && + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_VENDOR_ELEMS, + iftdata->vendor_elems.len, iftdata->vendor_elems.data)) + return -ENOBUFS; + return 0; } @@ -4781,11 +4786,10 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, sband->ht_cap.mcs.rx_mask, sizeof(mask->control[i].ht_mcs)); - if (!sband->vht_cap.vht_supported) - continue; - - vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map); - vht_build_mcs_mask(vht_tx_mcs_map, mask->control[i].vht_mcs); + if (sband->vht_cap.vht_supported) { + vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map); + vht_build_mcs_mask(vht_tx_mcs_map, mask->control[i].vht_mcs); + } he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype); if (!he_cap) @@ -13042,7 +13046,7 @@ static int nl80211_start_p2p_device(struct sk_buff *skb, struct genl_info *info) if (wdev_running(wdev)) return 0; - if (rfkill_blocked(rdev->rfkill)) + if (rfkill_blocked(rdev->wiphy.rfkill)) return -ERFKILL; err = rdev_start_p2p_device(rdev, wdev); @@ -13084,7 +13088,7 @@ static int nl80211_start_nan(struct sk_buff *skb, struct genl_info *info) if (wdev_running(wdev)) return -EEXIST; - if (rfkill_blocked(rdev->rfkill)) + if (rfkill_blocked(rdev->wiphy.rfkill)) return -ERFKILL; if (!info->attrs[NL80211_ATTR_NAN_MASTER_PREF]) diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index d245968b74cb..328cf54bda82 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -168,6 +168,18 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, return -EINVAL; } + if (tb[NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR]) { + if (!out->ftm.non_trigger_based && !out->ftm.trigger_based) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR], + "FTM: BSS color set for EDCA based ranging"); + return -EINVAL; + } + + out->ftm.bss_color = + nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR]); + } + return 0; } diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 8b1358d04ca2..b1d37f582dc6 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -464,8 +464,18 @@ static inline int rdev_assoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_assoc_request *req) { + const struct cfg80211_bss_ies *bss_ies; int ret; - trace_rdev_assoc(&rdev->wiphy, dev, req); + + /* + * Note: we might trace not exactly the data that's processed, + * due to races and the driver/mac80211 getting a newer copy. + */ + rcu_read_lock(); + bss_ies = rcu_dereference(req->bss->ies); + trace_rdev_assoc(&rdev->wiphy, dev, req, bss_ies); + rcu_read_unlock(); + ret = rdev->ops->assoc(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 0406ce7334fa..c2d0ff7f089f 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -3975,7 +3975,9 @@ static int __regulatory_set_wiphy_regd(struct wiphy *wiphy, "wiphy should have REGULATORY_WIPHY_SELF_MANAGED\n")) return -EPERM; - if (WARN(!is_valid_rd(rd), "Invalid regulatory domain detected\n")) { + if (WARN(!is_valid_rd(rd), + "Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1])) { print_regdomain_info(rd); return -EINVAL; } @@ -4049,6 +4051,7 @@ void wiphy_regulatory_register(struct wiphy *wiphy) wiphy_update_regulatory(wiphy, lr->initiator); wiphy_all_share_dfs_chan_state(wiphy); + reg_process_self_managed_hints(); } void wiphy_regulatory_deregister(struct wiphy *wiphy) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 4f06c1825029..f03c7ac8e184 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -5,7 +5,7 @@ * Copyright 2008 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/kernel.h> #include <linux/slab.h> @@ -618,7 +618,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, freq = ieee80211_channel_to_frequency(ap_info->channel, band); - if (end - pos < count * ap_info->tbtt_info_len) + if (end - pos < count * length) break; /* @@ -630,7 +630,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, if (band != NL80211_BAND_6GHZ || (length != IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM && length < IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM)) { - pos += count * ap_info->tbtt_info_len; + pos += count * length; continue; } @@ -653,7 +653,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, kfree(entry); } - pos += ap_info->tbtt_info_len; + pos += length; } } @@ -757,7 +757,8 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev) } request = kzalloc(struct_size(request, channels, n_channels) + - sizeof(*request->scan_6ghz_params) * count, + sizeof(*request->scan_6ghz_params) * count + + sizeof(*request->ssids) * rdev_req->n_ssids, GFP_KERNEL); if (!request) { cfg80211_free_coloc_ap_list(&coloc_ap_list); @@ -848,10 +849,19 @@ skip: if (request->n_channels) { struct cfg80211_scan_request *old = rdev->int_scan_req; - rdev->int_scan_req = request; /* + * Add the ssids from the parent scan request to the new scan + * request, so the driver would be able to use them in its + * probe requests to discover hidden APs on PSC channels. + */ + request->ssids = (void *)&request->channels[request->n_channels]; + request->n_ssids = rdev_req->n_ssids; + memcpy(request->ssids, rdev_req->ssids, sizeof(*request->ssids) * + request->n_ssids); + + /* * If this scan follows a previous scan, save the scan start * info from the first part of the scan */ diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 76b777d5903f..440bce5f0274 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1195,8 +1195,9 @@ TRACE_EVENT(rdev_auth, TRACE_EVENT(rdev_assoc, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, - struct cfg80211_assoc_request *req), - TP_ARGS(wiphy, netdev, req), + struct cfg80211_assoc_request *req, + const struct cfg80211_bss_ies *bss_ies), + TP_ARGS(wiphy, netdev, req, bss_ies), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY @@ -1204,6 +1205,17 @@ TRACE_EVENT(rdev_assoc, MAC_ENTRY(prev_bssid) __field(bool, use_mfp) __field(u32, flags) + __dynamic_array(u8, bss_elements, bss_ies->len) + __field(bool, bss_elements_bcon) + __field(u64, bss_elements_tsf) + __dynamic_array(u8, elements, req->ie_len) + __array(u8, ht_capa, sizeof(struct ieee80211_ht_cap)) + __array(u8, ht_capa_mask, sizeof(struct ieee80211_ht_cap)) + __array(u8, vht_capa, sizeof(struct ieee80211_vht_cap)) + __array(u8, vht_capa_mask, sizeof(struct ieee80211_vht_cap)) + __dynamic_array(u8, fils_kek, req->fils_kek_len) + __dynamic_array(u8, fils_nonces, + req->fils_nonces ? 2 * FILS_NONCE_LEN : 0) ), TP_fast_assign( WIPHY_ASSIGN; @@ -1215,6 +1227,26 @@ TRACE_EVENT(rdev_assoc, MAC_ASSIGN(prev_bssid, req->prev_bssid); __entry->use_mfp = req->use_mfp; __entry->flags = req->flags; + if (bss_ies->len) + memcpy(__get_dynamic_array(bss_elements), + bss_ies->data, bss_ies->len); + __entry->bss_elements_bcon = bss_ies->from_beacon; + __entry->bss_elements_tsf = bss_ies->tsf; + if (req->ie) + memcpy(__get_dynamic_array(elements), + req->ie, req->ie_len); + memcpy(__entry->ht_capa, &req->ht_capa, sizeof(req->ht_capa)); + memcpy(__entry->ht_capa_mask, &req->ht_capa_mask, + sizeof(req->ht_capa_mask)); + memcpy(__entry->vht_capa, &req->vht_capa, sizeof(req->vht_capa)); + memcpy(__entry->vht_capa_mask, &req->vht_capa_mask, + sizeof(req->vht_capa_mask)); + if (req->fils_kek) + memcpy(__get_dynamic_array(fils_kek), + req->fils_kek, req->fils_kek_len); + if (req->fils_nonces) + memcpy(__get_dynamic_array(fils_nonces), + req->fils_nonces, 2 * FILS_NONCE_LEN); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT ", previous bssid: " MAC_PR_FMT ", use mfp: %s, flags: %u", diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index a8320dc59af7..a32065d600a1 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -902,7 +902,7 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev, /* only change when not disabling */ if (!data->txpower.disabled) { - rfkill_set_sw_state(rdev->rfkill, false); + rfkill_set_sw_state(rdev->wiphy.rfkill, false); if (data->txpower.fixed) { /* @@ -927,7 +927,7 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev, } } } else { - if (rfkill_set_sw_state(rdev->rfkill, true)) + if (rfkill_set_sw_state(rdev->wiphy.rfkill, true)) schedule_work(&rdev->rfkill_block); return 0; } @@ -963,7 +963,7 @@ static int cfg80211_wext_giwtxpower(struct net_device *dev, /* well... oh well */ data->txpower.fixed = 1; - data->txpower.disabled = rfkill_blocked(rdev->rfkill); + data->txpower.disabled = rfkill_blocked(rdev->wiphy.rfkill); data->txpower.value = val; data->txpower.flags = IW_TXPOW_DBM; @@ -1167,7 +1167,7 @@ static int cfg80211_wext_siwpower(struct net_device *dev, { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - bool ps = wdev->ps; + bool ps; int timeout = wdev->ps_timeout; int err; diff --git a/net/wireless/wext-spy.c b/net/wireless/wext-spy.c index 33bef22e44e9..b379a0371653 100644 --- a/net/wireless/wext-spy.c +++ b/net/wireless/wext-spy.c @@ -120,8 +120,8 @@ int iw_handler_set_thrspy(struct net_device * dev, return -EOPNOTSUPP; /* Just do it */ - memcpy(&(spydata->spy_thr_low), &(threshold->low), - 2 * sizeof(struct iw_quality)); + spydata->spy_thr_low = threshold->low; + spydata->spy_thr_high = threshold->high; /* Clear flag */ memset(spydata->spy_thr_under, '\0', sizeof(spydata->spy_thr_under)); @@ -147,8 +147,8 @@ int iw_handler_get_thrspy(struct net_device * dev, return -EOPNOTSUPP; /* Just do it */ - memcpy(&(threshold->low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); + threshold->low = spydata->spy_thr_low; + threshold->high = spydata->spy_thr_high; return 0; } @@ -173,10 +173,10 @@ static void iw_send_thrspy_event(struct net_device * dev, memcpy(threshold.addr.sa_data, address, ETH_ALEN); threshold.addr.sa_family = ARPHRD_ETHER; /* Copy stats */ - memcpy(&(threshold.qual), wstats, sizeof(struct iw_quality)); + threshold.qual = *wstats; /* Copy also thresholds */ - memcpy(&(threshold.low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); + threshold.low = spydata->spy_thr_low; + threshold.high = spydata->spy_thr_high; /* Send event to user space */ wireless_send_event(dev, SIOCGIWTHRSPY, &wrqu, (char *) &threshold); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 1816899499ce..3583354a7d7f 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -366,7 +366,7 @@ static void x25_destroy_timer(struct timer_list *t) /* * This is called from user mode and the timers. Thus it protects itself - * against interrupt users but doesn't worry about being called during + * against interrupting users but doesn't worry about being called during * work. Once it is removed from the queue no interrupt or bottom half * will touch it and we are (fairly 8-) ) safe. * Not static as it's used by the timer diff --git a/net/x25/x25_forward.c b/net/x25/x25_forward.c index d48ad6d29197..21b30b56e889 100644 --- a/net/x25/x25_forward.c +++ b/net/x25/x25_forward.c @@ -19,7 +19,6 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from, { struct x25_route *rt; struct x25_neigh *neigh_new = NULL; - struct list_head *entry; struct x25_forward *x25_frwd, *new_frwd; struct sk_buff *skbn; short same_lci = 0; @@ -46,8 +45,7 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from, * established LCI? It shouldn't happen, just in case.. */ read_lock_bh(&x25_forward_list_lock); - list_for_each(entry, &x25_forward_list) { - x25_frwd = list_entry(entry, struct x25_forward, node); + list_for_each_entry(x25_frwd, &x25_forward_list, node) { if (x25_frwd->lci == lci) { pr_warn("call request for lci which is already registered!, transmitting but not registering new pair\n"); same_lci = 1; @@ -92,15 +90,13 @@ out_no_route: int x25_forward_data(int lci, struct x25_neigh *from, struct sk_buff *skb) { struct x25_forward *frwd; - struct list_head *entry; struct net_device *peer = NULL; struct x25_neigh *nb; struct sk_buff *skbn; int rc = 0; read_lock_bh(&x25_forward_list_lock); - list_for_each(entry, &x25_forward_list) { - frwd = list_entry(entry, struct x25_forward, node); + list_for_each_entry(frwd, &x25_forward_list, node) { if (frwd->lci == lci) { /* The call is established, either side can send */ if (from->dev == frwd->dev1) { diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 57a81100c5da..5460b9146dd8 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -332,12 +332,9 @@ void x25_link_device_down(struct net_device *dev) struct x25_neigh *x25_get_neigh(struct net_device *dev) { struct x25_neigh *nb, *use = NULL; - struct list_head *entry; read_lock_bh(&x25_neigh_list_lock); - list_for_each(entry, &x25_neigh_list) { - nb = list_entry(entry, struct x25_neigh, node); - + list_for_each_entry(nb, &x25_neigh_list, node) { if (nb->dev == dev) { use = nb; break; diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c index 9fbe4bb38d94..647f325ed867 100644 --- a/net/x25/x25_route.c +++ b/net/x25/x25_route.c @@ -27,14 +27,11 @@ static int x25_add_route(struct x25_address *address, unsigned int sigdigits, struct net_device *dev) { struct x25_route *rt; - struct list_head *entry; int rc = -EINVAL; write_lock_bh(&x25_route_list_lock); - list_for_each(entry, &x25_route_list) { - rt = list_entry(entry, struct x25_route, node); - + list_for_each_entry(rt, &x25_route_list, node) { if (!memcmp(&rt->address, address, sigdigits) && rt->sigdigits == sigdigits) goto out; @@ -78,14 +75,11 @@ static int x25_del_route(struct x25_address *address, unsigned int sigdigits, struct net_device *dev) { struct x25_route *rt; - struct list_head *entry; int rc = -EINVAL; write_lock_bh(&x25_route_list_lock); - list_for_each(entry, &x25_route_list) { - rt = list_entry(entry, struct x25_route, node); - + list_for_each_entry(rt, &x25_route_list, node) { if (!memcmp(&rt->address, address, sigdigits) && rt->sigdigits == sigdigits && rt->dev == dev) { __x25_remove_route(rt); @@ -141,13 +135,10 @@ struct net_device *x25_dev_get(char *devname) struct x25_route *x25_get_route(struct x25_address *addr) { struct x25_route *rt, *use = NULL; - struct list_head *entry; read_lock_bh(&x25_route_list_lock); - list_for_each(entry, &x25_route_list) { - rt = list_entry(entry, struct x25_route, node); - + list_for_each_entry(rt, &x25_route_list, node) { if (!memcmp(&rt->address, addr, rt->sigdigits)) { if (!use) use = rt; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 56a28a686988..f01ef6bda390 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -27,7 +27,7 @@ static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); - kfree(umem->pgs); + kvfree(umem->pgs); umem->pgs = NULL; } @@ -99,8 +99,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) long npgs; int err; - umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), - GFP_KERNEL | __GFP_NOWARN); + umem->pgs = kvcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL | __GFP_NOWARN); if (!umem->pgs) return -ENOMEM; @@ -123,7 +122,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) out_pin: xdp_umem_unpin_pages(umem); out_pgs: - kfree(umem->pgs); + kvfree(umem->pgs); umem->pgs = NULL; return err; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index cd62d4ba87a9..d6b500dc4208 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -749,7 +749,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs) } static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs, - struct xdp_sock ***map_entry) + struct xdp_sock __rcu ***map_entry) { struct xsk_map *map = NULL; struct xsk_map_node *node; @@ -785,7 +785,7 @@ static void xsk_delete_from_maps(struct xdp_sock *xs) * might be updates to the map between * xsk_get_map_list_entry() and xsk_map_try_sock_delete(). */ - struct xdp_sock **map_entry = NULL; + struct xdp_sock __rcu **map_entry = NULL; struct xsk_map *map; while ((map = xsk_get_map_list_entry(xs, &map_entry))) { @@ -1313,7 +1313,7 @@ static int xsk_notifier(struct notifier_block *this, if (xs->dev == dev) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); xsk_unbind_dev(xs); diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index edcf249ad1f1..a4bc4749faac 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -31,7 +31,7 @@ struct xdp_mmap_offsets_v1 { struct xsk_map_node { struct list_head node; struct xsk_map *map; - struct xdp_sock **map_entry; + struct xdp_sock __rcu **map_entry; }; static inline struct xdp_sock *xdp_sk(struct sock *sk) @@ -40,7 +40,7 @@ static inline struct xdp_sock *xdp_sk(struct sock *sk) } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, - struct xdp_sock **map_entry); + struct xdp_sock __rcu **map_entry); void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id); int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, u16 queue_id); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 9d2a89d793c0..9ae13cccfb28 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -128,12 +128,15 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 chunk; - - if (desc->len > pool->chunk_size) - return false; + u64 chunk, chunk_end; chunk = xp_aligned_extract_addr(pool, desc->addr); + if (likely(desc->len)) { + chunk_end = xp_aligned_extract_addr(pool, desc->addr + desc->len - 1); + if (chunk != chunk_end) + return false; + } + if (chunk >= pool->addrs_cnt) return false; diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 67b4ce504852..2e48d0e094d9 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -12,7 +12,7 @@ #include "xsk.h" static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { struct xsk_map_node *node; @@ -42,7 +42,7 @@ static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node) } static void xsk_map_sock_delete(struct xdp_sock *xs, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { struct xsk_map_node *n, *tmp; @@ -124,6 +124,10 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) return insn - insn_buf; } +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) { struct xsk_map *m = container_of(map, struct xsk_map, map); @@ -131,12 +135,11 @@ static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - return READ_ONCE(m->xsk_map[key]); + return rcu_dereference_check(m->xsk_map[key], rcu_read_lock_bh_held()); } static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) { - WARN_ON_ONCE(!rcu_read_lock_held()); return __xsk_map_lookup_elem(map, *(u32 *)key); } @@ -149,7 +152,8 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *xs, *old_xs, **map_entry; + struct xdp_sock __rcu **map_entry; + struct xdp_sock *xs, *old_xs; u32 i = *(u32 *)key, fd = *(u32 *)value; struct xsk_map_node *node; struct socket *sock; @@ -179,7 +183,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, } spin_lock_bh(&m->lock); - old_xs = READ_ONCE(*map_entry); + old_xs = rcu_dereference_protected(*map_entry, lockdep_is_held(&m->lock)); if (old_xs == xs) { err = 0; goto out; @@ -191,7 +195,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, goto out; } xsk_map_sock_add(xs, node); - WRITE_ONCE(*map_entry, xs); + rcu_assign_pointer(*map_entry, xs); if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); @@ -208,7 +212,8 @@ out: static int xsk_map_delete_elem(struct bpf_map *map, void *key) { struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *old_xs, **map_entry; + struct xdp_sock __rcu **map_entry; + struct xdp_sock *old_xs; int k = *(u32 *)key; if (k >= map->max_entries) @@ -216,7 +221,7 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) spin_lock_bh(&m->lock); map_entry = &m->xsk_map[k]; - old_xs = xchg(map_entry, NULL); + old_xs = unrcu_pointer(xchg(map_entry, NULL)); if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); @@ -226,15 +231,16 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + __xsk_map_lookup_elem); } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { spin_lock_bh(&map->lock); - if (READ_ONCE(*map_entry) == xs) { - WRITE_ONCE(*map_entry, NULL); + if (rcu_access_pointer(*map_entry) == xs) { + rcu_assign_pointer(*map_entry, NULL); xsk_map_sock_delete(xs, map_entry); } spin_unlock_bh(&map->lock); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 6d6917b68856..e843b0d9e2a6 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -268,6 +268,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, xso->num_exthdrs = 0; xso->flags = 0; xso->dev = NULL; + xso->real_dev = NULL; dev_put(dev); if (err != -EOPNOTSUPP) diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h index ce66323102f9..d12bb906c9c9 100644 --- a/net/xfrm/xfrm_hash.h +++ b/net/xfrm/xfrm_hash.h @@ -131,6 +131,13 @@ __xfrm_spi_hash(const xfrm_address_t *daddr, __be32 spi, u8 proto, return (h ^ (h >> 10) ^ (h >> 20)) & hmask; } +static inline unsigned int +__xfrm_seq_hash(u32 seq, unsigned int hmask) +{ + unsigned int h = seq; + return (h ^ (h >> 10) ^ (h >> 20)) & hmask; +} + static inline unsigned int __idx_hash(u32 index, unsigned int hmask) { return (index ^ (index >> 8)) & hmask; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 1158cd0311d7..3df0861d4390 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -612,7 +612,7 @@ lock: goto drop_unlock; } - if (x->repl->check(x, skb, seq)) { + if (xfrm_replay_check(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } @@ -660,12 +660,12 @@ resume: /* only the first xfrm gets the encap type */ encap_type = 0; - if (x->repl->recheck(x, skb, seq)) { + if (xfrm_replay_recheck(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } - x->repl->advance(x, seq); + xfrm_replay_advance(x, seq); x->curlft.bytes += skb->len; x->curlft.packets++; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index e4cb0ff4dcf4..229544bc70c2 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -77,6 +77,83 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } +#if IS_ENABLED(CONFIG_IPV6_MIP6) +static int mip6_rthdr_offset(struct sk_buff *skb, u8 **nexthdr, int type) +{ + const unsigned char *nh = skb_network_header(skb); + unsigned int offset = sizeof(struct ipv6hdr); + unsigned int packet_len; + int found_rhdr = 0; + + packet_len = skb_tail_pointer(skb) - nh; + *nexthdr = &ipv6_hdr(skb)->nexthdr; + + while (offset <= packet_len) { + struct ipv6_opt_hdr *exthdr; + + switch (**nexthdr) { + case NEXTHDR_HOP: + break; + case NEXTHDR_ROUTING: + if (type == IPPROTO_ROUTING && offset + 3 <= packet_len) { + struct ipv6_rt_hdr *rt; + + rt = (struct ipv6_rt_hdr *)(nh + offset); + if (rt->type != 0) + return offset; + } + found_rhdr = 1; + break; + case NEXTHDR_DEST: + /* HAO MUST NOT appear more than once. + * XXX: It is better to try to find by the end of + * XXX: packet if HAO exists. + */ + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) { + net_dbg_ratelimited("mip6: hao exists already, override\n"); + return offset; + } + + if (found_rhdr) + return offset; + + break; + default: + return offset; + } + + if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) + return -EINVAL; + + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + + offset); + offset += ipv6_optlen(exthdr); + if (offset > IPV6_MAXPLEN) + return -EINVAL; + *nexthdr = &exthdr->nexthdr; + } + + return -EINVAL; +} +#endif + +#if IS_ENABLED(CONFIG_IPV6) +static int xfrm6_hdr_offset(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr) +{ + switch (x->type->proto) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPPROTO_DSTOPTS: + case IPPROTO_ROUTING: + return mip6_rthdr_offset(skb, prevhdr, x->type->proto); +#endif + default: + break; + } + + return ip6_find_1stfragopt(skb, prevhdr); +} +#endif + /* Add encapsulation header. * * The IP header and mutable extension headers will be moved forward to make @@ -92,7 +169,7 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) iph = ipv6_hdr(skb); skb_set_inner_transport_header(skb, skb_transport_offset(skb)); - hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr); if (hdr_len < 0) return hdr_len; skb_set_mac_header(skb, @@ -122,7 +199,7 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) iph = ipv6_hdr(skb); - hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr); if (hdr_len < 0) return hdr_len; skb_set_mac_header(skb, @@ -448,7 +525,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) goto error; } - err = x->repl->overflow(x, skb); + err = xfrm_replay_overflow(x, skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR); goto error; @@ -565,6 +642,42 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb return 0; } +/* For partial checksum offload, the outer header checksum is calculated + * by software and the inner header checksum is calculated by hardware. + * This requires hardware to know the inner packet type to calculate + * the inner header checksum. Save inner ip protocol here to avoid + * traversing the packet in the vendor's xmit code. + * If the encap type is IPIP, just save skb->inner_ipproto. Otherwise, + * get the ip protocol from the IP header. + */ +static void xfrm_get_inner_ipproto(struct sk_buff *skb) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + const struct ethhdr *eth; + + if (!xo) + return; + + if (skb->inner_protocol_type == ENCAP_TYPE_IPPROTO) { + xo->inner_ipproto = skb->inner_ipproto; + return; + } + + if (skb->inner_protocol_type != ENCAP_TYPE_ETHER) + return; + + eth = (struct ethhdr *)skb_inner_mac_header(skb); + + switch (ntohs(eth->h_proto)) { + case ETH_P_IPV6: + xo->inner_ipproto = inner_ipv6_hdr(skb)->nexthdr; + break; + case ETH_P_IP: + xo->inner_ipproto = inner_ip_hdr(skb)->protocol; + break; + } +} + int xfrm_output(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -594,12 +707,15 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); return -ENOMEM; } - skb->encapsulation = 1; sp->olen++; sp->xvec[sp->len++] = x; xfrm_state_hold(x); + if (skb->encapsulation) + xfrm_get_inner_ipproto(skb); + skb->encapsulation = 1; + if (skb_is_gso(skb)) { if (skb->inner_protocol) return xfrm_output_gso(net, sk, skb); @@ -711,15 +827,8 @@ out: static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) - unsigned int ptr = 0; int err; - if (x->outer_mode.encap == XFRM_MODE_BEET && - ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL) >= 0) { - net_warn_ratelimited("BEET mode doesn't support inner IPv6 fragments\n"); - return -EAFNOSUPPORT; - } - err = xfrm6_tunnel_check_size(skb); if (err) return err; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e70cf1d2c0e0..827d84255021 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2091,12 +2091,15 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if (unlikely(!daddr || !saddr)) return NULL; - rcu_read_lock(); retry: - do { - sequence = read_seqcount_begin(&xfrm_policy_hash_generation); - chain = policy_hash_direct(net, daddr, saddr, family, dir); - } while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)); + sequence = read_seqcount_begin(&xfrm_policy_hash_generation); + rcu_read_lock(); + + chain = policy_hash_direct(net, daddr, saddr, family, dir); + if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { + rcu_read_unlock(); + goto retry; + } ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { @@ -2127,11 +2130,15 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } skip_inexact: - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) + if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { + rcu_read_unlock(); goto retry; + } - if (ret && !xfrm_pol_hold_rcu(ret)) + if (ret && !xfrm_pol_hold_rcu(ret)) { + rcu_read_unlock(); goto retry; + } fail: rcu_read_unlock(); @@ -3245,7 +3252,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, /* * 0 or more than 0 is returned when validation is succeeded (either bypass - * because of optional transport mode, or next index of the mathced secpath + * because of optional transport mode, or next index of the matched secpath * state with the template. * -1 is returned when no matching template is found. * Otherwise "-2 - errored_index" is returned. diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index c6a4338a0d08..9277d81b344c 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -34,8 +34,11 @@ u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq) return seq_hi; } EXPORT_SYMBOL(xfrm_replay_seqhi); -; -static void xfrm_replay_notify(struct xfrm_state *x, int event) + +static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event); +static void xfrm_replay_notify_esn(struct xfrm_state *x, int event); + +void xfrm_replay_notify(struct xfrm_state *x, int event) { struct km_event c; /* we send notify messages in case @@ -48,6 +51,17 @@ static void xfrm_replay_notify(struct xfrm_state *x, int event) * The state structure must be locked! */ + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + xfrm_replay_notify_bmp(x, event); + return; + case XFRM_REPLAY_MODE_ESN: + xfrm_replay_notify_esn(x, event); + return; + } + switch (event) { case XFRM_REPLAY_UPDATE: if (!x->replay_maxdiff || @@ -81,7 +95,7 @@ static void xfrm_replay_notify(struct xfrm_state *x, int event) x->xflags &= ~XFRM_TIME_DEFER; } -static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) +static int __xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) { int err = 0; struct net *net = xs_net(x); @@ -98,14 +112,14 @@ static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) return err; } if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; } -static int xfrm_replay_check(struct xfrm_state *x, - struct sk_buff *skb, __be32 net_seq) +static int xfrm_replay_check_legacy(struct xfrm_state *x, + struct sk_buff *skb, __be32 net_seq) { u32 diff; u32 seq = ntohl(net_seq); @@ -136,14 +150,26 @@ err: return -EINVAL; } -static void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq) +static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq); +static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq); + +void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq) { - u32 diff; - u32 seq = ntohl(net_seq); + u32 diff, seq; + + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + return xfrm_replay_advance_bmp(x, net_seq); + case XFRM_REPLAY_MODE_ESN: + return xfrm_replay_advance_esn(x, net_seq); + } if (!x->props.replay_window) return; + seq = ntohl(net_seq); if (seq > x->replay.seq) { diff = seq - x->replay.seq; if (diff < x->props.replay_window) @@ -157,7 +183,7 @@ static void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq) } if (xfrm_aevent_is_on(xs_net(x))) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb) @@ -178,7 +204,7 @@ static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb) return err; } if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; @@ -273,7 +299,7 @@ static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq) replay_esn->bmp[nr] |= (1U << bitnr); if (xfrm_aevent_is_on(xs_net(x))) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event) @@ -416,7 +442,7 @@ static int xfrm_replay_overflow_esn(struct xfrm_state *x, struct sk_buff *skb) } } if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; @@ -481,6 +507,21 @@ err: return -EINVAL; } +int xfrm_replay_check(struct xfrm_state *x, + struct sk_buff *skb, __be32 net_seq) +{ + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + return xfrm_replay_check_bmp(x, skb, net_seq); + case XFRM_REPLAY_MODE_ESN: + return xfrm_replay_check_esn(x, skb, net_seq); + } + + return xfrm_replay_check_legacy(x, skb, net_seq); +} + static int xfrm_replay_recheck_esn(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { @@ -493,6 +534,22 @@ static int xfrm_replay_recheck_esn(struct xfrm_state *x, return xfrm_replay_check_esn(x, skb, net_seq); } +int xfrm_replay_recheck(struct xfrm_state *x, + struct sk_buff *skb, __be32 net_seq) +{ + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + /* no special recheck treatment */ + return xfrm_replay_check_bmp(x, skb, net_seq); + case XFRM_REPLAY_MODE_ESN: + return xfrm_replay_recheck_esn(x, skb, net_seq); + } + + return xfrm_replay_check_legacy(x, skb, net_seq); +} + static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq) { unsigned int bitnr, nr, i; @@ -548,7 +605,7 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq) replay_esn->bmp[nr] |= (1U << bitnr); if (xfrm_aevent_is_on(xs_net(x))) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } #ifdef CONFIG_XFRM_OFFLOAD @@ -560,7 +617,7 @@ static int xfrm_replay_overflow_offload(struct xfrm_state *x, struct sk_buff *sk __u32 oseq = x->replay.oseq; if (!xo) - return xfrm_replay_overflow(x, skb); + return __xfrm_replay_overflow(x, skb); if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { if (!skb_is_gso(skb)) { @@ -585,7 +642,7 @@ static int xfrm_replay_overflow_offload(struct xfrm_state *x, struct sk_buff *sk x->replay.oseq = oseq; if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; @@ -625,7 +682,7 @@ static int xfrm_replay_overflow_offload_bmp(struct xfrm_state *x, struct sk_buff } if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; @@ -674,59 +731,39 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff replay_esn->oseq = oseq; if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; } -static const struct xfrm_replay xfrm_replay_legacy = { - .advance = xfrm_replay_advance, - .check = xfrm_replay_check, - .recheck = xfrm_replay_check, - .notify = xfrm_replay_notify, - .overflow = xfrm_replay_overflow_offload, -}; - -static const struct xfrm_replay xfrm_replay_bmp = { - .advance = xfrm_replay_advance_bmp, - .check = xfrm_replay_check_bmp, - .recheck = xfrm_replay_check_bmp, - .notify = xfrm_replay_notify_bmp, - .overflow = xfrm_replay_overflow_offload_bmp, -}; - -static const struct xfrm_replay xfrm_replay_esn = { - .advance = xfrm_replay_advance_esn, - .check = xfrm_replay_check_esn, - .recheck = xfrm_replay_recheck_esn, - .notify = xfrm_replay_notify_esn, - .overflow = xfrm_replay_overflow_offload_esn, -}; +int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) +{ + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + return xfrm_replay_overflow_offload_bmp(x, skb); + case XFRM_REPLAY_MODE_ESN: + return xfrm_replay_overflow_offload_esn(x, skb); + } + + return xfrm_replay_overflow_offload(x, skb); +} #else -static const struct xfrm_replay xfrm_replay_legacy = { - .advance = xfrm_replay_advance, - .check = xfrm_replay_check, - .recheck = xfrm_replay_check, - .notify = xfrm_replay_notify, - .overflow = xfrm_replay_overflow, -}; - -static const struct xfrm_replay xfrm_replay_bmp = { - .advance = xfrm_replay_advance_bmp, - .check = xfrm_replay_check_bmp, - .recheck = xfrm_replay_check_bmp, - .notify = xfrm_replay_notify_bmp, - .overflow = xfrm_replay_overflow_bmp, -}; - -static const struct xfrm_replay xfrm_replay_esn = { - .advance = xfrm_replay_advance_esn, - .check = xfrm_replay_check_esn, - .recheck = xfrm_replay_recheck_esn, - .notify = xfrm_replay_notify_esn, - .overflow = xfrm_replay_overflow_esn, -}; +int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) +{ + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + return xfrm_replay_overflow_bmp(x, skb); + case XFRM_REPLAY_MODE_ESN: + return xfrm_replay_overflow_esn(x, skb); + } + + return __xfrm_replay_overflow(x, skb); +} #endif int xfrm_init_replay(struct xfrm_state *x) @@ -741,12 +778,12 @@ int xfrm_init_replay(struct xfrm_state *x) if (x->props.flags & XFRM_STATE_ESN) { if (replay_esn->replay_window == 0) return -EINVAL; - x->repl = &xfrm_replay_esn; + x->repl_mode = XFRM_REPLAY_MODE_ESN; } else { - x->repl = &xfrm_replay_bmp; + x->repl_mode = XFRM_REPLAY_MODE_BMP; } } else { - x->repl = &xfrm_replay_legacy; + x->repl_mode = XFRM_REPLAY_MODE_LEGACY; } return 0; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 4496f7efa220..a2f4001221d1 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -78,10 +78,16 @@ xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr, return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask); } +static unsigned int xfrm_seq_hash(struct net *net, u32 seq) +{ + return __xfrm_seq_hash(seq, net->xfrm.state_hmask); +} + static void xfrm_hash_transfer(struct hlist_head *list, struct hlist_head *ndsttable, struct hlist_head *nsrctable, struct hlist_head *nspitable, + struct hlist_head *nseqtable, unsigned int nhashmask) { struct hlist_node *tmp; @@ -106,6 +112,11 @@ static void xfrm_hash_transfer(struct hlist_head *list, nhashmask); hlist_add_head_rcu(&x->byspi, nspitable + h); } + + if (x->km.seq) { + h = __xfrm_seq_hash(x->km.seq, nhashmask); + hlist_add_head_rcu(&x->byseq, nseqtable + h); + } } } @@ -117,7 +128,7 @@ static unsigned long xfrm_hash_new_size(unsigned int state_hmask) static void xfrm_hash_resize(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.state_hash_work); - struct hlist_head *ndst, *nsrc, *nspi, *odst, *osrc, *ospi; + struct hlist_head *ndst, *nsrc, *nspi, *nseq, *odst, *osrc, *ospi, *oseq; unsigned long nsize, osize; unsigned int nhashmask, ohashmask; int i; @@ -137,6 +148,13 @@ static void xfrm_hash_resize(struct work_struct *work) xfrm_hash_free(nsrc, nsize); return; } + nseq = xfrm_hash_alloc(nsize); + if (!nseq) { + xfrm_hash_free(ndst, nsize); + xfrm_hash_free(nsrc, nsize); + xfrm_hash_free(nspi, nsize); + return; + } spin_lock_bh(&net->xfrm.xfrm_state_lock); write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); @@ -144,15 +162,17 @@ static void xfrm_hash_resize(struct work_struct *work) nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net); for (i = net->xfrm.state_hmask; i >= 0; i--) - xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nhashmask); + xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nseq, nhashmask); osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net); ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net); + oseq = xfrm_state_deref_prot(net->xfrm.state_byseq, net); ohashmask = net->xfrm.state_hmask; rcu_assign_pointer(net->xfrm.state_bydst, ndst); rcu_assign_pointer(net->xfrm.state_bysrc, nsrc); rcu_assign_pointer(net->xfrm.state_byspi, nspi); + rcu_assign_pointer(net->xfrm.state_byseq, nseq); net->xfrm.state_hmask = nhashmask; write_seqcount_end(&net->xfrm.xfrm_state_hash_generation); @@ -165,6 +185,7 @@ static void xfrm_hash_resize(struct work_struct *work) xfrm_hash_free(odst, osize); xfrm_hash_free(osrc, osize); xfrm_hash_free(ospi, osize); + xfrm_hash_free(oseq, osize); } static DEFINE_SPINLOCK(xfrm_state_afinfo_lock); @@ -621,6 +642,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) INIT_HLIST_NODE(&x->bydst); INIT_HLIST_NODE(&x->bysrc); INIT_HLIST_NODE(&x->byspi); + INIT_HLIST_NODE(&x->byseq); hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT); x->mtimer.function = xfrm_timer_handler; timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0); @@ -664,6 +686,8 @@ int __xfrm_state_delete(struct xfrm_state *x) list_del(&x->km.all); hlist_del_rcu(&x->bydst); hlist_del_rcu(&x->bysrc); + if (x->km.seq) + hlist_del_rcu(&x->byseq); if (x->id.spi) hlist_del_rcu(&x->byspi); net->xfrm.state_num--; @@ -1148,6 +1172,10 @@ found: h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); } + if (x->km.seq) { + h = xfrm_seq_hash(net, x->km.seq); + hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h); + } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), @@ -1263,6 +1291,12 @@ static void __xfrm_state_insert(struct xfrm_state *x) hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); } + if (x->km.seq) { + h = xfrm_seq_hash(net, x->km.seq); + + hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h); + } + hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); @@ -1932,20 +1966,18 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq) { - int i; - - for (i = 0; i <= net->xfrm.state_hmask; i++) { - struct xfrm_state *x; + unsigned int h = xfrm_seq_hash(net, seq); + struct xfrm_state *x; - hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { - if (x->km.seq == seq && - (mark & x->mark.m) == x->mark.v && - x->km.state == XFRM_STATE_ACQ) { - xfrm_state_hold(x); - return x; - } + hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) { + if (x->km.seq == seq && + (mark & x->mark.m) == x->mark.v && + x->km.state == XFRM_STATE_ACQ) { + xfrm_state_hold(x); + return x; } } + return NULL; } @@ -2145,7 +2177,7 @@ static void xfrm_replay_timer_handler(struct timer_list *t) if (x->km.state == XFRM_STATE_VALID) { if (xfrm_aevent_is_on(xs_net(x))) - x->repl->notify(x, XFRM_REPLAY_TIMEOUT); + xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT); else x->xflags |= XFRM_TIME_DEFER; } @@ -2518,7 +2550,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_delete_tunnel); -u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) +u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu) { const struct xfrm_type *type = READ_ONCE(x->type); struct crypto_aead *aead; @@ -2549,7 +2581,17 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - net_adj) & ~(blksize - 1)) + net_adj - 2; } -EXPORT_SYMBOL_GPL(xfrm_state_mtu); +EXPORT_SYMBOL_GPL(__xfrm_state_mtu); + +u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) +{ + mtu = __xfrm_state_mtu(x, mtu); + + if (x->props.family == AF_INET6 && mtu < IPV6_MIN_MTU) + return IPV6_MIN_MTU; + + return mtu; +} int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) { @@ -2660,6 +2702,9 @@ int __net_init xfrm_state_init(struct net *net) net->xfrm.state_byspi = xfrm_hash_alloc(sz); if (!net->xfrm.state_byspi) goto out_byspi; + net->xfrm.state_byseq = xfrm_hash_alloc(sz); + if (!net->xfrm.state_byseq) + goto out_byseq; net->xfrm.state_hmask = ((sz / sizeof(struct hlist_head)) - 1); net->xfrm.state_num = 0; @@ -2669,6 +2714,8 @@ int __net_init xfrm_state_init(struct net *net) &net->xfrm.xfrm_state_lock); return 0; +out_byseq: + xfrm_hash_free(net->xfrm.state_byspi, sz); out_byspi: xfrm_hash_free(net->xfrm.state_bysrc, sz); out_bysrc: @@ -2688,6 +2735,8 @@ void xfrm_state_fini(struct net *net) WARN_ON(!list_empty(&net->xfrm.state_all)); sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); + WARN_ON(!hlist_empty(net->xfrm.state_byseq)); + xfrm_hash_free(net->xfrm.state_byseq, sz); WARN_ON(!hlist_empty(net->xfrm.state_byspi)); xfrm_hash_free(net->xfrm.state_byspi, sz); WARN_ON(!hlist_empty(net->xfrm.state_bysrc)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index f0aecee4d539..b47d613409b7 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -580,6 +580,20 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, copy_from_user_state(x, p); + if (attrs[XFRMA_ENCAP]) { + x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), + sizeof(*x->encap), GFP_KERNEL); + if (x->encap == NULL) + goto error; + } + + if (attrs[XFRMA_COADDR]) { + x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]), + sizeof(*x->coaddr), GFP_KERNEL); + if (x->coaddr == NULL) + goto error; + } + if (attrs[XFRMA_SA_EXTRA_FLAGS]) x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]); @@ -600,23 +614,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, attrs[XFRMA_ALG_COMP]))) goto error; - if (attrs[XFRMA_ENCAP]) { - x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), - sizeof(*x->encap), GFP_KERNEL); - if (x->encap == NULL) - goto error; - } - if (attrs[XFRMA_TFCPAD]) x->tfcpad = nla_get_u32(attrs[XFRMA_TFCPAD]); - if (attrs[XFRMA_COADDR]) { - x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]), - sizeof(*x->coaddr), GFP_KERNEL); - if (x->coaddr == NULL) - goto error; - } - xfrm_mark_get(attrs, &x->mark); xfrm_smark_init(attrs, &x->props.smark); |