diff options
author | Linus Torvalds | 2024-03-12 17:44:08 -0700 |
---|---|---|
committer | Linus Torvalds | 2024-03-12 17:44:08 -0700 |
commit | 9187210eee7d87eea37b45ea93454a88681894a4 (patch) | |
tree | 31b4610e62cdd5e1dfb700014aa619e41145d7d3 /net | |
parent | 1f440397665f4241346e4cc6d93f8b73880815d1 (diff) | |
parent | ed1f164038b50c5864aa85389f3ffd456f050cca (diff) |
Merge tag 'net-next-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core & protocols:
- Large effort by Eric to lower rtnl_lock pressure and remove locks:
- Make commonly used parts of rtnetlink (address, route dumps
etc) lockless, protected by RCU instead of rtnl_lock.
- Add a netns exit callback which already holds rtnl_lock,
allowing netns exit to take rtnl_lock once in the core instead
of once for each driver / callback.
- Remove locks / serialization in the socket diag interface.
- Remove 6 calls to synchronize_rcu() while holding rtnl_lock.
- Remove the dev_base_lock, depend on RCU where necessary.
- Support busy polling on a per-epoll context basis. Poll length and
budget parameters can be set independently of system defaults.
- Introduce struct net_hotdata, to make sure read-mostly global
config variables fit in as few cache lines as possible.
- Add optional per-nexthop statistics to ease monitoring / debug of
ECMP imbalance problems.
- Support TCP_NOTSENT_LOWAT in MPTCP.
- Ensure that IPv6 temporary addresses' preferred lifetimes are long
enough, compared to other configured lifetimes, and at least 2 sec.
- Support forwarding of ICMP Error messages in IPSec, per RFC 4301.
- Add support for the independent control state machine for bonding
per IEEE 802.1AX-2008 5.4.15 in addition to the existing coupled
control state machine.
- Add "network ID" to MCTP socket APIs to support hosts with multiple
disjoint MCTP networks.
- Re-use the mono_delivery_time skbuff bit for packets which user
space wants to be sent at a specified time. Maintain the timing
information while traversing veth links, bridge etc.
- Take advantage of MSG_SPLICE_PAGES for RxRPC DATA and ACK packets.
- Simplify many places iterating over netdevs by using an xarray
instead of a hash table walk (hash table remains in place, for use
on fastpaths).
- Speed up scanning for expired routes by keeping a dedicated list.
- Speed up "generic" XDP by trying harder to avoid large allocations.
- Support attaching arbitrary metadata to netconsole messages.
Things we sprinkled into general kernel code:
- Enforce VM_IOREMAP flag and range in ioremap_page_range and
introduce VM_SPARSE kind and vm_area_[un]map_pages (used by
bpf_arena).
- Rework selftest harness to enable the use of the full range of ksft
exit code (pass, fail, skip, xfail, xpass).
Netfilter:
- Allow userspace to define a table that is exclusively owned by a
daemon (via netlink socket aliveness) without auto-removing this
table when the userspace program exits. Such table gets marked as
orphaned and a restarting management daemon can re-attach/regain
ownership.
- Speed up element insertions to nftables' concatenated-ranges set
type. Compact a few related data structures.
BPF:
- Add BPF token support for delegating a subset of BPF subsystem
functionality from privileged system-wide daemons such as systemd
through special mount options for userns-bound BPF fs to a trusted
& unprivileged application.
- Introduce bpf_arena which is sparse shared memory region between
BPF program and user space where structures inside the arena can
have pointers to other areas of the arena, and pointers work
seamlessly for both user-space programs and BPF programs.
- Introduce may_goto instruction that is a contract between the
verifier and the program. The verifier allows the program to loop
assuming it's behaving well, but reserves the right to terminate
it.
- Extend the BPF verifier to enable static subprog calls in spin lock
critical sections.
- Support registration of struct_ops types from modules which helps
projects like fuse-bpf that seeks to implement a new struct_ops
type.
- Add support for retrieval of cookies for perf/kprobe multi links.
- Support arbitrary TCP SYN cookie generation / validation in the TC
layer with BPF to allow creating SYN flood handling in BPF
firewalls.
- Add code generation to inline the bpf_kptr_xchg() helper which
improves performance when stashing/popping the allocated BPF
objects.
Wireless:
- Add SPP (signaling and payload protected) AMSDU support.
- Support wider bandwidth OFDMA, as required for EHT operation.
Driver API:
- Major overhaul of the Energy Efficient Ethernet internals to
support new link modes (2.5GE, 5GE), share more code between
drivers (especially those using phylib), and encourage more
uniform behavior. Convert and clean up drivers.
- Define an API for querying per netdev queue statistics from
drivers.
- IPSec: account in global stats for fully offloaded sessions.
- Create a concept of Ethernet PHY Packages at the Device Tree level,
to allow parameterizing the existing PHY package code.
- Enable Rx hashing (RSS) on GTP protocol fields.
Misc:
- Improvements and refactoring all over networking selftests.
- Create uniform module aliases for TC classifiers, actions, and
packet schedulers to simplify creating modprobe policies.
- Address all missing MODULE_DESCRIPTION() warnings in networking.
- Extend the Netlink descriptions in YAML to cover message
encapsulation or "Netlink polymorphism", where interpretation of
nested attributes depends on link type, classifier type or some
other "class type".
Drivers:
- Ethernet high-speed NICs:
- Add a new driver for Marvell's Octeon PCI Endpoint NIC VF.
- Intel (100G, ice, idpf):
- support E825-C devices
- nVidia/Mellanox:
- support devices with one port and multiple PCIe links
- Broadcom (bnxt):
- support n-tuple filters
- support configuring the RSS key
- Wangxun (ngbe/txgbe):
- implement irq_domain for TXGBE's sub-interrupts
- Pensando/AMD:
- support XDP
- optimize queue submission and wakeup handling (+17% bps)
- optimize struct layout, saving 28% of memory on queues
- Ethernet NICs embedded and virtual:
- Google cloud vNIC:
- refactor driver to perform memory allocations for new queue
config before stopping and freeing the old queue memory
- Synopsys (stmmac):
- obey queueMaxSDU and implement counters required by 802.1Qbv
- Renesas (ravb):
- support packet checksum offload
- suspend to RAM and runtime PM support
- Ethernet switches:
- nVidia/Mellanox:
- support for nexthop group statistics
- Microchip:
- ksz8: implement PHY loopback
- add support for KSZ8567, a 7-port 10/100Mbps switch
- PTP:
- New driver for RENESAS FemtoClock3 Wireless clock generator.
- Support OCP PTP cards designed and built by Adva.
- CAN:
- Support recvmsg() flags for own, local and remote traffic on CAN
BCM sockets.
- Support for esd GmbH PCIe/402 CAN device family.
- m_can:
- Rx/Tx submission coalescing
- wake on frame Rx
- WiFi:
- Intel (iwlwifi):
- enable signaling and payload protected A-MSDUs
- support wider-bandwidth OFDMA
- support for new devices
- bump FW API to 89 for AX devices; 90 for BZ/SC devices
- MediaTek (mt76):
- mt7915: newer ADIE version support
- mt7925: radio temperature sensor support
- Qualcomm (ath11k):
- support 6 GHz station power modes: Low Power Indoor (LPI),
Standard Power) SP and Very Low Power (VLP)
- QCA6390 & WCN6855: support 2 concurrent station interfaces
- QCA2066 support
- Qualcomm (ath12k):
- refactoring in preparation for Multi-Link Operation (MLO)
support
- 1024 Block Ack window size support
- firmware-2.bin support
- support having multiple identical PCI devices (firmware needs
to have ATH12K_FW_FEATURE_MULTI_QRTR_ID)
- QCN9274: support split-PHY devices
- WCN7850: enable Power Save Mode in station mode
- WCN7850: P2P support
- RealTek:
- rtw88: support for more rtw8811cu and rtw8821cu devices
- rtw89: support SCAN_RANDOM_SN and SET_SCAN_DWELL
- rtlwifi: speed up USB firmware initialization
- rtwl8xxxu:
- RTL8188F: concurrent interface support
- Channel Switch Announcement (CSA) support in AP mode
- Broadcom (brcmfmac):
- per-vendor feature support
- per-vendor SAE password setup
- DMI nvram filename quirk for ACEPC W5 Pro"
* tag 'net-next-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2255 commits)
nexthop: Fix splat with CONFIG_DEBUG_PREEMPT=y
nexthop: Fix out-of-bounds access during attribute validation
nexthop: Only parse NHA_OP_FLAGS for dump messages that require it
nexthop: Only parse NHA_OP_FLAGS for get messages that require it
bpf: move sleepable flag from bpf_prog_aux to bpf_prog
bpf: hardcode BPF_PROG_PACK_SIZE to 2MB * num_possible_nodes()
selftests/bpf: Add kprobe multi triggering benchmarks
ptp: Move from simple ida to xarray
vxlan: Remove generic .ndo_get_stats64
vxlan: Do not alloc tstats manually
devlink: Add comments to use netlink gen tool
nfp: flower: handle acti_netdevs allocation failure
net/packet: Add getsockopt support for PACKET_COPY_THRESH
net/netlink: Add getsockopt support for NETLINK_LISTEN_ALL_NSID
selftests/bpf: Add bpf_arena_htab test.
selftests/bpf: Add bpf_arena_list test.
selftests/bpf: Add unit tests for bpf_arena_alloc/free_pages
bpf: Add helper macro bpf_addr_space_cast()
libbpf: Recognize __arena global variables.
bpftool: Recognize arena map type
...
Diffstat (limited to 'net')
389 files changed, 13482 insertions, 11915 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 407b2335f091..39876eff51d2 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -504,28 +504,6 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } -/* - * vlan network devices have devices nesting below it, and are a special - * "super class" of normal network devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key vlan_netdev_xmit_lock_key; -static struct lock_class_key vlan_netdev_addr_lock_key; - -static void vlan_dev_set_lockdep_one(struct net_device *dev, - struct netdev_queue *txq, - void *unused) -{ - lockdep_set_class(&txq->_xmit_lock, &vlan_netdev_xmit_lock_key); -} - -static void vlan_dev_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, - &vlan_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, NULL); -} - static __be16 vlan_parse_protocol(const struct sk_buff *skb) { struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data); @@ -559,7 +537,7 @@ static const struct header_ops vlan_passthru_header_ops = { .parse_protocol = vlan_parse_protocol, }; -static struct device_type vlan_type = { +static const struct device_type vlan_type = { .name = "vlan", }; @@ -627,7 +605,7 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - vlan_dev_set_lockdep_class(dev); + netdev_lockdep_set_classes(dev); vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->vlan_pcpu_stats) @@ -784,9 +762,9 @@ static void vlan_dev_netpoll_cleanup(struct net_device *dev) static int vlan_dev_get_iflink(const struct net_device *dev) { - struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; + const struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; - return real_dev->ifindex; + return READ_ONCE(real_dev->ifindex); } static int vlan_dev_fill_forward_path(struct net_device_path_ctx *ctx, diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index 7825c129742a..87b959da00cd 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -163,48 +163,34 @@ void vlan_proc_rem_dev(struct net_device *vlandev) * The following few functions build the content of /proc/net/vlan/config */ -/* start read of /proc/net/vlan/config */ -static void *vlan_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(rcu) +static void *vlan_seq_from_index(struct seq_file *seq, loff_t *pos) { + unsigned long ifindex = *pos; struct net_device *dev; - struct net *net = seq_file_net(seq); - loff_t i = 1; - - rcu_read_lock(); - if (*pos == 0) - return SEQ_START_TOKEN; - for_each_netdev_rcu(net, dev) { + for_each_netdev_dump(seq_file_net(seq), dev, ifindex) { if (!is_vlan_dev(dev)) continue; - - if (i++ == *pos) - return dev; + *pos = dev->ifindex; + return dev; } + return NULL; +} + +static void *vlan_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(rcu) +{ + rcu_read_lock(); + if (*pos == 0) + return SEQ_START_TOKEN; - return NULL; + return vlan_seq_from_index(seq, pos); } static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct net_device *dev; - struct net *net = seq_file_net(seq); - ++*pos; - - dev = v; - if (v == SEQ_START_TOKEN) - dev = net_device_entry(&net->dev_base_head); - - for_each_netdev_continue_rcu(net, dev) { - if (!is_vlan_dev(dev)) - continue; - - return dev; - } - - return NULL; + return vlan_seq_from_index(seq, pos); } static void vlan_seq_stop(struct seq_file *seq, void *v) diff --git a/net/Kconfig b/net/Kconfig index 4adc47d0c9c2..3e57ccf0da27 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -331,6 +331,7 @@ config NET_RX_BUSY_POLL config BQL bool + prompt "Enable Byte Queue Limits" depends on SYSFS select DQL default y diff --git a/net/Makefile b/net/Makefile index b06b5539e7a6..65bb8c72a35e 100644 --- a/net/Makefile +++ b/net/Makefile @@ -17,7 +17,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ -obj-$(CONFIG_UNIX_SCM) += unix/ +obj-$(CONFIG_UNIX) += unix/ obj-y += ipv6/ obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 28a939d56090..4c7e85534324 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -684,7 +684,7 @@ static bool batadv_dat_forward_data(struct batadv_priv *bat_priv, cand = batadv_dat_select_candidates(bat_priv, ip, vid); if (!cand) - goto out; + return ret; batadv_dbg(BATADV_DBG_DAT, bat_priv, "DHT_SEND for %pI4\n", &ip); @@ -728,7 +728,6 @@ free_orig: batadv_orig_node_put(cand[i].orig_node); } -out: kfree(cand); return ret; } diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 5fc754b0b3f7..75119f1ffccc 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -691,29 +691,31 @@ int batadv_throw_uevent(struct batadv_priv *bat_priv, enum batadv_uev_type type, "%s%s", BATADV_UEV_TYPE_VAR, batadv_uev_type_str[type]); if (!uevent_env[0]) - goto out; + goto report_error; uevent_env[1] = kasprintf(GFP_ATOMIC, "%s%s", BATADV_UEV_ACTION_VAR, batadv_uev_action_str[action]); if (!uevent_env[1]) - goto out; + goto free_first_env; /* If the event is DEL, ignore the data field */ if (action != BATADV_UEV_DEL) { uevent_env[2] = kasprintf(GFP_ATOMIC, "%s%s", BATADV_UEV_DATA_VAR, data); if (!uevent_env[2]) - goto out; + goto free_second_env; } ret = kobject_uevent_env(bat_kobj, KOBJ_CHANGE, uevent_env); -out: - kfree(uevent_env[0]); - kfree(uevent_env[1]); kfree(uevent_env[2]); +free_second_env: + kfree(uevent_env[1]); +free_first_env: + kfree(uevent_env[0]); if (ret) +report_error: batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Impossible to send uevent for (%s,%s,%s) event (err: %d)\n", batadv_uev_type_str[type], diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 870dcd7f1786..8ca854a75a32 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 "2024.0" +#define BATADV_SOURCE_VERSION "2024.1" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 1f7ed9d4f6fd..0954757f0b8b 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -15,7 +15,6 @@ #include <linux/cache.h> #include <linux/err.h> #include <linux/errno.h> -#include <linux/export.h> #include <linux/genetlink.h> #include <linux/gfp.h> #include <linux/if_ether.h> diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 4eb1b3ced0d2..27520a8a486f 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -572,7 +572,7 @@ static void netdev_setup(struct net_device *dev) dev->needs_free_netdev = true; } -static struct device_type bt_type = { +static const struct device_type bt_type = { .name = "bluetooth", }; @@ -892,7 +892,7 @@ static int bt_6lowpan_connect(bdaddr_t *addr, u8 dst_type) chan->ops = &bt_6lowpan_chan_ops; err = l2cap_chan_connect(chan, cpu_to_le16(L2CAP_PSM_IPSP), 0, - addr, dst_type); + addr, dst_type, L2CAP_CONN_TIMEOUT); BT_DBG("chan %p err %d", chan, err); if (err < 0) diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index da7cac0a1b71..6b2b65a66700 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -62,14 +62,6 @@ source "net/bluetooth/cmtp/Kconfig" source "net/bluetooth/hidp/Kconfig" -config BT_HS - bool "Bluetooth High Speed (HS) features" - depends on BT_BREDR - help - Bluetooth High Speed includes support for off-loading - Bluetooth connections via 802.11 (wifi) physical layer - available with Bluetooth version 3.0 or later. - config BT_LE bool "Bluetooth Low Energy (LE) features" depends on BT diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 141ac1fda0bf..628d448d78be 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -21,7 +21,6 @@ bluetooth-$(CONFIG_DEV_COREDUMP) += coredump.o bluetooth-$(CONFIG_BT_BREDR) += sco.o bluetooth-$(CONFIG_BT_LE) += iso.o -bluetooth-$(CONFIG_BT_HS) += a2mp.o amp.o bluetooth-$(CONFIG_BT_LEDS) += leds.o bluetooth-$(CONFIG_BT_MSFTEXT) += msft.o bluetooth-$(CONFIG_BT_AOSPEXT) += aosp.o diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c deleted file mode 100644 index e7adb8a98cf9..000000000000 --- a/net/bluetooth/a2mp.c +++ /dev/null @@ -1,1054 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - Copyright (c) 2010,2011 Code Aurora Forum. All rights reserved. - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#include <net/bluetooth/bluetooth.h> -#include <net/bluetooth/hci_core.h> -#include <net/bluetooth/l2cap.h> - -#include "hci_request.h" -#include "a2mp.h" -#include "amp.h" - -#define A2MP_FEAT_EXT 0x8000 - -/* Global AMP Manager list */ -static LIST_HEAD(amp_mgr_list); -static DEFINE_MUTEX(amp_mgr_list_lock); - -/* A2MP build & send command helper functions */ -static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data) -{ - struct a2mp_cmd *cmd; - int plen; - - plen = sizeof(*cmd) + len; - cmd = kzalloc(plen, GFP_KERNEL); - if (!cmd) - return NULL; - - cmd->code = code; - cmd->ident = ident; - cmd->len = cpu_to_le16(len); - - memcpy(cmd->data, data, len); - - return cmd; -} - -static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data) -{ - struct l2cap_chan *chan = mgr->a2mp_chan; - struct a2mp_cmd *cmd; - u16 total_len = len + sizeof(*cmd); - struct kvec iv; - struct msghdr msg; - - cmd = __a2mp_build(code, ident, len, data); - if (!cmd) - return; - - iv.iov_base = cmd; - iv.iov_len = total_len; - - memset(&msg, 0, sizeof(msg)); - - iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iv, 1, total_len); - - l2cap_chan_send(chan, &msg, total_len); - - kfree(cmd); -} - -static u8 __next_ident(struct amp_mgr *mgr) -{ - if (++mgr->ident == 0) - mgr->ident = 1; - - return mgr->ident; -} - -static struct amp_mgr *amp_mgr_lookup_by_state(u8 state) -{ - struct amp_mgr *mgr; - - mutex_lock(&_mgr_list_lock); - list_for_each_entry(mgr, &_mgr_list, list) { - if (test_and_clear_bit(state, &mgr->state)) { - amp_mgr_get(mgr); - mutex_unlock(&_mgr_list_lock); - return mgr; - } - } - mutex_unlock(&_mgr_list_lock); - - return NULL; -} - -/* hci_dev_list shall be locked */ -static void __a2mp_add_cl(struct amp_mgr *mgr, struct a2mp_cl *cl) -{ - struct hci_dev *hdev; - int i = 1; - - cl[0].id = AMP_ID_BREDR; - cl[0].type = AMP_TYPE_BREDR; - cl[0].status = AMP_STATUS_BLUETOOTH_ONLY; - - list_for_each_entry(hdev, &hci_dev_list, list) { - if (hdev->dev_type == HCI_AMP) { - cl[i].id = hdev->id; - cl[i].type = hdev->amp_type; - if (test_bit(HCI_UP, &hdev->flags)) - cl[i].status = hdev->amp_status; - else - cl[i].status = AMP_STATUS_POWERED_DOWN; - i++; - } - } -} - -/* Processing A2MP messages */ -static int a2mp_command_rej(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_cmd_rej *rej = (void *) skb->data; - - if (le16_to_cpu(hdr->len) < sizeof(*rej)) - return -EINVAL; - - BT_DBG("ident %u reason %d", hdr->ident, le16_to_cpu(rej->reason)); - - skb_pull(skb, sizeof(*rej)); - - return 0; -} - -static int a2mp_discover_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_discov_req *req = (void *) skb->data; - u16 len = le16_to_cpu(hdr->len); - struct a2mp_discov_rsp *rsp; - u16 ext_feat; - u8 num_ctrl; - struct hci_dev *hdev; - - if (len < sizeof(*req)) - return -EINVAL; - - skb_pull(skb, sizeof(*req)); - - ext_feat = le16_to_cpu(req->ext_feat); - - BT_DBG("mtu %d efm 0x%4.4x", le16_to_cpu(req->mtu), ext_feat); - - /* check that packet is not broken for now */ - while (ext_feat & A2MP_FEAT_EXT) { - if (len < sizeof(ext_feat)) - return -EINVAL; - - ext_feat = get_unaligned_le16(skb->data); - BT_DBG("efm 0x%4.4x", ext_feat); - len -= sizeof(ext_feat); - skb_pull(skb, sizeof(ext_feat)); - } - - read_lock(&hci_dev_list_lock); - - /* at minimum the BR/EDR needs to be listed */ - num_ctrl = 1; - - list_for_each_entry(hdev, &hci_dev_list, list) { - if (hdev->dev_type == HCI_AMP) - num_ctrl++; - } - - len = struct_size(rsp, cl, num_ctrl); - rsp = kmalloc(len, GFP_ATOMIC); - if (!rsp) { - read_unlock(&hci_dev_list_lock); - return -ENOMEM; - } - - rsp->mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); - rsp->ext_feat = 0; - - __a2mp_add_cl(mgr, rsp->cl); - - read_unlock(&hci_dev_list_lock); - - a2mp_send(mgr, A2MP_DISCOVER_RSP, hdr->ident, len, rsp); - - kfree(rsp); - return 0; -} - -static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_discov_rsp *rsp = (void *) skb->data; - u16 len = le16_to_cpu(hdr->len); - struct a2mp_cl *cl; - u16 ext_feat; - bool found = false; - - if (len < sizeof(*rsp)) - return -EINVAL; - - len -= sizeof(*rsp); - skb_pull(skb, sizeof(*rsp)); - - ext_feat = le16_to_cpu(rsp->ext_feat); - - BT_DBG("mtu %d efm 0x%4.4x", le16_to_cpu(rsp->mtu), ext_feat); - - /* check that packet is not broken for now */ - while (ext_feat & A2MP_FEAT_EXT) { - if (len < sizeof(ext_feat)) - return -EINVAL; - - ext_feat = get_unaligned_le16(skb->data); - BT_DBG("efm 0x%4.4x", ext_feat); - len -= sizeof(ext_feat); - skb_pull(skb, sizeof(ext_feat)); - } - - cl = (void *) skb->data; - while (len >= sizeof(*cl)) { - 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) { - struct a2mp_info_req req; - - found = true; - - memset(&req, 0, sizeof(req)); - - req.id = cl->id; - a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr), - sizeof(req), &req); - } - - len -= sizeof(*cl); - cl = skb_pull(skb, sizeof(*cl)); - } - - /* Fall back to L2CAP init sequence */ - if (!found) { - struct l2cap_conn *conn = mgr->l2cap_conn; - struct l2cap_chan *chan; - - mutex_lock(&conn->chan_lock); - - list_for_each_entry(chan, &conn->chan_l, list) { - - BT_DBG("chan %p state %s", chan, - state_to_string(chan->state)); - - if (chan->scid == L2CAP_CID_A2MP) - continue; - - l2cap_chan_lock(chan); - - if (chan->state == BT_CONNECT) - l2cap_send_conn_req(chan); - - l2cap_chan_unlock(chan); - } - - mutex_unlock(&conn->chan_lock); - } - - return 0; -} - -static int a2mp_change_notify(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_cl *cl = (void *) skb->data; - - while (skb->len >= sizeof(*cl)) { - BT_DBG("Controller id %u type %u status %u", cl->id, cl->type, - cl->status); - cl = skb_pull(skb, sizeof(*cl)); - } - - /* TODO send A2MP_CHANGE_RSP */ - - return 0; -} - -static void read_local_amp_info_complete(struct hci_dev *hdev, u8 status, - u16 opcode) -{ - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - a2mp_send_getinfo_rsp(hdev); -} - -static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_info_req *req = (void *) skb->data; - struct hci_dev *hdev; - struct hci_request hreq; - int err = 0; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("id %u", req->id); - - hdev = hci_dev_get(req->id); - if (!hdev || hdev->dev_type != HCI_AMP) { - struct a2mp_info_rsp rsp; - - memset(&rsp, 0, sizeof(rsp)); - - rsp.id = req->id; - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - - a2mp_send(mgr, A2MP_GETINFO_RSP, hdr->ident, sizeof(rsp), - &rsp); - - goto done; - } - - set_bit(READ_LOC_AMP_INFO, &mgr->state); - hci_req_init(&hreq, hdev); - hci_req_add(&hreq, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL); - err = hci_req_run(&hreq, read_local_amp_info_complete); - if (err < 0) - a2mp_send_getinfo_rsp(hdev); - -done: - if (hdev) - hci_dev_put(hdev); - - skb_pull(skb, sizeof(*req)); - return 0; -} - -static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_info_rsp *rsp = (struct a2mp_info_rsp *) skb->data; - struct a2mp_amp_assoc_req req; - struct amp_ctrl *ctrl; - - if (le16_to_cpu(hdr->len) < sizeof(*rsp)) - return -EINVAL; - - BT_DBG("id %u status 0x%2.2x", rsp->id, rsp->status); - - if (rsp->status) - return -EINVAL; - - ctrl = amp_ctrl_add(mgr, rsp->id); - if (!ctrl) - return -ENOMEM; - - memset(&req, 0, sizeof(req)); - - req.id = rsp->id; - a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req), - &req); - - skb_pull(skb, sizeof(*rsp)); - return 0; -} - -static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_amp_assoc_req *req = (void *) skb->data; - struct hci_dev *hdev; - struct amp_mgr *tmp; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("id %u", req->id); - - /* Make sure that other request is not processed */ - tmp = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC); - - hdev = hci_dev_get(req->id); - if (!hdev || hdev->amp_type == AMP_TYPE_BREDR || tmp) { - struct a2mp_amp_assoc_rsp rsp; - - memset(&rsp, 0, sizeof(rsp)); - rsp.id = req->id; - - if (tmp) { - rsp.status = A2MP_STATUS_COLLISION_OCCURED; - amp_mgr_put(tmp); - } else { - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - } - - a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, hdr->ident, sizeof(rsp), - &rsp); - - goto done; - } - - amp_read_loc_assoc(hdev, mgr); - -done: - if (hdev) - hci_dev_put(hdev); - - skb_pull(skb, sizeof(*req)); - return 0; -} - -static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_amp_assoc_rsp *rsp = (void *) skb->data; - u16 len = le16_to_cpu(hdr->len); - struct hci_dev *hdev; - struct amp_ctrl *ctrl; - struct hci_conn *hcon; - size_t assoc_len; - - if (len < sizeof(*rsp)) - return -EINVAL; - - assoc_len = len - sizeof(*rsp); - - BT_DBG("id %u status 0x%2.2x assoc len %zu", rsp->id, rsp->status, - assoc_len); - - if (rsp->status) - return -EINVAL; - - /* Save remote ASSOC data */ - ctrl = amp_ctrl_lookup(mgr, rsp->id); - if (ctrl) { - u8 *assoc; - - assoc = kmemdup(rsp->amp_assoc, assoc_len, GFP_KERNEL); - if (!assoc) { - amp_ctrl_put(ctrl); - return -ENOMEM; - } - - ctrl->assoc = assoc; - ctrl->assoc_len = assoc_len; - ctrl->assoc_rem_len = assoc_len; - ctrl->assoc_len_so_far = 0; - - amp_ctrl_put(ctrl); - } - - /* Create Phys Link */ - hdev = hci_dev_get(rsp->id); - if (!hdev) - return -EINVAL; - - hcon = phylink_add(hdev, mgr, rsp->id, true); - if (!hcon) - goto done; - - BT_DBG("Created hcon %p: loc:%u -> rem:%u", hcon, hdev->id, rsp->id); - - mgr->bredr_chan->remote_amp_id = rsp->id; - - amp_create_phylink(hdev, mgr, hcon); - -done: - hci_dev_put(hdev); - skb_pull(skb, len); - return 0; -} - -static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_physlink_req *req = (void *) skb->data; - struct a2mp_physlink_rsp rsp; - struct hci_dev *hdev; - struct hci_conn *hcon; - struct amp_ctrl *ctrl; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("local_id %u, remote_id %u", req->local_id, req->remote_id); - - memset(&rsp, 0, sizeof(rsp)); - - rsp.local_id = req->remote_id; - rsp.remote_id = req->local_id; - - hdev = hci_dev_get(req->remote_id); - if (!hdev || hdev->amp_type == AMP_TYPE_BREDR) { - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - goto send_rsp; - } - - ctrl = amp_ctrl_lookup(mgr, rsp.remote_id); - if (!ctrl) { - ctrl = amp_ctrl_add(mgr, rsp.remote_id); - if (ctrl) { - amp_ctrl_get(ctrl); - } else { - rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; - goto send_rsp; - } - } - - if (ctrl) { - size_t assoc_len = le16_to_cpu(hdr->len) - sizeof(*req); - u8 *assoc; - - assoc = kmemdup(req->amp_assoc, assoc_len, GFP_KERNEL); - if (!assoc) { - amp_ctrl_put(ctrl); - hci_dev_put(hdev); - return -ENOMEM; - } - - ctrl->assoc = assoc; - ctrl->assoc_len = assoc_len; - ctrl->assoc_rem_len = assoc_len; - ctrl->assoc_len_so_far = 0; - - amp_ctrl_put(ctrl); - } - - hcon = phylink_add(hdev, mgr, req->local_id, false); - if (hcon) { - amp_accept_phylink(hdev, mgr, hcon); - rsp.status = A2MP_STATUS_SUCCESS; - } else { - rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; - } - -send_rsp: - if (hdev) - hci_dev_put(hdev); - - /* Reply error now and success after HCI Write Remote AMP Assoc - command complete with success status - */ - if (rsp.status != A2MP_STATUS_SUCCESS) { - a2mp_send(mgr, A2MP_CREATEPHYSLINK_RSP, hdr->ident, - sizeof(rsp), &rsp); - } else { - set_bit(WRITE_REMOTE_AMP_ASSOC, &mgr->state); - mgr->ident = hdr->ident; - } - - skb_pull(skb, le16_to_cpu(hdr->len)); - return 0; -} - -static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_physlink_req *req = (void *) skb->data; - struct a2mp_physlink_rsp rsp; - struct hci_dev *hdev; - struct hci_conn *hcon; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("local_id %u remote_id %u", req->local_id, req->remote_id); - - memset(&rsp, 0, sizeof(rsp)); - - rsp.local_id = req->remote_id; - rsp.remote_id = req->local_id; - rsp.status = A2MP_STATUS_SUCCESS; - - hdev = hci_dev_get(req->remote_id); - if (!hdev) { - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - goto send_rsp; - } - - hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, - &mgr->l2cap_conn->hcon->dst); - if (!hcon) { - bt_dev_err(hdev, "no phys link exist"); - rsp.status = A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS; - goto clean; - } - - /* TODO Disconnect Phys Link here */ - -clean: - hci_dev_put(hdev); - -send_rsp: - a2mp_send(mgr, A2MP_DISCONNPHYSLINK_RSP, hdr->ident, sizeof(rsp), &rsp); - - skb_pull(skb, sizeof(*req)); - return 0; -} - -static inline int a2mp_cmd_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - BT_DBG("ident %u code 0x%2.2x", hdr->ident, hdr->code); - - skb_pull(skb, le16_to_cpu(hdr->len)); - return 0; -} - -/* Handle A2MP signalling */ -static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) -{ - struct a2mp_cmd *hdr; - struct amp_mgr *mgr = chan->data; - int err = 0; - - amp_mgr_get(mgr); - - while (skb->len >= sizeof(*hdr)) { - u16 len; - - hdr = (void *) skb->data; - len = le16_to_cpu(hdr->len); - - BT_DBG("code 0x%2.2x id %u len %u", hdr->code, hdr->ident, len); - - skb_pull(skb, sizeof(*hdr)); - - if (len > skb->len || !hdr->ident) { - err = -EINVAL; - break; - } - - mgr->ident = hdr->ident; - - switch (hdr->code) { - case A2MP_COMMAND_REJ: - a2mp_command_rej(mgr, skb, hdr); - break; - - case A2MP_DISCOVER_REQ: - err = a2mp_discover_req(mgr, skb, hdr); - break; - - case A2MP_CHANGE_NOTIFY: - err = a2mp_change_notify(mgr, skb, hdr); - break; - - case A2MP_GETINFO_REQ: - err = a2mp_getinfo_req(mgr, skb, hdr); - break; - - case A2MP_GETAMPASSOC_REQ: - err = a2mp_getampassoc_req(mgr, skb, hdr); - break; - - case A2MP_CREATEPHYSLINK_REQ: - err = a2mp_createphyslink_req(mgr, skb, hdr); - break; - - case A2MP_DISCONNPHYSLINK_REQ: - err = a2mp_discphyslink_req(mgr, skb, hdr); - break; - - case A2MP_DISCOVER_RSP: - err = a2mp_discover_rsp(mgr, skb, hdr); - break; - - case A2MP_GETINFO_RSP: - err = a2mp_getinfo_rsp(mgr, skb, hdr); - break; - - case A2MP_GETAMPASSOC_RSP: - err = a2mp_getampassoc_rsp(mgr, skb, hdr); - break; - - case A2MP_CHANGE_RSP: - case A2MP_CREATEPHYSLINK_RSP: - case A2MP_DISCONNPHYSLINK_RSP: - err = a2mp_cmd_rsp(mgr, skb, hdr); - break; - - default: - BT_ERR("Unknown A2MP sig cmd 0x%2.2x", hdr->code); - err = -EINVAL; - break; - } - } - - if (err) { - struct a2mp_cmd_rej rej; - - memset(&rej, 0, sizeof(rej)); - - rej.reason = cpu_to_le16(0); - hdr = (void *) skb->data; - - BT_DBG("Send A2MP Rej: cmd 0x%2.2x err %d", hdr->code, err); - - a2mp_send(mgr, A2MP_COMMAND_REJ, hdr->ident, sizeof(rej), - &rej); - } - - /* Always free skb and return success error code to prevent - from sending L2CAP Disconnect over A2MP channel */ - kfree_skb(skb); - - amp_mgr_put(mgr); - - return 0; -} - -static void a2mp_chan_close_cb(struct l2cap_chan *chan) -{ - l2cap_chan_put(chan); -} - -static void a2mp_chan_state_change_cb(struct l2cap_chan *chan, int state, - int err) -{ - struct amp_mgr *mgr = chan->data; - - if (!mgr) - return; - - BT_DBG("chan %p state %s", chan, state_to_string(state)); - - chan->state = state; - - switch (state) { - case BT_CLOSED: - if (mgr) - amp_mgr_put(mgr); - break; - } -} - -static struct sk_buff *a2mp_chan_alloc_skb_cb(struct l2cap_chan *chan, - unsigned long hdr_len, - unsigned long len, int nb) -{ - struct sk_buff *skb; - - skb = bt_skb_alloc(hdr_len + len, GFP_KERNEL); - if (!skb) - return ERR_PTR(-ENOMEM); - - return skb; -} - -static const struct l2cap_ops a2mp_chan_ops = { - .name = "L2CAP A2MP channel", - .recv = a2mp_chan_recv_cb, - .close = a2mp_chan_close_cb, - .state_change = a2mp_chan_state_change_cb, - .alloc_skb = a2mp_chan_alloc_skb_cb, - - /* Not implemented for A2MP */ - .new_connection = l2cap_chan_no_new_connection, - .teardown = l2cap_chan_no_teardown, - .ready = l2cap_chan_no_ready, - .defer = l2cap_chan_no_defer, - .resume = l2cap_chan_no_resume, - .set_shutdown = l2cap_chan_no_set_shutdown, - .get_sndtimeo = l2cap_chan_no_get_sndtimeo, -}; - -static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked) -{ - struct l2cap_chan *chan; - int err; - - chan = l2cap_chan_create(); - if (!chan) - return NULL; - - BT_DBG("chan %p", chan); - - chan->chan_type = L2CAP_CHAN_FIXED; - chan->scid = L2CAP_CID_A2MP; - chan->dcid = L2CAP_CID_A2MP; - chan->omtu = L2CAP_A2MP_DEFAULT_MTU; - chan->imtu = L2CAP_A2MP_DEFAULT_MTU; - chan->flush_to = L2CAP_DEFAULT_FLUSH_TO; - - chan->ops = &a2mp_chan_ops; - - l2cap_chan_set_defaults(chan); - chan->remote_max_tx = chan->max_tx; - chan->remote_tx_win = chan->tx_win; - - chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO; - chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO; - - skb_queue_head_init(&chan->tx_q); - - chan->mode = L2CAP_MODE_ERTM; - - err = l2cap_ertm_init(chan); - if (err < 0) { - l2cap_chan_del(chan, 0); - return NULL; - } - - chan->conf_state = 0; - - if (locked) - __l2cap_chan_add(conn, chan); - else - l2cap_chan_add(conn, chan); - - chan->remote_mps = chan->omtu; - chan->mps = chan->omtu; - - chan->state = BT_CONNECTED; - - return chan; -} - -/* AMP Manager functions */ -struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr) -{ - BT_DBG("mgr %p orig refcnt %d", mgr, kref_read(&mgr->kref)); - - kref_get(&mgr->kref); - - return mgr; -} - -static void amp_mgr_destroy(struct kref *kref) -{ - struct amp_mgr *mgr = container_of(kref, struct amp_mgr, kref); - - BT_DBG("mgr %p", mgr); - - mutex_lock(&_mgr_list_lock); - list_del(&mgr->list); - mutex_unlock(&_mgr_list_lock); - - amp_ctrl_list_flush(mgr); - kfree(mgr); -} - -int amp_mgr_put(struct amp_mgr *mgr) -{ - BT_DBG("mgr %p orig refcnt %d", mgr, kref_read(&mgr->kref)); - - return kref_put(&mgr->kref, &_mgr_destroy); -} - -static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn, bool locked) -{ - struct amp_mgr *mgr; - struct l2cap_chan *chan; - - mgr = kzalloc(sizeof(*mgr), GFP_KERNEL); - if (!mgr) - return NULL; - - BT_DBG("conn %p mgr %p", conn, mgr); - - mgr->l2cap_conn = conn; - - chan = a2mp_chan_open(conn, locked); - if (!chan) { - kfree(mgr); - return NULL; - } - - mgr->a2mp_chan = chan; - chan->data = mgr; - - conn->hcon->amp_mgr = mgr; - - kref_init(&mgr->kref); - - /* Remote AMP ctrl list initialization */ - INIT_LIST_HEAD(&mgr->amp_ctrls); - mutex_init(&mgr->amp_ctrls_lock); - - mutex_lock(&_mgr_list_lock); - list_add(&mgr->list, &_mgr_list); - mutex_unlock(&_mgr_list_lock); - - return mgr; -} - -struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, - struct sk_buff *skb) -{ - struct amp_mgr *mgr; - - if (conn->hcon->type != ACL_LINK) - return NULL; - - mgr = amp_mgr_create(conn, false); - if (!mgr) { - BT_ERR("Could not create AMP manager"); - return NULL; - } - - BT_DBG("mgr: %p chan %p", mgr, mgr->a2mp_chan); - - return mgr->a2mp_chan; -} - -void a2mp_send_getinfo_rsp(struct hci_dev *hdev) -{ - struct amp_mgr *mgr; - struct a2mp_info_rsp rsp; - - mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_INFO); - if (!mgr) - return; - - BT_DBG("%s mgr %p", hdev->name, mgr); - - memset(&rsp, 0, sizeof(rsp)); - - rsp.id = hdev->id; - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - - if (hdev->amp_type != AMP_TYPE_BREDR) { - rsp.status = 0; - rsp.total_bw = cpu_to_le32(hdev->amp_total_bw); - rsp.max_bw = cpu_to_le32(hdev->amp_max_bw); - rsp.min_latency = cpu_to_le32(hdev->amp_min_latency); - rsp.pal_cap = cpu_to_le16(hdev->amp_pal_cap); - rsp.assoc_size = cpu_to_le16(hdev->amp_assoc_size); - } - - a2mp_send(mgr, A2MP_GETINFO_RSP, mgr->ident, sizeof(rsp), &rsp); - amp_mgr_put(mgr); -} - -void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status) -{ - struct amp_mgr *mgr; - struct amp_assoc *loc_assoc = &hdev->loc_assoc; - struct a2mp_amp_assoc_rsp *rsp; - size_t len; - - mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC); - if (!mgr) - return; - - BT_DBG("%s mgr %p", hdev->name, mgr); - - len = sizeof(struct a2mp_amp_assoc_rsp) + loc_assoc->len; - rsp = kzalloc(len, GFP_KERNEL); - if (!rsp) { - amp_mgr_put(mgr); - return; - } - - rsp->id = hdev->id; - - if (status) { - rsp->status = A2MP_STATUS_INVALID_CTRL_ID; - } else { - rsp->status = A2MP_STATUS_SUCCESS; - memcpy(rsp->amp_assoc, loc_assoc->data, loc_assoc->len); - } - - a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, mgr->ident, len, rsp); - amp_mgr_put(mgr); - kfree(rsp); -} - -void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status) -{ - struct amp_mgr *mgr; - struct amp_assoc *loc_assoc = &hdev->loc_assoc; - struct a2mp_physlink_req *req; - struct l2cap_chan *bredr_chan; - size_t len; - - mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC_FINAL); - if (!mgr) - return; - - len = sizeof(*req) + loc_assoc->len; - - BT_DBG("%s mgr %p assoc_len %zu", hdev->name, mgr, len); - - req = kzalloc(len, GFP_KERNEL); - if (!req) { - amp_mgr_put(mgr); - return; - } - - bredr_chan = mgr->bredr_chan; - if (!bredr_chan) - goto clean; - - req->local_id = hdev->id; - req->remote_id = bredr_chan->remote_amp_id; - memcpy(req->amp_assoc, loc_assoc->data, loc_assoc->len); - - a2mp_send(mgr, A2MP_CREATEPHYSLINK_REQ, __next_ident(mgr), len, req); - -clean: - amp_mgr_put(mgr); - kfree(req); -} - -void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status) -{ - struct amp_mgr *mgr; - struct a2mp_physlink_rsp rsp; - struct hci_conn *hs_hcon; - - mgr = amp_mgr_lookup_by_state(WRITE_REMOTE_AMP_ASSOC); - if (!mgr) - return; - - memset(&rsp, 0, sizeof(rsp)); - - hs_hcon = hci_conn_hash_lookup_state(hdev, AMP_LINK, BT_CONNECT); - if (!hs_hcon) { - rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; - } else { - rsp.remote_id = hs_hcon->remote_id; - rsp.status = A2MP_STATUS_SUCCESS; - } - - BT_DBG("%s mgr %p hs_hcon %p status %u", hdev->name, mgr, hs_hcon, - status); - - rsp.local_id = hdev->id; - a2mp_send(mgr, A2MP_CREATEPHYSLINK_RSP, mgr->ident, sizeof(rsp), &rsp); - amp_mgr_put(mgr); -} - -void a2mp_discover_amp(struct l2cap_chan *chan) -{ - struct l2cap_conn *conn = chan->conn; - struct amp_mgr *mgr = conn->hcon->amp_mgr; - struct a2mp_discov_req req; - - BT_DBG("chan %p conn %p mgr %p", chan, conn, mgr); - - if (!mgr) { - mgr = amp_mgr_create(conn, true); - if (!mgr) - return; - } - - mgr->bredr_chan = chan; - - memset(&req, 0, sizeof(req)); - - req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); - req.ext_feat = 0; - a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req); -} diff --git a/net/bluetooth/a2mp.h b/net/bluetooth/a2mp.h deleted file mode 100644 index 2fd253a61a2a..000000000000 --- a/net/bluetooth/a2mp.h +++ /dev/null @@ -1,154 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - Copyright (c) 2010,2011 Code Aurora Forum. All rights reserved. - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#ifndef __A2MP_H -#define __A2MP_H - -#include <net/bluetooth/l2cap.h> - -enum amp_mgr_state { - READ_LOC_AMP_INFO, - READ_LOC_AMP_ASSOC, - READ_LOC_AMP_ASSOC_FINAL, - WRITE_REMOTE_AMP_ASSOC, -}; - -struct amp_mgr { - struct list_head list; - struct l2cap_conn *l2cap_conn; - struct l2cap_chan *a2mp_chan; - struct l2cap_chan *bredr_chan; - struct kref kref; - __u8 ident; - __u8 handle; - unsigned long state; - unsigned long flags; - - struct list_head amp_ctrls; - struct mutex amp_ctrls_lock; -}; - -struct a2mp_cmd { - __u8 code; - __u8 ident; - __le16 len; - __u8 data[]; -} __packed; - -/* A2MP command codes */ -#define A2MP_COMMAND_REJ 0x01 -struct a2mp_cmd_rej { - __le16 reason; - __u8 data[]; -} __packed; - -#define A2MP_DISCOVER_REQ 0x02 -struct a2mp_discov_req { - __le16 mtu; - __le16 ext_feat; -} __packed; - -struct a2mp_cl { - __u8 id; - __u8 type; - __u8 status; -} __packed; - -#define A2MP_DISCOVER_RSP 0x03 -struct a2mp_discov_rsp { - __le16 mtu; - __le16 ext_feat; - struct a2mp_cl cl[]; -} __packed; - -#define A2MP_CHANGE_NOTIFY 0x04 -#define A2MP_CHANGE_RSP 0x05 - -#define A2MP_GETINFO_REQ 0x06 -struct a2mp_info_req { - __u8 id; -} __packed; - -#define A2MP_GETINFO_RSP 0x07 -struct a2mp_info_rsp { - __u8 id; - __u8 status; - __le32 total_bw; - __le32 max_bw; - __le32 min_latency; - __le16 pal_cap; - __le16 assoc_size; -} __packed; - -#define A2MP_GETAMPASSOC_REQ 0x08 -struct a2mp_amp_assoc_req { - __u8 id; -} __packed; - -#define A2MP_GETAMPASSOC_RSP 0x09 -struct a2mp_amp_assoc_rsp { - __u8 id; - __u8 status; - __u8 amp_assoc[]; -} __packed; - -#define A2MP_CREATEPHYSLINK_REQ 0x0A -#define A2MP_DISCONNPHYSLINK_REQ 0x0C -struct a2mp_physlink_req { - __u8 local_id; - __u8 remote_id; - __u8 amp_assoc[]; -} __packed; - -#define A2MP_CREATEPHYSLINK_RSP 0x0B -#define A2MP_DISCONNPHYSLINK_RSP 0x0D -struct a2mp_physlink_rsp { - __u8 local_id; - __u8 remote_id; - __u8 status; -} __packed; - -/* A2MP response status */ -#define A2MP_STATUS_SUCCESS 0x00 -#define A2MP_STATUS_INVALID_CTRL_ID 0x01 -#define A2MP_STATUS_UNABLE_START_LINK_CREATION 0x02 -#define A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS 0x02 -#define A2MP_STATUS_COLLISION_OCCURED 0x03 -#define A2MP_STATUS_DISCONN_REQ_RECVD 0x04 -#define A2MP_STATUS_PHYS_LINK_EXISTS 0x05 -#define A2MP_STATUS_SECURITY_VIOLATION 0x06 - -struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr); - -#if IS_ENABLED(CONFIG_BT_HS) -int amp_mgr_put(struct amp_mgr *mgr); -struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, - struct sk_buff *skb); -void a2mp_discover_amp(struct l2cap_chan *chan); -#else -static inline int amp_mgr_put(struct amp_mgr *mgr) -{ - return 0; -} - -static inline struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, - struct sk_buff *skb) -{ - return NULL; -} - -static inline void a2mp_discover_amp(struct l2cap_chan *chan) -{ -} -#endif - -void a2mp_send_getinfo_rsp(struct hci_dev *hdev); -void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status); -void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status); -void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status); - -#endif /* __A2MP_H */ diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index b93464ac3517..67604ccec2f4 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -309,14 +309,11 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (flags & MSG_OOB) return -EOPNOTSUPP; - lock_sock(sk); - skb = skb_recv_datagram(sk, flags, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) err = 0; - release_sock(sk); return err; } @@ -346,8 +343,6 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - release_sock(sk); - if (flags & MSG_TRUNC) copied = skblen; @@ -570,10 +565,11 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) if (sk->sk_state == BT_LISTEN) return -EINVAL; - lock_sock(sk); + spin_lock(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; - release_sock(sk); + spin_unlock(&sk->sk_receive_queue.lock); + err = put_user(amount, (int __user *)arg); break; diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c deleted file mode 100644 index 5d698f19868c..000000000000 --- a/net/bluetooth/amp.c +++ /dev/null @@ -1,590 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#include <net/bluetooth/bluetooth.h> -#include <net/bluetooth/hci.h> -#include <net/bluetooth/hci_core.h> -#include <crypto/hash.h> - -#include "hci_request.h" -#include "a2mp.h" -#include "amp.h" - -/* Remote AMP Controllers interface */ -void amp_ctrl_get(struct amp_ctrl *ctrl) -{ - BT_DBG("ctrl %p orig refcnt %d", ctrl, - kref_read(&ctrl->kref)); - - kref_get(&ctrl->kref); -} - -static void amp_ctrl_destroy(struct kref *kref) -{ - struct amp_ctrl *ctrl = container_of(kref, struct amp_ctrl, kref); - - BT_DBG("ctrl %p", ctrl); - - kfree(ctrl->assoc); - kfree(ctrl); -} - -int amp_ctrl_put(struct amp_ctrl *ctrl) -{ - BT_DBG("ctrl %p orig refcnt %d", ctrl, - kref_read(&ctrl->kref)); - - return kref_put(&ctrl->kref, &_ctrl_destroy); -} - -struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id) -{ - struct amp_ctrl *ctrl; - - ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); - if (!ctrl) - return NULL; - - kref_init(&ctrl->kref); - ctrl->id = id; - - mutex_lock(&mgr->amp_ctrls_lock); - list_add(&ctrl->list, &mgr->amp_ctrls); - mutex_unlock(&mgr->amp_ctrls_lock); - - BT_DBG("mgr %p ctrl %p", mgr, ctrl); - - return ctrl; -} - -void amp_ctrl_list_flush(struct amp_mgr *mgr) -{ - struct amp_ctrl *ctrl, *n; - - BT_DBG("mgr %p", mgr); - - mutex_lock(&mgr->amp_ctrls_lock); - list_for_each_entry_safe(ctrl, n, &mgr->amp_ctrls, list) { - list_del(&ctrl->list); - amp_ctrl_put(ctrl); - } - mutex_unlock(&mgr->amp_ctrls_lock); -} - -struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id) -{ - struct amp_ctrl *ctrl; - - BT_DBG("mgr %p id %u", mgr, id); - - mutex_lock(&mgr->amp_ctrls_lock); - list_for_each_entry(ctrl, &mgr->amp_ctrls, list) { - if (ctrl->id == id) { - amp_ctrl_get(ctrl); - mutex_unlock(&mgr->amp_ctrls_lock); - return ctrl; - } - } - mutex_unlock(&mgr->amp_ctrls_lock); - - return NULL; -} - -/* Physical Link interface */ -static u8 __next_handle(struct amp_mgr *mgr) -{ - if (++mgr->handle == 0) - mgr->handle = 1; - - return mgr->handle; -} - -struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, - u8 remote_id, bool out) -{ - bdaddr_t *dst = &mgr->l2cap_conn->hcon->dst; - struct hci_conn *hcon; - u8 role = out ? HCI_ROLE_MASTER : HCI_ROLE_SLAVE; - - hcon = hci_conn_add(hdev, AMP_LINK, dst, role, __next_handle(mgr)); - if (!hcon) - return NULL; - - BT_DBG("hcon %p dst %pMR", hcon, dst); - - hcon->state = BT_CONNECT; - hcon->attempt++; - hcon->remote_id = remote_id; - hcon->amp_mgr = amp_mgr_get(mgr); - - return hcon; -} - -/* AMP crypto key generation interface */ -static int hmac_sha256(u8 *key, u8 ksize, char *plaintext, u8 psize, u8 *output) -{ - struct crypto_shash *tfm; - struct shash_desc *shash; - int ret; - - if (!ksize) - return -EINVAL; - - tfm = crypto_alloc_shash("hmac(sha256)", 0, 0); - if (IS_ERR(tfm)) { - BT_DBG("crypto_alloc_ahash failed: err %ld", PTR_ERR(tfm)); - return PTR_ERR(tfm); - } - - ret = crypto_shash_setkey(tfm, key, ksize); - if (ret) { - BT_DBG("crypto_ahash_setkey failed: err %d", ret); - goto failed; - } - - shash = kzalloc(sizeof(*shash) + crypto_shash_descsize(tfm), - GFP_KERNEL); - if (!shash) { - ret = -ENOMEM; - goto failed; - } - - shash->tfm = tfm; - - ret = crypto_shash_digest(shash, plaintext, psize, output); - - kfree(shash); - -failed: - crypto_free_shash(tfm); - return ret; -} - -int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type) -{ - struct hci_dev *hdev = conn->hdev; - struct link_key *key; - u8 keybuf[HCI_AMP_LINK_KEY_SIZE]; - u8 gamp_key[HCI_AMP_LINK_KEY_SIZE]; - int err; - - if (!hci_conn_check_link_mode(conn)) - return -EACCES; - - BT_DBG("conn %p key_type %d", conn, conn->key_type); - - /* Legacy key */ - if (conn->key_type < 3) { - bt_dev_err(hdev, "legacy key type %u", conn->key_type); - return -EACCES; - } - - *type = conn->key_type; - *len = HCI_AMP_LINK_KEY_SIZE; - - key = hci_find_link_key(hdev, &conn->dst); - if (!key) { - BT_DBG("No Link key for conn %p dst %pMR", conn, &conn->dst); - return -EACCES; - } - - /* BR/EDR Link Key concatenated together with itself */ - memcpy(&keybuf[0], key->val, HCI_LINK_KEY_SIZE); - memcpy(&keybuf[HCI_LINK_KEY_SIZE], key->val, HCI_LINK_KEY_SIZE); - - /* Derive Generic AMP Link Key (gamp) */ - err = hmac_sha256(keybuf, HCI_AMP_LINK_KEY_SIZE, "gamp", 4, gamp_key); - if (err) { - bt_dev_err(hdev, "could not derive Generic AMP Key: err %d", err); - return err; - } - - if (conn->key_type == HCI_LK_DEBUG_COMBINATION) { - BT_DBG("Use Generic AMP Key (gamp)"); - memcpy(data, gamp_key, HCI_AMP_LINK_KEY_SIZE); - return err; - } - - /* Derive Dedicated AMP Link Key: "802b" is 802.11 PAL keyID */ - return hmac_sha256(gamp_key, HCI_AMP_LINK_KEY_SIZE, "802b", 4, data); -} - -static void read_local_amp_assoc_complete(struct hci_dev *hdev, u8 status, - u16 opcode, struct sk_buff *skb) -{ - struct hci_rp_read_local_amp_assoc *rp = (void *)skb->data; - struct amp_assoc *assoc = &hdev->loc_assoc; - size_t rem_len, frag_len; - - BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - - if (rp->status) - goto send_rsp; - - frag_len = skb->len - sizeof(*rp); - rem_len = __le16_to_cpu(rp->rem_len); - - if (rem_len > frag_len) { - BT_DBG("frag_len %zu rem_len %zu", frag_len, rem_len); - - memcpy(assoc->data + assoc->offset, rp->frag, frag_len); - assoc->offset += frag_len; - - /* Read other fragments */ - amp_read_loc_assoc_frag(hdev, rp->phy_handle); - - return; - } - - memcpy(assoc->data + assoc->offset, rp->frag, rem_len); - assoc->len = assoc->offset + rem_len; - assoc->offset = 0; - -send_rsp: - /* Send A2MP Rsp when all fragments are received */ - a2mp_send_getampassoc_rsp(hdev, rp->status); - a2mp_send_create_phy_link_req(hdev, rp->status); -} - -void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle) -{ - struct hci_cp_read_local_amp_assoc cp; - struct amp_assoc *loc_assoc = &hdev->loc_assoc; - struct hci_request req; - int err; - - BT_DBG("%s handle %u", hdev->name, phy_handle); - - cp.phy_handle = phy_handle; - cp.max_len = cpu_to_le16(hdev->amp_assoc_size); - cp.len_so_far = cpu_to_le16(loc_assoc->offset); - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); - err = hci_req_run_skb(&req, read_local_amp_assoc_complete); - if (err < 0) - a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); -} - -void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr) -{ - struct hci_cp_read_local_amp_assoc cp; - struct hci_request req; - int err; - - memset(&hdev->loc_assoc, 0, sizeof(struct amp_assoc)); - memset(&cp, 0, sizeof(cp)); - - cp.max_len = cpu_to_le16(hdev->amp_assoc_size); - - set_bit(READ_LOC_AMP_ASSOC, &mgr->state); - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); - err = hci_req_run_skb(&req, read_local_amp_assoc_complete); - if (err < 0) - a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); -} - -void amp_read_loc_assoc_final_data(struct hci_dev *hdev, - struct hci_conn *hcon) -{ - struct hci_cp_read_local_amp_assoc cp; - struct amp_mgr *mgr = hcon->amp_mgr; - struct hci_request req; - int err; - - if (!mgr) - return; - - cp.phy_handle = hcon->handle; - cp.len_so_far = cpu_to_le16(0); - cp.max_len = cpu_to_le16(hdev->amp_assoc_size); - - set_bit(READ_LOC_AMP_ASSOC_FINAL, &mgr->state); - - /* Read Local AMP Assoc final link information data */ - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); - err = hci_req_run_skb(&req, read_local_amp_assoc_complete); - if (err < 0) - a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); -} - -static void write_remote_amp_assoc_complete(struct hci_dev *hdev, u8 status, - u16 opcode, struct sk_buff *skb) -{ - struct hci_rp_write_remote_amp_assoc *rp = (void *)skb->data; - - BT_DBG("%s status 0x%2.2x phy_handle 0x%2.2x", - hdev->name, rp->status, rp->phy_handle); - - if (rp->status) - return; - - amp_write_rem_assoc_continue(hdev, rp->phy_handle); -} - -/* Write AMP Assoc data fragments, returns true with last fragment written*/ -static bool amp_write_rem_assoc_frag(struct hci_dev *hdev, - struct hci_conn *hcon) -{ - struct hci_cp_write_remote_amp_assoc *cp; - struct amp_mgr *mgr = hcon->amp_mgr; - struct amp_ctrl *ctrl; - struct hci_request req; - u16 frag_len, len; - - ctrl = amp_ctrl_lookup(mgr, hcon->remote_id); - if (!ctrl) - return false; - - if (!ctrl->assoc_rem_len) { - BT_DBG("all fragments are written"); - ctrl->assoc_rem_len = ctrl->assoc_len; - ctrl->assoc_len_so_far = 0; - - amp_ctrl_put(ctrl); - return true; - } - - frag_len = min_t(u16, 248, ctrl->assoc_rem_len); - len = frag_len + sizeof(*cp); - - cp = kzalloc(len, GFP_KERNEL); - if (!cp) { - amp_ctrl_put(ctrl); - return false; - } - - BT_DBG("hcon %p ctrl %p frag_len %u assoc_len %u rem_len %u", - hcon, ctrl, frag_len, ctrl->assoc_len, ctrl->assoc_rem_len); - - cp->phy_handle = hcon->handle; - cp->len_so_far = cpu_to_le16(ctrl->assoc_len_so_far); - cp->rem_len = cpu_to_le16(ctrl->assoc_rem_len); - memcpy(cp->frag, ctrl->assoc, frag_len); - - ctrl->assoc_len_so_far += frag_len; - ctrl->assoc_rem_len -= frag_len; - - amp_ctrl_put(ctrl); - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_WRITE_REMOTE_AMP_ASSOC, len, cp); - hci_req_run_skb(&req, write_remote_amp_assoc_complete); - - kfree(cp); - - return false; -} - -void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle) -{ - struct hci_conn *hcon; - - BT_DBG("%s phy handle 0x%2.2x", hdev->name, handle); - - hcon = hci_conn_hash_lookup_handle(hdev, handle); - if (!hcon) - return; - - /* Send A2MP create phylink rsp when all fragments are written */ - if (amp_write_rem_assoc_frag(hdev, hcon)) - a2mp_send_create_phy_link_rsp(hdev, 0); -} - -void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle) -{ - struct hci_conn *hcon; - - BT_DBG("%s phy handle 0x%2.2x", hdev->name, handle); - - hcon = hci_conn_hash_lookup_handle(hdev, handle); - if (!hcon) - return; - - BT_DBG("%s phy handle 0x%2.2x hcon %p", hdev->name, handle, hcon); - - amp_write_rem_assoc_frag(hdev, hcon); -} - -static void create_phylink_complete(struct hci_dev *hdev, u8 status, - u16 opcode) -{ - struct hci_cp_create_phy_link *cp; - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_PHY_LINK); - if (!cp) - return; - - hci_dev_lock(hdev); - - if (status) { - struct hci_conn *hcon; - - hcon = hci_conn_hash_lookup_handle(hdev, cp->phy_handle); - if (hcon) - hci_conn_del(hcon); - } else { - amp_write_remote_assoc(hdev, cp->phy_handle); - } - - hci_dev_unlock(hdev); -} - -void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon) -{ - struct hci_cp_create_phy_link cp; - struct hci_request req; - - cp.phy_handle = hcon->handle; - - BT_DBG("%s hcon %p phy handle 0x%2.2x", hdev->name, hcon, - hcon->handle); - - if (phylink_gen_key(mgr->l2cap_conn->hcon, cp.key, &cp.key_len, - &cp.key_type)) { - BT_DBG("Cannot create link key"); - return; - } - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_CREATE_PHY_LINK, sizeof(cp), &cp); - hci_req_run(&req, create_phylink_complete); -} - -static void accept_phylink_complete(struct hci_dev *hdev, u8 status, - u16 opcode) -{ - struct hci_cp_accept_phy_link *cp; - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - if (status) - return; - - cp = hci_sent_cmd_data(hdev, HCI_OP_ACCEPT_PHY_LINK); - if (!cp) - return; - - amp_write_remote_assoc(hdev, cp->phy_handle); -} - -void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon) -{ - struct hci_cp_accept_phy_link cp; - struct hci_request req; - - cp.phy_handle = hcon->handle; - - BT_DBG("%s hcon %p phy handle 0x%2.2x", hdev->name, hcon, - hcon->handle); - - if (phylink_gen_key(mgr->l2cap_conn->hcon, cp.key, &cp.key_len, - &cp.key_type)) { - BT_DBG("Cannot create link key"); - return; - } - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp); - hci_req_run(&req, accept_phylink_complete); -} - -void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon) -{ - struct hci_dev *bredr_hdev = hci_dev_hold(bredr_hcon->hdev); - struct amp_mgr *mgr = hs_hcon->amp_mgr; - struct l2cap_chan *bredr_chan; - - BT_DBG("bredr_hcon %p hs_hcon %p mgr %p", bredr_hcon, hs_hcon, mgr); - - if (!bredr_hdev || !mgr || !mgr->bredr_chan) - return; - - bredr_chan = mgr->bredr_chan; - - l2cap_chan_lock(bredr_chan); - - set_bit(FLAG_EFS_ENABLE, &bredr_chan->flags); - bredr_chan->remote_amp_id = hs_hcon->remote_id; - bredr_chan->local_amp_id = hs_hcon->hdev->id; - bredr_chan->hs_hcon = hs_hcon; - bredr_chan->conn->mtu = hs_hcon->hdev->block_mtu; - - __l2cap_physical_cfm(bredr_chan, 0); - - l2cap_chan_unlock(bredr_chan); - - hci_dev_put(bredr_hdev); -} - -void amp_create_logical_link(struct l2cap_chan *chan) -{ - struct hci_conn *hs_hcon = chan->hs_hcon; - struct hci_cp_create_accept_logical_link cp; - struct hci_dev *hdev; - - BT_DBG("chan %p hs_hcon %p dst %pMR", chan, hs_hcon, - &chan->conn->hcon->dst); - - if (!hs_hcon) - return; - - hdev = hci_dev_hold(chan->hs_hcon->hdev); - if (!hdev) - return; - - cp.phy_handle = hs_hcon->handle; - - cp.tx_flow_spec.id = chan->local_id; - cp.tx_flow_spec.stype = chan->local_stype; - cp.tx_flow_spec.msdu = cpu_to_le16(chan->local_msdu); - cp.tx_flow_spec.sdu_itime = cpu_to_le32(chan->local_sdu_itime); - cp.tx_flow_spec.acc_lat = cpu_to_le32(chan->local_acc_lat); - cp.tx_flow_spec.flush_to = cpu_to_le32(chan->local_flush_to); - - cp.rx_flow_spec.id = chan->remote_id; - cp.rx_flow_spec.stype = chan->remote_stype; - cp.rx_flow_spec.msdu = cpu_to_le16(chan->remote_msdu); - cp.rx_flow_spec.sdu_itime = cpu_to_le32(chan->remote_sdu_itime); - cp.rx_flow_spec.acc_lat = cpu_to_le32(chan->remote_acc_lat); - cp.rx_flow_spec.flush_to = cpu_to_le32(chan->remote_flush_to); - - if (hs_hcon->out) - hci_send_cmd(hdev, HCI_OP_CREATE_LOGICAL_LINK, sizeof(cp), - &cp); - else - hci_send_cmd(hdev, HCI_OP_ACCEPT_LOGICAL_LINK, sizeof(cp), - &cp); - - hci_dev_put(hdev); -} - -void amp_disconnect_logical_link(struct hci_chan *hchan) -{ - struct hci_conn *hcon = hchan->conn; - struct hci_cp_disconn_logical_link cp; - - if (hcon->state != BT_CONNECTED) { - BT_DBG("hchan %p not connected", hchan); - return; - } - - cp.log_handle = cpu_to_le16(hchan->handle); - hci_send_cmd(hcon->hdev, HCI_OP_DISCONN_LOGICAL_LINK, sizeof(cp), &cp); -} - -void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason) -{ - BT_DBG("hchan %p", hchan); - - hci_chan_del(hchan); -} diff --git a/net/bluetooth/amp.h b/net/bluetooth/amp.h deleted file mode 100644 index 97c87abd129f..000000000000 --- a/net/bluetooth/amp.h +++ /dev/null @@ -1,60 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#ifndef __AMP_H -#define __AMP_H - -struct amp_ctrl { - struct list_head list; - struct kref kref; - __u8 id; - __u16 assoc_len_so_far; - __u16 assoc_rem_len; - __u16 assoc_len; - __u8 *assoc; -}; - -int amp_ctrl_put(struct amp_ctrl *ctrl); -void amp_ctrl_get(struct amp_ctrl *ctrl); -struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id); -struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id); -void amp_ctrl_list_flush(struct amp_mgr *mgr); - -struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, - u8 remote_id, bool out); - -int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type); - -void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle); -void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr); -void amp_read_loc_assoc_final_data(struct hci_dev *hdev, - struct hci_conn *hcon); -void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon); -void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon); - -#if IS_ENABLED(CONFIG_BT_HS) -void amp_create_logical_link(struct l2cap_chan *chan); -void amp_disconnect_logical_link(struct hci_chan *hchan); -#else -static inline void amp_create_logical_link(struct l2cap_chan *chan) -{ -} - -static inline void amp_disconnect_logical_link(struct hci_chan *hchan) -{ -} -#endif - -void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle); -void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle); -void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon); -void amp_create_logical_link(struct l2cap_chan *chan); -void amp_disconnect_logical_link(struct hci_chan *hchan); -void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason); - -#endif /* __AMP_H */ diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 5a6a49885ab6..ec45f77fce21 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -385,7 +385,8 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb) case BNEP_COMPRESSED_DST_ONLY: __skb_put_data(nskb, skb_mac_header(skb), ETH_ALEN); - __skb_put_data(nskb, s->eh.h_source, ETH_ALEN + 2); + __skb_put_data(nskb, s->eh.h_source, ETH_ALEN); + put_unaligned(s->eh.h_proto, (__be16 *)__skb_put(nskb, 2)); break; case BNEP_GENERAL: @@ -549,7 +550,7 @@ static struct device *bnep_get_device(struct bnep_session *session) return &conn->hcon->dev; } -static struct device_type bnep_type = { +static const struct device_type bnep_type = { .name = "bluetooth", }; diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c index 9214189279e8..1bc51e2b05a3 100644 --- a/net/bluetooth/eir.c +++ b/net/bluetooth/eir.c @@ -13,48 +13,33 @@ #define PNP_INFO_SVCLASS_ID 0x1200 -static u8 eir_append_name(u8 *eir, u16 eir_len, u8 type, u8 *data, u8 data_len) -{ - u8 name[HCI_MAX_SHORT_NAME_LENGTH + 1]; - - /* If data is already NULL terminated just pass it directly */ - if (data[data_len - 1] == '\0') - return eir_append_data(eir, eir_len, type, data, data_len); - - memcpy(name, data, HCI_MAX_SHORT_NAME_LENGTH); - name[HCI_MAX_SHORT_NAME_LENGTH] = '\0'; - - return eir_append_data(eir, eir_len, type, name, sizeof(name)); -} - u8 eir_append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len) { size_t short_len; size_t complete_len; - /* no space left for name (+ NULL + type + len) */ - if ((max_adv_len(hdev) - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3) + /* no space left for name (+ type + len) */ + if ((max_adv_len(hdev) - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 2) return ad_len; /* use complete name if present and fits */ complete_len = strnlen(hdev->dev_name, sizeof(hdev->dev_name)); if (complete_len && complete_len <= HCI_MAX_SHORT_NAME_LENGTH) - return eir_append_name(ptr, ad_len, EIR_NAME_COMPLETE, - hdev->dev_name, complete_len + 1); + return eir_append_data(ptr, ad_len, EIR_NAME_COMPLETE, + hdev->dev_name, complete_len); /* use short name if present */ short_len = strnlen(hdev->short_name, sizeof(hdev->short_name)); if (short_len) - return eir_append_name(ptr, ad_len, EIR_NAME_SHORT, + return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, hdev->short_name, - short_len == HCI_MAX_SHORT_NAME_LENGTH ? - short_len : short_len + 1); + short_len); /* use shortened full name if present, we already know that name * is longer then HCI_MAX_SHORT_NAME_LENGTH */ if (complete_len) - return eir_append_name(ptr, ad_len, EIR_NAME_SHORT, + return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, hdev->dev_name, HCI_MAX_SHORT_NAME_LENGTH); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index a41d2693f4d8..3ad74f76983b 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1,7 +1,7 @@ /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. - Copyright 2023 NXP + Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> @@ -36,7 +36,6 @@ #include "hci_request.h" #include "smp.h" -#include "a2mp.h" #include "eir.h" struct sco_param { @@ -69,7 +68,7 @@ static const struct sco_param esco_param_msbc[] = { }; /* This function requires the caller holds hdev->lock */ -static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) +void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) { struct hci_conn_params *params; struct hci_dev *hdev = conn->hdev; @@ -179,64 +178,6 @@ static void hci_conn_cleanup(struct hci_conn *conn) hci_dev_put(hdev); } -static void hci_acl_create_connection(struct hci_conn *conn) -{ - struct hci_dev *hdev = conn->hdev; - struct inquiry_entry *ie; - struct hci_cp_create_conn cp; - - BT_DBG("hcon %p", conn); - - /* Many controllers disallow HCI Create Connection while it is doing - * HCI Inquiry. So we cancel the Inquiry first before issuing HCI Create - * Connection. This may cause the MGMT discovering state to become false - * without user space's request but it is okay since the MGMT Discovery - * APIs do not promise that discovery should be done forever. Instead, - * the user space monitors the status of MGMT discovering and it may - * request for discovery again when this flag becomes false. - */ - if (test_bit(HCI_INQUIRY, &hdev->flags)) { - /* Put this connection to "pending" state so that it will be - * executed after the inquiry cancel command complete event. - */ - conn->state = BT_CONNECT2; - hci_send_cmd(hdev, HCI_OP_INQUIRY_CANCEL, 0, NULL); - return; - } - - conn->state = BT_CONNECT; - conn->out = true; - conn->role = HCI_ROLE_MASTER; - - conn->attempt++; - - conn->link_policy = hdev->link_policy; - - memset(&cp, 0, sizeof(cp)); - bacpy(&cp.bdaddr, &conn->dst); - cp.pscan_rep_mode = 0x02; - - ie = hci_inquiry_cache_lookup(hdev, &conn->dst); - if (ie) { - if (inquiry_entry_age(ie) <= INQUIRY_ENTRY_AGE_MAX) { - cp.pscan_rep_mode = ie->data.pscan_rep_mode; - cp.pscan_mode = ie->data.pscan_mode; - cp.clock_offset = ie->data.clock_offset | - cpu_to_le16(0x8000); - } - - memcpy(conn->dev_class, ie->data.dev_class, 3); - } - - cp.pkt_type = cpu_to_le16(conn->pkt_type); - if (lmp_rswitch_capable(hdev) && !(hdev->link_mode & HCI_LM_MASTER)) - cp.role_switch = 0x01; - else - cp.role_switch = 0x00; - - hci_send_cmd(hdev, HCI_OP_CREATE_CONN, sizeof(cp), &cp); -} - int hci_disconnect(struct hci_conn *conn, __u8 reason) { BT_DBG("hcon %p", conn); @@ -1175,9 +1116,6 @@ void hci_conn_del(struct hci_conn *conn) } } - if (conn->amp_mgr) - amp_mgr_put(conn->amp_mgr); - skb_queue_purge(&conn->data_q); /* Remove the connection from the list and cleanup its remaining @@ -1186,6 +1124,9 @@ void hci_conn_del(struct hci_conn *conn) * rest of hci_conn_del. */ hci_conn_cleanup(conn); + + /* Dequeue callbacks using connection pointer as data */ + hci_cmd_sync_dequeue(hdev, NULL, conn, NULL); } struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) @@ -1320,53 +1261,6 @@ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) return 0; } -static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) -{ - struct hci_conn *conn; - u16 handle = PTR_UINT(data); - - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return; - - bt_dev_dbg(hdev, "err %d", err); - - hci_dev_lock(hdev); - - if (!err) { - hci_connect_le_scan_cleanup(conn, 0x00); - goto done; - } - - /* Check if connection is still pending */ - if (conn != hci_lookup_le_connect(hdev)) - goto done; - - /* Flush to make sure we send create conn cancel command if needed */ - flush_delayed_work(&conn->le_conn_timeout); - hci_conn_failed(conn, bt_status(err)); - -done: - hci_dev_unlock(hdev); -} - -static int hci_connect_le_sync(struct hci_dev *hdev, void *data) -{ - struct hci_conn *conn; - u16 handle = PTR_UINT(data); - - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return 0; - - bt_dev_dbg(hdev, "conn %p", conn); - - clear_bit(HCI_CONN_SCANNING, &conn->flags); - conn->state = BT_CONNECT; - - return hci_le_create_conn_sync(hdev, conn); -} - struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, u16 conn_timeout, u8 role) @@ -1433,9 +1327,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, conn->sec_level = BT_SECURITY_LOW; conn->conn_timeout = conn_timeout; - err = hci_cmd_sync_queue(hdev, hci_connect_le_sync, - UINT_PTR(conn->handle), - create_le_conn_complete); + err = hci_connect_le_sync(hdev, conn); if (err) { hci_conn_del(conn); return ERR_PTR(err); @@ -1669,7 +1561,7 @@ done: struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, - enum conn_reasons conn_reason) + enum conn_reasons conn_reason, u16 timeout) { struct hci_conn *acl; @@ -1700,10 +1592,18 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, acl->conn_reason = conn_reason; if (acl->state == BT_OPEN || acl->state == BT_CLOSED) { + int err; + acl->sec_level = BT_SECURITY_LOW; acl->pending_sec_level = sec_level; acl->auth_type = auth_type; - hci_acl_create_connection(acl); + acl->conn_timeout = timeout; + + err = hci_connect_acl_sync(hdev, acl); + if (err) { + hci_conn_del(acl); + return ERR_PTR(err); + } } return acl; @@ -1738,14 +1638,15 @@ static struct hci_link *hci_conn_link(struct hci_conn *parent, } struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, - __u16 setting, struct bt_codec *codec) + __u16 setting, struct bt_codec *codec, + u16 timeout) { struct hci_conn *acl; struct hci_conn *sco; struct hci_link *link; acl = hci_connect_acl(hdev, dst, BT_SECURITY_LOW, HCI_AT_NO_BONDING, - CONN_REASON_SCO_CONNECT); + CONN_REASON_SCO_CONNECT, timeout); if (IS_ERR(acl)) return acl; @@ -2156,18 +2057,31 @@ static int create_pa_sync(struct hci_dev *hdev, void *data) return hci_update_passive_scan_sync(hdev); } -int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, - __u8 sid, struct bt_iso_qos *qos) +struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, + __u8 dst_type, __u8 sid, + struct bt_iso_qos *qos) { struct hci_cp_le_pa_create_sync *cp; + struct hci_conn *conn; + int err; if (hci_dev_test_and_set_flag(hdev, HCI_PA_SYNC)) - return -EBUSY; + return ERR_PTR(-EBUSY); + + conn = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_SLAVE); + if (!conn) + return ERR_PTR(-ENOMEM); + + conn->iso_qos = *qos; + conn->state = BT_LISTEN; + + hci_conn_hold(conn); cp = kzalloc(sizeof(*cp), GFP_KERNEL); if (!cp) { hci_dev_clear_flag(hdev, HCI_PA_SYNC); - return -ENOMEM; + hci_conn_drop(conn); + return ERR_PTR(-ENOMEM); } cp->options = qos->bcast.options; @@ -2179,7 +2093,14 @@ int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, cp->sync_cte_type = qos->bcast.sync_cte_type; /* Queue start pa_create_sync and scan */ - return hci_cmd_sync_queue(hdev, create_pa_sync, cp, create_pa_complete); + err = hci_cmd_sync_queue(hdev, create_pa_sync, cp, create_pa_complete); + if (err < 0) { + hci_conn_drop(conn); + kfree(cp); + return ERR_PTR(err); + } + + return conn; } int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, @@ -2647,22 +2568,6 @@ void hci_conn_hash_flush(struct hci_dev *hdev) } } -/* Check pending connect attempts */ -void hci_conn_check_pending(struct hci_dev *hdev) -{ - struct hci_conn *conn; - - BT_DBG("hdev %s", hdev->name); - - hci_dev_lock(hdev); - - conn = hci_conn_hash_lookup_state(hdev, ACL_LINK, BT_CONNECT2); - if (conn) - hci_acl_create_connection(conn); - - hci_dev_unlock(hdev); -} - static u32 get_link_mode(struct hci_conn *conn) { u32 link_mode = 0; @@ -2978,12 +2883,10 @@ u32 hci_conn_get_phy(struct hci_conn *conn) static int abort_conn_sync(struct hci_dev *hdev, void *data) { - struct hci_conn *conn; - u16 handle = PTR_UINT(data); + struct hci_conn *conn = data; - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return 0; + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; return hci_abort_conn_sync(hdev, conn, conn->abort_reason); } @@ -3011,14 +2914,17 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) */ if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) { switch (hci_skb_event(hdev->sent_cmd)) { + case HCI_EV_CONN_COMPLETE: case HCI_EV_LE_CONN_COMPLETE: case HCI_EV_LE_ENHANCED_CONN_COMPLETE: case HCI_EVT_LE_CIS_ESTABLISHED: - hci_cmd_sync_cancel(hdev, -ECANCELED); + hci_cmd_sync_cancel(hdev, ECANCELED); break; } + /* Cancel connect attempt if still queued/pending */ + } else if (!hci_cancel_connect_sync(hdev, conn)) { + return 0; } - return hci_cmd_sync_queue(hdev, abort_conn_sync, UINT_PTR(conn->handle), - NULL); + return hci_cmd_sync_queue_once(hdev, abort_conn_sync, conn, NULL); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2821a42cefdc..1690ae57a09d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -908,7 +908,7 @@ int hci_get_dev_info(void __user *arg) else flags = hdev->flags; - strcpy(di.name, hdev->name); + strscpy(di.name, hdev->name, sizeof(di.name)); di.bdaddr = hdev->bdaddr; di.type = (hdev->bus & 0x0f) | ((hdev->dev_type & 0x03) << 4); di.flags = flags; @@ -940,20 +940,51 @@ int hci_get_dev_info(void __user *arg) /* ---- Interface to HCI drivers ---- */ +static int hci_dev_do_poweroff(struct hci_dev *hdev) +{ + int err; + + BT_DBG("%s %p", hdev->name, hdev); + + hci_req_sync_lock(hdev); + + err = hci_set_powered_sync(hdev, false); + + hci_req_sync_unlock(hdev); + + return err; +} + static int hci_rfkill_set_block(void *data, bool blocked) { struct hci_dev *hdev = data; + int err; BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; + if (blocked == hci_dev_test_flag(hdev, HCI_RFKILLED)) + return 0; + if (blocked) { hci_dev_set_flag(hdev, HCI_RFKILLED); + if (!hci_dev_test_flag(hdev, HCI_SETUP) && - !hci_dev_test_flag(hdev, HCI_CONFIG)) - hci_dev_do_close(hdev); + !hci_dev_test_flag(hdev, HCI_CONFIG)) { + err = hci_dev_do_poweroff(hdev); + if (err) { + bt_dev_err(hdev, "Error when powering off device on rfkill (%d)", + err); + + /* Make sure the device is still closed even if + * anything during power off sequence (eg. + * disconnecting devices) failed. + */ + hci_dev_do_close(hdev); + } + } } else { hci_dev_clear_flag(hdev, HCI_RFKILLED); } @@ -1491,11 +1522,12 @@ static void hci_cmd_timeout(struct work_struct *work) struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_timer.work); - if (hdev->sent_cmd) { - struct hci_command_hdr *sent = (void *) hdev->sent_cmd->data; - u16 opcode = __le16_to_cpu(sent->opcode); + if (hdev->req_skb) { + u16 opcode = hci_skb_opcode(hdev->req_skb); bt_dev_err(hdev, "command 0x%4.4x tx timeout", opcode); + + hci_cmd_sync_cancel_sync(hdev, ETIMEDOUT); } else { bt_dev_err(hdev, "command tx timeout"); } @@ -2608,10 +2640,11 @@ int hci_register_dev(struct hci_dev *hdev) */ switch (hdev->dev_type) { case HCI_PRIMARY: - id = ida_simple_get(&hci_index_ida, 0, HCI_MAX_ID, GFP_KERNEL); + id = ida_alloc_max(&hci_index_ida, HCI_MAX_ID - 1, GFP_KERNEL); break; case HCI_AMP: - id = ida_simple_get(&hci_index_ida, 1, HCI_MAX_ID, GFP_KERNEL); + id = ida_alloc_range(&hci_index_ida, 1, HCI_MAX_ID - 1, + GFP_KERNEL); break; default: return -EINVAL; @@ -2710,7 +2743,7 @@ err_wqueue: destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); err: - ida_simple_remove(&hci_index_ida, hdev->id); + ida_free(&hci_index_ida, hdev->id); return error; } @@ -2793,8 +2826,9 @@ void hci_release_dev(struct hci_dev *hdev) hci_dev_unlock(hdev); ida_destroy(&hdev->unset_handle_ida); - ida_simple_remove(&hci_index_ida, hdev->id); + ida_free(&hci_index_ida, hdev->id); kfree_skb(hdev->sent_cmd); + kfree_skb(hdev->req_skb); kfree_skb(hdev->recv_event); kfree(hdev); } @@ -2826,6 +2860,23 @@ int hci_unregister_suspend_notifier(struct hci_dev *hdev) return ret; } +/* Cancel ongoing command synchronously: + * + * - Cancel command timer + * - Reset command counter + * - Cancel command request + */ +static void hci_cancel_cmd_sync(struct hci_dev *hdev, int err) +{ + bt_dev_dbg(hdev, "err 0x%2.2x", err); + + cancel_delayed_work_sync(&hdev->cmd_timer); + cancel_delayed_work_sync(&hdev->ncmd_timer); + atomic_set(&hdev->cmd_cnt, 1); + + hci_cmd_sync_cancel_sync(hdev, -err); +} + /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) { @@ -2843,7 +2894,7 @@ int hci_suspend_dev(struct hci_dev *hdev) return 0; /* Cancel potentially blocking sync operation before suspend */ - __hci_cmd_sync_cancel(hdev, -EHOSTDOWN); + hci_cancel_cmd_sync(hdev, -EHOSTDOWN); hci_req_sync_lock(hdev); ret = hci_suspend_sync(hdev); @@ -3107,21 +3158,33 @@ int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, EXPORT_SYMBOL(__hci_cmd_send); /* Get data from the previously sent command */ -void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) +static void *hci_cmd_data(struct sk_buff *skb, __u16 opcode) { struct hci_command_hdr *hdr; - if (!hdev->sent_cmd) + if (!skb || skb->len < HCI_COMMAND_HDR_SIZE) return NULL; - hdr = (void *) hdev->sent_cmd->data; + hdr = (void *)skb->data; if (hdr->opcode != cpu_to_le16(opcode)) return NULL; - BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); + return skb->data + HCI_COMMAND_HDR_SIZE; +} - return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE; +/* Get data from the previously sent command */ +void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) +{ + void *data; + + /* Check if opcode matches last sent command */ + data = hci_cmd_data(hdev->sent_cmd, opcode); + if (!data) + /* Check if opcode matches last request */ + data = hci_cmd_data(hdev->req_skb, opcode); + + return data; } /* Get data from last received event */ @@ -4022,17 +4085,19 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, if (!status && !hci_req_is_complete(hdev)) return; + skb = hdev->req_skb; + /* If this was the last command in a request the complete - * callback would be found in hdev->sent_cmd instead of the + * callback would be found in hdev->req_skb instead of the * command queue (hdev->cmd_q). */ - if (bt_cb(hdev->sent_cmd)->hci.req_flags & HCI_REQ_SKB) { - *req_complete_skb = bt_cb(hdev->sent_cmd)->hci.req_complete_skb; + if (skb && bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) { + *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; return; } - if (bt_cb(hdev->sent_cmd)->hci.req_complete) { - *req_complete = bt_cb(hdev->sent_cmd)->hci.req_complete; + if (skb && bt_cb(skb)->hci.req_complete) { + *req_complete = bt_cb(skb)->hci.req_complete; return; } @@ -4128,6 +4193,36 @@ static void hci_rx_work(struct work_struct *work) } } +static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) +{ + int err; + + bt_dev_dbg(hdev, "skb %p", skb); + + kfree_skb(hdev->sent_cmd); + + hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); + if (!hdev->sent_cmd) { + skb_queue_head(&hdev->cmd_q, skb); + queue_work(hdev->workqueue, &hdev->cmd_work); + return; + } + + err = hci_send_frame(hdev, skb); + if (err < 0) { + hci_cmd_sync_cancel_sync(hdev, err); + return; + } + + if (hci_req_status_pend(hdev) && + !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) { + kfree_skb(hdev->req_skb); + hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); + } + + atomic_dec(&hdev->cmd_cnt); +} + static void hci_cmd_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_work); @@ -4142,30 +4237,15 @@ static void hci_cmd_work(struct work_struct *work) if (!skb) return; - kfree_skb(hdev->sent_cmd); - - hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); - if (hdev->sent_cmd) { - int res; - if (hci_req_status_pend(hdev)) - hci_dev_set_flag(hdev, HCI_CMD_PENDING); - atomic_dec(&hdev->cmd_cnt); + hci_send_cmd_sync(hdev, skb); - res = hci_send_frame(hdev, skb); - if (res < 0) - __hci_cmd_sync_cancel(hdev, -res); - - rcu_read_lock(); - if (test_bit(HCI_RESET, &hdev->flags) || - hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) - cancel_delayed_work(&hdev->cmd_timer); - else - queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, - HCI_CMD_TIMEOUT); - rcu_read_unlock(); - } else { - skb_queue_head(&hdev->cmd_q, skb); - queue_work(hdev->workqueue, &hdev->cmd_work); - } + rcu_read_lock(); + if (test_bit(HCI_RESET, &hdev->flags) || + hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) + cancel_delayed_work(&hdev->cmd_timer); + else + queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, + HCI_CMD_TIMEOUT); + rcu_read_unlock(); } } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 2a5f5a7d2412..4ae224824012 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -36,8 +36,6 @@ #include "hci_request.h" #include "hci_debugfs.h" #include "hci_codec.h" -#include "a2mp.h" -#include "amp.h" #include "smp.h" #include "msft.h" #include "eir.h" @@ -95,11 +93,11 @@ static u8 hci_cc_inquiry_cancel(struct hci_dev *hdev, void *data, /* It is possible that we receive Inquiry Complete event right * before we receive Inquiry Cancel Command Complete event, in * which case the latter event should have status of Command - * Disallowed (0x0c). This should not be treated as error, since + * Disallowed. This should not be treated as error, since * we actually achieve what Inquiry Cancel wants to achieve, * which is to end the last Inquiry session. */ - if (rp->status == 0x0c && !test_bit(HCI_INQUIRY, &hdev->flags)) { + if (rp->status == HCI_ERROR_COMMAND_DISALLOWED && !test_bit(HCI_INQUIRY, &hdev->flags)) { bt_dev_warn(hdev, "Ignoring error of Inquiry Cancel command"); rp->status = 0x00; } @@ -120,8 +118,6 @@ static u8 hci_cc_inquiry_cancel(struct hci_dev *hdev, void *data, hci_discovery_set_state(hdev, DISCOVERY_STOPPED); hci_dev_unlock(hdev); - hci_conn_check_pending(hdev); - return rp->status; } @@ -152,8 +148,6 @@ static u8 hci_cc_exit_periodic_inq(struct hci_dev *hdev, void *data, hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); - hci_conn_check_pending(hdev); - return rp->status; } @@ -2314,10 +2308,8 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) { bt_dev_dbg(hdev, "status 0x%2.2x", status); - if (status) { - hci_conn_check_pending(hdev); + if (status) return; - } if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY)) set_bit(HCI_INQUIRY, &hdev->flags); @@ -2342,12 +2334,9 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) if (status) { if (conn && conn->state == BT_CONNECT) { - if (status != 0x0c || conn->attempt > 2) { - conn->state = BT_CLOSED; - hci_connect_cfm(conn, status); - hci_conn_del(conn); - } else - conn->state = BT_CONNECT2; + conn->state = BT_CLOSED; + hci_connect_cfm(conn, status); + hci_conn_del(conn); } } else { if (!conn) { @@ -2526,9 +2515,7 @@ static void hci_check_pending_name(struct hci_dev *hdev, struct hci_conn *conn, * Only those in BT_CONFIG or BT_CONNECTED states can be * considered connected. */ - if (conn && - (conn->state == BT_CONFIG || conn->state == BT_CONNECTED) && - !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + if (conn && (conn->state == BT_CONFIG || conn->state == BT_CONNECTED)) mgmt_device_connected(hdev, conn, name, name_len); if (discov->state == DISCOVERY_STOPPED) @@ -3039,8 +3026,6 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - hci_conn_check_pending(hdev); - if (!test_and_clear_bit(HCI_INQUIRY, &hdev->flags)) return; @@ -3262,8 +3247,6 @@ done: unlock: hci_dev_unlock(hdev); - - hci_conn_check_pending(hdev); } static void hci_reject_conn(struct hci_dev *hdev, bdaddr_t *bdaddr) @@ -3556,8 +3539,6 @@ static void hci_remote_name_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - hci_conn_check_pending(hdev); - hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); @@ -3660,7 +3641,8 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, * controller really supports it. If it doesn't, assume * the default size (16). */ - if (!(hdev->commands[20] & 0x10)) { + if (!(hdev->commands[20] & 0x10) || + test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) { conn->enc_key_size = HCI_LINK_KEY_SIZE; goto notify; } @@ -3762,8 +3744,9 @@ static void hci_remote_features_evt(struct hci_dev *hdev, void *data, bacpy(&cp.bdaddr, &conn->dst); 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)) + } else { mgmt_device_connected(hdev, conn, NULL, 0); + } if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; @@ -3936,6 +3919,11 @@ static u8 hci_cc_le_setup_iso_path(struct hci_dev *hdev, void *data, * last. */ hci_connect_cfm(conn, rp->status); + + /* Notify device connected in case it is a BIG Sync */ + if (!rp->status && test_bit(HCI_CONN_BIG_SYNC, &conn->flags)) + mgmt_device_connected(hdev, conn, NULL, 0); + break; } @@ -4381,7 +4369,7 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, void *data, * (since for this kind of commands there will not be a command * complete event). */ - if (ev->status || (hdev->sent_cmd && !hci_skb_event(hdev->sent_cmd))) { + if (ev->status || (hdev->req_skb && !hci_skb_event(hdev->req_skb))) { hci_req_cmd_complete(hdev, *opcode, ev->status, req_complete, req_complete_skb); if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) { @@ -5010,8 +4998,9 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev, void *data, bacpy(&cp.bdaddr, &conn->dst); 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)) + } else { mgmt_device_connected(hdev, conn, NULL, 0); + } if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; @@ -5675,150 +5664,6 @@ unlock: hci_dev_unlock(hdev); } -#if IS_ENABLED(CONFIG_BT_HS) -static void hci_chan_selected_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_channel_selected *ev = data; - struct hci_conn *hcon; - - bt_dev_dbg(hdev, "handle 0x%2.2x", ev->phy_handle); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - return; - - amp_read_loc_assoc_final_data(hdev, hcon); -} - -static void hci_phy_link_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_phy_link_complete *ev = data; - struct hci_conn *hcon, *bredr_hcon; - - bt_dev_dbg(hdev, "handle 0x%2.2x status 0x%2.2x", ev->phy_handle, - ev->status); - - hci_dev_lock(hdev); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - goto unlock; - - if (!hcon->amp_mgr) - goto unlock; - - if (ev->status) { - hci_conn_del(hcon); - goto unlock; - } - - bredr_hcon = hcon->amp_mgr->l2cap_conn->hcon; - - hcon->state = BT_CONNECTED; - bacpy(&hcon->dst, &bredr_hcon->dst); - - hci_conn_hold(hcon); - hcon->disc_timeout = HCI_DISCONN_TIMEOUT; - hci_conn_drop(hcon); - - hci_debugfs_create_conn(hcon); - hci_conn_add_sysfs(hcon); - - amp_physical_cfm(bredr_hcon, hcon); - -unlock: - hci_dev_unlock(hdev); -} - -static void hci_loglink_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_logical_link_complete *ev = data; - struct hci_conn *hcon; - struct hci_chan *hchan; - struct amp_mgr *mgr; - - bt_dev_dbg(hdev, "log_handle 0x%4.4x phy_handle 0x%2.2x status 0x%2.2x", - le16_to_cpu(ev->handle), ev->phy_handle, ev->status); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - return; - - /* Create AMP hchan */ - hchan = hci_chan_create(hcon); - if (!hchan) - return; - - hchan->handle = le16_to_cpu(ev->handle); - hchan->amp = true; - - BT_DBG("hcon %p mgr %p hchan %p", hcon, hcon->amp_mgr, hchan); - - mgr = hcon->amp_mgr; - if (mgr && mgr->bredr_chan) { - struct l2cap_chan *bredr_chan = mgr->bredr_chan; - - l2cap_chan_lock(bredr_chan); - - bredr_chan->conn->mtu = hdev->block_mtu; - l2cap_logical_cfm(bredr_chan, hchan, 0); - hci_conn_hold(hcon); - - l2cap_chan_unlock(bredr_chan); - } -} - -static void hci_disconn_loglink_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_disconn_logical_link_complete *ev = data; - struct hci_chan *hchan; - - bt_dev_dbg(hdev, "handle 0x%4.4x status 0x%2.2x", - le16_to_cpu(ev->handle), ev->status); - - if (ev->status) - return; - - hci_dev_lock(hdev); - - hchan = hci_chan_lookup_handle(hdev, le16_to_cpu(ev->handle)); - if (!hchan || !hchan->amp) - goto unlock; - - amp_destroy_logical_link(hchan, ev->reason); - -unlock: - hci_dev_unlock(hdev); -} - -static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_disconn_phy_link_complete *ev = data; - struct hci_conn *hcon; - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - - if (ev->status) - return; - - hci_dev_lock(hdev); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (hcon && hcon->type == AMP_LINK) { - hcon->state = BT_CLOSED; - hci_disconn_cfm(hcon, ev->reason); - hci_conn_del(hcon); - } - - hci_dev_unlock(hdev); -} -#endif - static void le_conn_update_addr(struct hci_conn *conn, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *local_rpa) { @@ -5984,8 +5829,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, goto unlock; } - if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, NULL, 0); + mgmt_device_connected(hdev, conn, NULL, 0); conn->sec_level = BT_SECURITY_LOW; conn->state = BT_CONFIG; @@ -6684,7 +6528,7 @@ static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, void *data, * transition into connected state and mark it as * successful. */ - if (!conn->out && ev->status == 0x1a && + if (!conn->out && ev->status == HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE && (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) status = 0x00; else @@ -7214,6 +7058,9 @@ static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data, /* Notify iso layer */ hci_connect_cfm(pa_sync, 0x00); + /* Notify MGMT layer */ + mgmt_device_connected(hdev, pa_sync, NULL, 0); + unlock: hci_dev_unlock(hdev); } @@ -7324,10 +7171,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "subevent 0x%2.2x", ev->subevent); /* Only match event if command OGF is for LE */ - if (hdev->sent_cmd && - hci_opcode_ogf(hci_skb_opcode(hdev->sent_cmd)) == 0x08 && - hci_skb_event(hdev->sent_cmd) == ev->subevent) { - *opcode = hci_skb_opcode(hdev->sent_cmd); + if (hdev->req_skb && + hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) == 0x08 && + hci_skb_event(hdev->req_skb) == ev->subevent) { + *opcode = hci_skb_opcode(hdev->req_skb); hci_req_cmd_complete(hdev, *opcode, 0x00, req_complete, req_complete_skb); } @@ -7626,25 +7473,6 @@ static const struct hci_ev { /* [0x3e = HCI_EV_LE_META] */ HCI_EV_REQ_VL(HCI_EV_LE_META, hci_le_meta_evt, sizeof(struct hci_ev_le_meta), HCI_MAX_EVENT_SIZE), -#if IS_ENABLED(CONFIG_BT_HS) - /* [0x40 = HCI_EV_PHY_LINK_COMPLETE] */ - HCI_EV(HCI_EV_PHY_LINK_COMPLETE, hci_phy_link_complete_evt, - sizeof(struct hci_ev_phy_link_complete)), - /* [0x41 = HCI_EV_CHANNEL_SELECTED] */ - HCI_EV(HCI_EV_CHANNEL_SELECTED, hci_chan_selected_evt, - sizeof(struct hci_ev_channel_selected)), - /* [0x42 = HCI_EV_DISCONN_PHY_LINK_COMPLETE] */ - HCI_EV(HCI_EV_DISCONN_LOGICAL_LINK_COMPLETE, - hci_disconn_loglink_complete_evt, - sizeof(struct hci_ev_disconn_logical_link_complete)), - /* [0x45 = HCI_EV_LOGICAL_LINK_COMPLETE] */ - HCI_EV(HCI_EV_LOGICAL_LINK_COMPLETE, hci_loglink_complete_evt, - sizeof(struct hci_ev_logical_link_complete)), - /* [0x46 = HCI_EV_DISCONN_LOGICAL_LINK_COMPLETE] */ - HCI_EV(HCI_EV_DISCONN_PHY_LINK_COMPLETE, - hci_disconn_phylink_complete_evt, - sizeof(struct hci_ev_disconn_phy_link_complete)), -#endif /* [0x48 = HCI_EV_NUM_COMP_BLOCKS] */ HCI_EV(HCI_EV_NUM_COMP_BLOCKS, hci_num_comp_blocks_evt, sizeof(struct hci_ev_num_comp_blocks)), @@ -7714,10 +7542,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) } /* Only match event if command OGF is not for LE */ - if (hdev->sent_cmd && - hci_opcode_ogf(hci_skb_opcode(hdev->sent_cmd)) != 0x08 && - hci_skb_event(hdev->sent_cmd) == event) { - hci_req_cmd_complete(hdev, hci_skb_opcode(hdev->sent_cmd), + if (hdev->req_skb && + hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) != 0x08 && + hci_skb_event(hdev->req_skb) == event) { + hci_req_cmd_complete(hdev, hci_skb_opcode(hdev->req_skb), status, &req_complete, &req_complete_skb); req_evt = event; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 6e023b0104b0..00e02138003e 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -895,7 +895,7 @@ void hci_request_setup(struct hci_dev *hdev) void hci_request_cancel_all(struct hci_dev *hdev) { - __hci_cmd_sync_cancel(hdev, ENODEV); + hci_cmd_sync_cancel_sync(hdev, ENODEV); cancel_interleave_scan(hdev); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 3e7cd330d731..4ee1b976678b 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -101,7 +101,7 @@ static bool hci_sock_gen_cookie(struct sock *sk) int id = hci_pi(sk)->cookie; if (!id) { - id = ida_simple_get(&sock_cookie_ida, 1, 0, GFP_KERNEL); + id = ida_alloc_min(&sock_cookie_ida, 1, GFP_KERNEL); if (id < 0) id = 0xffffffff; @@ -119,7 +119,7 @@ static void hci_sock_free_cookie(struct sock *sk) if (id) { hci_pi(sk)->cookie = 0xffffffff; - ida_simple_remove(&sock_cookie_ida, id); + ida_free(&sock_cookie_ida, id); } } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 5716345a26df..f6b662369322 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -32,6 +32,10 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, hdev->req_result = result; hdev->req_status = HCI_REQ_DONE; + /* Free the request command so it is not used as response */ + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + if (skb) { struct sock *sk = hci_skb_sk(skb); @@ -39,7 +43,7 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, if (sk) sock_put(sk); - hdev->req_skb = skb_get(skb); + hdev->req_rsp = skb_get(skb); } wake_up_interruptible(&hdev->req_wait_q); @@ -187,8 +191,8 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, hdev->req_status = 0; hdev->req_result = 0; - skb = hdev->req_skb; - hdev->req_skb = NULL; + skb = hdev->req_rsp; + hdev->req_rsp = NULL; bt_dev_dbg(hdev, "end: err %d", err); @@ -566,6 +570,17 @@ void hci_cmd_sync_init(struct hci_dev *hdev) INIT_DELAYED_WORK(&hdev->adv_instance_expire, adv_timeout_expire); } +static void _hci_cmd_sync_cancel_entry(struct hci_dev *hdev, + struct hci_cmd_sync_work_entry *entry, + int err) +{ + if (entry->destroy) + entry->destroy(hdev, entry->data, err); + + list_del(&entry->list); + kfree(entry); +} + void hci_cmd_sync_clear(struct hci_dev *hdev) { struct hci_cmd_sync_work_entry *entry, *tmp; @@ -574,17 +589,12 @@ void hci_cmd_sync_clear(struct hci_dev *hdev) cancel_work_sync(&hdev->reenable_adv_work); mutex_lock(&hdev->cmd_sync_work_lock); - list_for_each_entry_safe(entry, tmp, &hdev->cmd_sync_work_list, list) { - if (entry->destroy) - entry->destroy(hdev, entry->data, -ECANCELED); - - list_del(&entry->list); - kfree(entry); - } + list_for_each_entry_safe(entry, tmp, &hdev->cmd_sync_work_list, list) + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); mutex_unlock(&hdev->cmd_sync_work_lock); } -void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err) +void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); @@ -592,15 +602,17 @@ void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err) hdev->req_result = err; hdev->req_status = HCI_REQ_CANCELED; - cancel_delayed_work_sync(&hdev->cmd_timer); - cancel_delayed_work_sync(&hdev->ncmd_timer); - atomic_set(&hdev->cmd_cnt, 1); - - wake_up_interruptible(&hdev->req_wait_q); + queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work); } } +EXPORT_SYMBOL(hci_cmd_sync_cancel); -void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) +/* Cancel ongoing command request synchronously: + * + * - Set result and mark status to HCI_REQ_CANCELED + * - Wakeup command sync thread + */ +void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); @@ -608,10 +620,10 @@ void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) hdev->req_result = err; hdev->req_status = HCI_REQ_CANCELED; - queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work); + wake_up_interruptible(&hdev->req_wait_q); } } -EXPORT_SYMBOL(hci_cmd_sync_cancel); +EXPORT_SYMBOL(hci_cmd_sync_cancel_sync); /* Submit HCI command to be run in as cmd_sync_work: * @@ -667,6 +679,115 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, } EXPORT_SYMBOL(hci_cmd_sync_queue); +static struct hci_cmd_sync_work_entry * +_hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &hdev->cmd_sync_work_list, list) { + if (func && entry->func != func) + continue; + + if (data && entry->data != data) + continue; + + if (destroy && entry->destroy != destroy) + continue; + + return entry; + } + + return NULL; +} + +/* Queue HCI command entry once: + * + * - Lookup if an entry already exist and only if it doesn't creates a new entry + * and queue it. + */ +int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy)) + return 0; + + return hci_cmd_sync_queue(hdev, func, data, destroy); +} +EXPORT_SYMBOL(hci_cmd_sync_queue_once); + +/* Lookup HCI command entry: + * + * - Return first entry that matches by function callback or data or + * destroy callback. + */ +struct hci_cmd_sync_work_entry * +hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry; + + mutex_lock(&hdev->cmd_sync_work_lock); + entry = _hci_cmd_sync_lookup_entry(hdev, func, data, destroy); + mutex_unlock(&hdev->cmd_sync_work_lock); + + return entry; +} +EXPORT_SYMBOL(hci_cmd_sync_lookup_entry); + +/* Cancel HCI command entry */ +void hci_cmd_sync_cancel_entry(struct hci_dev *hdev, + struct hci_cmd_sync_work_entry *entry) +{ + mutex_lock(&hdev->cmd_sync_work_lock); + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + mutex_unlock(&hdev->cmd_sync_work_lock); +} +EXPORT_SYMBOL(hci_cmd_sync_cancel_entry); + +/* Dequeue one HCI command entry: + * + * - Lookup and cancel first entry that matches. + */ +bool hci_cmd_sync_dequeue_once(struct hci_dev *hdev, + hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry; + + entry = hci_cmd_sync_lookup_entry(hdev, func, data, destroy); + if (!entry) + return false; + + hci_cmd_sync_cancel_entry(hdev, entry); + + return true; +} +EXPORT_SYMBOL(hci_cmd_sync_dequeue_once); + +/* Dequeue HCI command entry: + * + * - Lookup and cancel any entry that matches by function callback or data or + * destroy callback. + */ +bool hci_cmd_sync_dequeue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry; + bool ret = false; + + mutex_lock(&hdev->cmd_sync_work_lock); + while ((entry = _hci_cmd_sync_lookup_entry(hdev, func, data, + destroy))) { + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + ret = true; + } + mutex_unlock(&hdev->cmd_sync_work_lock); + + return ret; +} +EXPORT_SYMBOL(hci_cmd_sync_dequeue); + int hci_update_eir_sync(struct hci_dev *hdev) { struct hci_cp_write_eir cp; @@ -2445,6 +2566,16 @@ static struct conn_params *conn_params_copy(struct list_head *list, size_t *n) return p; } +/* Clear LE Accept List */ +static int hci_le_clear_accept_list_sync(struct hci_dev *hdev) +{ + if (!(hdev->commands[26] & 0x80)) + return 0; + + return __hci_cmd_sync_status(hdev, HCI_OP_LE_CLEAR_ACCEPT_LIST, 0, NULL, + HCI_CMD_TIMEOUT); +} + /* Device must not be scanning when updating the accept list. * * Update is done using the following sequence: @@ -2493,6 +2624,31 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) goto done; } + /* Force address filtering if PA Sync is in progress */ + if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) { + struct hci_cp_le_pa_create_sync *sent; + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_PA_CREATE_SYNC); + if (sent) { + struct conn_params pa; + + memset(&pa, 0, sizeof(pa)); + + bacpy(&pa.addr, &sent->addr); + pa.addr_type = sent->addr_type; + + /* Clear first since there could be addresses left + * behind. + */ + hci_le_clear_accept_list_sync(hdev); + + num_entries = 1; + err = hci_le_add_accept_list_sync(hdev, &pa, + &num_entries); + goto done; + } + } + /* Go through the current accept list programmed into the * controller one by one and check if that address is connected or is * still in the list of pending connections or list of devices to @@ -2602,6 +2758,14 @@ done: return filter_policy; } +static void hci_le_scan_phy_params(struct hci_cp_le_scan_phy_params *cp, + u8 type, u16 interval, u16 window) +{ + cp->type = type; + cp->interval = cpu_to_le16(interval); + cp->window = cpu_to_le16(window); +} + static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, u16 interval, u16 window, u8 own_addr_type, u8 filter_policy) @@ -2609,7 +2773,7 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, struct hci_cp_le_set_ext_scan_params *cp; struct hci_cp_le_scan_phy_params *phy; u8 data[sizeof(*cp) + sizeof(*phy) * 2]; - u8 num_phy = 0; + u8 num_phy = 0x00; cp = (void *)data; phy = (void *)cp->data; @@ -2619,28 +2783,64 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, cp->own_addr_type = own_addr_type; cp->filter_policy = filter_policy; + /* Check if PA Sync is in progress then select the PHY based on the + * hci_conn.iso_qos. + */ + if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) { + struct hci_cp_le_add_to_accept_list *sent; + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_ACCEPT_LIST); + if (sent) { + struct hci_conn *conn; + + conn = hci_conn_hash_lookup_ba(hdev, ISO_LINK, + &sent->bdaddr); + if (conn) { + struct bt_iso_qos *qos = &conn->iso_qos; + + if (qos->bcast.in.phy & BT_ISO_PHY_1M || + qos->bcast.in.phy & BT_ISO_PHY_2M) { + cp->scanning_phys |= LE_SCAN_PHY_1M; + hci_le_scan_phy_params(phy, type, + interval, + window); + num_phy++; + phy++; + } + + if (qos->bcast.in.phy & BT_ISO_PHY_CODED) { + cp->scanning_phys |= LE_SCAN_PHY_CODED; + hci_le_scan_phy_params(phy, type, + interval, + window); + num_phy++; + phy++; + } + + if (num_phy) + goto done; + } + } + } + if (scan_1m(hdev) || scan_2m(hdev)) { cp->scanning_phys |= LE_SCAN_PHY_1M; - - phy->type = type; - phy->interval = cpu_to_le16(interval); - phy->window = cpu_to_le16(window); - + hci_le_scan_phy_params(phy, type, interval, window); num_phy++; phy++; } if (scan_coded(hdev)) { cp->scanning_phys |= LE_SCAN_PHY_CODED; - - phy->type = type; - phy->interval = cpu_to_le16(interval); - phy->window = cpu_to_le16(window); - + hci_le_scan_phy_params(phy, type, interval, window); num_phy++; phy++; } +done: + if (!num_phy) + return -EINVAL; + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_SCAN_PARAMS, sizeof(*cp) + sizeof(*phy) * num_phy, data, HCI_CMD_TIMEOUT); @@ -2879,7 +3079,8 @@ int hci_update_passive_scan(struct hci_dev *hdev) hci_dev_test_flag(hdev, HCI_UNREGISTER)) return 0; - return hci_cmd_sync_queue(hdev, update_passive_scan_sync, NULL, NULL); + return hci_cmd_sync_queue_once(hdev, update_passive_scan_sync, NULL, + NULL); } int hci_write_sc_support_sync(struct hci_dev *hdev, u8 val) @@ -4098,16 +4299,6 @@ static int hci_le_read_accept_list_size_sync(struct hci_dev *hdev) 0, NULL, HCI_CMD_TIMEOUT); } -/* Clear LE Accept List */ -static int hci_le_clear_accept_list_sync(struct hci_dev *hdev) -{ - if (!(hdev->commands[26] & 0x80)) - return 0; - - return __hci_cmd_sync_status(hdev, HCI_OP_LE_CLEAR_ACCEPT_LIST, 0, NULL, - HCI_CMD_TIMEOUT); -} - /* Read LE Resolving List Size */ static int hci_le_read_resolv_list_size_sync(struct hci_dev *hdev) { @@ -4834,6 +5025,11 @@ int hci_dev_open_sync(struct hci_dev *hdev) hdev->sent_cmd = NULL; } + if (hdev->req_skb) { + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + } + clear_bit(HCI_RUNNING, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_CLOSE); @@ -4994,6 +5190,12 @@ int hci_dev_close_sync(struct hci_dev *hdev) hdev->sent_cmd = NULL; } + /* Drop last request */ + if (hdev->req_skb) { + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + } + clear_bit(HCI_RUNNING, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_CLOSE); @@ -5403,27 +5605,33 @@ static int hci_power_off_sync(struct hci_dev *hdev) if (!test_bit(HCI_UP, &hdev->flags)) return 0; + hci_dev_set_flag(hdev, HCI_POWERING_DOWN); + if (test_bit(HCI_ISCAN, &hdev->flags) || test_bit(HCI_PSCAN, &hdev->flags)) { err = hci_write_scan_enable_sync(hdev, 0x00); if (err) - return err; + goto out; } err = hci_clear_adv_sync(hdev, NULL, false); if (err) - return err; + goto out; err = hci_stop_discovery_sync(hdev); if (err) - return err; + goto out; /* Terminated due to Power Off */ err = hci_disconnect_all_sync(hdev, HCI_ERROR_REMOTE_POWER_OFF); if (err) - return err; + goto out; + + err = hci_dev_close_sync(hdev); - return hci_dev_close_sync(hdev); +out: + hci_dev_clear_flag(hdev, HCI_POWERING_DOWN); + return err; } int hci_set_powered_sync(struct hci_dev *hdev, u8 val) @@ -6161,12 +6369,21 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, conn->conn_timeout, NULL); } -int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) +static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) { struct hci_cp_le_create_conn cp; struct hci_conn_params *params; u8 own_addr_type; int err; + struct hci_conn *conn = data; + + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; + + bt_dev_dbg(hdev, "conn %p", conn); + + clear_bit(HCI_CONN_SCANNING, &conn->flags); + conn->state = BT_CONNECT; /* If requested to connect as peripheral use directed advertising */ if (conn->role == HCI_ROLE_SLAVE) { @@ -6484,3 +6701,125 @@ int hci_update_adv_data(struct hci_dev *hdev, u8 instance) return hci_cmd_sync_queue(hdev, _update_adv_data_sync, UINT_PTR(instance), NULL); } + +static int hci_acl_create_conn_sync(struct hci_dev *hdev, void *data) +{ + struct hci_conn *conn = data; + struct inquiry_entry *ie; + struct hci_cp_create_conn cp; + int err; + + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; + + /* Many controllers disallow HCI Create Connection while it is doing + * HCI Inquiry. So we cancel the Inquiry first before issuing HCI Create + * Connection. This may cause the MGMT discovering state to become false + * without user space's request but it is okay since the MGMT Discovery + * APIs do not promise that discovery should be done forever. Instead, + * the user space monitors the status of MGMT discovering and it may + * request for discovery again when this flag becomes false. + */ + if (test_bit(HCI_INQUIRY, &hdev->flags)) { + err = __hci_cmd_sync_status(hdev, HCI_OP_INQUIRY_CANCEL, 0, + NULL, HCI_CMD_TIMEOUT); + if (err) + bt_dev_warn(hdev, "Failed to cancel inquiry %d", err); + } + + conn->state = BT_CONNECT; + conn->out = true; + conn->role = HCI_ROLE_MASTER; + + conn->attempt++; + + conn->link_policy = hdev->link_policy; + + memset(&cp, 0, sizeof(cp)); + bacpy(&cp.bdaddr, &conn->dst); + cp.pscan_rep_mode = 0x02; + + ie = hci_inquiry_cache_lookup(hdev, &conn->dst); + if (ie) { + if (inquiry_entry_age(ie) <= INQUIRY_ENTRY_AGE_MAX) { + cp.pscan_rep_mode = ie->data.pscan_rep_mode; + cp.pscan_mode = ie->data.pscan_mode; + cp.clock_offset = ie->data.clock_offset | + cpu_to_le16(0x8000); + } + + memcpy(conn->dev_class, ie->data.dev_class, 3); + } + + cp.pkt_type = cpu_to_le16(conn->pkt_type); + if (lmp_rswitch_capable(hdev) && !(hdev->link_mode & HCI_LM_MASTER)) + cp.role_switch = 0x01; + else + cp.role_switch = 0x00; + + return __hci_cmd_sync_status_sk(hdev, HCI_OP_CREATE_CONN, + sizeof(cp), &cp, + HCI_EV_CONN_COMPLETE, + conn->conn_timeout, NULL); +} + +int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ + return hci_cmd_sync_queue_once(hdev, hci_acl_create_conn_sync, conn, + NULL); +} + +static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) +{ + struct hci_conn *conn = data; + + bt_dev_dbg(hdev, "err %d", err); + + if (err == -ECANCELED) + return; + + hci_dev_lock(hdev); + + if (!hci_conn_valid(hdev, conn)) + goto done; + + if (!err) { + hci_connect_le_scan_cleanup(conn, 0x00); + goto done; + } + + /* Check if connection is still pending */ + if (conn != hci_lookup_le_connect(hdev)) + goto done; + + /* Flush to make sure we send create conn cancel command if needed */ + flush_delayed_work(&conn->le_conn_timeout); + hci_conn_failed(conn, bt_status(err)); + +done: + hci_dev_unlock(hdev); +} + +int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ + return hci_cmd_sync_queue_once(hdev, hci_le_create_conn_sync, conn, + create_le_conn_complete); +} + +int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ + if (conn->state != BT_OPEN) + return -EINVAL; + + switch (conn->type) { + case ACL_LINK: + return !hci_cmd_sync_dequeue_once(hdev, + hci_acl_create_conn_sync, + conn, NULL); + case LE_LINK: + return !hci_cmd_sync_dequeue_once(hdev, hci_le_create_conn_sync, + conn, create_le_conn_complete); + } + + return -ENOENT; +} diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 04f6572d35f1..c8793e57f4b5 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -3,7 +3,7 @@ * BlueZ - Bluetooth protocol stack for Linux * * Copyright (C) 2022 Intel Corporation - * Copyright 2023 NXP + * Copyright 2023-2024 NXP */ #include <linux/module.h> @@ -690,11 +690,8 @@ static void iso_sock_cleanup_listen(struct sock *parent) iso_sock_kill(sk); } - /* If listening socket stands for a PA sync connection, - * properly disconnect the hcon and socket. - */ - if (iso_pi(parent)->conn && iso_pi(parent)->conn->hcon && - test_bit(HCI_CONN_PA_SYNC, &iso_pi(parent)->conn->hcon->flags)) { + /* If listening socket has a hcon, properly disconnect it */ + if (iso_pi(parent)->conn && iso_pi(parent)->conn->hcon) { iso_sock_disconn(parent); return; } @@ -837,10 +834,10 @@ static struct bt_iso_qos default_qos = { .bcode = {0x00}, .options = 0x00, .skip = 0x0000, - .sync_timeout = 0x4000, + .sync_timeout = BT_ISO_SYNC_TIMEOUT, .sync_cte_type = 0x00, .mse = 0x00, - .timeout = 0x4000, + .timeout = BT_ISO_SYNC_TIMEOUT, }, }; @@ -1076,6 +1073,8 @@ static int iso_listen_bis(struct sock *sk) { struct hci_dev *hdev; int err = 0; + struct iso_conn *conn; + struct hci_conn *hcon; BT_DBG("%pMR -> %pMR (SID 0x%2.2x)", &iso_pi(sk)->src, &iso_pi(sk)->dst, iso_pi(sk)->bc_sid); @@ -1096,18 +1095,40 @@ static int iso_listen_bis(struct sock *sk) if (!hdev) return -EHOSTUNREACH; + hci_dev_lock(hdev); + /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_bcast_qos(&iso_pi(sk)->qos)) { iso_pi(sk)->qos = default_qos; - return -EINVAL; + err = -EINVAL; + goto unlock; + } + + hcon = hci_pa_create_sync(hdev, &iso_pi(sk)->dst, + le_addr_type(iso_pi(sk)->dst_type), + iso_pi(sk)->bc_sid, &iso_pi(sk)->qos); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; } - err = hci_pa_create_sync(hdev, &iso_pi(sk)->dst, - le_addr_type(iso_pi(sk)->dst_type), - iso_pi(sk)->bc_sid, &iso_pi(sk)->qos); + conn = iso_conn_add(hcon); + if (!conn) { + hci_conn_drop(hcon); + err = -ENOMEM; + goto unlock; + } + + err = iso_chan_add(conn, sk, NULL); + if (err) { + hci_conn_drop(hcon); + goto unlock; + } hci_dev_put(hdev); +unlock: + hci_dev_unlock(hdev); return err; } @@ -1889,7 +1910,6 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) struct hci_evt_le_big_info_adv_report *ev2; struct hci_ev_le_per_adv_report *ev3; struct sock *sk; - int lm = 0; bt_dev_dbg(hdev, "bdaddr %pMR", bdaddr); @@ -1933,7 +1953,7 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) if (sk && test_bit(BT_SK_PA_SYNC_TERM, &iso_pi(sk)->flags)) - return lm; + return 0; } if (sk) { @@ -1961,16 +1981,58 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) ev3 = hci_recv_event_data(hdev, HCI_EV_LE_PER_ADV_REPORT); if (ev3) { - size_t base_len = ev3->length; + size_t base_len = 0; u8 *base; + struct hci_conn *hcon; sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, iso_match_sync_handle_pa_report, ev3); - base = eir_get_service_data(ev3->data, ev3->length, - EIR_BAA_SERVICE_UUID, &base_len); - if (base && sk && base_len <= sizeof(iso_pi(sk)->base)) { + if (!sk) + goto done; + + hcon = iso_pi(sk)->conn->hcon; + if (!hcon) + goto done; + + if (ev3->data_status == LE_PA_DATA_TRUNCATED) { + /* The controller was unable to retrieve PA data. */ + memset(hcon->le_per_adv_data, 0, + HCI_MAX_PER_AD_TOT_LEN); + hcon->le_per_adv_data_len = 0; + hcon->le_per_adv_data_offset = 0; + goto done; + } + + if (hcon->le_per_adv_data_offset + ev3->length > + HCI_MAX_PER_AD_TOT_LEN) + goto done; + + memcpy(hcon->le_per_adv_data + hcon->le_per_adv_data_offset, + ev3->data, ev3->length); + hcon->le_per_adv_data_offset += ev3->length; + + if (ev3->data_status == LE_PA_DATA_COMPLETE) { + /* All PA data has been received. */ + hcon->le_per_adv_data_len = + hcon->le_per_adv_data_offset; + hcon->le_per_adv_data_offset = 0; + + /* Extract BASE */ + base = eir_get_service_data(hcon->le_per_adv_data, + hcon->le_per_adv_data_len, + EIR_BAA_SERVICE_UUID, + &base_len); + + if (!base || base_len > BASE_MAX_LENGTH) + goto done; + memcpy(iso_pi(sk)->base, base, base_len); iso_pi(sk)->base_len = base_len; + } else { + /* This is a PA data fragment. Keep pa_data_len set to 0 + * until all data has been reassembled. + */ + hcon->le_per_adv_data_len = 0; } } else { sk = iso_get_sock_listen(&hdev->bdaddr, BDADDR_ANY, NULL, NULL); @@ -1978,16 +2040,14 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) done: if (!sk) - return lm; - - lm |= HCI_LM_ACCEPT; + return 0; if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) *flags |= HCI_PROTO_DEFER; sock_put(sk); - return lm; + return HCI_LM_ACCEPT; } static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 656f49b299d2..467b242d8be0 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -39,8 +39,6 @@ #include <net/bluetooth/l2cap.h> #include "smp.h" -#include "a2mp.h" -#include "amp.h" #define LE_FLOWCTL_MAX_CREDITS 65535 @@ -167,24 +165,6 @@ static struct l2cap_chan *__l2cap_get_chan_by_ident(struct l2cap_conn *conn, return NULL; } -static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn, - u8 ident) -{ - struct l2cap_chan *c; - - mutex_lock(&conn->chan_lock); - c = __l2cap_get_chan_by_ident(conn, ident); - if (c) { - /* Only lock if chan reference is not 0 */ - c = l2cap_chan_hold_unless_zero(c); - if (c) - l2cap_chan_lock(c); - } - mutex_unlock(&conn->chan_lock); - - return c; -} - static struct l2cap_chan *__l2cap_global_chan_by_addr(__le16 psm, bdaddr_t *src, u8 src_type) { @@ -651,7 +631,6 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) chan->ops->teardown(chan, err); if (conn) { - struct amp_mgr *mgr = conn->hcon->amp_mgr; /* Delete from channel list */ list_del(&chan->list); @@ -666,16 +645,6 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) if (chan->chan_type != L2CAP_CHAN_FIXED || test_bit(FLAG_HOLD_HCI_CONN, &chan->flags)) hci_conn_drop(conn->hcon); - - if (mgr && mgr->bredr_chan == chan) - mgr->bredr_chan = NULL; - } - - if (chan->hs_hchan) { - struct hci_chan *hs_hchan = chan->hs_hchan; - - BT_DBG("chan %p disconnect hs_hchan %p", chan, hs_hchan); - amp_disconnect_logical_link(hs_hchan); } if (test_bit(CONF_NOT_COMPLETE, &chan->conf_state)) @@ -977,12 +946,6 @@ static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, hci_send_acl(conn->hchan, skb, flags); } -static bool __chan_is_moving(struct l2cap_chan *chan) -{ - return chan->move_state != L2CAP_MOVE_STABLE && - chan->move_state != L2CAP_MOVE_WAIT_PREPARE; -} - static void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) { struct hci_conn *hcon = chan->conn->hcon; @@ -991,15 +954,6 @@ static void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) BT_DBG("chan %p, skb %p len %d priority %u", chan, skb, skb->len, skb->priority); - if (chan->hs_hcon && !__chan_is_moving(chan)) { - if (chan->hs_hchan) - hci_send_acl(chan->hs_hchan, skb, ACL_COMPLETE); - else - kfree_skb(skb); - - return; - } - /* Use NO_FLUSH for LE links (where this is the only option) or * if the BR/EDR link supports it and flushing has not been * explicitly requested (through FLAG_FLUSHABLE). @@ -1180,9 +1134,6 @@ static void l2cap_send_sframe(struct l2cap_chan *chan, if (!control->sframe) return; - if (__chan_is_moving(chan)) - return; - if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state) && !control->poll) control->final = 1; @@ -1237,40 +1188,6 @@ static inline int __l2cap_no_conn_pending(struct l2cap_chan *chan) return !test_bit(CONF_CONNECT_PEND, &chan->conf_state); } -static bool __amp_capable(struct l2cap_chan *chan) -{ - struct l2cap_conn *conn = chan->conn; - struct hci_dev *hdev; - bool amp_available = false; - - if (!(conn->local_fixed_chan & L2CAP_FC_A2MP)) - return false; - - if (!(conn->remote_fixed_chan & L2CAP_FC_A2MP)) - return false; - - read_lock(&hci_dev_list_lock); - list_for_each_entry(hdev, &hci_dev_list, list) { - if (hdev->amp_type != AMP_TYPE_BREDR && - test_bit(HCI_UP, &hdev->flags)) { - amp_available = true; - break; - } - } - read_unlock(&hci_dev_list_lock); - - if (chan->chan_policy == BT_CHANNEL_POLICY_AMP_PREFERRED) - return amp_available; - - return false; -} - -static bool l2cap_check_efs(struct l2cap_chan *chan) -{ - /* Check EFS parameters */ - return true; -} - void l2cap_send_conn_req(struct l2cap_chan *chan) { struct l2cap_conn *conn = chan->conn; @@ -1286,76 +1203,6 @@ void l2cap_send_conn_req(struct l2cap_chan *chan) l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_REQ, sizeof(req), &req); } -static void l2cap_send_create_chan_req(struct l2cap_chan *chan, u8 amp_id) -{ - struct l2cap_create_chan_req req; - req.scid = cpu_to_le16(chan->scid); - req.psm = chan->psm; - req.amp_id = amp_id; - - chan->ident = l2cap_get_ident(chan->conn); - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_CREATE_CHAN_REQ, - sizeof(req), &req); -} - -static void l2cap_move_setup(struct l2cap_chan *chan) -{ - struct sk_buff *skb; - - BT_DBG("chan %p", chan); - - if (chan->mode != L2CAP_MODE_ERTM) - return; - - __clear_retrans_timer(chan); - __clear_monitor_timer(chan); - __clear_ack_timer(chan); - - chan->retry_count = 0; - skb_queue_walk(&chan->tx_q, skb) { - if (bt_cb(skb)->l2cap.retries) - bt_cb(skb)->l2cap.retries = 1; - else - break; - } - - chan->expected_tx_seq = chan->buffer_seq; - - clear_bit(CONN_REJ_ACT, &chan->conn_state); - clear_bit(CONN_SREJ_ACT, &chan->conn_state); - l2cap_seq_list_clear(&chan->retrans_list); - l2cap_seq_list_clear(&chan->srej_list); - skb_queue_purge(&chan->srej_q); - - chan->tx_state = L2CAP_TX_STATE_XMIT; - chan->rx_state = L2CAP_RX_STATE_MOVE; - - set_bit(CONN_REMOTE_BUSY, &chan->conn_state); -} - -static void l2cap_move_done(struct l2cap_chan *chan) -{ - u8 move_role = chan->move_role; - BT_DBG("chan %p", chan); - - chan->move_state = L2CAP_MOVE_STABLE; - chan->move_role = L2CAP_MOVE_ROLE_NONE; - - if (chan->mode != L2CAP_MODE_ERTM) - return; - - switch (move_role) { - case L2CAP_MOVE_ROLE_INITIATOR: - l2cap_tx(chan, NULL, NULL, L2CAP_EV_EXPLICIT_POLL); - chan->rx_state = L2CAP_RX_STATE_WAIT_F; - break; - case L2CAP_MOVE_ROLE_RESPONDER: - chan->rx_state = L2CAP_RX_STATE_WAIT_P; - break; - } -} - static void l2cap_chan_ready(struct l2cap_chan *chan) { /* The channel may have already been flagged as connected in @@ -1505,10 +1352,7 @@ static void l2cap_le_start(struct l2cap_chan *chan) static void l2cap_start_connection(struct l2cap_chan *chan) { - if (__amp_capable(chan)) { - BT_DBG("chan %p AMP capable: discover AMPs", chan); - a2mp_discover_amp(chan); - } else if (chan->conn->hcon->type == LE_LINK) { + if (chan->conn->hcon->type == LE_LINK) { l2cap_le_start(chan); } else { l2cap_send_conn_req(chan); @@ -1611,11 +1455,6 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err) __clear_ack_timer(chan); } - if (chan->scid == L2CAP_CID_A2MP) { - l2cap_state_change(chan, BT_DISCONN); - return; - } - req.dcid = cpu_to_le16(chan->dcid); req.scid = cpu_to_le16(chan->scid); l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_DISCONN_REQ, @@ -1754,11 +1593,6 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) l2cap_chan_lock(chan); - if (chan->scid == L2CAP_CID_A2MP) { - l2cap_chan_unlock(chan); - continue; - } - if (hcon->type == LE_LINK) { l2cap_le_start(chan); } else if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { @@ -2067,9 +1901,6 @@ static void l2cap_streaming_send(struct l2cap_chan *chan, BT_DBG("chan %p, skbs %p", chan, skbs); - if (__chan_is_moving(chan)) - return; - skb_queue_splice_tail_init(skbs, &chan->tx_q); while (!skb_queue_empty(&chan->tx_q)) { @@ -2112,9 +1943,6 @@ static int l2cap_ertm_send(struct l2cap_chan *chan) if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) return 0; - if (__chan_is_moving(chan)) - return 0; - while (chan->tx_send_head && chan->unacked_frames < chan->remote_tx_win && chan->tx_state == L2CAP_TX_STATE_XMIT) { @@ -2180,9 +2008,6 @@ static void l2cap_ertm_resend(struct l2cap_chan *chan) if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) return; - if (__chan_is_moving(chan)) - return; - while (chan->retrans_list.head != L2CAP_SEQ_LIST_CLEAR) { seq = l2cap_seq_list_pop(&chan->retrans_list); @@ -2522,8 +2347,7 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, pdu_len = chan->conn->mtu; /* Constrain PDU size for BR/EDR connections */ - if (!chan->hs_hcon) - pdu_len = min_t(size_t, pdu_len, L2CAP_BREDR_MAX_PAYLOAD); + pdu_len = min_t(size_t, pdu_len, L2CAP_BREDR_MAX_PAYLOAD); /* Adjust for largest possible L2CAP overhead. */ if (chan->fcs) @@ -3287,11 +3111,6 @@ int l2cap_ertm_init(struct l2cap_chan *chan) skb_queue_head_init(&chan->tx_q); - chan->local_amp_id = AMP_ID_BREDR; - chan->move_id = AMP_ID_BREDR; - chan->move_state = L2CAP_MOVE_STABLE; - chan->move_role = L2CAP_MOVE_ROLE_NONE; - if (chan->mode != L2CAP_MODE_ERTM) return 0; @@ -3326,52 +3145,19 @@ static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask) static inline bool __l2cap_ews_supported(struct l2cap_conn *conn) { - return ((conn->local_fixed_chan & L2CAP_FC_A2MP) && - (conn->feat_mask & L2CAP_FEAT_EXT_WINDOW)); + return (conn->feat_mask & L2CAP_FEAT_EXT_WINDOW); } static inline bool __l2cap_efs_supported(struct l2cap_conn *conn) { - return ((conn->local_fixed_chan & L2CAP_FC_A2MP) && - (conn->feat_mask & L2CAP_FEAT_EXT_FLOW)); + return (conn->feat_mask & L2CAP_FEAT_EXT_FLOW); } static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan, struct l2cap_conf_rfc *rfc) { - if (chan->local_amp_id != AMP_ID_BREDR && chan->hs_hcon) { - u64 ertm_to = chan->hs_hcon->hdev->amp_be_flush_to; - - /* Class 1 devices have must have ERTM timeouts - * exceeding the Link Supervision Timeout. The - * default Link Supervision Timeout for AMP - * controllers is 10 seconds. - * - * Class 1 devices use 0xffffffff for their - * best-effort flush timeout, so the clamping logic - * will result in a timeout that meets the above - * requirement. ERTM timeouts are 16-bit values, so - * the maximum timeout is 65.535 seconds. - */ - - /* Convert timeout to milliseconds and round */ - ertm_to = DIV_ROUND_UP_ULL(ertm_to, 1000); - - /* This is the recommended formula for class 2 devices - * that start ERTM timers when packets are sent to the - * controller. - */ - ertm_to = 3 * ertm_to + 500; - - if (ertm_to > 0xffff) - ertm_to = 0xffff; - - rfc->retrans_timeout = cpu_to_le16((u16) ertm_to); - rfc->monitor_timeout = rfc->retrans_timeout; - } else { - rfc->retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); - rfc->monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); - } + rfc->retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); + rfc->monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); } static inline void l2cap_txwin_setup(struct l2cap_chan *chan) @@ -3623,13 +3409,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data case L2CAP_CONF_EWS: if (olen != 2) break; - if (!(chan->conn->local_fixed_chan & L2CAP_FC_A2MP)) - return -ECONNREFUSED; - set_bit(FLAG_EXT_CTRL, &chan->flags); - set_bit(CONF_EWS_RECV, &chan->conf_state); - chan->tx_win_max = L2CAP_DEFAULT_EXT_WINDOW; - chan->remote_tx_win = val; - break; + return -ECONNREFUSED; default: if (hint) @@ -4027,11 +3807,7 @@ void __l2cap_connect_rsp_defer(struct l2cap_chan *chan) rsp.dcid = cpu_to_le16(chan->scid); rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - - if (chan->hs_hcon) - rsp_code = L2CAP_CREATE_CHAN_RSP; - else - rsp_code = L2CAP_CONN_RSP; + rsp_code = L2CAP_CONN_RSP; BT_DBG("chan %p rsp_code %u", chan, rsp_code); @@ -4190,7 +3966,6 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, chan->dst_type = bdaddr_dst_type(conn->hcon); chan->psm = psm; chan->dcid = scid; - chan->local_amp_id = amp_id; __l2cap_chan_add(conn, chan); @@ -4516,10 +4291,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, /* check compatibility */ /* Send rsp for BR/EDR channel */ - if (!chan->hs_hcon) - l2cap_send_efs_conf_rsp(chan, rsp, cmd->ident, flags); - else - chan->ident = cmd->ident; + l2cap_send_efs_conf_rsp(chan, rsp, cmd->ident, flags); } unlock: @@ -4571,15 +4343,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, goto done; } - if (!chan->hs_hcon) { - l2cap_send_efs_conf_rsp(chan, buf, cmd->ident, - 0); - } else { - if (l2cap_check_efs(chan)) { - amp_create_logical_link(chan); - chan->ident = cmd->ident; - } - } + l2cap_send_efs_conf_rsp(chan, buf, cmd->ident, 0); } goto done; @@ -4750,9 +4514,6 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, if (!disable_ertm) feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING | L2CAP_FEAT_FCS; - if (conn->local_fixed_chan & L2CAP_FC_A2MP) - feat_mask |= L2CAP_FEAT_EXT_FLOW - | L2CAP_FEAT_EXT_WINDOW; put_unaligned_le32(feat_mask, rsp->data); l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf), @@ -4841,751 +4602,6 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, return 0; } -static int l2cap_create_channel_req(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_create_chan_req *req = data; - struct l2cap_create_chan_rsp rsp; - struct l2cap_chan *chan; - struct hci_dev *hdev; - u16 psm, scid; - - if (cmd_len != sizeof(*req)) - return -EPROTO; - - if (!(conn->local_fixed_chan & L2CAP_FC_A2MP)) - return -EINVAL; - - psm = le16_to_cpu(req->psm); - scid = le16_to_cpu(req->scid); - - BT_DBG("psm 0x%2.2x, scid 0x%4.4x, amp_id %d", psm, scid, req->amp_id); - - /* For controller id 0 make BR/EDR connection */ - if (req->amp_id == AMP_ID_BREDR) { - l2cap_connect(conn, cmd, data, L2CAP_CREATE_CHAN_RSP, - req->amp_id); - return 0; - } - - /* Validate AMP controller id */ - hdev = hci_dev_get(req->amp_id); - if (!hdev) - goto error; - - if (hdev->dev_type != HCI_AMP || !test_bit(HCI_UP, &hdev->flags)) { - hci_dev_put(hdev); - goto error; - } - - chan = l2cap_connect(conn, cmd, data, L2CAP_CREATE_CHAN_RSP, - req->amp_id); - if (chan) { - struct amp_mgr *mgr = conn->hcon->amp_mgr; - struct hci_conn *hs_hcon; - - hs_hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, - &conn->hcon->dst); - if (!hs_hcon) { - hci_dev_put(hdev); - cmd_reject_invalid_cid(conn, cmd->ident, chan->scid, - chan->dcid); - return 0; - } - - BT_DBG("mgr %p bredr_chan %p hs_hcon %p", mgr, chan, hs_hcon); - - mgr->bredr_chan = chan; - chan->hs_hcon = hs_hcon; - chan->fcs = L2CAP_FCS_NONE; - conn->mtu = hdev->block_mtu; - } - - hci_dev_put(hdev); - - return 0; - -error: - rsp.dcid = 0; - rsp.scid = cpu_to_le16(scid); - rsp.result = cpu_to_le16(L2CAP_CR_BAD_AMP); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - - l2cap_send_cmd(conn, cmd->ident, L2CAP_CREATE_CHAN_RSP, - sizeof(rsp), &rsp); - - return 0; -} - -static void l2cap_send_move_chan_req(struct l2cap_chan *chan, u8 dest_amp_id) -{ - struct l2cap_move_chan_req req; - u8 ident; - - BT_DBG("chan %p, dest_amp_id %d", chan, dest_amp_id); - - ident = l2cap_get_ident(chan->conn); - chan->ident = ident; - - req.icid = cpu_to_le16(chan->scid); - req.dest_amp_id = dest_amp_id; - - l2cap_send_cmd(chan->conn, ident, L2CAP_MOVE_CHAN_REQ, sizeof(req), - &req); - - __set_chan_timer(chan, L2CAP_MOVE_TIMEOUT); -} - -static void l2cap_send_move_chan_rsp(struct l2cap_chan *chan, u16 result) -{ - struct l2cap_move_chan_rsp rsp; - - BT_DBG("chan %p, result 0x%4.4x", chan, result); - - rsp.icid = cpu_to_le16(chan->dcid); - rsp.result = cpu_to_le16(result); - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_MOVE_CHAN_RSP, - sizeof(rsp), &rsp); -} - -static void l2cap_send_move_chan_cfm(struct l2cap_chan *chan, u16 result) -{ - struct l2cap_move_chan_cfm cfm; - - BT_DBG("chan %p, result 0x%4.4x", chan, result); - - chan->ident = l2cap_get_ident(chan->conn); - - cfm.icid = cpu_to_le16(chan->scid); - cfm.result = cpu_to_le16(result); - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_MOVE_CHAN_CFM, - sizeof(cfm), &cfm); - - __set_chan_timer(chan, L2CAP_MOVE_TIMEOUT); -} - -static void l2cap_send_move_chan_cfm_icid(struct l2cap_conn *conn, u16 icid) -{ - struct l2cap_move_chan_cfm cfm; - - BT_DBG("conn %p, icid 0x%4.4x", conn, icid); - - cfm.icid = cpu_to_le16(icid); - cfm.result = cpu_to_le16(L2CAP_MC_UNCONFIRMED); - - l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_MOVE_CHAN_CFM, - sizeof(cfm), &cfm); -} - -static void l2cap_send_move_chan_cfm_rsp(struct l2cap_conn *conn, u8 ident, - u16 icid) -{ - struct l2cap_move_chan_cfm_rsp rsp; - - BT_DBG("icid 0x%4.4x", icid); - - rsp.icid = cpu_to_le16(icid); - l2cap_send_cmd(conn, ident, L2CAP_MOVE_CHAN_CFM_RSP, sizeof(rsp), &rsp); -} - -static void __release_logical_link(struct l2cap_chan *chan) -{ - chan->hs_hchan = NULL; - chan->hs_hcon = NULL; - - /* Placeholder - release the logical link */ -} - -static void l2cap_logical_fail(struct l2cap_chan *chan) -{ - /* Logical link setup failed */ - if (chan->state != BT_CONNECTED) { - /* Create channel failure, disconnect */ - l2cap_send_disconn_req(chan, ECONNRESET); - return; - } - - switch (chan->move_role) { - case L2CAP_MOVE_ROLE_RESPONDER: - l2cap_move_done(chan); - l2cap_send_move_chan_rsp(chan, L2CAP_MR_NOT_SUPP); - break; - case L2CAP_MOVE_ROLE_INITIATOR: - if (chan->move_state == L2CAP_MOVE_WAIT_LOGICAL_COMP || - chan->move_state == L2CAP_MOVE_WAIT_LOGICAL_CFM) { - /* Remote has only sent pending or - * success responses, clean up - */ - l2cap_move_done(chan); - } - - /* Other amp move states imply that the move - * has already aborted - */ - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - break; - } -} - -static void l2cap_logical_finish_create(struct l2cap_chan *chan, - struct hci_chan *hchan) -{ - struct l2cap_conf_rsp rsp; - - chan->hs_hchan = hchan; - chan->hs_hcon->l2cap_data = chan->conn; - - l2cap_send_efs_conf_rsp(chan, &rsp, chan->ident, 0); - - if (test_bit(CONF_INPUT_DONE, &chan->conf_state)) { - int err; - - set_default_fcs(chan); - - err = l2cap_ertm_init(chan); - if (err < 0) - l2cap_send_disconn_req(chan, -err); - else - l2cap_chan_ready(chan); - } -} - -static void l2cap_logical_finish_move(struct l2cap_chan *chan, - struct hci_chan *hchan) -{ - chan->hs_hcon = hchan->conn; - chan->hs_hcon->l2cap_data = chan->conn; - - BT_DBG("move_state %d", chan->move_state); - - switch (chan->move_state) { - case L2CAP_MOVE_WAIT_LOGICAL_COMP: - /* Move confirm will be sent after a success - * response is received - */ - chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; - break; - case L2CAP_MOVE_WAIT_LOGICAL_CFM: - if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; - } else if (chan->move_role == L2CAP_MOVE_ROLE_INITIATOR) { - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM_RSP; - l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); - } else if (chan->move_role == L2CAP_MOVE_ROLE_RESPONDER) { - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; - l2cap_send_move_chan_rsp(chan, L2CAP_MR_SUCCESS); - } - break; - default: - /* Move was not in expected state, free the channel */ - __release_logical_link(chan); - - chan->move_state = L2CAP_MOVE_STABLE; - } -} - -/* Call with chan locked */ -void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan, - u8 status) -{ - BT_DBG("chan %p, hchan %p, status %d", chan, hchan, status); - - if (status) { - l2cap_logical_fail(chan); - __release_logical_link(chan); - return; - } - - if (chan->state != BT_CONNECTED) { - /* Ignore logical link if channel is on BR/EDR */ - if (chan->local_amp_id != AMP_ID_BREDR) - l2cap_logical_finish_create(chan, hchan); - } else { - l2cap_logical_finish_move(chan, hchan); - } -} - -void l2cap_move_start(struct l2cap_chan *chan) -{ - BT_DBG("chan %p", chan); - - if (chan->local_amp_id == AMP_ID_BREDR) { - if (chan->chan_policy != BT_CHANNEL_POLICY_AMP_PREFERRED) - return; - chan->move_role = L2CAP_MOVE_ROLE_INITIATOR; - chan->move_state = L2CAP_MOVE_WAIT_PREPARE; - /* Placeholder - start physical link setup */ - } else { - chan->move_role = L2CAP_MOVE_ROLE_INITIATOR; - chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; - chan->move_id = 0; - l2cap_move_setup(chan); - l2cap_send_move_chan_req(chan, 0); - } -} - -static void l2cap_do_create(struct l2cap_chan *chan, int result, - u8 local_amp_id, u8 remote_amp_id) -{ - BT_DBG("chan %p state %s %u -> %u", chan, state_to_string(chan->state), - local_amp_id, remote_amp_id); - - chan->fcs = L2CAP_FCS_NONE; - - /* Outgoing channel on AMP */ - if (chan->state == BT_CONNECT) { - if (result == L2CAP_CR_SUCCESS) { - chan->local_amp_id = local_amp_id; - l2cap_send_create_chan_req(chan, remote_amp_id); - } else { - /* Revert to BR/EDR connect */ - l2cap_send_conn_req(chan); - } - - return; - } - - /* Incoming channel on AMP */ - if (__l2cap_no_conn_pending(chan)) { - struct l2cap_conn_rsp rsp; - char buf[128]; - rsp.scid = cpu_to_le16(chan->dcid); - rsp.dcid = cpu_to_le16(chan->scid); - - if (result == L2CAP_CR_SUCCESS) { - /* Send successful response */ - rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - } else { - /* Send negative response */ - rsp.result = cpu_to_le16(L2CAP_CR_NO_MEM); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - } - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_CREATE_CHAN_RSP, - sizeof(rsp), &rsp); - - if (result == L2CAP_CR_SUCCESS) { - l2cap_state_change(chan, BT_CONFIG); - set_bit(CONF_REQ_SENT, &chan->conf_state); - l2cap_send_cmd(chan->conn, l2cap_get_ident(chan->conn), - L2CAP_CONF_REQ, - l2cap_build_conf_req(chan, buf, sizeof(buf)), buf); - chan->num_conf_req++; - } - } -} - -static void l2cap_do_move_initiate(struct l2cap_chan *chan, u8 local_amp_id, - u8 remote_amp_id) -{ - l2cap_move_setup(chan); - chan->move_id = local_amp_id; - chan->move_state = L2CAP_MOVE_WAIT_RSP; - - l2cap_send_move_chan_req(chan, remote_amp_id); -} - -static void l2cap_do_move_respond(struct l2cap_chan *chan, int result) -{ - struct hci_chan *hchan = NULL; - - /* Placeholder - get hci_chan for logical link */ - - if (hchan) { - if (hchan->state == BT_CONNECTED) { - /* Logical link is ready to go */ - chan->hs_hcon = hchan->conn; - chan->hs_hcon->l2cap_data = chan->conn; - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; - l2cap_send_move_chan_rsp(chan, L2CAP_MR_SUCCESS); - - l2cap_logical_cfm(chan, hchan, L2CAP_MR_SUCCESS); - } else { - /* Wait for logical link to be ready */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; - } - } else { - /* Logical link not available */ - l2cap_send_move_chan_rsp(chan, L2CAP_MR_NOT_ALLOWED); - } -} - -static void l2cap_do_move_cancel(struct l2cap_chan *chan, int result) -{ - if (chan->move_role == L2CAP_MOVE_ROLE_RESPONDER) { - u8 rsp_result; - if (result == -EINVAL) - rsp_result = L2CAP_MR_BAD_ID; - else - rsp_result = L2CAP_MR_NOT_ALLOWED; - - l2cap_send_move_chan_rsp(chan, rsp_result); - } - - chan->move_role = L2CAP_MOVE_ROLE_NONE; - chan->move_state = L2CAP_MOVE_STABLE; - - /* Restart data transmission */ - l2cap_ertm_send(chan); -} - -/* Invoke with locked chan */ -void __l2cap_physical_cfm(struct l2cap_chan *chan, int result) -{ - u8 local_amp_id = chan->local_amp_id; - u8 remote_amp_id = chan->remote_amp_id; - - BT_DBG("chan %p, result %d, local_amp_id %d, remote_amp_id %d", - chan, result, local_amp_id, remote_amp_id); - - if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) - return; - - if (chan->state != BT_CONNECTED) { - l2cap_do_create(chan, result, local_amp_id, remote_amp_id); - } else if (result != L2CAP_MR_SUCCESS) { - l2cap_do_move_cancel(chan, result); - } else { - switch (chan->move_role) { - case L2CAP_MOVE_ROLE_INITIATOR: - l2cap_do_move_initiate(chan, local_amp_id, - remote_amp_id); - break; - case L2CAP_MOVE_ROLE_RESPONDER: - l2cap_do_move_respond(chan, result); - break; - default: - l2cap_do_move_cancel(chan, result); - break; - } - } -} - -static inline int l2cap_move_channel_req(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_req *req = data; - struct l2cap_move_chan_rsp rsp; - struct l2cap_chan *chan; - u16 icid = 0; - u16 result = L2CAP_MR_NOT_ALLOWED; - - if (cmd_len != sizeof(*req)) - return -EPROTO; - - icid = le16_to_cpu(req->icid); - - BT_DBG("icid 0x%4.4x, dest_amp_id %d", icid, req->dest_amp_id); - - if (!(conn->local_fixed_chan & L2CAP_FC_A2MP)) - return -EINVAL; - - chan = l2cap_get_chan_by_dcid(conn, icid); - if (!chan) { - rsp.icid = cpu_to_le16(icid); - rsp.result = cpu_to_le16(L2CAP_MR_NOT_ALLOWED); - l2cap_send_cmd(conn, cmd->ident, L2CAP_MOVE_CHAN_RSP, - sizeof(rsp), &rsp); - return 0; - } - - chan->ident = cmd->ident; - - if (chan->scid < L2CAP_CID_DYN_START || - chan->chan_policy == BT_CHANNEL_POLICY_BREDR_ONLY || - (chan->mode != L2CAP_MODE_ERTM && - chan->mode != L2CAP_MODE_STREAMING)) { - result = L2CAP_MR_NOT_ALLOWED; - goto send_move_response; - } - - if (chan->local_amp_id == req->dest_amp_id) { - result = L2CAP_MR_SAME_ID; - goto send_move_response; - } - - if (req->dest_amp_id != AMP_ID_BREDR) { - struct hci_dev *hdev; - hdev = hci_dev_get(req->dest_amp_id); - if (!hdev || hdev->dev_type != HCI_AMP || - !test_bit(HCI_UP, &hdev->flags)) { - if (hdev) - hci_dev_put(hdev); - - result = L2CAP_MR_BAD_ID; - goto send_move_response; - } - hci_dev_put(hdev); - } - - /* Detect a move collision. Only send a collision response - * if this side has "lost", otherwise proceed with the move. - * The winner has the larger bd_addr. - */ - if ((__chan_is_moving(chan) || - chan->move_role != L2CAP_MOVE_ROLE_NONE) && - bacmp(&conn->hcon->src, &conn->hcon->dst) > 0) { - result = L2CAP_MR_COLLISION; - goto send_move_response; - } - - chan->move_role = L2CAP_MOVE_ROLE_RESPONDER; - l2cap_move_setup(chan); - chan->move_id = req->dest_amp_id; - - if (req->dest_amp_id == AMP_ID_BREDR) { - /* Moving to BR/EDR */ - if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; - result = L2CAP_MR_PEND; - } else { - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; - result = L2CAP_MR_SUCCESS; - } - } else { - chan->move_state = L2CAP_MOVE_WAIT_PREPARE; - /* Placeholder - uncomment when amp functions are available */ - /*amp_accept_physical(chan, req->dest_amp_id);*/ - result = L2CAP_MR_PEND; - } - -send_move_response: - l2cap_send_move_chan_rsp(chan, result); - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); - - return 0; -} - -static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result) -{ - struct l2cap_chan *chan; - struct hci_chan *hchan = NULL; - - chan = l2cap_get_chan_by_scid(conn, icid); - if (!chan) { - l2cap_send_move_chan_cfm_icid(conn, icid); - return; - } - - __clear_chan_timer(chan); - if (result == L2CAP_MR_PEND) - __set_chan_timer(chan, L2CAP_MOVE_ERTX_TIMEOUT); - - switch (chan->move_state) { - case L2CAP_MOVE_WAIT_LOGICAL_COMP: - /* Move confirm will be sent when logical link - * is complete. - */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; - break; - case L2CAP_MOVE_WAIT_RSP_SUCCESS: - if (result == L2CAP_MR_PEND) { - break; - } else if (test_bit(CONN_LOCAL_BUSY, - &chan->conn_state)) { - chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; - } else { - /* Logical link is up or moving to BR/EDR, - * proceed with move - */ - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM_RSP; - l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); - } - break; - case L2CAP_MOVE_WAIT_RSP: - /* Moving to AMP */ - if (result == L2CAP_MR_SUCCESS) { - /* Remote is ready, send confirm immediately - * after logical link is ready - */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; - } else { - /* Both logical link and move success - * are required to confirm - */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_COMP; - } - - /* Placeholder - get hci_chan for logical link */ - if (!hchan) { - /* Logical link not available */ - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - break; - } - - /* If the logical link is not yet connected, do not - * send confirmation. - */ - if (hchan->state != BT_CONNECTED) - break; - - /* Logical link is already ready to go */ - - chan->hs_hcon = hchan->conn; - chan->hs_hcon->l2cap_data = chan->conn; - - if (result == L2CAP_MR_SUCCESS) { - /* Can confirm now */ - l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); - } else { - /* Now only need move success - * to confirm - */ - chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; - } - - l2cap_logical_cfm(chan, hchan, L2CAP_MR_SUCCESS); - break; - default: - /* Any other amp move state means the move failed. */ - chan->move_id = chan->local_amp_id; - l2cap_move_done(chan); - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - } - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); -} - -static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid, - u16 result) -{ - struct l2cap_chan *chan; - - chan = l2cap_get_chan_by_ident(conn, ident); - if (!chan) { - /* Could not locate channel, icid is best guess */ - l2cap_send_move_chan_cfm_icid(conn, icid); - return; - } - - __clear_chan_timer(chan); - - if (chan->move_role == L2CAP_MOVE_ROLE_INITIATOR) { - if (result == L2CAP_MR_COLLISION) { - chan->move_role = L2CAP_MOVE_ROLE_RESPONDER; - } else { - /* Cleanup - cancel move */ - chan->move_id = chan->local_amp_id; - l2cap_move_done(chan); - } - } - - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); -} - -static int l2cap_move_channel_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_rsp *rsp = data; - u16 icid, result; - - if (cmd_len != sizeof(*rsp)) - return -EPROTO; - - icid = le16_to_cpu(rsp->icid); - result = le16_to_cpu(rsp->result); - - BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); - - if (result == L2CAP_MR_SUCCESS || result == L2CAP_MR_PEND) - l2cap_move_continue(conn, icid, result); - else - l2cap_move_fail(conn, cmd->ident, icid, result); - - return 0; -} - -static int l2cap_move_channel_confirm(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_cfm *cfm = data; - struct l2cap_chan *chan; - u16 icid, result; - - if (cmd_len != sizeof(*cfm)) - return -EPROTO; - - icid = le16_to_cpu(cfm->icid); - result = le16_to_cpu(cfm->result); - - BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); - - chan = l2cap_get_chan_by_dcid(conn, icid); - if (!chan) { - /* Spec requires a response even if the icid was not found */ - l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); - return 0; - } - - if (chan->move_state == L2CAP_MOVE_WAIT_CONFIRM) { - if (result == L2CAP_MC_CONFIRMED) { - chan->local_amp_id = chan->move_id; - if (chan->local_amp_id == AMP_ID_BREDR) - __release_logical_link(chan); - } else { - chan->move_id = chan->local_amp_id; - } - - l2cap_move_done(chan); - } - - l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); - - return 0; -} - -static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_cfm_rsp *rsp = data; - struct l2cap_chan *chan; - u16 icid; - - if (cmd_len != sizeof(*rsp)) - return -EPROTO; - - icid = le16_to_cpu(rsp->icid); - - BT_DBG("icid 0x%4.4x", icid); - - chan = l2cap_get_chan_by_scid(conn, icid); - if (!chan) - return 0; - - __clear_chan_timer(chan); - - if (chan->move_state == L2CAP_MOVE_WAIT_CONFIRM_RSP) { - chan->local_amp_id = chan->move_id; - - if (chan->local_amp_id == AMP_ID_BREDR && chan->hs_hchan) - __release_logical_link(chan); - - l2cap_move_done(chan); - } - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); - - return 0; -} - static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data) @@ -5745,7 +4761,6 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, break; case L2CAP_CONN_RSP: - case L2CAP_CREATE_CHAN_RSP: l2cap_connect_create_rsp(conn, cmd, cmd_len, data); break; @@ -5780,26 +4795,6 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, l2cap_information_rsp(conn, cmd, cmd_len, data); break; - case L2CAP_CREATE_CHAN_REQ: - err = l2cap_create_channel_req(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_REQ: - err = l2cap_move_channel_req(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_RSP: - l2cap_move_channel_rsp(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_CFM: - err = l2cap_move_channel_confirm(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_CFM_RSP: - l2cap_move_channel_confirm_rsp(conn, cmd, cmd_len, data); - break; - default: BT_ERR("Unknown BR/EDR signaling command 0x%2.2x", cmd->code); err = -EINVAL; @@ -7051,8 +6046,8 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, if (control->final) { clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state) && - !__chan_is_moving(chan)) { + if (!test_and_clear_bit(CONN_REJ_ACT, + &chan->conn_state)) { control->final = 0; l2cap_retransmit_all(chan, control); } @@ -7245,11 +6240,7 @@ static int l2cap_finish_move(struct l2cap_chan *chan) BT_DBG("chan %p", chan); chan->rx_state = L2CAP_RX_STATE_RECV; - - if (chan->hs_hcon) - chan->conn->mtu = chan->hs_hcon->hdev->block_mtu; - else - chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; + chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; return l2cap_resegment(chan); } @@ -7316,11 +6307,7 @@ static int l2cap_rx_state_wait_f(struct l2cap_chan *chan, */ chan->next_tx_seq = control->reqseq; chan->unacked_frames = 0; - - if (chan->hs_hcon) - chan->conn->mtu = chan->hs_hcon->hdev->block_mtu; - else - chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; + chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; err = l2cap_resegment(chan); @@ -7672,21 +6659,10 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, chan = l2cap_get_chan_by_scid(conn, cid); if (!chan) { - if (cid == L2CAP_CID_A2MP) { - chan = a2mp_channel_create(conn, skb); - if (!chan) { - kfree_skb(skb); - return; - } - - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - } else { - BT_DBG("unknown cid 0x%4.4x", cid); - /* Drop packet and return */ - kfree_skb(skb); - return; - } + BT_DBG("unknown cid 0x%4.4x", cid); + /* Drop packet and return */ + kfree_skb(skb); + return; } BT_DBG("chan %p, len %d", chan, skb->len); @@ -7887,10 +6863,6 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) conn->local_fixed_chan = L2CAP_FC_SIG_BREDR | L2CAP_FC_CONNLESS; - if (hcon->type == ACL_LINK && - hci_dev_test_flag(hcon->hdev, HCI_HS_ENABLED)) - conn->local_fixed_chan |= L2CAP_FC_A2MP; - if (hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED) && (bredr_sc_enabled(hcon->hdev) || hci_dev_test_flag(hcon->hdev, HCI_FORCE_BREDR_SMP))) @@ -7953,7 +6925,7 @@ static void l2cap_chan_by_pid(struct l2cap_chan *chan, void *data) } int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, - bdaddr_t *dst, u8 dst_type) + bdaddr_t *dst, u8 dst_type, u16 timeout) { struct l2cap_conn *conn; struct hci_conn *hcon; @@ -8046,19 +7018,17 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) hcon = hci_connect_le(hdev, dst, dst_type, false, - chan->sec_level, - HCI_LE_CONN_TIMEOUT, + chan->sec_level, timeout, HCI_ROLE_SLAVE); else hcon = hci_connect_le_scan(hdev, dst, dst_type, - chan->sec_level, - HCI_LE_CONN_TIMEOUT, + chan->sec_level, timeout, CONN_REASON_L2CAP_CHAN); } else { u8 auth_type = l2cap_get_auth_type(chan); hcon = hci_connect_acl(hdev, dst, chan->sec_level, auth_type, - CONN_REASON_L2CAP_CHAN); + CONN_REASON_L2CAP_CHAN, timeout); } if (IS_ERR(hcon)) { @@ -8355,11 +7325,6 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) BT_DBG("chan %p scid 0x%4.4x state %s", chan, chan->scid, state_to_string(chan->state)); - if (chan->scid == L2CAP_CID_A2MP) { - l2cap_chan_unlock(chan); - continue; - } - if (!status && encrypt) chan->sec_level = hcon->sec_level; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index e50d3d102078..4287aa6cc988 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -254,7 +254,8 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, chan->mode = L2CAP_MODE_LE_FLOWCTL; err = l2cap_chan_connect(chan, la.l2_psm, __le16_to_cpu(la.l2_cid), - &la.l2_bdaddr, la.l2_bdaddr_type); + &la.l2_bdaddr, la.l2_bdaddr_type, + sk->sk_sndtimeo); if (err) return err; @@ -1027,23 +1028,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (opt > BT_CHANNEL_POLICY_AMP_PREFERRED) { - err = -EINVAL; - break; - } - - if (chan->mode != L2CAP_MODE_ERTM && - chan->mode != L2CAP_MODE_STREAMING) { - err = -EOPNOTSUPP; - break; - } - - chan->chan_policy = (u8) opt; - - if (sk->sk_state == BT_CONNECTED && - chan->move_role == L2CAP_MOVE_ROLE_NONE) - l2cap_move_start(chan); - + err = -EOPNOTSUPP; break; case BT_SNDMTU: diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ee3b4aad8bd8..32ed6e9245a3 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -835,8 +835,6 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (lmp_ssp_capable(hdev)) { settings |= MGMT_SETTING_SSP; - if (IS_ENABLED(CONFIG_BT_HS)) - settings |= MGMT_SETTING_HS; } if (lmp_sc_capable(hdev)) @@ -901,9 +899,6 @@ static u32 get_current_settings(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) settings |= MGMT_SETTING_SSP; - if (hci_dev_test_flag(hdev, HCI_HS_ENABLED)) - settings |= MGMT_SETTING_HS; - if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) settings |= MGMT_SETTING_ADVERTISING; @@ -1390,6 +1385,14 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); + if (!cp->val) { + if (hci_dev_test_flag(hdev, HCI_POWERING_DOWN)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED, + MGMT_STATUS_BUSY); + goto failed; + } + } + if (pending_find(MGMT_OP_SET_POWERED, hdev)) { err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED, MGMT_STATUS_BUSY); @@ -1409,7 +1412,7 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, /* Cancel potentially blocking sync operation before power off */ if (cp->val == 0x00) { - __hci_cmd_sync_cancel(hdev, -EHOSTDOWN); + hci_cmd_sync_cancel_sync(hdev, -EHOSTDOWN); err = hci_cmd_sync_queue(hdev, set_powered_sync, cmd, mgmt_set_powered_complete); } else { @@ -1704,8 +1707,7 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data, new_settings(hdev, cmd->sk); done: - if (cmd) - mgmt_pending_remove(cmd); + mgmt_pending_remove(cmd); hci_dev_unlock(hdev); } @@ -1930,7 +1932,6 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) if (enable && hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED)) { - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); new_settings(hdev, NULL); } @@ -1943,12 +1944,6 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) changed = !hci_dev_test_and_set_flag(hdev, HCI_SSP_ENABLED); } else { changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED); - - if (!changed) - changed = hci_dev_test_and_clear_flag(hdev, - HCI_HS_ENABLED); - else - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, settings_rsp, &match); @@ -2012,11 +2007,6 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) } else { changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED); - if (!changed) - changed = hci_dev_test_and_clear_flag(hdev, - HCI_HS_ENABLED); - else - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } err = send_settings_rsp(sk, MGMT_OP_SET_SSP, hdev); @@ -2062,63 +2052,10 @@ failed: static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { - struct mgmt_mode *cp = data; - bool changed; - u8 status; - int err; - bt_dev_dbg(hdev, "sock %p", sk); - if (!IS_ENABLED(CONFIG_BT_HS)) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, MGMT_STATUS_NOT_SUPPORTED); - - status = mgmt_bredr_support(hdev); - if (status) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status); - - if (!lmp_ssp_capable(hdev)) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_NOT_SUPPORTED); - - if (!hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_REJECTED); - - if (cp->val != 0x00 && cp->val != 0x01) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_INVALID_PARAMS); - - hci_dev_lock(hdev); - - if (pending_find(MGMT_OP_SET_SSP, hdev)) { - err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_BUSY); - goto unlock; - } - - if (cp->val) { - changed = !hci_dev_test_and_set_flag(hdev, HCI_HS_ENABLED); - } else { - if (hdev_is_powered(hdev)) { - err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_REJECTED); - goto unlock; - } - - changed = hci_dev_test_and_clear_flag(hdev, HCI_HS_ENABLED); - } - - err = send_settings_rsp(sk, MGMT_OP_SET_HS, hdev); - if (err < 0) - goto unlock; - - if (changed) - err = new_settings(hdev, sk); - -unlock: - hci_dev_unlock(hdev); - return err; } static void set_le_complete(struct hci_dev *hdev, void *data, int err) @@ -3188,6 +3125,7 @@ failed: static u8 link_to_bdaddr(u8 link_type, u8 addr_type) { switch (link_type) { + case ISO_LINK: case LE_LINK: switch (addr_type) { case ADDR_LE_DEV_PUBLIC: @@ -3505,7 +3443,8 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, if (cp->addr.type == BDADDR_BREDR) { conn = hci_connect_acl(hdev, &cp->addr.bdaddr, sec_level, - auth_type, CONN_REASON_PAIR_DEVICE); + auth_type, CONN_REASON_PAIR_DEVICE, + HCI_ACL_CONN_TIMEOUT); } else { u8 addr_type = le_addr_type(cp->addr.type); struct hci_conn_params *p; @@ -6766,7 +6705,6 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) hci_dev_clear_flag(hdev, HCI_SSP_ENABLED); hci_dev_clear_flag(hdev, HCI_LINK_SECURITY); hci_dev_clear_flag(hdev, HCI_FAST_CONNECTABLE); - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } hci_dev_change_flag(hdev, HCI_BREDR_ENABLED); @@ -8470,7 +8408,7 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, static u8 calculate_name_len(struct hci_dev *hdev) { - u8 buf[HCI_MAX_SHORT_NAME_LENGTH + 3]; + u8 buf[HCI_MAX_SHORT_NAME_LENGTH + 2]; /* len + type + name */ return eir_append_local_name(hdev, buf, 0); } @@ -8829,8 +8767,7 @@ static void add_ext_adv_params_complete(struct hci_dev *hdev, void *data, } unlock: - if (cmd) - mgmt_pending_free(cmd); + mgmt_pending_free(cmd); hci_dev_unlock(hdev); } @@ -9681,6 +9618,9 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, u16 eir_len = 0; u32 flags = 0; + if (test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + return; + /* allocate buff for LE or BR/EDR adv */ if (conn->le_adv_data_len > 0) skb = mgmt_alloc_skb(hdev, MGMT_EV_DEVICE_CONNECTED, @@ -9748,6 +9688,9 @@ bool mgmt_powering_down(struct hci_dev *hdev) struct mgmt_pending_cmd *cmd; struct mgmt_mode *cp; + if (hci_dev_test_flag(hdev, HCI_POWERING_DOWN)) + return true; + cmd = pending_find(MGMT_OP_SET_POWERED, hdev); if (!cmd) return false; @@ -9766,14 +9709,6 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, struct mgmt_ev_device_disconnected ev; struct sock *sk = NULL; - /* The connection is still in hci_conn_hash so test for 1 - * instead of 0 to know if this is the last one. - */ - if (mgmt_powering_down(hdev) && hci_conn_count(hdev) == 1) { - cancel_delayed_work(&hdev->power_off); - queue_work(hdev->req_workqueue, &hdev->power_off.work); - } - if (!mgmt_connected) return; @@ -9830,14 +9765,6 @@ void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, { struct mgmt_ev_connect_failed ev; - /* The connection is still in hci_conn_hash so test for 1 - * instead of 0 to know if this is the last one. - */ - if (mgmt_powering_down(hdev) && hci_conn_count(hdev) == 1) { - cancel_delayed_work(&hdev->power_off); - queue_work(hdev->req_workqueue, &hdev->power_off.work); - } - bacpy(&ev.addr.bdaddr, bdaddr); ev.addr.type = link_to_bdaddr(link_type, addr_type); ev.status = mgmt_status(status); @@ -10071,6 +9998,9 @@ void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status) /* If this is a HCI command related to powering on the * HCI dev don't send any mgmt signals. */ + if (hci_dev_test_flag(hdev, HCI_POWERING_DOWN)) + return; + if (pending_find(MGMT_OP_SET_POWERED, hdev)) return; } diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index 630e3023273b..9612c5d1b13f 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -875,6 +875,7 @@ static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data) remove = true; goto done; } + cp->sub_opcode = MSFT_OP_LE_MONITOR_ADVERTISEMENT; cp->rssi_high = address_filter->rssi_high; cp->rssi_low = address_filter->rssi_low; @@ -887,6 +888,8 @@ static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data) skb = __hci_cmd_sync(hdev, hdev->msft_opcode, size, cp, HCI_CMD_TIMEOUT); + kfree(cp); + if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to enable address %pMR filter", &address_filter->bdaddr); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index c736186aba26..43daf965a01e 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -264,7 +264,8 @@ static int sco_connect(struct sock *sk) } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, - sco_pi(sk)->setting, &sco_pi(sk)->codec); + sco_pi(sk)->setting, &sco_pi(sk)->codec, + sk->sk_sndtimeo); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 8906f7bdf4a9..de33dc1b0daa 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -7,7 +7,7 @@ #include <linux/bpf.h> #include <linux/btf.h> -extern struct bpf_struct_ops bpf_bpf_dummy_ops; +static struct bpf_struct_ops bpf_bpf_dummy_ops; /* A common type for test_N with return value in bpf_dummy_ops */ typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...); @@ -22,6 +22,8 @@ struct bpf_dummy_ops_test_args { struct bpf_dummy_ops_state state; }; +static struct btf *bpf_dummy_ops_btf; + static struct bpf_dummy_ops_test_args * dummy_ops_init_args(const union bpf_attr *kattr, unsigned int nr) { @@ -89,10 +91,17 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, struct bpf_tramp_link *link = NULL; void *image = NULL; unsigned int op_idx; + u32 image_off = 0; int prog_ret; + s32 type_id; int err; - if (prog->aux->attach_btf_id != st_ops->type_id) + type_id = btf_find_by_name_kind(bpf_dummy_ops_btf, + bpf_bpf_dummy_ops.name, + BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + if (prog->aux->attach_btf_id != type_id) return -EOPNOTSUPP; func_proto = prog->aux->attach_func_proto; @@ -106,12 +115,6 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, goto out; } - image = arch_alloc_bpf_trampoline(PAGE_SIZE); - if (!image) { - err = -ENOMEM; - goto out; - } - link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; @@ -125,7 +128,8 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, err = bpf_struct_ops_prepare_trampoline(tlinks, link, &st_ops->func_models[op_idx], &dummy_ops_test_ret_function, - image, image + PAGE_SIZE); + &image, &image_off, + true); if (err < 0) goto out; @@ -139,7 +143,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, err = -EFAULT; out: kfree(args); - arch_free_bpf_trampoline(image, PAGE_SIZE); + bpf_struct_ops_image_free(image); if (link) bpf_link_put(&link->link); kfree(tlinks); @@ -148,6 +152,7 @@ out: static int bpf_dummy_init(struct btf *btf) { + bpf_dummy_ops_btf = btf; return 0; } @@ -169,7 +174,7 @@ static int bpf_dummy_ops_check_member(const struct btf_type *t, case offsetof(struct bpf_dummy_ops, test_sleepable): break; default: - if (prog->aux->sleepable) + if (prog->sleepable) return -EINVAL; } @@ -247,7 +252,7 @@ static struct bpf_dummy_ops __bpf_bpf_dummy_ops = { .test_sleepable = bpf_dummy_test_sleepable, }; -struct bpf_struct_ops bpf_bpf_dummy_ops = { +static struct bpf_struct_ops bpf_bpf_dummy_ops = { .verifier_ops = &bpf_dummy_verifier_ops, .init = bpf_dummy_init, .check_member = bpf_dummy_ops_check_member, @@ -256,4 +261,11 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = { .unreg = bpf_dummy_unreg, .name = "bpf_dummy_ops", .cfi_stubs = &__bpf_bpf_dummy_ops, + .owner = THIS_MODULE, }; + +static int __init bpf_dummy_struct_ops_init(void) +{ + return register_bpf_struct_ops(&bpf_bpf_dummy_ops, bpf_dummy_ops); +} +late_initcall(bpf_dummy_struct_ops_init); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index dfd919374017..61efeadaff8d 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -12,6 +12,7 @@ #include <linux/rcupdate_trace.h> #include <linux/sched/signal.h> #include <net/bpf_sk_storage.h> +#include <net/hotdata.h> #include <net/sock.h> #include <net/tcp.h> #include <net/net_namespace.h> @@ -254,7 +255,8 @@ static int xdp_recv_frames(struct xdp_frame **frames, int nframes, int i, n; LIST_HEAD(list); - n = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, (void **)skbs); + n = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, nframes, + (void **)skbs); if (unlikely(n == 0)) { for (i = 0; i < nframes; i++) xdp_return_frame(frames[i]); @@ -617,21 +619,21 @@ CFI_NOSEAL(bpf_kfunc_call_memb_release_dtor); __bpf_kfunc_end_defs(); -BTF_SET8_START(bpf_test_modify_return_ids) +BTF_KFUNCS_START(bpf_test_modify_return_ids) BTF_ID_FLAGS(func, bpf_modify_return_test) BTF_ID_FLAGS(func, bpf_modify_return_test2) BTF_ID_FLAGS(func, bpf_fentry_test1, KF_SLEEPABLE) -BTF_SET8_END(bpf_test_modify_return_ids) +BTF_KFUNCS_END(bpf_test_modify_return_ids) static const struct btf_kfunc_id_set bpf_test_modify_return_set = { .owner = THIS_MODULE, .set = &bpf_test_modify_return_ids, }; -BTF_SET8_START(test_sk_check_kfunc_ids) +BTF_KFUNCS_START(test_sk_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_kfunc_call_test_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_kfunc_call_memb_release, KF_RELEASE) -BTF_SET8_END(test_sk_check_kfunc_ids) +BTF_KFUNCS_END(test_sk_check_kfunc_ids) static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, u32 size, u32 headroom, u32 tailroom) diff --git a/net/bridge/br.c b/net/bridge/br.c index ac19b797dbec..2cab878e0a39 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -356,26 +356,21 @@ void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on) clear_bit(opt, &br->options); } -static void __net_exit br_net_exit_batch(struct list_head *net_list) +static void __net_exit br_net_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { struct net_device *dev; struct net *net; - LIST_HEAD(list); - - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) for_each_netdev(net, dev) if (netif_is_bridge_master(dev)) - br_dev_delete(dev, &list); - - unregister_netdevice_many(&list); - - rtnl_unlock(); + br_dev_delete(dev, dev_to_kill); } static struct pernet_operations br_net_ops = { - .exit_batch = br_net_exit_batch, + .exit_batch_rtnl = br_net_exit_batch_rtnl, }; static const struct stp_proto br_stp_proto = { diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 65cee0ad3c1b..c366ccc8b3db 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -108,38 +108,23 @@ out: return NETDEV_TX_OK; } -static struct lock_class_key bridge_netdev_addr_lock_key; - -static void br_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key); -} - static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - err = br_fdb_hash_init(br); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } err = br_mdb_hash_init(br); if (err) { - free_percpu(dev->tstats); br_fdb_hash_fini(br); return err; } err = br_vlan_init(br); if (err) { - free_percpu(dev->tstats); br_mdb_hash_fini(br); br_fdb_hash_fini(br); return err; @@ -147,14 +132,14 @@ static int br_dev_init(struct net_device *dev) err = br_multicast_init_stats(br); if (err) { - free_percpu(dev->tstats); br_vlan_flush(br); br_mdb_hash_fini(br); br_fdb_hash_fini(br); + return err; } - br_set_lockdep_class(dev); - return err; + netdev_lockdep_set_classes(dev); + return 0; } static void br_dev_uninit(struct net_device *dev) @@ -166,7 +151,6 @@ static void br_dev_uninit(struct net_device *dev) br_vlan_flush(br); br_mdb_hash_fini(br); br_fdb_hash_fini(br); - free_percpu(dev->tstats); } static int br_dev_open(struct net_device *dev) @@ -481,7 +465,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_fill_forward_path = br_fill_forward_path, }; -static struct device_type br_type = { +static const struct device_type br_type = { .name = "bridge", }; @@ -503,6 +487,7 @@ void br_dev_setup(struct net_device *dev) dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->vlan_features = COMMON_FEATURES; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; br->dev = dev; spin_lock_init(&br->lock); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index c622de5eccd0..c77591e63841 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -35,10 +35,7 @@ static struct kmem_cache *br_fdb_cache __read_mostly; int __init br_fdb_init(void) { - br_fdb_cache = kmem_cache_create("bridge_fdb_cache", - sizeof(struct net_bridge_fdb_entry), - 0, - SLAB_HWCACHE_ALIGN, NULL); + br_fdb_cache = KMEM_CACHE(net_bridge_fdb_entry, SLAB_HWCACHE_ALIGN); if (!br_fdb_cache) return -ENOMEM; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5ad4abfcb7ba..2cf4fc756263 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -455,7 +455,8 @@ static int br_fill_ifinfo(struct sk_buff *skb, u32 filter_mask, const struct net_device *dev, bool getlink) { - u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + u8 operstate = netif_running(dev) ? READ_ONCE(dev->operstate) : + IF_OPER_DOWN; struct nlattr *af = NULL; struct net_bridge *br; struct ifinfomsg *hdr; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 15f44d026e75..9c2fffb827ab 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -841,7 +841,7 @@ void br_vlan_flush(struct net_bridge *br) vg = br_vlan_group(br); __vlan_flush(br, NULL, vg); RCU_INIT_POINTER(br->vlgrp, NULL); - synchronize_rcu(); + synchronize_net(); __vlan_group_free(vg); } @@ -1372,7 +1372,7 @@ void nbp_vlan_flush(struct net_bridge_port *port) vg = nbp_vlan_group(port); __vlan_flush(port->br, port, vg); RCU_INIT_POINTER(port->vlgrp, NULL); - synchronize_rcu(); + synchronize_net(); __vlan_group_free(vg); } diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 7f304a19ac1b..104c0125e32e 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -39,6 +39,10 @@ config NF_CONNTRACK_BRIDGE To compile it as a module, choose M here. If unsure, say N. +# old sockopt interface and eval loop +config BRIDGE_NF_EBTABLES_LEGACY + tristate + menuconfig BRIDGE_NF_EBTABLES tristate "Ethernet Bridge tables (ebtables) support" depends on BRIDGE && NETFILTER && NETFILTER_XTABLES @@ -55,6 +59,7 @@ if BRIDGE_NF_EBTABLES # config BRIDGE_EBT_BROUTE tristate "ebt: broute table support" + select BRIDGE_NF_EBTABLES_LEGACY help The ebtables broute table is used to define rules that decide between bridging and routing frames, giving Linux the functionality of a @@ -65,6 +70,7 @@ config BRIDGE_EBT_BROUTE config BRIDGE_EBT_T_FILTER tristate "ebt: filter table support" + select BRIDGE_NF_EBTABLES_LEGACY help The ebtables filter table is used to define frame filtering rules at local input, forwarding and local output. See the man page for @@ -74,6 +80,7 @@ config BRIDGE_EBT_T_FILTER config BRIDGE_EBT_T_NAT tristate "ebt: nat table support" + select BRIDGE_NF_EBTABLES_LEGACY help The ebtables nat table is used to define rules that alter the MAC source address (MAC SNAT) or the MAC destination address (MAC DNAT). diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile index 1c9ce49ab651..b9a1303da977 100644 --- a/net/bridge/netfilter/Makefile +++ b/net/bridge/netfilter/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_NFT_BRIDGE_REJECT) += nft_reject_bridge.o # connection tracking obj-$(CONFIG_NF_CONNTRACK_BRIDGE) += nf_conntrack_bridge.o -obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o +obj-$(CONFIG_BRIDGE_NF_EBTABLES_LEGACY) += ebtables.o # tables obj-$(CONFIG_BRIDGE_EBT_BROUTE) += ebtable_broute.o diff --git a/net/can/af_can.c b/net/can/af_can.c index 7343fd487dbe..707576eeeb58 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -865,6 +865,8 @@ static __init int can_init(void) /* check for correct padding to be able to use the structs similarly */ BUILD_BUG_ON(offsetof(struct can_frame, len) != offsetof(struct canfd_frame, len) || + offsetof(struct can_frame, len) != + offsetof(struct canxl_frame, flags) || offsetof(struct can_frame, data) != offsetof(struct canfd_frame, data)); diff --git a/net/can/bcm.c b/net/can/bcm.c index 9168114fc87f..27d5fcf0eac9 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -72,9 +72,11 @@ #define BCM_TIMER_SEC_MAX (400 * 24 * 60 * 60) /* use of last_frames[index].flags */ +#define RX_LOCAL 0x10 /* frame was created on the local host */ +#define RX_OWN 0x20 /* frame was sent via the socket it was received on */ #define RX_RECV 0x40 /* received data for this element */ #define RX_THR 0x80 /* element not been sent due to throttle feature */ -#define BCM_CAN_FLAGS_MASK 0x3F /* to clean private flags after usage */ +#define BCM_CAN_FLAGS_MASK 0x0F /* to clean private flags after usage */ /* get best masking value for can_rx_register() for a given single can_id */ #define REGMASK(id) ((id & CAN_EFF_FLAG) ? \ @@ -138,6 +140,16 @@ static LIST_HEAD(bcm_notifier_list); static DEFINE_SPINLOCK(bcm_notifier_lock); static struct bcm_sock *bcm_busy_notifier; +/* Return pointer to store the extra msg flags for bcm_recvmsg(). + * We use the space of one unsigned int beyond the 'struct sockaddr_can' + * in skb->cb. + */ +static inline unsigned int *bcm_flags(struct sk_buff *skb) +{ + /* return pointer after struct sockaddr_can */ + return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]); +} + static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; @@ -325,6 +337,7 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, struct sock *sk = op->sk; unsigned int datalen = head->nframes * op->cfsiz; int err; + unsigned int *pflags; skb = alloc_skb(sizeof(*head) + datalen, gfp_any()); if (!skb) @@ -332,6 +345,14 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, skb_put_data(skb, head, sizeof(*head)); + /* ensure space for sockaddr_can and msg flags */ + sock_skb_cb_check_size(sizeof(struct sockaddr_can) + + sizeof(unsigned int)); + + /* initialize msg flags */ + pflags = bcm_flags(skb); + *pflags = 0; + if (head->nframes) { /* CAN frames starting here */ firstframe = (struct canfd_frame *)skb_tail_pointer(skb); @@ -344,8 +365,14 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, * relevant for updates that are generated by the * BCM, where nframes is 1 */ - if (head->nframes == 1) + if (head->nframes == 1) { + if (firstframe->flags & RX_LOCAL) + *pflags |= MSG_DONTROUTE; + if (firstframe->flags & RX_OWN) + *pflags |= MSG_CONFIRM; + firstframe->flags &= BCM_CAN_FLAGS_MASK; + } } if (has_timestamp) { @@ -360,7 +387,6 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, * containing the interface index. */ - sock_skb_cb_check_size(sizeof(struct sockaddr_can)); addr = (struct sockaddr_can *)skb->cb; memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; @@ -444,7 +470,7 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) op->frames_filtered = op->frames_abs = 0; /* this element is not throttled anymore */ - data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV); + data->flags &= ~RX_THR; memset(&head, 0, sizeof(head)); head.opcode = RX_CHANGED; @@ -465,13 +491,17 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) */ static void bcm_rx_update_and_send(struct bcm_op *op, struct canfd_frame *lastdata, - const struct canfd_frame *rxdata) + const struct canfd_frame *rxdata, + unsigned char traffic_flags) { memcpy(lastdata, rxdata, op->cfsiz); /* mark as used and throttled by default */ lastdata->flags |= (RX_RECV|RX_THR); + /* add own/local/remote traffic flags */ + lastdata->flags |= traffic_flags; + /* throttling mode inactive ? */ if (!op->kt_ival2) { /* send RX_CHANGED to the user immediately */ @@ -508,7 +538,8 @@ rx_changed_settime: * received data stored in op->last_frames[] */ static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index, - const struct canfd_frame *rxdata) + const struct canfd_frame *rxdata, + unsigned char traffic_flags) { struct canfd_frame *cf = op->frames + op->cfsiz * index; struct canfd_frame *lcf = op->last_frames + op->cfsiz * index; @@ -521,7 +552,7 @@ static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index, if (!(lcf->flags & RX_RECV)) { /* received data for the first time => send update to user */ - bcm_rx_update_and_send(op, lcf, rxdata); + bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } @@ -529,7 +560,7 @@ static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index, for (i = 0; i < rxdata->len; i += 8) { if ((get_u64(cf, i) & get_u64(rxdata, i)) != (get_u64(cf, i) & get_u64(lcf, i))) { - bcm_rx_update_and_send(op, lcf, rxdata); + bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } } @@ -537,7 +568,7 @@ static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index, if (op->flags & RX_CHECK_DLC) { /* do a real check in CAN frame length */ if (rxdata->len != lcf->len) { - bcm_rx_update_and_send(op, lcf, rxdata); + bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } } @@ -644,6 +675,7 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) struct bcm_op *op = (struct bcm_op *)data; const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data; unsigned int i; + unsigned char traffic_flags; if (op->can_id != rxframe->can_id) return; @@ -673,15 +705,24 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) return; } + /* compute flags to distinguish between own/local/remote CAN traffic */ + traffic_flags = 0; + if (skb->sk) { + traffic_flags |= RX_LOCAL; + if (skb->sk == op->sk) + traffic_flags |= RX_OWN; + } + if (op->flags & RX_FILTER_ID) { /* the easiest case */ - bcm_rx_update_and_send(op, op->last_frames, rxframe); + bcm_rx_update_and_send(op, op->last_frames, rxframe, + traffic_flags); goto rx_starttimer; } if (op->nframes == 1) { /* simple compare with index 0 */ - bcm_rx_cmp_to_index(op, 0, rxframe); + bcm_rx_cmp_to_index(op, 0, rxframe, traffic_flags); goto rx_starttimer; } @@ -698,7 +739,8 @@ static void bcm_rx_handler(struct sk_buff *skb, void *data) if ((get_u64(op->frames, 0) & get_u64(rxframe, 0)) == (get_u64(op->frames, 0) & get_u64(op->frames + op->cfsiz * i, 0))) { - bcm_rx_cmp_to_index(op, i, rxframe); + bcm_rx_cmp_to_index(op, i, rxframe, + traffic_flags); break; } } @@ -1675,6 +1717,9 @@ static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } + /* assign the flags that have been recorded in bcm_send_to_user() */ + msg->msg_flags |= *(bcm_flags(skb)); + skb_free_datagram(sk, skb); return size; diff --git a/net/can/isotp.c b/net/can/isotp.c index d1c6f206f429..25bac0fafc83 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -381,8 +381,9 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) return 1; } - /* get communication parameters only from the first FC frame */ - if (so->tx.state == ISOTP_WAIT_FIRST_FC) { + /* get static/dynamic communication params from first/every FC frame */ + if (so->tx.state == ISOTP_WAIT_FIRST_FC || + so->opt.flags & CAN_ISOTP_DYN_FC_PARMS) { so->txfc.bs = cf->data[ae + 1]; so->txfc.stmin = cf->data[ae + 2]; diff --git a/net/can/raw.c b/net/can/raw.c index e6b822624ba2..00533f64d69d 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -91,6 +91,10 @@ struct raw_sock { int recv_own_msgs; int fd_frames; int xl_frames; + struct can_raw_vcid_options raw_vcid_opts; + canid_t tx_vcid_shifted; + canid_t rx_vcid_shifted; + canid_t rx_vcid_mask_shifted; int join_filters; int count; /* number of active filters */ struct can_filter dfilter; /* default/single filter */ @@ -134,10 +138,29 @@ static void raw_rcv(struct sk_buff *oskb, void *data) return; /* make sure to not pass oversized frames to the socket */ - if ((!ro->fd_frames && can_is_canfd_skb(oskb)) || - (!ro->xl_frames && can_is_canxl_skb(oskb))) + if (!ro->fd_frames && can_is_canfd_skb(oskb)) return; + if (can_is_canxl_skb(oskb)) { + struct canxl_frame *cxl = (struct canxl_frame *)oskb->data; + + /* make sure to not pass oversized frames to the socket */ + if (!ro->xl_frames) + return; + + /* filter CAN XL VCID content */ + if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_RX_FILTER) { + /* apply VCID filter if user enabled the filter */ + if ((cxl->prio & ro->rx_vcid_mask_shifted) != + (ro->rx_vcid_shifted & ro->rx_vcid_mask_shifted)) + return; + } else { + /* no filter => do not forward VCID tagged frames */ + if (cxl->prio & CANXL_VCID_MASK) + return; + } + } + /* eliminate multiple filter matches for the same skb */ if (this_cpu_ptr(ro->uniq)->skb == oskb && this_cpu_ptr(ro->uniq)->skbcnt == can_skb_prv(oskb)->skbcnt) { @@ -698,6 +721,19 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->fd_frames = ro->xl_frames; break; + case CAN_RAW_XL_VCID_OPTS: + if (optlen != sizeof(ro->raw_vcid_opts)) + return -EINVAL; + + if (copy_from_sockptr(&ro->raw_vcid_opts, optval, optlen)) + return -EFAULT; + + /* prepare 32 bit values for handling in hot path */ + ro->tx_vcid_shifted = ro->raw_vcid_opts.tx_vcid << CANXL_VCID_OFFSET; + ro->rx_vcid_shifted = ro->raw_vcid_opts.rx_vcid << CANXL_VCID_OFFSET; + ro->rx_vcid_mask_shifted = ro->raw_vcid_opts.rx_vcid_mask << CANXL_VCID_OFFSET; + break; + case CAN_RAW_JOIN_FILTERS: if (optlen != sizeof(ro->join_filters)) return -EINVAL; @@ -720,7 +756,6 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, struct raw_sock *ro = raw_sk(sk); int len; void *val; - int err = 0; if (level != SOL_CAN_RAW) return -EINVAL; @@ -730,7 +765,9 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, return -EINVAL; switch (optname) { - case CAN_RAW_FILTER: + case CAN_RAW_FILTER: { + int err = 0; + lock_sock(sk); if (ro->count > 0) { int fsize = ro->count * sizeof(struct can_filter); @@ -755,7 +792,7 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, if (!err) err = put_user(len, optlen); return err; - + } case CAN_RAW_ERR_FILTER: if (len > sizeof(can_err_mask_t)) len = sizeof(can_err_mask_t); @@ -786,6 +823,25 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, val = &ro->xl_frames; break; + case CAN_RAW_XL_VCID_OPTS: { + int err = 0; + + /* user space buffer to small for VCID opts? */ + if (len < sizeof(ro->raw_vcid_opts)) { + /* return -ERANGE and needed space in optlen */ + err = -ERANGE; + if (put_user(sizeof(ro->raw_vcid_opts), optlen)) + err = -EFAULT; + } else { + if (len > sizeof(ro->raw_vcid_opts)) + len = sizeof(ro->raw_vcid_opts); + if (copy_to_user(optval, &ro->raw_vcid_opts, len)) + err = -EFAULT; + } + if (!err) + err = put_user(len, optlen); + return err; + } case CAN_RAW_JOIN_FILTERS: if (len > sizeof(int)) len = sizeof(int); @@ -803,23 +859,41 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, return 0; } -static bool raw_bad_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) +static void raw_put_canxl_vcid(struct raw_sock *ro, struct sk_buff *skb) +{ + struct canxl_frame *cxl = (struct canxl_frame *)skb->data; + + /* sanitize non CAN XL bits */ + cxl->prio &= (CANXL_PRIO_MASK | CANXL_VCID_MASK); + + /* clear VCID in CAN XL frame if pass through is disabled */ + if (!(ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_PASS)) + cxl->prio &= CANXL_PRIO_MASK; + + /* set VCID in CAN XL frame if enabled */ + if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_SET) { + cxl->prio &= CANXL_PRIO_MASK; + cxl->prio |= ro->tx_vcid_shifted; + } +} + +static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) { /* Classical CAN -> no checks for flags and device capabilities */ if (can_is_can_skb(skb)) - return false; + return CAN_MTU; /* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */ if (ro->fd_frames && can_is_canfd_skb(skb) && (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu))) - return false; + return CANFD_MTU; /* CAN XL -> needs to be enabled and a CAN XL device */ if (ro->xl_frames && can_is_canxl_skb(skb) && can_is_canxl_dev_mtu(mtu)) - return false; + return CANXL_MTU; - return true; + return 0; } static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) @@ -829,6 +903,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) struct sockcm_cookie sockc; struct sk_buff *skb; struct net_device *dev; + unsigned int txmtu; int ifindex; int err = -EINVAL; @@ -869,9 +944,16 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) goto free_skb; err = -EINVAL; - if (raw_bad_txframe(ro, skb, dev->mtu)) + + /* check for valid CAN (CC/FD/XL) frame content */ + txmtu = raw_check_txframe(ro, skb, dev->mtu); + if (!txmtu) goto free_skb; + /* only CANXL: clear/forward/set VCID value */ + if (txmtu == CANXL_MTU) + raw_put_canxl_vcid(ro, skb); + sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); diff --git a/net/core/Makefile b/net/core/Makefile index 821aec06abf1..6e6548011fae 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -18,6 +18,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o obj-y += net-sysfs.o +obj-y += hotdata.o obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o diff --git a/net/core/dev.c b/net/core/dev.c index a892f7265189..0766a245816b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -153,41 +153,21 @@ #include <linux/prandom.h> #include <linux/once_lite.h> #include <net/netdev_rx_queue.h> +#include <net/page_pool/types.h> +#include <net/page_pool/helpers.h> +#include <net/rps.h> #include "dev.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; -struct list_head ptype_all __read_mostly; /* Taps */ static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack); -/* - * The @dev_base_head list is protected by @dev_base_lock and the rtnl - * semaphore. - * - * Pure readers hold dev_base_lock for reading, or rcu_read_lock() - * - * Writers must hold the rtnl semaphore while they loop through the - * dev_base_head list, and hold dev_base_lock for writing when they do the - * actual updates. This allows pure readers to access the list even - * while a writer is preparing to update it. - * - * To put it another way, dev_base_lock is held for writing only to - * protect against pure readers; the rtnl semaphore provides the - * protection against other writers. - * - * See, for example usages, register_netdevice() and - * unregister_netdevice(), which must be called with the rtnl - * semaphore held. - */ -DEFINE_RWLOCK(dev_base_lock); -EXPORT_SYMBOL(dev_base_lock); - static DEFINE_MUTEX(ifalias_mutex); /* protects napi_hash addition/deletion and napi_gen_id */ @@ -200,8 +180,9 @@ static DECLARE_RWSEM(devnet_rename_sem); static inline void dev_base_seq_inc(struct net *net) { - while (++net->dev_base_seq == 0) - ; + unsigned int val = net->dev_base_seq + 1; + + WRITE_ONCE(net->dev_base_seq, val ?: 1); } static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) @@ -341,13 +322,22 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name) return 0; } -static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) +static void netdev_name_node_alt_free(struct rcu_head *head) { - list_del(&name_node->list); + struct netdev_name_node *name_node = + container_of(head, struct netdev_name_node, rcu); + kfree(name_node->name); netdev_name_node_free(name_node); } +static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) +{ + netdev_name_node_del(name_node); + list_del(&name_node->list); + call_rcu(&name_node->rcu, netdev_name_node_alt_free); +} + int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; @@ -362,10 +352,7 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) if (name_node == dev->name_node || name_node->dev != dev) return -EINVAL; - netdev_name_node_del(name_node); - synchronize_rcu(); __netdev_name_node_alt_destroy(name_node); - return 0; } @@ -373,8 +360,10 @@ static void netdev_name_node_alt_flush(struct net_device *dev) { struct netdev_name_node *name_node, *tmp; - list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) - __netdev_name_node_alt_destroy(name_node); + list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) { + list_del(&name_node->list); + netdev_name_node_alt_free(&name_node->rcu); + } } /* Device list insertion */ @@ -385,12 +374,10 @@ static void list_netdevice(struct net_device *dev) ASSERT_RTNL(); - write_lock(&dev_base_lock); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); - write_unlock(&dev_base_lock); netdev_for_each_altname(dev, name_node) netdev_name_node_add(net, name_node); @@ -404,7 +391,7 @@ static void list_netdevice(struct net_device *dev) /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */ -static void unlist_netdevice(struct net_device *dev, bool lock) +static void unlist_netdevice(struct net_device *dev) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); @@ -417,13 +404,9 @@ static void unlist_netdevice(struct net_device *dev, bool lock) netdev_name_node_del(name_node); /* Unlink dev from the device chain */ - if (lock) - write_lock(&dev_base_lock); list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); - if (lock) - write_unlock(&dev_base_lock); dev_base_seq_inc(dev_net(dev)); } @@ -442,6 +425,12 @@ static RAW_NOTIFIER_HEAD(netdev_chain); DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); EXPORT_PER_CPU_SYMBOL(softnet_data); +/* Page_pool has a lockless array/stack to alloc/recycle pages. + * PP consumers must pay attention to run APIs in the appropriate context + * (e.g. NAPI context). + */ +static DEFINE_PER_CPU_ALIGNED(struct page_pool *, system_page_pool); + #ifdef CONFIG_LOCKDEP /* * register_netdevice() inits txq->_xmit_lock and sets lockdep class @@ -551,7 +540,7 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) static inline struct list_head *ptype_head(const struct packet_type *pt) { if (pt->type == htons(ETH_P_ALL)) - return pt->dev ? &pt->dev->ptype_all : &ptype_all; + return pt->dev ? &pt->dev->ptype_all : &net_hotdata.ptype_all; else return pt->dev ? &pt->dev->ptype_specific : &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; @@ -653,7 +642,7 @@ int dev_get_iflink(const struct net_device *dev) if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink) return dev->netdev_ops->ndo_get_iflink(dev); - return dev->ifindex; + return READ_ONCE(dev->ifindex); } EXPORT_SYMBOL(dev_get_iflink); @@ -738,9 +727,9 @@ EXPORT_SYMBOL_GPL(dev_fill_forward_path); * @net: the applicable net namespace * @name: name to find * - * Find an interface by name. Must be called under RTNL semaphore - * or @dev_base_lock. If the name is found a pointer to the device - * is returned. If the name is not found then %NULL is returned. The + * Find an interface by name. Must be called under RTNL semaphore. + * If the name is found a pointer to the device is returned. + * If the name is not found then %NULL is returned. The * reference counters are not incremented so the caller must be * careful with locks. */ @@ -821,8 +810,7 @@ EXPORT_SYMBOL(netdev_get_by_name); * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful - * about locking. The caller must hold either the RTNL semaphore - * or @dev_base_lock. + * about locking. The caller must hold the RTNL semaphore. */ struct net_device *__dev_get_by_index(struct net *net, int ifindex) @@ -1212,13 +1200,13 @@ int dev_change_name(struct net_device *dev, const char *newname) dev->flags & IFF_UP ? " (while UP)" : ""); old_assign_type = dev->name_assign_type; - dev->name_assign_type = NET_NAME_RENAMED; + WRITE_ONCE(dev->name_assign_type, NET_NAME_RENAMED); rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); - dev->name_assign_type = old_assign_type; + WRITE_ONCE(dev->name_assign_type, old_assign_type); up_write(&devnet_rename_sem); return ret; } @@ -1227,15 +1215,11 @@ rollback: netdev_adjacent_rename_links(dev, oldname); - write_lock(&dev_base_lock); netdev_name_node_del(dev->name_node); - write_unlock(&dev_base_lock); - synchronize_rcu(); + synchronize_net(); - write_lock(&dev_base_lock); netdev_name_node_add(net, dev->name_node); - write_unlock(&dev_base_lock); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); ret = notifier_to_errno(ret); @@ -1247,7 +1231,7 @@ rollback: down_write(&devnet_rename_sem); memcpy(dev->name, oldname, IFNAMSIZ); memcpy(oldname, newname, IFNAMSIZ); - dev->name_assign_type = old_assign_type; + WRITE_ONCE(dev->name_assign_type, old_assign_type); old_assign_type = NET_NAME_RENAMED; goto rollback; } else { @@ -2242,7 +2226,8 @@ static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) */ bool dev_nit_active(struct net_device *dev) { - return !list_empty(&ptype_all) || !list_empty(&dev->ptype_all); + return !list_empty(&net_hotdata.ptype_all) || + !list_empty(&dev->ptype_all); } EXPORT_SYMBOL_GPL(dev_nit_active); @@ -2253,10 +2238,9 @@ EXPORT_SYMBOL_GPL(dev_nit_active); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { - struct packet_type *ptype; + struct list_head *ptype_list = &net_hotdata.ptype_all; + struct packet_type *ptype, *pt_prev = NULL; struct sk_buff *skb2 = NULL; - struct packet_type *pt_prev = NULL; - struct list_head *ptype_list = &ptype_all; rcu_read_lock(); again: @@ -2302,7 +2286,7 @@ again: pt_prev = ptype; } - if (ptype_list == &ptype_all) { + if (ptype_list == &net_hotdata.ptype_all) { ptype_list = &dev->ptype_all; goto again; } @@ -4421,19 +4405,10 @@ EXPORT_SYMBOL(__dev_direct_xmit); * Receiver routines *************************************************************************/ -int netdev_max_backlog __read_mostly = 1000; -EXPORT_SYMBOL(netdev_max_backlog); - -int netdev_tstamp_prequeue __read_mostly = 1; unsigned int sysctl_skb_defer_max __read_mostly = 64; -int netdev_budget __read_mostly = 300; -/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ -unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ -int dev_rx_weight __read_mostly = 64; -int dev_tx_weight __read_mostly = 64; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -4475,12 +4450,6 @@ static inline void ____napi_schedule(struct softnet_data *sd, #ifdef CONFIG_RPS -/* One global table that all flow-based protocols share. */ -struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; -EXPORT_SYMBOL(rps_sock_flow_table); -u32 rps_cpu_mask __read_mostly; -EXPORT_SYMBOL(rps_cpu_mask); - struct static_key_false rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); struct static_key_false rfs_needed __read_mostly; @@ -4572,7 +4541,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, if (!hash) goto done; - sock_flow_table = rcu_dereference(rps_sock_flow_table); + sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); if (flow_table && sock_flow_table) { struct rps_dev_flow *rflow; u32 next_cpu; @@ -4582,10 +4551,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). */ ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); - if ((ident ^ hash) & ~rps_cpu_mask) + if ((ident ^ hash) & ~net_hotdata.rps_cpu_mask) goto try_rps; - next_cpu = ident & rps_cpu_mask; + next_cpu = ident & net_hotdata.rps_cpu_mask; /* OK, now we know there is a match, * we can look at the local (per receive queue) flow table @@ -4734,7 +4703,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) struct softnet_data *sd; unsigned int old_flow, new_flow; - if (qlen < (READ_ONCE(netdev_max_backlog) >> 1)) + if (qlen < (READ_ONCE(net_hotdata.max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); @@ -4782,7 +4751,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) { + if (qlen <= READ_ONCE(net_hotdata.max_backlog) && + !skb_flow_limit(skb, qlen)) { if (qlen) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); @@ -4858,6 +4828,12 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, skb_headlen(skb) + mac_len, true); + if (skb_is_nonlinear(skb)) { + skb_shinfo(skb)->xdp_frags_size = skb->data_len; + xdp_buff_set_frags_flag(xdp); + } else { + xdp_buff_clear_frags_flag(xdp); + } orig_data_end = xdp->data_end; orig_data = xdp->data; @@ -4887,6 +4863,14 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, skb->len += off; /* positive on grow, negative on shrink */ } + /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers + * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. + */ + if (xdp_buff_has_frags(xdp)) + skb->data_len = skb_shinfo(skb)->xdp_frags_size; + else + skb->data_len = 0; + /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; if ((orig_eth_type != eth->h_proto) || @@ -4920,11 +4904,35 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, return act; } -static u32 netif_receive_generic_xdp(struct sk_buff *skb, +static int +netif_skb_check_for_xdp(struct sk_buff **pskb, struct bpf_prog *prog) +{ + struct sk_buff *skb = *pskb; + int err, hroom, troom; + + if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog)) + return 0; + + /* In case we have to go down the path and also linearize, + * then lets do the pskb_expand_head() work just once here. + */ + hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); + troom = skb->tail + skb->data_len - skb->end; + err = pskb_expand_head(skb, + hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, + troom > 0 ? troom + 128 : 0, GFP_ATOMIC); + if (err) + return err; + + return skb_linearize(skb); +} + +static u32 netif_receive_generic_xdp(struct sk_buff **pskb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - u32 act = XDP_DROP; + struct sk_buff *skb = *pskb; + u32 mac_len, act = XDP_DROP; /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. @@ -4932,41 +4940,36 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, if (skb_is_redirected(skb)) return XDP_PASS; - /* XDP packets must be linear and must have sufficient headroom - * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also - * native XDP provides, thus we need to do it here as well. + /* XDP packets must have sufficient headroom of XDP_PACKET_HEADROOM + * bytes. This is the guarantee that also native XDP provides, + * thus we need to do it here as well. */ + mac_len = skb->data - skb_mac_header(skb); + __skb_push(skb, mac_len); + if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { - int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); - int troom = skb->tail + skb->data_len - skb->end; - - /* In case we have to go down the path and also linearize, - * then lets do the pskb_expand_head() work just once here. - */ - if (pskb_expand_head(skb, - hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, - troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) - goto do_drop; - if (skb_linearize(skb)) + if (netif_skb_check_for_xdp(pskb, xdp_prog)) goto do_drop; } - act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog); + __skb_pull(*pskb, mac_len); + + act = bpf_prog_run_generic_xdp(*pskb, xdp, xdp_prog); switch (act) { case XDP_REDIRECT: case XDP_TX: case XDP_PASS: break; default: - bpf_warn_invalid_xdp_action(skb->dev, xdp_prog, act); + bpf_warn_invalid_xdp_action((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: - trace_xdp_exception(skb->dev, xdp_prog, act); + trace_xdp_exception((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_DROP: do_drop: - kfree_skb(skb); + kfree_skb(*pskb); break; } @@ -5004,24 +5007,24 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); -int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb) +int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb) { if (xdp_prog) { struct xdp_buff xdp; u32 act; int err; - act = netif_receive_generic_xdp(skb, &xdp, xdp_prog); + act = netif_receive_generic_xdp(pskb, &xdp, xdp_prog); if (act != XDP_PASS) { switch (act) { case XDP_REDIRECT: - err = xdp_do_generic_redirect(skb->dev, skb, + err = xdp_do_generic_redirect((*pskb)->dev, *pskb, &xdp, xdp_prog); if (err) goto out_redir; break; case XDP_TX: - generic_xdp_tx(skb, xdp_prog); + generic_xdp_tx(*pskb, xdp_prog); break; } return XDP_DROP; @@ -5029,7 +5032,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb) } return XDP_PASS; out_redir: - kfree_skb_reason(skb, SKB_DROP_REASON_XDP); + kfree_skb_reason(*pskb, SKB_DROP_REASON_XDP); return XDP_DROP; } EXPORT_SYMBOL_GPL(do_xdp_generic); @@ -5038,7 +5041,7 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_rx(skb); @@ -5330,7 +5333,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, int ret = NET_RX_DROP; __be16 type; - net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(!READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_receive_skb(skb); @@ -5352,7 +5355,8 @@ another_round: int ret2; migrate_disable(); - ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); + ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), + &skb); migrate_enable(); if (ret2 != XDP_PASS) { @@ -5373,7 +5377,7 @@ another_round: if (pfmemalloc) goto skip_taps; - list_for_each_entry_rcu(ptype, &ptype_all, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -5713,7 +5717,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; @@ -5743,7 +5747,8 @@ void netif_receive_skb_list_internal(struct list_head *head) INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), + skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); @@ -5967,7 +5972,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = READ_ONCE(dev_rx_weight); + napi->weight = READ_ONCE(net_hotdata.dev_rx_weight); while (again) { struct sk_buff *skb; @@ -6156,6 +6161,27 @@ struct napi_struct *napi_by_id(unsigned int napi_id) return NULL; } +static void skb_defer_free_flush(struct softnet_data *sd) +{ + struct sk_buff *skb, *next; + + /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */ + if (!READ_ONCE(sd->defer_list)) + return; + + spin_lock(&sd->defer_lock); + skb = sd->defer_list; + sd->defer_list = NULL; + sd->defer_count = 0; + spin_unlock(&sd->defer_lock); + + while (skb != NULL) { + next = skb->next; + napi_consume_skb(skb, 1); + skb = next; + } +} + #if defined(CONFIG_NET_RX_BUSY_POLL) static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) @@ -6280,6 +6306,7 @@ count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), LINUX_MIB_BUSYPOLLRXPACKETS, work); + skb_defer_free_flush(this_cpu_ptr(&softnet_data)); local_bh_enable(); if (!loop_end || loop_end(loop_end_arg, start_time)) @@ -6709,27 +6736,6 @@ static int napi_thread_wait(struct napi_struct *napi) return -1; } -static void skb_defer_free_flush(struct softnet_data *sd) -{ - struct sk_buff *skb, *next; - - /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */ - if (!READ_ONCE(sd->defer_list)) - return; - - spin_lock(&sd->defer_lock); - skb = sd->defer_list; - sd->defer_list = NULL; - sd->defer_count = 0; - spin_unlock(&sd->defer_lock); - - while (skb != NULL) { - next = skb->next; - napi_consume_skb(skb, 1); - skb = next; - } -} - static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; @@ -6771,8 +6777,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + - usecs_to_jiffies(READ_ONCE(netdev_budget_usecs)); - int budget = READ_ONCE(netdev_budget); + usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs)); + int budget = READ_ONCE(net_hotdata.netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); @@ -8615,12 +8621,12 @@ unsigned int dev_get_flags(const struct net_device *dev) { unsigned int flags; - flags = (dev->flags & ~(IFF_PROMISC | + flags = (READ_ONCE(dev->flags) & ~(IFF_PROMISC | IFF_ALLMULTI | IFF_RUNNING | IFF_LOWER_UP | IFF_DORMANT)) | - (dev->gflags & (IFF_PROMISC | + (READ_ONCE(dev->gflags) & (IFF_PROMISC | IFF_ALLMULTI)); if (netif_running(dev)) { @@ -8943,7 +8949,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, } EXPORT_SYMBOL(dev_set_mac_address); -static DECLARE_RWSEM(dev_addr_sem); +DECLARE_RWSEM(dev_addr_sem); int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack) @@ -9697,11 +9703,11 @@ static void dev_index_release(struct net *net, int ifindex) /* Delayed registration/unregisteration */ LIST_HEAD(net_todo_list); DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); +atomic_t dev_unreg_count = ATOMIC_INIT(0); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); - atomic_inc(&dev_net(dev)->dev_unreg_count); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, @@ -10266,9 +10272,9 @@ int register_netdevice(struct net_device *dev) goto err_ifindex_release; ret = netdev_register_kobject(dev); - write_lock(&dev_base_lock); - dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; - write_unlock(&dev_base_lock); + + WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED); + if (ret) goto err_uninit_notify; @@ -10344,7 +10350,7 @@ EXPORT_SYMBOL(register_netdevice); * that need to tie several hardware interfaces to a single NAPI * poll scheduler due to HW limitations. */ -int init_dummy_netdev(struct net_device *dev) +void init_dummy_netdev(struct net_device *dev) { /* Clear everything. Note we don't initialize spinlocks * are they aren't supposed to be taken by any of the @@ -10372,8 +10378,6 @@ int init_dummy_netdev(struct net_device *dev) * because users of this 'device' dont need to change * its refcount. */ - - return 0; } EXPORT_SYMBOL_GPL(init_dummy_netdev); @@ -10528,6 +10532,7 @@ void netdev_run_todo(void) { struct net_device *dev, *tmp; struct list_head list; + int cnt; #ifdef CONFIG_LOCKDEP struct list_head unlink_list; @@ -10558,12 +10563,11 @@ void netdev_run_todo(void) continue; } - write_lock(&dev_base_lock); - dev->reg_state = NETREG_UNREGISTERED; - write_unlock(&dev_base_lock); + WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED); linkwatch_sync_dev(dev); } + cnt = 0; while (!list_empty(&list)) { dev = netdev_wait_allrefs_any(&list); list_del(&dev->todo_list); @@ -10581,12 +10585,13 @@ void netdev_run_todo(void) if (dev->needs_free_netdev) free_netdev(dev); - if (atomic_dec_and_test(&dev_net(dev)->dev_unreg_count)) - wake_up(&netdev_unregistering_wq); + cnt++; /* Free network device */ kobject_put(&dev->dev.kobj); } + if (cnt && atomic_sub_and_test(cnt, &dev_unreg_count)) + wake_up(&netdev_unregistering_wq); } /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has @@ -10663,6 +10668,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, ops->ndo_get_stats64(dev, storage); } else if (ops->ndo_get_stats) { netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); + } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) { + dev_get_tstats64(dev, storage); } else { netdev_stats_to_stats64(storage, &dev->stats); } @@ -10977,7 +10984,7 @@ void free_netdev(struct net_device *dev) } BUG_ON(dev->reg_state != NETREG_UNREGISTERED); - dev->reg_state = NETREG_RELEASED; + WRITE_ONCE(dev->reg_state, NETREG_RELEASED); /* will free via device release */ put_device(&dev->dev); @@ -11033,6 +11040,7 @@ void unregister_netdevice_many_notify(struct list_head *head, { struct net_device *dev, *tmp; LIST_HEAD(close_head); + int cnt = 0; BUG_ON(dev_boot_phase); ASSERT_RTNL(); @@ -11064,10 +11072,8 @@ void unregister_netdevice_many_notify(struct list_head *head, list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ - write_lock(&dev_base_lock); - unlist_netdevice(dev, false); - dev->reg_state = NETREG_UNREGISTERING; - write_unlock(&dev_base_lock); + unlist_netdevice(dev); + WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING); } flush_all_backlogs(); @@ -11129,7 +11135,9 @@ void unregister_netdevice_many_notify(struct list_head *head, list_for_each_entry(dev, head, unreg_list) { netdev_put(dev, &dev->dev_registered_tracker); net_set_todo(dev); + cnt++; } + atomic_add(cnt, &dev_unreg_count); list_del(head); } @@ -11247,7 +11255,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, dev_close(dev); /* And unlink it from device chain */ - unlist_netdevice(dev, true); + unlist_netdevice(dev); synchronize_net(); @@ -11583,11 +11591,8 @@ static void __net_exit default_device_exit_net(struct net *net) snprintf(fb_name, IFNAMSIZ, "dev%%d"); netdev_for_each_altname_safe(dev, name_node, tmp) - if (netdev_name_in_use(&init_net, name_node->name)) { - netdev_name_node_del(name_node); - synchronize_rcu(); + if (netdev_name_in_use(&init_net, name_node->name)) __netdev_name_node_alt_destroy(name_node); - } err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { @@ -11694,6 +11699,28 @@ static void __init net_dev_struct_check(void) * */ +/* We allocate 256 pages for each CPU if PAGE_SHIFT is 12 */ +#define SYSTEM_PERCPU_PAGE_POOL_SIZE ((1 << 20) / PAGE_SIZE) + +static int net_page_pool_create(int cpuid) +{ +#if IS_ENABLED(CONFIG_PAGE_POOL) + struct page_pool_params page_pool_params = { + .pool_size = SYSTEM_PERCPU_PAGE_POOL_SIZE, + .flags = PP_FLAG_SYSTEM_POOL, + .nid = NUMA_NO_NODE, + }; + struct page_pool *pp_ptr; + + pp_ptr = page_pool_create_percpu(&page_pool_params, cpuid); + if (IS_ERR(pp_ptr)) + return -ENOMEM; + + per_cpu(system_page_pool, cpuid) = pp_ptr; +#endif + return 0; +} + /* * This is called single threaded during boot, so no need * to take the rtnl semaphore. @@ -11712,7 +11739,6 @@ static int __init net_dev_init(void) if (netdev_kobject_init()) goto out; - INIT_LIST_HEAD(&ptype_all); for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); @@ -11746,6 +11772,9 @@ static int __init net_dev_init(void) init_gro_hash(&sd->backlog); sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; + + if (net_page_pool_create(i)) + goto out; } dev_boot_phase = 0; @@ -11773,6 +11802,19 @@ static int __init net_dev_init(void) WARN_ON(rc < 0); rc = 0; out: + if (rc < 0) { + for_each_possible_cpu(i) { + struct page_pool *pp_ptr; + + pp_ptr = per_cpu(system_page_pool, i); + if (!pp_ptr) + continue; + + page_pool_destroy(pp_ptr); + per_cpu(system_page_pool, i) = NULL; + } + } + return rc; } diff --git a/net/core/dev.h b/net/core/dev.h index 7480b4c84298..2bcaf8eee50c 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -3,6 +3,7 @@ #define _NET_CORE_DEV_H #include <linux/types.h> +#include <linux/rwsem.h> struct net; struct net_device; @@ -37,15 +38,14 @@ int dev_addr_init(struct net_device *dev); void dev_addr_check(struct net_device *dev); /* sysctls not referred to from outside net/core/ */ -extern int netdev_budget; -extern unsigned int netdev_budget_usecs; extern unsigned int sysctl_skb_defer_max; -extern int netdev_tstamp_prequeue; extern int netdev_unregister_timeout_secs; extern int weight_p; extern int dev_weight_rx_bias; extern int dev_weight_tx_bias; +extern struct rw_semaphore dev_addr_sem; + /* rtnl helpers */ extern struct list_head net_todo_list; void netdev_run_todo(void); @@ -56,6 +56,7 @@ struct netdev_name_node { struct list_head list; struct net_device *dev; const char *name; + struct rcu_head rcu; }; int netdev_get_name(struct net *net, char *name, int ifindex); diff --git a/net/core/dst.c b/net/core/dst.c index 6838d3212c37..95f533844f17 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -96,7 +96,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, } EXPORT_SYMBOL(dst_alloc); -struct dst_entry *dst_destroy(struct dst_entry * dst) +static void dst_destroy(struct dst_entry *dst) { struct dst_entry *child = NULL; @@ -126,15 +126,13 @@ struct dst_entry *dst_destroy(struct dst_entry * dst) dst = child; if (dst) dst_release_immediate(dst); - return NULL; } -EXPORT_SYMBOL(dst_destroy); static void dst_destroy_rcu(struct rcu_head *head) { struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); - dst = dst_destroy(dst); + dst_destroy(dst); } /* Operations to mark dst as DEAD and clean up the net device referenced diff --git a/net/core/filter.c b/net/core/filter.c index ef3e78b6a39c..8adf95765cdd 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -88,7 +88,7 @@ #include "dev.h" static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id); +bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { @@ -778,7 +778,7 @@ jmp_rest: BPF_EMIT_JMP; break; - /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ + /* ldxb 4 * ([14] & 0xf) is remapped into 6 insns. */ case BPF_LDX | BPF_MSH | BPF_B: { struct sock_filter tmp = { .code = BPF_LD | BPF_ABS | BPF_B, @@ -804,7 +804,7 @@ jmp_rest: *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break; } - /* RET_K is remaped into 2 insns. RET_A case doesn't need an + /* RET_K is remapped into 2 insns. RET_A case doesn't need an * extra mov as BPF_REG_0 is already mapped into BPF_REG_A. */ case BPF_RET | BPF_A: @@ -2968,7 +2968,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, * * Then if B is non-zero AND there is no space allocate space and * compact A, B regions into page. If there is space shift ring to - * the rigth free'ing the next element in ring to place B, leaving + * the right free'ing the next element in ring to place B, leaving * A untouched except to reduce length. */ if (start != offset) { @@ -5988,7 +5988,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, return -ENODEV; idev = __in6_dev_get_safely(dev); - if (unlikely(!idev || !idev->cnf.forwarding)) + if (unlikely(!idev || !READ_ONCE(idev->cnf.forwarding))) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { @@ -7894,7 +7894,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -7987,7 +7987,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8006,7 +8006,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8193,7 +8193,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8252,13 +8252,13 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) /* The nf_conn___init type is used in the NF_CONNTRACK kfuncs. The * kfuncs are defined in two different modules, and we want to be able - * to use them interchangably with the same BTF type ID. Because modules + * to use them interchangeably with the same BTF type ID. Because modules * can't de-duplicate BTF IDs between each other, we need the type to be * referenced in the vmlinux BTF or the verifier will get confused about * the different types. So we add this dummy type reference which will @@ -8313,7 +8313,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8355,7 +8355,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_cgroup_classid_curr_proto; #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8399,7 +8399,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_lookup_tcp_proto; #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8410,7 +8410,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8437,7 +8437,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8612,7 +8612,7 @@ static bool cg_skb_is_valid_access(int off, int size, return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; } @@ -8624,7 +8624,7 @@ static bool cg_skb_is_valid_access(int off, int size, case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; default: @@ -11268,7 +11268,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -11450,7 +11450,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -11784,7 +11784,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = { }; static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id) +bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func; @@ -11813,10 +11813,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; return func; @@ -11869,6 +11869,103 @@ __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern, return 0; } + +__bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct sk_buff *skb, struct sock *sk, + struct bpf_tcp_req_attrs *attrs, int attrs__sz) +{ +#if IS_ENABLED(CONFIG_SYN_COOKIES) + const struct request_sock_ops *ops; + struct inet_request_sock *ireq; + struct tcp_request_sock *treq; + struct request_sock *req; + struct net *net; + __u16 min_mss; + u32 tsoff = 0; + + if (attrs__sz != sizeof(*attrs) || + attrs->reserved[0] || attrs->reserved[1] || attrs->reserved[2]) + return -EINVAL; + + if (!skb_at_tc_ingress(skb)) + return -EINVAL; + + net = dev_net(skb->dev); + if (net != sock_net(sk)) + return -ENETUNREACH; + + switch (skb->protocol) { + case htons(ETH_P_IP): + ops = &tcp_request_sock_ops; + min_mss = 536; + break; +#if IS_BUILTIN(CONFIG_IPV6) + case htons(ETH_P_IPV6): + ops = &tcp6_request_sock_ops; + min_mss = IPV6_MIN_MTU - 60; + break; +#endif + default: + return -EINVAL; + } + + if (sk->sk_type != SOCK_STREAM || sk->sk_state != TCP_LISTEN || + sk_is_mptcp(sk)) + return -EINVAL; + + if (attrs->mss < min_mss) + return -EINVAL; + + if (attrs->wscale_ok) { + if (!READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) + return -EINVAL; + + if (attrs->snd_wscale > TCP_MAX_WSCALE || + attrs->rcv_wscale > TCP_MAX_WSCALE) + return -EINVAL; + } + + if (attrs->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack)) + return -EINVAL; + + if (attrs->tstamp_ok) { + if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps)) + return -EINVAL; + + tsoff = attrs->rcv_tsecr - tcp_ns_to_ts(attrs->usec_ts_ok, tcp_clock_ns()); + } + + req = inet_reqsk_alloc(ops, sk, false); + if (!req) + return -ENOMEM; + + ireq = inet_rsk(req); + treq = tcp_rsk(req); + + req->rsk_listener = sk; + req->syncookie = 1; + req->mss = attrs->mss; + req->ts_recent = attrs->rcv_tsval; + + ireq->snd_wscale = attrs->snd_wscale; + ireq->rcv_wscale = attrs->rcv_wscale; + ireq->tstamp_ok = !!attrs->tstamp_ok; + ireq->sack_ok = !!attrs->sack_ok; + ireq->wscale_ok = !!attrs->wscale_ok; + ireq->ecn_ok = !!attrs->ecn_ok; + + treq->req_usec_ts = !!attrs->usec_ts_ok; + treq->ts_off = tsoff; + + skb_orphan(skb); + skb->sk = req_to_sk(req); + skb->destructor = sock_pfree; + + return 0; +#else + return -EOPNOTSUPP; +#endif +} + __bpf_kfunc_end_defs(); int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, @@ -11885,17 +11982,21 @@ int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, return 0; } -BTF_SET8_START(bpf_kfunc_check_set_skb) +BTF_KFUNCS_START(bpf_kfunc_check_set_skb) BTF_ID_FLAGS(func, bpf_dynptr_from_skb) -BTF_SET8_END(bpf_kfunc_check_set_skb) +BTF_KFUNCS_END(bpf_kfunc_check_set_skb) -BTF_SET8_START(bpf_kfunc_check_set_xdp) +BTF_KFUNCS_START(bpf_kfunc_check_set_xdp) BTF_ID_FLAGS(func, bpf_dynptr_from_xdp) -BTF_SET8_END(bpf_kfunc_check_set_xdp) +BTF_KFUNCS_END(bpf_kfunc_check_set_xdp) -BTF_SET8_START(bpf_kfunc_check_set_sock_addr) +BTF_KFUNCS_START(bpf_kfunc_check_set_sock_addr) BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path) -BTF_SET8_END(bpf_kfunc_check_set_sock_addr) +BTF_KFUNCS_END(bpf_kfunc_check_set_sock_addr) + +BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk) +BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS) +BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk) static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner = THIS_MODULE, @@ -11912,6 +12013,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_sock_addr = { .set = &bpf_kfunc_check_set_sock_addr, }; +static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = { + .owner = THIS_MODULE, + .set = &bpf_kfunc_check_set_tcp_reqsk, +}; + static int __init bpf_kfunc_init(void) { int ret; @@ -11927,8 +12033,9 @@ static int __init bpf_kfunc_init(void) ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); - return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - &bpf_kfunc_set_sock_addr); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + &bpf_kfunc_set_sock_addr); + return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk); } late_initcall(bpf_kfunc_init); @@ -11968,9 +12075,9 @@ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock) __bpf_kfunc_end_defs(); -BTF_SET8_START(bpf_sk_iter_kfunc_ids) +BTF_KFUNCS_START(bpf_sk_iter_kfunc_ids) BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS) -BTF_SET8_END(bpf_sk_iter_kfunc_ids) +BTF_KFUNCS_END(bpf_sk_iter_kfunc_ids) static int tracing_iter_filter(const struct bpf_prog *prog, u32 kfunc_id) { diff --git a/net/core/gro.c b/net/core/gro.c index 0759277dc14e..ee30d4f0c038 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -10,9 +10,6 @@ #define GRO_MAX_HEAD (MAX_HEADER + 128) static DEFINE_SPINLOCK(offload_lock); -struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base); -/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ -int gro_normal_batch __read_mostly = 8; /** * dev_add_offload - register offload handlers @@ -31,7 +28,7 @@ void dev_add_offload(struct packet_offload *po) struct packet_offload *elem; spin_lock(&offload_lock); - list_for_each_entry(elem, &offload_base, list) { + list_for_each_entry(elem, &net_hotdata.offload_base, list) { if (po->priority < elem->priority) break; } @@ -55,7 +52,7 @@ EXPORT_SYMBOL(dev_add_offload); */ static void __dev_remove_offload(struct packet_offload *po) { - struct list_head *head = &offload_base; + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *po1; spin_lock(&offload_lock); @@ -235,9 +232,9 @@ done: static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &offload_base; int err = -ENOENT; BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); @@ -369,15 +366,21 @@ static void gro_list_prepare(const struct list_head *head, static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) { - const struct skb_shared_info *pinfo = skb_shinfo(skb); - const skb_frag_t *frag0 = &pinfo->frags[0]; + const struct skb_shared_info *pinfo; + const skb_frag_t *frag0; + unsigned int headlen; NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; + headlen = skb_headlen(skb); + NAPI_GRO_CB(skb)->frag0 = skb->data; + NAPI_GRO_CB(skb)->frag0_len = headlen; + if (headlen) + return; + + pinfo = skb_shinfo(skb); + frag0 = &pinfo->frags[0]; - if (!skb_headlen(skb) && pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0)) && + if (pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) && (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, @@ -438,7 +441,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff { u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); struct gro_list *gro_list = &napi->gro_hash[bucket]; - struct list_head *head = &offload_base; + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; struct sk_buff *pp = NULL; @@ -544,7 +547,7 @@ normal: struct packet_offload *gro_find_receive_by_type(__be16 type) { - struct list_head *offload_head = &offload_base; + struct list_head *offload_head = &net_hotdata.offload_base; struct packet_offload *ptype; list_for_each_entry_rcu(ptype, offload_head, list) { @@ -558,7 +561,7 @@ EXPORT_SYMBOL(gro_find_receive_by_type); struct packet_offload *gro_find_complete_by_type(__be16 type) { - struct list_head *offload_head = &offload_base; + struct list_head *offload_head = &net_hotdata.offload_base; struct packet_offload *ptype; list_for_each_entry_rcu(ptype, offload_head, list) { @@ -700,7 +703,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) skb_reset_mac_header(skb); skb_gro_reset_offset(skb, hlen); - if (unlikely(skb_gro_header_hard(skb, hlen))) { + if (unlikely(!skb_gro_may_pull(skb, hlen))) { eth = skb_gro_header_slow(skb, hlen, 0); if (unlikely(!eth)) { net_warn_ratelimited("%s: dropping impossible skb from %s\n", @@ -710,7 +713,10 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) } } else { eth = (const struct ethhdr *)skb->data; - gro_pull_from_frag0(skb, hlen); + + if (NAPI_GRO_CB(skb)->frag0 != skb->data) + gro_pull_from_frag0(skb, hlen); + NAPI_GRO_CB(skb)->frag0 += hlen; NAPI_GRO_CB(skb)->frag0_len -= hlen; } diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index ed5ec5de47f6..ff8e5b64bf6b 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -3,6 +3,7 @@ #include <linux/slab.h> #include <linux/netdevice.h> #include <net/gro_cells.h> +#include <net/hotdata.h> struct gro_cell { struct sk_buff_head napi_skbs; @@ -26,7 +27,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) cell = this_cpu_ptr(gcells->cells); - if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) { + if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(net_hotdata.max_backlog)) { drop: dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); diff --git a/net/core/gso.c b/net/core/gso.c index 9e1803bfc9c6..bcd156372f4d 100644 --- a/net/core/gso.c +++ b/net/core/gso.c @@ -17,7 +17,7 @@ struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, struct packet_offload *ptype; rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; @@ -48,7 +48,7 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, __skb_pull(skb, vlan_depth); rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; diff --git a/net/core/hotdata.c b/net/core/hotdata.c new file mode 100644 index 000000000000..c8a7a451c18a --- /dev/null +++ b/net/core/hotdata.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <net/hotdata.h> +#include <linux/cache.h> +#include <linux/jiffies.h> +#include <linux/list.h> + + +struct net_hotdata net_hotdata __cacheline_aligned = { + .offload_base = LIST_HEAD_INIT(net_hotdata.offload_base), + .ptype_all = LIST_HEAD_INIT(net_hotdata.ptype_all), + .gro_normal_batch = 8, + + .netdev_budget = 300, + /* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ + .netdev_budget_usecs = 2 * USEC_PER_SEC / HZ, + + .tstamp_prequeue = 1, + .max_backlog = 1000, + .dev_tx_weight = 64, + .dev_rx_weight = 64, +}; +EXPORT_SYMBOL(net_hotdata); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 429571c258da..8ec35194bfcb 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -33,7 +33,7 @@ static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event); static LIST_HEAD(lweventlist); static DEFINE_SPINLOCK(lweventlist_lock); -static unsigned char default_operstate(const struct net_device *dev) +static unsigned int default_operstate(const struct net_device *dev) { if (netif_testing(dev)) return IF_OPER_TESTING; @@ -62,16 +62,13 @@ static unsigned char default_operstate(const struct net_device *dev) return IF_OPER_UP; } - static void rfc2863_policy(struct net_device *dev) { - unsigned char operstate = default_operstate(dev); + unsigned int operstate = default_operstate(dev); - if (operstate == dev->operstate) + if (operstate == READ_ONCE(dev->operstate)) return; - write_lock(&dev_base_lock); - switch(dev->link_mode) { case IF_LINK_MODE_TESTING: if (operstate == IF_OPER_UP) @@ -87,9 +84,7 @@ static void rfc2863_policy(struct net_device *dev) break; } - dev->operstate = operstate; - - write_unlock(&dev_base_lock); + WRITE_ONCE(dev->operstate, operstate); } diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 09f7ed1a04e8..a97eceb84e61 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -3,52 +3,22 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/wext.h> +#include <net/hotdata.h> #include "dev.h" -#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) - -#define get_bucket(x) ((x) >> BUCKET_SPACE) -#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) -#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) - -static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) +static void *dev_seq_from_index(struct seq_file *seq, loff_t *pos) { - struct net *net = seq_file_net(seq); + unsigned long ifindex = *pos; struct net_device *dev; - struct hlist_head *h; - unsigned int count = 0, offset = get_offset(*pos); - h = &net->dev_index_head[get_bucket(*pos)]; - hlist_for_each_entry_rcu(dev, h, index_hlist) { - if (++count == offset) - return dev; + for_each_netdev_dump(seq_file_net(seq), dev, ifindex) { + *pos = dev->ifindex; + return dev; } - - return NULL; -} - -static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos) -{ - struct net_device *dev; - unsigned int bucket; - - do { - dev = dev_from_same_bucket(seq, pos); - if (dev) - return dev; - - bucket = get_bucket(*pos) + 1; - *pos = set_bucket_offset(bucket, 1); - } while (bucket < NETDEV_HASHENTRIES); - return NULL; } -/* - * This is invoked by the /proc filesystem handler to display a device - * in detail. - */ static void *dev_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { @@ -56,16 +26,13 @@ static void *dev_seq_start(struct seq_file *seq, loff_t *pos) if (!*pos) return SEQ_START_TOKEN; - if (get_bucket(*pos) >= NETDEV_HASHENTRIES) - return NULL; - - return dev_from_bucket(seq, pos); + return dev_seq_from_index(seq, pos); } static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; - return dev_from_bucket(seq, pos); + return dev_seq_from_index(seq, pos); } static void dev_seq_stop(struct seq_file *seq, void *v) @@ -217,7 +184,7 @@ static void *ptype_get_idx(struct seq_file *seq, loff_t pos) } } - list_for_each_entry_rcu(pt, &ptype_all, list) { + list_for_each_entry_rcu(pt, &net_hotdata.ptype_all, list) { if (i == pos) return pt; ++i; @@ -265,13 +232,13 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) } } - nxt = ptype_all.next; + nxt = net_hotdata.ptype_all.next; goto ptype_all; } if (pt->type == htons(ETH_P_ALL)) { ptype_all: - if (nxt != &ptype_all) + if (nxt != &net_hotdata.ptype_all) goto found; hash = 0; nxt = ptype_base[0].next; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index a09d507c5b03..e3d7a8cfa20b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -24,6 +24,7 @@ #include <linux/of_net.h> #include <linux/cpu.h> #include <net/netdev_rx_queue.h> +#include <net/rps.h> #include "dev.h" #include "net-sysfs.h" @@ -34,10 +35,10 @@ static const char fmt_dec[] = "%d\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; -/* Caller holds RTNL or dev_base_lock */ +/* Caller holds RTNL or RCU */ static inline int dev_isalive(const struct net_device *dev) { - return dev->reg_state <= NETREG_REGISTERED; + return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED; } /* use same locking rules as GIF* ioctl's */ @@ -48,10 +49,10 @@ static ssize_t netdev_show(const struct device *dev, struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; - read_lock(&dev_base_lock); + rcu_read_lock(); if (dev_isalive(ndev)) ret = (*format)(ndev, buf); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return ret; } @@ -60,7 +61,7 @@ static ssize_t netdev_show(const struct device *dev, #define NETDEVICE_SHOW(field, format_string) \ static ssize_t format_##field(const struct net_device *dev, char *buf) \ { \ - return sysfs_emit(buf, format_string, dev->field); \ + return sysfs_emit(buf, format_string, READ_ONCE(dev->field)); \ } \ static ssize_t field##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ @@ -125,7 +126,7 @@ static DEVICE_ATTR_RO(iflink); static ssize_t format_name_assign_type(const struct net_device *dev, char *buf) { - return sysfs_emit(buf, fmt_dec, dev->name_assign_type); + return sysfs_emit(buf, fmt_dec, READ_ONCE(dev->name_assign_type)); } static ssize_t name_assign_type_show(struct device *dev, @@ -135,24 +136,28 @@ static ssize_t name_assign_type_show(struct device *dev, struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; - if (ndev->name_assign_type != NET_NAME_UNKNOWN) + if (READ_ONCE(ndev->name_assign_type) != NET_NAME_UNKNOWN) ret = netdev_show(dev, attr, buf, format_name_assign_type); return ret; } static DEVICE_ATTR_RO(name_assign_type); -/* use same locking rules as GIFHWADDR ioctl's */ +/* use same locking rules as GIFHWADDR ioctl's (dev_get_mac_address()) */ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; - read_lock(&dev_base_lock); + down_read(&dev_addr_sem); + + rcu_read_lock(); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len); - read_unlock(&dev_base_lock); + rcu_read_unlock(); + + up_read(&dev_addr_sem); return ret; } static DEVICE_ATTR_RO(address); @@ -161,10 +166,13 @@ static ssize_t broadcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); + int ret = -EINVAL; + rcu_read_lock(); if (dev_isalive(ndev)) - return sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len); - return -EINVAL; + ret = sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len); + rcu_read_unlock(); + return ret; } static DEVICE_ATTR_RO(broadcast); @@ -318,11 +326,9 @@ static ssize_t operstate_show(struct device *dev, const struct net_device *netdev = to_net_dev(dev); unsigned char operstate; - read_lock(&dev_base_lock); - operstate = netdev->operstate; + operstate = READ_ONCE(netdev->operstate); if (!netif_running(netdev)) operstate = IF_OPER_DOWN; - read_unlock(&dev_base_lock); if (operstate >= ARRAY_SIZE(operstates)) return -EINVAL; /* should not happen */ @@ -680,14 +686,14 @@ static ssize_t netstat_show(const struct device *d, WARN_ON(offset > sizeof(struct rtnl_link_stats64) || offset % sizeof(u64) != 0); - read_lock(&dev_base_lock); + rcu_read_lock(); if (dev_isalive(dev)) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); ret = sysfs_emit(buf, fmt_u64, *(u64 *)(((u8 *)stats) + offset)); } - read_unlock(&dev_base_lock); + rcu_read_unlock(); return ret; } @@ -1409,6 +1415,65 @@ static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init = __ATTR(hold_time, 0644, bql_show_hold_time, bql_set_hold_time); +static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); +} + +static ssize_t bql_set_stall_thrs(struct netdev_queue *queue, + const char *buf, size_t len) +{ + struct dql *dql = &queue->dql; + unsigned int value; + int err; + + err = kstrtouint(buf, 10, &value); + if (err < 0) + return err; + + value = msecs_to_jiffies(value); + if (value && (value < 4 || value > 4 / 2 * BITS_PER_LONG)) + return -ERANGE; + + if (!dql->stall_thrs && value) + dql->last_reap = jiffies; + /* Force last_reap to be live */ + smp_wmb(); + dql->stall_thrs = value; + + return len; +} + +static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init = + __ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs); + +static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf) +{ + return sprintf(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); +} + +static ssize_t bql_set_stall_max(struct netdev_queue *queue, + const char *buf, size_t len) +{ + WRITE_ONCE(queue->dql.stall_max, 0); + return len; +} + +static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init = + __ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max); + +static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%lu\n", dql->stall_cnt); +} + +static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init = + __ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL); + static ssize_t bql_show_inflight(struct netdev_queue *queue, char *buf) { @@ -1447,6 +1512,9 @@ static struct attribute *dql_attrs[] __ro_after_init = { &bql_limit_min_attribute.attr, &bql_hold_time_attribute.attr, &bql_inflight_attribute.attr, + &bql_stall_thrs_attribute.attr, + &bql_stall_cnt_attribute.attr, + &bql_stall_max_attribute.attr, NULL }; @@ -1454,6 +1522,9 @@ static const struct attribute_group dql_group = { .name = "byte_queue_limits", .attrs = dql_attrs, }; +#else +/* Fake declaration, all the code using it should be dead */ +extern const struct attribute_group dql_group; #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS @@ -1691,6 +1762,15 @@ static const struct kobj_type netdev_queue_ktype = { .get_ownership = netdev_queue_get_ownership, }; +static bool netdev_uses_bql(const struct net_device *dev) +{ + if (dev->features & NETIF_F_LLTX || + dev->priv_flags & IFF_NO_QUEUE) + return false; + + return IS_ENABLED(CONFIG_BQL); +} + static int netdev_queue_add_kobject(struct net_device *dev, int index) { struct netdev_queue *queue = dev->_tx + index; @@ -1708,11 +1788,11 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) if (error) goto err; -#ifdef CONFIG_BQL - error = sysfs_create_group(kobj, &dql_group); - if (error) - goto err; -#endif + if (netdev_uses_bql(dev)) { + error = sysfs_create_group(kobj, &dql_group); + if (error) + goto err; + } kobject_uevent(kobj, KOBJ_ADD); return 0; @@ -1733,9 +1813,9 @@ static int tx_queue_change_owner(struct net_device *ndev, int index, if (error) return error; -#ifdef CONFIG_BQL - error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); -#endif + if (netdev_uses_bql(ndev)) + error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); + return error; } #endif /* CONFIG_SYSFS */ @@ -1767,9 +1847,10 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) if (!refcount_read(&dev_net(dev)->ns.count)) queue->kobj.uevent_suppress = 1; -#ifdef CONFIG_BQL - sysfs_remove_group(&queue->kobj, &dql_group); -#endif + + if (netdev_uses_bql(dev)) + sysfs_remove_group(&queue->kobj, &dql_group); + kobject_put(&queue->kobj); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 72799533426b..f0540c557515 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -318,8 +318,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) { /* Must be called with pernet_ops_rwsem held */ const struct pernet_operations *ops, *saved_ops; - int error = 0; LIST_HEAD(net_exit_list); + LIST_HEAD(dev_kill_list); + int error = 0; refcount_set(&net->ns.count, 1); ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); @@ -358,6 +359,15 @@ out_undo: synchronize_rcu(); ops = saved_ops; + rtnl_lock(); + list_for_each_entry_continue_reverse(ops, &pernet_list, list) { + if (ops->exit_batch_rtnl) + ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list); + } + unregister_netdevice_many(&dev_kill_list); + rtnl_unlock(); + + ops = saved_ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); @@ -573,6 +583,7 @@ static void cleanup_net(struct work_struct *work) struct net *net, *tmp, *last; struct llist_node *net_kill_list; LIST_HEAD(net_exit_list); + LIST_HEAD(dev_kill_list); /* Atomically snapshot the list of namespaces to cleanup */ net_kill_list = llist_del_all(&cleanup_list); @@ -611,7 +622,15 @@ static void cleanup_net(struct work_struct *work) * the rcu_barrier() below isn't sufficient alone. * Also the pre_exit() and exit() methods need this barrier. */ - synchronize_rcu(); + synchronize_rcu_expedited(); + + rtnl_lock(); + list_for_each_entry_reverse(ops, &pernet_list, list) { + if (ops->exit_batch_rtnl) + ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list); + } + unregister_netdevice_many(&dev_kill_list); + rtnl_unlock(); /* Run all of the network namespace exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) @@ -1193,7 +1212,17 @@ static void free_exit_list(struct pernet_operations *ops, struct list_head *net_ { ops_pre_exit_list(ops, net_exit_list); synchronize_rcu(); + + if (ops->exit_batch_rtnl) { + LIST_HEAD(dev_kill_list); + + rtnl_lock(); + ops->exit_batch_rtnl(net_exit_list, &dev_kill_list); + unregister_netdevice_many(&dev_kill_list); + rtnl_unlock(); + } ops_exit_list(ops, net_exit_list); + ops_free_list(ops, net_exit_list); } diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index be7f2ebd61b2..8d8ace9ef87f 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -68,6 +68,11 @@ static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFIN [NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; +/* NETDEV_CMD_QSTATS_GET - dump */ +static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE + 1] = { + [NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -138,6 +143,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_NAPI_IFINDEX, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = NETDEV_CMD_QSTATS_GET, + .dumpit = netdev_nl_qstats_get_dumpit, + .policy = netdev_qstats_get_nl_policy, + .maxattr = NETDEV_A_QSTATS_SCOPE, + .flags = GENL_CMD_CAP_DUMP, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index a47f2bcbe4fa..4db40fd5b4a9 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -28,6 +28,8 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index fd98936da3ae..7004b3399c2b 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -8,6 +8,7 @@ #include <net/xdp.h> #include <net/xdp_sock.h> #include <net/netdev_rx_queue.h> +#include <net/netdev_queues.h> #include <net/busy_poll.h> #include "netdev-genl-gen.h" @@ -152,10 +153,7 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } rtnl_unlock(); - if (err != -EMSGSIZE) - return err; - - return skb->len; + return err; } static int @@ -287,10 +285,7 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } rtnl_unlock(); - if (err != -EMSGSIZE) - return err; - - return skb->len; + return err; } static int @@ -463,10 +458,220 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } rtnl_unlock(); - if (err != -EMSGSIZE) - return err; + return err; +} + +#define NETDEV_STAT_NOT_SET (~0ULL) + +static void netdev_nl_stats_add(void *_sum, const void *_add, size_t size) +{ + const u64 *add = _add; + u64 *sum = _sum; + + while (size) { + if (*add != NETDEV_STAT_NOT_SET && *sum != NETDEV_STAT_NOT_SET) + *sum += *add; + sum++; + add++; + size -= 8; + } +} + +static int netdev_stat_put(struct sk_buff *rsp, unsigned int attr_id, u64 value) +{ + if (value == NETDEV_STAT_NOT_SET) + return 0; + return nla_put_uint(rsp, attr_id, value); +} + +static int +netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) +{ + if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail)) + return -EMSGSIZE; + return 0; +} + +static int +netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx) +{ + if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes)) + return -EMSGSIZE; + return 0; +} + +static int +netdev_nl_stats_queue(struct net_device *netdev, struct sk_buff *rsp, + u32 q_type, int i, const struct genl_info *info) +{ + const struct netdev_stat_ops *ops = netdev->stat_ops; + struct netdev_queue_stats_rx rx; + struct netdev_queue_stats_tx tx; + void *hdr; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex) || + nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_TYPE, q_type) || + nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_ID, i)) + goto nla_put_failure; + + switch (q_type) { + case NETDEV_QUEUE_TYPE_RX: + memset(&rx, 0xff, sizeof(rx)); + ops->get_queue_stats_rx(netdev, i, &rx); + if (!memchr_inv(&rx, 0xff, sizeof(rx))) + goto nla_cancel; + if (netdev_nl_stats_write_rx(rsp, &rx)) + goto nla_put_failure; + break; + case NETDEV_QUEUE_TYPE_TX: + memset(&tx, 0xff, sizeof(tx)); + ops->get_queue_stats_tx(netdev, i, &tx); + if (!memchr_inv(&tx, 0xff, sizeof(tx))) + goto nla_cancel; + if (netdev_nl_stats_write_tx(rsp, &tx)) + goto nla_put_failure; + break; + } + + genlmsg_end(rsp, hdr); + return 0; + +nla_cancel: + genlmsg_cancel(rsp, hdr); + return 0; +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +static int +netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info, + struct netdev_nl_dump_ctx *ctx) +{ + const struct netdev_stat_ops *ops = netdev->stat_ops; + int i, err; + + if (!(netdev->flags & IFF_UP)) + return 0; + + i = ctx->rxq_idx; + while (ops->get_queue_stats_rx && i < netdev->real_num_rx_queues) { + err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_RX, + i, info); + if (err) + return err; + ctx->rxq_idx = i++; + } + i = ctx->txq_idx; + while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { + err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_TX, + i, info); + if (err) + return err; + ctx->txq_idx = i++; + } + + ctx->rxq_idx = 0; + ctx->txq_idx = 0; + return 0; +} + +static int +netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info) +{ + struct netdev_queue_stats_rx rx_sum, rx; + struct netdev_queue_stats_tx tx_sum, tx; + const struct netdev_stat_ops *ops; + void *hdr; + int i; + + ops = netdev->stat_ops; + /* Netdev can't guarantee any complete counters */ + if (!ops->get_base_stats) + return 0; + + memset(&rx_sum, 0xff, sizeof(rx_sum)); + memset(&tx_sum, 0xff, sizeof(tx_sum)); + + ops->get_base_stats(netdev, &rx_sum, &tx_sum); + + /* The op was there, but nothing reported, don't bother */ + if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) && + !memchr_inv(&tx_sum, 0xff, sizeof(tx_sum))) + return 0; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex)) + goto nla_put_failure; + + for (i = 0; i < netdev->real_num_rx_queues; i++) { + memset(&rx, 0xff, sizeof(rx)); + if (ops->get_queue_stats_rx) + ops->get_queue_stats_rx(netdev, i, &rx); + netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx)); + } + for (i = 0; i < netdev->real_num_tx_queues; i++) { + memset(&tx, 0xff, sizeof(tx)); + if (ops->get_queue_stats_tx) + ops->get_queue_stats_tx(netdev, i, &tx); + netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx)); + } + + if (netdev_nl_stats_write_rx(rsp, &rx_sum) || + netdev_nl_stats_write_tx(rsp, &tx_sum)) + goto nla_put_failure; + + genlmsg_end(rsp, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + unsigned int scope; + int err = 0; + + scope = 0; + if (info->attrs[NETDEV_A_QSTATS_SCOPE]) + scope = nla_get_uint(info->attrs[NETDEV_A_QSTATS_SCOPE]); + + rtnl_lock(); + for_each_netdev_dump(net, netdev, ctx->ifindex) { + if (!netdev->stat_ops) + continue; + + switch (scope) { + case 0: + err = netdev_nl_stats_by_netdev(netdev, skb, info); + break; + case NETDEV_QSTATS_SCOPE_QUEUE: + err = netdev_nl_stats_by_queue(netdev, skb, info, ctx); + break; + } + if (err < 0) + break; + } + rtnl_unlock(); - return skb->len; + return err; } static int netdev_genl_netdevice_event(struct notifier_block *nb, diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 4933762e5a6b..dd364d738c00 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -31,6 +31,8 @@ #define BIAS_MAX (LONG_MAX >> 1) #ifdef CONFIG_PAGE_POOL_STATS +static DEFINE_PER_CPU(struct page_pool_recycle_stats, pp_system_recycle_stats); + /* alloc_stat_inc is intended to be used in softirq context */ #define alloc_stat_inc(pool, __stat) (pool->alloc_stats.__stat++) /* recycle_stat_inc is safe to use when preemption is possible. */ @@ -171,13 +173,16 @@ static void page_pool_producer_unlock(struct page_pool *pool, } static int page_pool_init(struct page_pool *pool, - const struct page_pool_params *params) + const struct page_pool_params *params, + int cpuid) { unsigned int ring_qsize = 1024; /* Default */ memcpy(&pool->p, ¶ms->fast, sizeof(pool->p)); memcpy(&pool->slow, ¶ms->slow, sizeof(pool->slow)); + pool->cpuid = cpuid; + /* Validate only known flags were used */ if (pool->p.flags & ~(PP_FLAG_ALL)) return -EINVAL; @@ -217,14 +222,23 @@ static int page_pool_init(struct page_pool *pool, pool->has_init_callback = !!pool->slow.init_callback; #ifdef CONFIG_PAGE_POOL_STATS - pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats); - if (!pool->recycle_stats) - return -ENOMEM; + if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) { + pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats); + if (!pool->recycle_stats) + return -ENOMEM; + } else { + /* For system page pool instance we use a singular stats object + * instead of allocating a separate percpu variable for each + * (also percpu) page pool instance. + */ + pool->recycle_stats = &pp_system_recycle_stats; + } #endif if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) { #ifdef CONFIG_PAGE_POOL_STATS - free_percpu(pool->recycle_stats); + if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) + free_percpu(pool->recycle_stats); #endif return -ENOMEM; } @@ -248,15 +262,18 @@ static void page_pool_uninit(struct page_pool *pool) put_device(pool->p.dev); #ifdef CONFIG_PAGE_POOL_STATS - free_percpu(pool->recycle_stats); + if (!(pool->p.flags & PP_FLAG_SYSTEM_POOL)) + free_percpu(pool->recycle_stats); #endif } /** - * page_pool_create() - create a page pool. + * page_pool_create_percpu() - create a page pool for a given cpu. * @params: parameters, see struct page_pool_params + * @cpuid: cpu identifier */ -struct page_pool *page_pool_create(const struct page_pool_params *params) +struct page_pool * +page_pool_create_percpu(const struct page_pool_params *params, int cpuid) { struct page_pool *pool; int err; @@ -265,7 +282,7 @@ struct page_pool *page_pool_create(const struct page_pool_params *params) if (!pool) return ERR_PTR(-ENOMEM); - err = page_pool_init(pool, params); + err = page_pool_init(pool, params, cpuid); if (err < 0) goto err_free; @@ -282,6 +299,16 @@ err_free: kfree(pool); return ERR_PTR(err); } +EXPORT_SYMBOL(page_pool_create_percpu); + +/** + * page_pool_create() - create a page pool + * @params: parameters, see struct page_pool_params + */ +struct page_pool *page_pool_create(const struct page_pool_params *params) +{ + return page_pool_create_percpu(params, -1); +} EXPORT_SYMBOL(page_pool_create); static void page_pool_return_page(struct page_pool *pool, struct page *page); @@ -630,6 +657,11 @@ static bool page_pool_recycle_in_cache(struct page *page, return true; } +static bool __page_pool_page_can_be_recycled(const struct page *page) +{ + return page_ref_count(page) == 1 && !page_is_pfmemalloc(page); +} + /* If the page refcnt == 1, this will try to recycle the page. * if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for * the configured size min(dma_sync_size, pool->max_len). @@ -651,7 +683,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, * page is NOT reusable when allocated when system is under * some pressure. (page_is_pfmemalloc) */ - if (likely(page_ref_count(page) == 1 && !page_is_pfmemalloc(page))) { + if (likely(__page_pool_page_can_be_recycled(page))) { /* Read barrier done in page_ref_count / READ_ONCE */ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) @@ -766,7 +798,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool, if (likely(page_pool_unref_page(page, drain_count))) return NULL; - if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) { + if (__page_pool_page_can_be_recycled(page)) { if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) page_pool_dma_sync_for_device(pool, page, -1); @@ -934,8 +966,13 @@ void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), pool->xdp_mem_id = mem->id; } -void page_pool_unlink_napi(struct page_pool *pool) +static void page_pool_disable_direct_recycling(struct page_pool *pool) { + /* Disable direct recycling based on pool->cpuid. + * Paired with READ_ONCE() in napi_pp_put_page(). + */ + WRITE_ONCE(pool->cpuid, -1); + if (!pool->p.napi) return; @@ -947,7 +984,6 @@ void page_pool_unlink_napi(struct page_pool *pool) WRITE_ONCE(pool->p.napi, NULL); } -EXPORT_SYMBOL(page_pool_unlink_napi); void page_pool_destroy(struct page_pool *pool) { @@ -957,7 +993,7 @@ void page_pool_destroy(struct page_pool *pool) if (!page_pool_put(pool)) return; - page_pool_unlink_napi(pool); + page_pool_disable_direct_recycling(pool); page_pool_free_frag(pool); if (!page_pool_release(pool)) diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 278294aca66a..3a3277ba167b 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -103,8 +103,6 @@ out: mutex_unlock(&page_pools_lock); rtnl_unlock(); - if (skb->len && err == -EMSGSIZE) - return skb->len; return err; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bd50e9fe3234..a3d7847ce69d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -483,24 +483,15 @@ EXPORT_SYMBOL_GPL(__rtnl_link_unregister); */ static void rtnl_lock_unregistering_all(void) { - struct net *net; - bool unregistering; DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(&netdev_unregistering_wq, &wait); for (;;) { - unregistering = false; rtnl_lock(); /* We held write locked pernet_ops_rwsem, and parallel * setup_net() and cleanup_net() are not possible. */ - for_each_net(net) { - if (atomic_read(&net->dev_unreg_count) > 0) { - unregistering = true; - break; - } - } - if (!unregistering) + if (!atomic_read(&dev_unreg_count)) break; __rtnl_unlock(); @@ -851,9 +842,22 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, } EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo); +void netdev_set_operstate(struct net_device *dev, int newstate) +{ + unsigned int old = READ_ONCE(dev->operstate); + + do { + if (old == newstate) + return; + } while (!try_cmpxchg(&dev->operstate, &old, newstate)); + + netdev_state_change(dev); +} +EXPORT_SYMBOL(netdev_set_operstate); + static void set_operstate(struct net_device *dev, unsigned char transition) { - unsigned char operstate = dev->operstate; + unsigned char operstate = READ_ONCE(dev->operstate); switch (transition) { case IF_OPER_UP: @@ -875,12 +879,7 @@ static void set_operstate(struct net_device *dev, unsigned char transition) break; } - if (dev->operstate != operstate) { - write_lock(&dev_base_lock); - dev->operstate = operstate; - write_unlock(&dev_base_lock); - netdev_state_change(dev); - } + netdev_set_operstate(dev, operstate); } static unsigned int rtnl_dev_get_flags(const struct net_device *dev) @@ -1456,17 +1455,18 @@ static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb, return 0; } -static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) +static int rtnl_fill_link_ifmap(struct sk_buff *skb, + const struct net_device *dev) { struct rtnl_link_ifmap map; memset(&map, 0, sizeof(map)); - map.mem_start = dev->mem_start; - map.mem_end = dev->mem_end; - map.base_addr = dev->base_addr; - map.irq = dev->irq; - map.dma = dev->dma; - map.port = dev->if_port; + map.mem_start = READ_ONCE(dev->mem_start); + map.mem_end = READ_ONCE(dev->mem_end); + map.base_addr = READ_ONCE(dev->base_addr); + map.irq = READ_ONCE(dev->irq); + map.dma = READ_ONCE(dev->dma); + map.port = READ_ONCE(dev->if_port); if (nla_put_64bit(skb, IFLA_MAP, sizeof(map), &map, IFLA_PAD)) return -EMSGSIZE; @@ -1612,10 +1612,10 @@ static int put_master_ifindex(struct sk_buff *skb, struct net_device *dev) static int nla_put_iflink(struct sk_buff *skb, const struct net_device *dev, bool force) { - int ifindex = dev_get_iflink(dev); + int iflink = dev_get_iflink(dev); - if (force || dev->ifindex != ifindex) - return nla_put_u32(skb, IFLA_LINK, ifindex); + if (force || READ_ONCE(dev->ifindex) != iflink) + return nla_put_u32(skb, IFLA_LINK, iflink); return 0; } @@ -1699,7 +1699,7 @@ static int rtnl_fill_alt_ifnames(struct sk_buff *skb, struct netdev_name_node *name_node; int count = 0; - list_for_each_entry(name_node, &dev->name_node->list, list) { + list_for_each_entry_rcu(name_node, &dev->name_node->list, list) { if (nla_put_string(skb, IFLA_ALT_IFNAME, name_node->name)) return -EMSGSIZE; count++; @@ -1707,6 +1707,7 @@ static int rtnl_fill_alt_ifnames(struct sk_buff *skb, return count; } +/* RCU protected. */ static int rtnl_fill_prop_list(struct sk_buff *skb, const struct net_device *dev) { @@ -1876,9 +1877,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; } - if (rtnl_fill_link_ifmap(skb, dev)) - goto nla_put_failure; - if (dev->addr_len) { if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) || nla_put(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast)) @@ -1928,10 +1926,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, rcu_read_lock(); if (rtnl_fill_link_af(skb, dev, ext_filter_mask)) goto nla_put_failure_rcu; - rcu_read_unlock(); - + if (rtnl_fill_link_ifmap(skb, dev)) + goto nla_put_failure_rcu; if (rtnl_fill_prop_list(skb, dev)) - goto nla_put_failure; + goto nla_put_failure_rcu; + rcu_read_unlock(); if (dev->dev.parent && nla_put_string(skb, IFLA_PARENT_DEV_NAME, @@ -2200,25 +2199,22 @@ static int rtnl_valid_dump_ifinfo_req(const struct nlmsghdr *nlh, static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { + const struct rtnl_link_ops *kind_ops = NULL; struct netlink_ext_ack *extack = cb->extack; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); - struct net *tgt_net = net; - int h, s_h; - int idx = 0, s_idx; - struct net_device *dev; - struct hlist_head *head; + unsigned int flags = NLM_F_MULTI; struct nlattr *tb[IFLA_MAX+1]; + struct { + unsigned long ifindex; + } *ctx = (void *)cb->ctx; + struct net *tgt_net = net; u32 ext_filter_mask = 0; - const struct rtnl_link_ops *kind_ops = NULL; - unsigned int flags = NLM_F_MULTI; + struct net_device *dev; int master_idx = 0; int netnsid = -1; int err, i; - s_h = cb->args[0]; - s_idx = cb->args[1]; - err = rtnl_valid_dump_ifinfo_req(nlh, cb->strict_check, tb, extack); if (err < 0) { if (cb->strict_check) @@ -2262,36 +2258,18 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) flags |= NLM_F_DUMP_FILTERED; walk_entries: - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &tgt_net->dev_index_head[h]; - hlist_for_each_entry(dev, head, index_hlist) { - if (link_dump_filtered(dev, master_idx, kind_ops)) - goto cont; - if (idx < s_idx) - goto cont; - err = rtnl_fill_ifinfo(skb, dev, net, - RTM_NEWLINK, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, 0, flags, - ext_filter_mask, 0, NULL, 0, - netnsid, GFP_KERNEL); - - if (err < 0) { - if (likely(skb->len)) - goto out; - - goto out_err; - } -cont: - idx++; - } + err = 0; + for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { + if (link_dump_filtered(dev, master_idx, kind_ops)) + continue; + err = rtnl_fill_ifinfo(skb, dev, net, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, 0, flags, + ext_filter_mask, 0, NULL, 0, + netnsid, GFP_KERNEL); + if (err < 0) + break; } -out: - err = skb->len; -out_err: - cb->args[1] = idx; - cb->args[0] = h; cb->seq = tgt_net->dev_base_seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); if (netnsid >= 0) @@ -2983,11 +2961,9 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_LINKMODE]) { unsigned char value = nla_get_u8(tb[IFLA_LINKMODE]); - write_lock(&dev_base_lock); if (dev->link_mode ^ value) status |= DO_SETLINK_NOTIFY; - dev->link_mode = value; - write_unlock(&dev_base_lock); + WRITE_ONCE(dev->link_mode, value); } if (tb[IFLA_VFINFO_LIST]) { @@ -6552,6 +6528,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, } owner = link->owner; dumpit = link->dumpit; + flags = link->flags; if (type == RTM_GETLINK - RTM_BASE) min_dump_alloc = rtnl_calcit(skb, nlh); @@ -6569,6 +6546,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, .dump = dumpit, .min_dump_alloc = min_dump_alloc, .module = owner, + .flags = flags, }; err = netlink_dump_start(rtnl, skb, nlh, &c); /* netlink_dump_start() will keep a reference on diff --git a/net/core/scm.c b/net/core/scm.c index d0e0852a24d5..9cd4b0a01cd6 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -36,6 +36,7 @@ #include <net/compat.h> #include <net/scm.h> #include <net/cls_cgroup.h> +#include <net/af_unix.h> /* @@ -85,6 +86,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) return -ENOMEM; *fplp = fpl; fpl->count = 0; + fpl->count_unix = 0; fpl->max = SCM_MAX_FD; fpl->user = NULL; } @@ -109,6 +111,9 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) fput(file); return -EINVAL; } + if (unix_get_socket(file)) + fpl->count_unix++; + *fpp++ = file; fpl->count++; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index edbbef563d4d..b99127712e67 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -69,6 +69,7 @@ #include <net/sock.h> #include <net/checksum.h> #include <net/gso.h> +#include <net/hotdata.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> @@ -88,15 +89,10 @@ #include "dev.h" #include "sock_destructor.h" -struct kmem_cache *skbuff_cache __ro_after_init; -static struct kmem_cache *skbuff_fclone_cache __ro_after_init; #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif - -static struct kmem_cache *skb_small_head_cache __ro_after_init; - #define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. @@ -115,6 +111,24 @@ static struct kmem_cache *skb_small_head_cache __ro_after_init; int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); +/* kcm_write_msgs() relies on casting paged frags to bio_vec to use + * iov_iter_bvec(). These static asserts ensure the cast is valid is long as the + * netmem is a page. + */ +static_assert(offsetof(struct bio_vec, bv_page) == + offsetof(skb_frag_t, netmem)); +static_assert(sizeof_field(struct bio_vec, bv_page) == + sizeof_field(skb_frag_t, netmem)); + +static_assert(offsetof(struct bio_vec, bv_len) == offsetof(skb_frag_t, len)); +static_assert(sizeof_field(struct bio_vec, bv_len) == + sizeof_field(skb_frag_t, len)); + +static_assert(offsetof(struct bio_vec, bv_offset) == + offsetof(skb_frag_t, offset)); +static_assert(sizeof_field(struct bio_vec, bv_offset) == + sizeof_field(skb_frag_t, offset)); + #undef FN #define FN(reason) [SKB_DROP_REASON_##reason] = #reason, static const char * const drop_reasons[] = { @@ -297,7 +311,8 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) fragsz = SKB_DATA_ALIGN(fragsz); - return page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); + return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, + align_mask); } EXPORT_SYMBOL(__napi_alloc_frag_align); @@ -309,13 +324,15 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) if (in_hardirq() || irqs_disabled()) { struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); - data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); + data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, + align_mask); } else { struct napi_alloc_cache *nc; local_bh_disable(); nc = this_cpu_ptr(&napi_alloc_cache); - data = page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); + data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, + align_mask); local_bh_enable(); } return data; @@ -328,7 +345,7 @@ static struct sk_buff *napi_skb_cache_get(void) struct sk_buff *skb; if (unlikely(!nc->skb_count)) { - nc->skb_count = kmem_cache_alloc_bulk(skbuff_cache, + nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); @@ -337,7 +354,7 @@ static struct sk_buff *napi_skb_cache_get(void) } skb = nc->skb_cache[--nc->skb_count]; - kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache)); + kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache)); return skb; } @@ -395,7 +412,7 @@ struct sk_buff *slab_build_skb(void *data) struct sk_buff *skb; unsigned int size; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -446,7 +463,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -557,7 +574,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, obj_size = SKB_HEAD_ALIGN(*size); if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && !(flags & KMALLOC_NOT_NORMAL_BITS)) { - obj = kmem_cache_alloc_node(skb_small_head_cache, + obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); *size = SKB_SMALL_HEAD_CACHE_SIZE; @@ -565,7 +582,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, goto out; /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; - obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node); + obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node); goto out; } @@ -628,7 +645,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, u8 *data; cache = (flags & SKB_ALLOC_FCLONE) - ? skbuff_fclone_cache : skbuff_cache; + ? net_hotdata.skbuff_fclone_cache : net_hotdata.skbuff_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; @@ -845,17 +862,17 @@ skb_fail: } EXPORT_SYMBOL(__napi_alloc_skb); -void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, - int size, unsigned int truesize) +void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, + int off, int size, unsigned int truesize) { DEBUG_NET_WARN_ON_ONCE(size > truesize); - skb_fill_page_desc(skb, i, page, off, size); + skb_fill_netmem_desc(skb, i, netmem, off, size); skb->len += size; skb->data_len += size; skb->truesize += truesize; } -EXPORT_SYMBOL(skb_add_rx_frag); +EXPORT_SYMBOL(skb_add_rx_frag_netmem); void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize) @@ -895,6 +912,98 @@ static bool is_pp_page(struct page *page) return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; } +int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, + unsigned int headroom) +{ +#if IS_ENABLED(CONFIG_PAGE_POOL) + u32 size, truesize, len, max_head_size, off; + struct sk_buff *skb = *pskb, *nskb; + int err, i, head_off; + void *data; + + /* XDP does not support fraglist so we need to linearize + * the skb. + */ + if (skb_has_frag_list(skb)) + return -EOPNOTSUPP; + + max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom); + if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE) + return -ENOMEM; + + size = min_t(u32, skb->len, max_head_size); + truesize = SKB_HEAD_ALIGN(size) + headroom; + data = page_pool_dev_alloc_va(pool, &truesize); + if (!data) + return -ENOMEM; + + nskb = napi_build_skb(data, truesize); + if (!nskb) { + page_pool_free_va(pool, data, true); + return -ENOMEM; + } + + skb_reserve(nskb, headroom); + skb_copy_header(nskb, skb); + skb_mark_for_recycle(nskb); + + err = skb_copy_bits(skb, 0, nskb->data, size); + if (err) { + consume_skb(nskb); + return err; + } + skb_put(nskb, size); + + head_off = skb_headroom(nskb) - skb_headroom(skb); + skb_headers_offset_update(nskb, head_off); + + off = size; + len = skb->len - off; + for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) { + struct page *page; + u32 page_off; + + size = min_t(u32, len, PAGE_SIZE); + truesize = size; + + page = page_pool_dev_alloc(pool, &page_off, &truesize); + if (!page) { + consume_skb(nskb); + return -ENOMEM; + } + + skb_add_rx_frag(nskb, i, page, page_off, size, truesize); + err = skb_copy_bits(skb, off, page_address(page) + page_off, + size); + if (err) { + consume_skb(nskb); + return err; + } + + len -= size; + off += size; + } + + consume_skb(skb); + *pskb = nskb; + + return 0; +#else + return -EOPNOTSUPP; +#endif +} +EXPORT_SYMBOL(skb_pp_cow_data); + +int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, + struct bpf_prog *prog) +{ + if (!prog->aux->xdp_has_frags) + return -EINVAL; + + return skb_pp_cow_data(pool, pskb, XDP_PACKET_HEADROOM); +} +EXPORT_SYMBOL(skb_cow_data_for_xdp); + #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(struct page *page, bool napi_safe) { @@ -923,9 +1032,10 @@ bool napi_pp_put_page(struct page *page, bool napi_safe) */ if (napi_safe || in_softirq()) { const struct napi_struct *napi = READ_ONCE(pp->p.napi); + unsigned int cpuid = smp_processor_id(); - allow_direct = napi && - READ_ONCE(napi->list_owner) == smp_processor_id(); + allow_direct = napi && READ_ONCE(napi->list_owner) == cpuid; + allow_direct |= READ_ONCE(pp->cpuid) == cpuid; } /* Driver set this to memory recycling info. Reset it on recycle. @@ -981,7 +1091,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb) static void skb_kfree_head(void *head, unsigned int end_offset) { if (end_offset == SKB_SMALL_HEAD_HEADROOM) - kmem_cache_free(skb_small_head_cache, head); + kmem_cache_free(net_hotdata.skb_small_head_cache, head); else kfree(head); } @@ -1005,9 +1115,7 @@ static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason, struct skb_shared_info *shinfo = skb_shinfo(skb); int i; - if (skb->cloned && - atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1, - &shinfo->dataref)) + if (!skb_data_unref(skb, shinfo)) goto exit; if (skb_zcopy(skb)) { @@ -1048,7 +1156,7 @@ static void kfree_skbmem(struct sk_buff *skb) switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: - kmem_cache_free(skbuff_cache, skb); + kmem_cache_free(net_hotdata.skbuff_cache, skb); return; case SKB_FCLONE_ORIG: @@ -1069,7 +1177,7 @@ static void kfree_skbmem(struct sk_buff *skb) if (!refcount_dec_and_test(&fclones->fclone_ref)) return; fastpath: - kmem_cache_free(skbuff_fclone_cache, fclones); + kmem_cache_free(net_hotdata.skbuff_fclone_cache, fclones); } void skb_release_head_state(struct sk_buff *skb) @@ -1166,7 +1274,7 @@ static void kfree_skb_add_bulk(struct sk_buff *skb, sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { - kmem_cache_free_bulk(skbuff_cache, KFREE_SKB_BULK_SIZE, + kmem_cache_free_bulk(net_hotdata.skbuff_cache, KFREE_SKB_BULK_SIZE, sa->skb_array); sa->skb_count = 0; } @@ -1191,7 +1299,7 @@ kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) } if (sa.skb_count) - kmem_cache_free_bulk(skbuff_cache, sa.skb_count, sa.skb_array); + kmem_cache_free_bulk(net_hotdata.skbuff_cache, sa.skb_count, sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); @@ -1353,9 +1461,9 @@ static void napi_skb_cache_put(struct sk_buff *skb) if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) kasan_mempool_unpoison_object(nc->skb_cache[i], - kmem_cache_size(skbuff_cache)); + kmem_cache_size(net_hotdata.skbuff_cache)); - kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF, + kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); nc->skb_count = NAPI_SKB_CACHE_HALF; } @@ -1906,10 +2014,11 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) /* skb frags point to kernel buffers */ for (i = 0; i < new_frags - 1; i++) { - __skb_fill_page_desc(skb, i, head, 0, psize); + __skb_fill_netmem_desc(skb, i, page_to_netmem(head), 0, psize); head = (struct page *)page_private(head); } - __skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off); + __skb_fill_netmem_desc(skb, new_frags - 1, page_to_netmem(head), 0, + d_off); skb_shinfo(skb)->nr_frags = new_frags; release: @@ -1951,7 +2060,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - n = kmem_cache_alloc(skbuff_cache, gfp_mask); + n = kmem_cache_alloc(net_hotdata.skbuff_cache, gfp_mask); if (!n) return NULL; @@ -3647,7 +3756,8 @@ skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) if (plen) { page = virt_to_head_page(from->head); offset = from->data - (unsigned char *)page_address(page); - __skb_fill_page_desc(to, 0, page, offset, plen); + __skb_fill_netmem_desc(to, 0, page_to_netmem(page), + offset, plen); get_page(page); j = 1; len -= plen; @@ -4889,7 +4999,7 @@ static void skb_extensions_init(void) {} void __init skb_init(void) { - skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", + net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC| @@ -4897,7 +5007,7 @@ void __init skb_init(void) offsetof(struct sk_buff, cb), sizeof_field(struct sk_buff, cb), NULL); - skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", + net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, @@ -4906,7 +5016,7 @@ void __init skb_init(void) * struct skb_shared_info is located at the end of skb->head, * and should not be copied to/from user. */ - skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", + net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", SKB_SMALL_HEAD_CACHE_SIZE, 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, @@ -5779,7 +5889,7 @@ void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); - kmem_cache_free(skbuff_cache, skb); + kmem_cache_free(net_hotdata.skbuff_cache, skb); } else { __kfree_skb(skb); } @@ -6737,6 +6847,14 @@ static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, xfrm_state_hold(sp->xvec[i]); } #endif +#ifdef CONFIG_MCTP_FLOWS + if (old_active & (1 << SKB_EXT_MCTP)) { + struct mctp_flow *flow = skb_ext_get_ptr(old, SKB_EXT_MCTP); + + if (flow->key) + refcount_inc(&flow->key->refs); + } +#endif __skb_ext_put(old); return new; } diff --git a/net/core/sock.c b/net/core/sock.c index 5e78798456fd..43bf3818c19e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -283,6 +283,7 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; +int sysctl_mem_pcpu_rsv __read_mostly = SK_MEMORY_PCPU_RESERVE; int sysctl_tstamp_allow_data __read_mostly = 1; @@ -2052,8 +2053,9 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); - memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, - prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); + unsafe_memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, + prot->obj_size - offsetof(struct sock, sk_dontcopy_end), + /* alloc is larger than struct, see sk_prot_alloc() */); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; @@ -2582,8 +2584,18 @@ EXPORT_SYMBOL(sock_efree); #ifdef CONFIG_INET void sock_pfree(struct sk_buff *skb) { - if (sk_is_refcounted(skb->sk)) - sock_gen_put(skb->sk); + struct sock *sk = skb->sk; + + if (!sk_is_refcounted(sk)) + return; + + if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) { + inet_reqsk(sk)->rsk_listener = NULL; + reqsk_free(inet_reqsk(sk)); + return; + } + + sock_gen_put(sk); } EXPORT_SYMBOL(sock_pfree); #endif /* CONFIG_INET */ @@ -4223,3 +4235,65 @@ int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) return sock_ioctl_out(sk, cmd, arg); } EXPORT_SYMBOL(sk_ioctl); + +static int __init sock_struct_check(void) +{ + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_drops); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_peek_off); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_error_queue); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_receive_queue); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rx, sk_backlog); + + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_ifindex); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rx_dst_cookie); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvbuf); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_filter); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_wq); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_data_ready); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvtimeo); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rx, sk_rcvlowat); + + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_err); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_socket); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_rxtx, sk_memcg); + + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_lock); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_reserved_mem); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_forward_alloc); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_rxtx, sk_tsflags); + + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_omem_alloc); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_sndbuf); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_queued); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_wmem_alloc); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tsq_flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_send_head); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_queue); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_pending); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_dst_pending_confirm); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_status); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_frag); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_timer); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_rate); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_zckey); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tskey); + + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_max_pacing_rate); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_sndtimeo); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_priority); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_mark); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_dst_cache); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_route_caps); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_type); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_size); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_allocation); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_txhash); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_gso_max_segs); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_pacing_shift); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_use_task_frag); + return 0; +} + +core_initcall(sock_struct_check); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index b1e29e18d1d6..654122838025 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -16,9 +16,10 @@ #include <linux/inet_diag.h> #include <linux/sock_diag.h> -static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; -static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); -static DEFINE_MUTEX(sock_diag_table_mutex); +static const struct sock_diag_handler __rcu *sock_diag_handlers[AF_MAX]; + +static struct sock_diag_inet_compat __rcu *inet_rcv_compat; + static struct workqueue_struct *broadcast_wq; DEFINE_COOKIE(sock_cookie); @@ -122,6 +123,24 @@ static size_t sock_diag_nlmsg_size(void) + nla_total_size_64bit(sizeof(struct tcp_info))); /* INET_DIAG_INFO */ } +static const struct sock_diag_handler *sock_diag_lock_handler(int family) +{ + const struct sock_diag_handler *handler; + + rcu_read_lock(); + handler = rcu_dereference(sock_diag_handlers[family]); + if (handler && !try_module_get(handler->owner)) + handler = NULL; + rcu_read_unlock(); + + return handler; +} + +static void sock_diag_unlock_handler(const struct sock_diag_handler *handler) +{ + module_put(handler->owner); +} + static void sock_diag_broadcast_destroy_work(struct work_struct *work) { struct broadcast_sk *bsk = @@ -138,12 +157,12 @@ static void sock_diag_broadcast_destroy_work(struct work_struct *work) if (!skb) goto out; - mutex_lock(&sock_diag_table_mutex); - hndl = sock_diag_handlers[sk->sk_family]; - if (hndl && hndl->get_info) - err = hndl->get_info(skb, sk); - mutex_unlock(&sock_diag_table_mutex); - + hndl = sock_diag_lock_handler(sk->sk_family); + if (hndl) { + if (hndl->get_info) + err = hndl->get_info(skb, sk); + sock_diag_unlock_handler(hndl); + } if (!err) nlmsg_multicast(sock_net(sk)->diag_nlsk, skb, 0, group, GFP_KERNEL); @@ -166,51 +185,45 @@ void sock_diag_broadcast_destroy(struct sock *sk) queue_work(broadcast_wq, &bsk->work); } -void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) +void sock_diag_register_inet_compat(const struct sock_diag_inet_compat *ptr) { - mutex_lock(&sock_diag_table_mutex); - inet_rcv_compat = fn; - mutex_unlock(&sock_diag_table_mutex); + xchg((__force const struct sock_diag_inet_compat **)&inet_rcv_compat, + ptr); } EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat); -void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) +void sock_diag_unregister_inet_compat(const struct sock_diag_inet_compat *ptr) { - mutex_lock(&sock_diag_table_mutex); - inet_rcv_compat = NULL; - mutex_unlock(&sock_diag_table_mutex); + const struct sock_diag_inet_compat *old; + + old = xchg((__force const struct sock_diag_inet_compat **)&inet_rcv_compat, + NULL); + WARN_ON_ONCE(old != ptr); } EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); int sock_diag_register(const struct sock_diag_handler *hndl) { - int err = 0; + int family = hndl->family; - if (hndl->family >= AF_MAX) + if (family >= AF_MAX) return -EINVAL; - mutex_lock(&sock_diag_table_mutex); - if (sock_diag_handlers[hndl->family]) - err = -EBUSY; - else - sock_diag_handlers[hndl->family] = hndl; - mutex_unlock(&sock_diag_table_mutex); - - return err; + return !cmpxchg((const struct sock_diag_handler **) + &sock_diag_handlers[family], + NULL, hndl) ? 0 : -EBUSY; } EXPORT_SYMBOL_GPL(sock_diag_register); -void sock_diag_unregister(const struct sock_diag_handler *hnld) +void sock_diag_unregister(const struct sock_diag_handler *hndl) { - int family = hnld->family; + int family = hndl->family; if (family >= AF_MAX) return; - mutex_lock(&sock_diag_table_mutex); - BUG_ON(sock_diag_handlers[family] != hnld); - sock_diag_handlers[family] = NULL; - mutex_unlock(&sock_diag_table_mutex); + xchg((const struct sock_diag_handler **)&sock_diag_handlers[family], + NULL); } EXPORT_SYMBOL_GPL(sock_diag_unregister); @@ -227,20 +240,20 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX); - if (sock_diag_handlers[req->sdiag_family] == NULL) + if (!rcu_access_pointer(sock_diag_handlers[req->sdiag_family])) sock_load_diag_module(req->sdiag_family, 0); - mutex_lock(&sock_diag_table_mutex); - hndl = sock_diag_handlers[req->sdiag_family]; + hndl = sock_diag_lock_handler(req->sdiag_family); if (hndl == NULL) - err = -ENOENT; - else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY) + return -ENOENT; + + if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY) err = hndl->dump(skb, nlh); else if (nlh->nlmsg_type == SOCK_DESTROY && hndl->destroy) err = hndl->destroy(skb, nlh); else err = -EOPNOTSUPP; - mutex_unlock(&sock_diag_table_mutex); + sock_diag_unlock_handler(hndl); return err; } @@ -248,20 +261,27 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + const struct sock_diag_inet_compat *ptr; int ret; switch (nlh->nlmsg_type) { case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: - if (inet_rcv_compat == NULL) + + if (!rcu_access_pointer(inet_rcv_compat)) sock_load_diag_module(AF_INET, 0); - mutex_lock(&sock_diag_table_mutex); - if (inet_rcv_compat != NULL) - ret = inet_rcv_compat(skb, nlh); - else - ret = -EOPNOTSUPP; - mutex_unlock(&sock_diag_table_mutex); + rcu_read_lock(); + ptr = rcu_dereference(inet_rcv_compat); + if (ptr && !try_module_get(ptr->owner)) + ptr = NULL; + rcu_read_unlock(); + + ret = -EOPNOTSUPP; + if (ptr) { + ret = ptr->fn(skb, nlh); + module_put(ptr->owner); + } return ret; case SOCK_DIAG_BY_FAMILY: @@ -272,13 +292,9 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, } } -static DEFINE_MUTEX(sock_diag_mutex); - static void sock_diag_rcv(struct sk_buff *skb) { - mutex_lock(&sock_diag_mutex); netlink_rcv_skb(skb, &sock_diag_rcv_msg); - mutex_unlock(&sock_diag_mutex); } static int sock_diag_bind(struct net *net, int group) @@ -286,12 +302,12 @@ static int sock_diag_bind(struct net *net, int group) switch (group) { case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: - if (!sock_diag_handlers[AF_INET]) + if (!rcu_access_pointer(sock_diag_handlers[AF_INET])) sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: - if (!sock_diag_handlers[AF_INET6]) + if (!rcu_access_pointer(sock_diag_handlers[AF_INET6])) sock_load_diag_module(AF_INET6, 0); break; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 0f0cb1465e08..6973dda3abda 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -23,6 +23,8 @@ #include <net/net_ratelimit.h> #include <net/busy_poll.h> #include <net/pkt_sched.h> +#include <net/hotdata.h> +#include <net/rps.h> #include "dev.h" @@ -30,6 +32,7 @@ static int int_3600 = 3600; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; +static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -137,7 +140,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, mutex_lock(&sock_flow_mutex); - orig_sock_table = rcu_dereference_protected(rps_sock_flow_table, + orig_sock_table = rcu_dereference_protected( + net_hotdata.rps_sock_flow_table, lockdep_is_held(&sock_flow_mutex)); size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; @@ -158,7 +162,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, mutex_unlock(&sock_flow_mutex); return -ENOMEM; } - rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1; + net_hotdata.rps_cpu_mask = + roundup_pow_of_two(nr_cpu_ids) - 1; sock_table->mask = size - 1; } else sock_table = orig_sock_table; @@ -169,7 +174,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, sock_table = NULL; if (sock_table != orig_sock_table) { - rcu_assign_pointer(rps_sock_flow_table, sock_table); + rcu_assign_pointer(net_hotdata.rps_sock_flow_table, + sock_table); if (sock_table) { static_branch_inc(&rps_needed); static_branch_inc(&rfs_needed); @@ -299,8 +305,8 @@ static int proc_do_dev_weight(struct ctl_table *table, int write, ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) { weight = READ_ONCE(weight_p); - WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias); - WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias); + WRITE_ONCE(net_hotdata.dev_rx_weight, weight * dev_weight_rx_bias); + WRITE_ONCE(net_hotdata.dev_tx_weight, weight * dev_weight_tx_bias); } mutex_unlock(&dev_weight_mutex); @@ -408,6 +414,14 @@ static struct ctl_table net_core_table[] = { .extra1 = &min_rcvbuf, }, { + .procname = "mem_pcpu_rsv", + .data = &sysctl_mem_pcpu_rsv, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_mem_pcpu_rsv, + }, + { .procname = "dev_weight", .data = &weight_p, .maxlen = sizeof(int), @@ -430,7 +444,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "netdev_max_backlog", - .data = &netdev_max_backlog, + .data = &net_hotdata.max_backlog, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -489,7 +503,7 @@ static struct ctl_table net_core_table[] = { #endif { .procname = "netdev_tstamp_prequeue", - .data = &netdev_tstamp_prequeue, + .data = &net_hotdata.tstamp_prequeue, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -567,7 +581,7 @@ static struct ctl_table net_core_table[] = { #endif { .procname = "netdev_budget", - .data = &netdev_budget, + .data = &net_hotdata.netdev_budget, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -590,7 +604,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "netdev_budget_usecs", - .data = &netdev_budget_usecs, + .data = &net_hotdata.netdev_budget_usecs, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -623,7 +637,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "gro_normal_batch", - .data = &gro_normal_batch, + .data = &net_hotdata.gro_normal_batch, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, diff --git a/net/core/xdp.c b/net/core/xdp.c index 4869c1c2d8f3..41693154e426 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -16,6 +16,7 @@ #include <linux/bug.h> #include <net/page_pool/helpers.h> +#include <net/hotdata.h> #include <net/xdp.h> #include <net/xdp_priv.h> /* struct xdp_mem_allocator */ #include <trace/events/xdp.h> @@ -75,7 +76,7 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) xa = container_of(rcu, struct xdp_mem_allocator, rcu); /* Allow this ID to be reused */ - ida_simple_remove(&mem_id_pool, xa->mem.id); + ida_free(&mem_id_pool, xa->mem.id); kfree(xa); } @@ -242,7 +243,7 @@ static int __mem_id_cyclic_get(gfp_t gfp) int id; again: - id = ida_simple_get(&mem_id_pool, mem_id_next, MEM_ID_MAX, gfp); + id = ida_alloc_range(&mem_id_pool, mem_id_next, MEM_ID_MAX - 1, gfp); if (id < 0) { if (id == -ENOSPC) { /* Cyclic allocator, reset next id */ @@ -317,7 +318,7 @@ static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem, /* Insert allocator into ID lookup table */ ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); if (IS_ERR(ptr)) { - ida_simple_remove(&mem_id_pool, mem->id); + ida_free(&mem_id_pool, mem->id); mem->id = 0; errno = PTR_ERR(ptr); goto err; @@ -589,7 +590,7 @@ EXPORT_SYMBOL_GPL(xdp_warn); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) { - n_skb = kmem_cache_alloc_bulk(skbuff_cache, gfp, n_skb, skbs); + n_skb = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, n_skb, skbs); if (unlikely(!n_skb)) return -ENOMEM; @@ -658,7 +659,7 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -771,11 +772,11 @@ __bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, __bpf_kfunc_end_defs(); -BTF_SET8_START(xdp_metadata_kfunc_ids) +BTF_KFUNCS_START(xdp_metadata_kfunc_ids) #define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS) XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC -BTF_SET8_END(xdp_metadata_kfunc_ids) +BTF_KFUNCS_END(xdp_metadata_kfunc_ids) static const struct btf_kfunc_id_set xdp_metadata_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index c4bbac99740d..1cba001bb4c8 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -376,15 +376,11 @@ EXPORT_SYMBOL_GPL(dccp_ackvec_parsed_cleanup); int __init dccp_ackvec_init(void) { - dccp_ackvec_slab = kmem_cache_create("dccp_ackvec", - sizeof(struct dccp_ackvec), 0, - SLAB_HWCACHE_ALIGN, NULL); + dccp_ackvec_slab = KMEM_CACHE(dccp_ackvec, SLAB_HWCACHE_ALIGN); if (dccp_ackvec_slab == NULL) goto out_err; - dccp_ackvec_record_slab = kmem_cache_create("dccp_ackvec_record", - sizeof(struct dccp_ackvec_record), - 0, SLAB_HWCACHE_ALIGN, NULL); + dccp_ackvec_record_slab = KMEM_CACHE(dccp_ackvec_record, SLAB_HWCACHE_ALIGN); if (dccp_ackvec_record_slab == NULL) goto out_destroy_slab; diff --git a/net/dccp/diag.c b/net/dccp/diag.c index 8a82c5a2c5a8..f5019d95c3ae 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -58,6 +58,7 @@ static int dccp_diag_dump_one(struct netlink_callback *cb, } static const struct inet_diag_handler dccp_diag_handler = { + .owner = THIS_MODULE, .dump = dccp_diag_dump, .dump_one = dccp_diag_dump_one, .idiag_get_info = dccp_diag_get_info, diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index c81cf2dd154f..f9786d51f68f 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -198,7 +198,7 @@ static const struct nla_policy devlink_eswitch_set_nl_policy[DEVLINK_ATTR_ESWITC [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_MAX(NLA_U16, 1), - [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = NLA_POLICY_MAX(NLA_U16, 3), + [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = NLA_POLICY_MAX(NLA_U8, 3), [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = NLA_POLICY_MAX(NLA_U8, 1), }; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index ac7be864e80d..09d2f5d4b3dd 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -15,7 +15,6 @@ #include <linux/slab.h> #include <linux/rtnetlink.h> #include <linux/of.h> -#include <linux/of_mdio.h> #include <linux/of_net.h> #include <net/dsa_stubs.h> #include <net/sch_generic.h> @@ -626,7 +625,6 @@ static void dsa_switch_teardown_tag_protocol(struct dsa_switch *ds) static int dsa_switch_setup(struct dsa_switch *ds) { - struct device_node *dn; int err; if (ds->setup) @@ -666,10 +664,7 @@ static int dsa_switch_setup(struct dsa_switch *ds) dsa_user_mii_bus_init(ds); - dn = of_get_child_by_name(ds->dev->of_node, "mdio"); - - err = of_mdiobus_register(ds->user_mii_bus, dn); - of_node_put(dn); + err = mdiobus_register(ds->user_mii_bus); if (err < 0) goto free_user_mii_bus; } diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 2717e9d7b612..1aba1d05c27a 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -75,7 +75,7 @@ sja1105_tagger_private(struct dsa_switch *ds) } /* 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) +static bool sja1105_is_link_local(const struct sk_buff *skb) { const struct ethhdr *hdr = eth_hdr(skb); u64 dmac = ether_addr_to_u64(hdr->h_dest); @@ -121,7 +121,7 @@ static void sja1105_meta_unpack(const struct sk_buff *skb, packing(buf + 7, &meta->switch_id, 7, 0, 1, UNPACK, 0); } -static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) +static bool sja1105_is_meta_frame(const struct sk_buff *skb) { const struct ethhdr *hdr = eth_hdr(skb); u64 smac = ether_addr_to_u64(hdr->h_source); diff --git a/net/dsa/user.c b/net/dsa/user.c index b15e71cc342c..16d395bb1a1f 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -210,7 +210,7 @@ static int dsa_user_sync_uc(struct net_device *dev, return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, - &ctx); + &ctx); } static int dsa_user_unsync_uc(struct net_device *dev, @@ -230,7 +230,7 @@ static int dsa_user_unsync_uc(struct net_device *dev, return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, - &ctx); + &ctx); } static int dsa_user_sync_mc(struct net_device *dev, @@ -250,7 +250,7 @@ static int dsa_user_sync_mc(struct net_device *dev, return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, - &ctx); + &ctx); } static int dsa_user_unsync_mc(struct net_device *dev, @@ -270,7 +270,7 @@ static int dsa_user_unsync_mc(struct net_device *dev, return 0; return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, - &ctx); + &ctx); } void dsa_user_sync_ha(struct net_device *dev) @@ -352,7 +352,7 @@ void dsa_user_mii_bus_init(struct dsa_switch *ds) /* user device handling ****************************************************/ static int dsa_user_get_iflink(const struct net_device *dev) { - return dsa_user_to_conduit(dev)->ifindex; + return READ_ONCE(dsa_user_to_conduit(dev)->ifindex); } static int dsa_user_open(struct net_device *dev) @@ -875,8 +875,8 @@ static int dsa_user_port_obj_del(struct net_device *dev, const void *ctx, return err; } -static inline netdev_tx_t dsa_user_netpoll_send_skb(struct net_device *dev, - struct sk_buff *skb) +static netdev_tx_t dsa_user_netpoll_send_skb(struct net_device *dev, + struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER struct dsa_user_priv *p = netdev_priv(dev); @@ -1222,7 +1222,7 @@ static int dsa_user_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) return ret; } -static int dsa_user_set_eee(struct net_device *dev, struct ethtool_eee *e) +static int dsa_user_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; @@ -1242,7 +1242,7 @@ static int dsa_user_set_eee(struct net_device *dev, struct ethtool_eee *e) return phylink_ethtool_set_eee(dp->pl, e); } -static int dsa_user_get_eee(struct net_device *dev, struct ethtool_eee *e) +static int dsa_user_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; @@ -2429,7 +2429,7 @@ static const struct net_device_ops dsa_user_netdev_ops = { .ndo_fill_forward_path = dsa_user_fill_forward_path, }; -static struct device_type dsa_type = { +static const struct device_type dsa_type = { .name = "dsa", }; @@ -2625,11 +2625,7 @@ int dsa_user_create(struct dsa_port *port) user_dev->vlan_features = conduit->vlan_features; p = netdev_priv(user_dev); - user_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!user_dev->tstats) { - free_netdev(user_dev); - return -ENOMEM; - } + user_dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ret = gro_cells_init(&p->gcells, user_dev); if (ret) @@ -2695,7 +2691,6 @@ out_phy: out_gcells: gro_cells_destroy(&p->gcells); out_free: - free_percpu(user_dev->tstats); free_netdev(user_dev); port->user = NULL; return ret; @@ -2716,7 +2711,6 @@ void dsa_user_destroy(struct net_device *user_dev) dsa_port_phylink_destroy(dp); gro_cells_destroy(&p->gcells); - free_percpu(user_dev->tstats); free_netdev(user_dev); } diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c index 2853394d06a8..bf398973eb8a 100644 --- a/net/ethtool/eee.c +++ b/net/ethtool/eee.c @@ -4,16 +4,13 @@ #include "common.h" #include "bitset.h" -#define EEE_MODES_COUNT \ - (sizeof_field(struct ethtool_eee, supported) * BITS_PER_BYTE) - struct eee_req_info { struct ethnl_req_info base; }; struct eee_reply_data { struct ethnl_reply_data base; - struct ethtool_eee eee; + struct ethtool_keee eee; }; #define EEE_REPDATA(__reply_base) \ @@ -30,6 +27,7 @@ static int eee_prepare_data(const struct ethnl_req_info *req_base, { struct eee_reply_data *data = EEE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; + struct ethtool_keee *eee = &data->eee; int ret; if (!dev->ethtool_ops->get_eee) @@ -37,7 +35,7 @@ static int eee_prepare_data(const struct ethnl_req_info *req_base, ret = ethnl_ops_begin(dev); if (ret < 0) return ret; - ret = dev->ethtool_ops->get_eee(dev, &data->eee); + ret = dev->ethtool_ops->get_eee(dev, eee); ethnl_ops_complete(dev); return ret; @@ -48,24 +46,21 @@ static int eee_reply_size(const struct ethnl_req_info *req_base, { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct eee_reply_data *data = EEE_REPDATA(reply_base); - const struct ethtool_eee *eee = &data->eee; + const struct ethtool_keee *eee = &data->eee; int len = 0; int ret; - BUILD_BUG_ON(sizeof(eee->advertised) * BITS_PER_BYTE != - EEE_MODES_COUNT); - BUILD_BUG_ON(sizeof(eee->lp_advertised) * BITS_PER_BYTE != - EEE_MODES_COUNT); - /* MODES_OURS */ - ret = ethnl_bitset32_size(&eee->advertised, &eee->supported, - EEE_MODES_COUNT, link_mode_names, compact); + ret = ethnl_bitset_size(eee->advertised, eee->supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); if (ret < 0) return ret; len += ret; /* MODES_PEERS */ - ret = ethnl_bitset32_size(&eee->lp_advertised, NULL, - EEE_MODES_COUNT, link_mode_names, compact); + ret = ethnl_bitset_size(eee->lp_advertised, NULL, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); if (ret < 0) return ret; len += ret; @@ -84,24 +79,26 @@ static int eee_fill_reply(struct sk_buff *skb, { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct eee_reply_data *data = EEE_REPDATA(reply_base); - const struct ethtool_eee *eee = &data->eee; + const struct ethtool_keee *eee = &data->eee; int ret; - ret = ethnl_put_bitset32(skb, ETHTOOL_A_EEE_MODES_OURS, - &eee->advertised, &eee->supported, - EEE_MODES_COUNT, link_mode_names, compact); + ret = ethnl_put_bitset(skb, ETHTOOL_A_EEE_MODES_OURS, + eee->advertised, eee->supported, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); if (ret < 0) return ret; - ret = ethnl_put_bitset32(skb, ETHTOOL_A_EEE_MODES_PEER, - &eee->lp_advertised, NULL, EEE_MODES_COUNT, - link_mode_names, compact); + ret = ethnl_put_bitset(skb, ETHTOOL_A_EEE_MODES_PEER, + eee->lp_advertised, NULL, + __ETHTOOL_LINK_MODE_MASK_NBITS, + link_mode_names, compact); if (ret < 0) return ret; - if (nla_put_u8(skb, ETHTOOL_A_EEE_ACTIVE, !!eee->eee_active) || - nla_put_u8(skb, ETHTOOL_A_EEE_ENABLED, !!eee->eee_enabled) || + if (nla_put_u8(skb, ETHTOOL_A_EEE_ACTIVE, eee->eee_active) || + nla_put_u8(skb, ETHTOOL_A_EEE_ENABLED, eee->eee_enabled) || nla_put_u8(skb, ETHTOOL_A_EEE_TX_LPI_ENABLED, - !!eee->tx_lpi_enabled) || + eee->tx_lpi_enabled) || nla_put_u32(skb, ETHTOOL_A_EEE_TX_LPI_TIMER, eee->tx_lpi_timer)) return -EMSGSIZE; @@ -132,7 +129,7 @@ ethnl_set_eee(struct ethnl_req_info *req_info, struct genl_info *info) { struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; - struct ethtool_eee eee = {}; + struct ethtool_keee eee = {}; bool mod = false; int ret; @@ -140,14 +137,15 @@ ethnl_set_eee(struct ethnl_req_info *req_info, struct genl_info *info) if (ret < 0) return ret; - ret = ethnl_update_bitset32(&eee.advertised, EEE_MODES_COUNT, - tb[ETHTOOL_A_EEE_MODES_OURS], - link_mode_names, info->extack, &mod); + ret = ethnl_update_bitset(eee.advertised, + __ETHTOOL_LINK_MODE_MASK_NBITS, + tb[ETHTOOL_A_EEE_MODES_OURS], + link_mode_names, info->extack, &mod); if (ret < 0) return ret; - ethnl_update_bool32(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod); - ethnl_update_bool32(&eee.tx_lpi_enabled, - tb[ETHTOOL_A_EEE_TX_LPI_ENABLED], &mod); + ethnl_update_bool(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod); + ethnl_update_bool(&eee.tx_lpi_enabled, tb[ETHTOOL_A_EEE_TX_LPI_ENABLED], + &mod); ethnl_update_u32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER], &mod); if (!mod) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7519b0818b91..5a55270aa86e 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -26,12 +26,12 @@ #include <linux/sched/signal.h> #include <linux/net.h> #include <linux/pm_runtime.h> +#include <linux/utsname.h> #include <net/devlink.h> #include <net/ipv6.h> #include <net/xdp_sock_drv.h> #include <net/flow_offload.h> #include <linux/ethtool_netlink.h> -#include <generated/utsrelease.h> #include "common.h" /* State held across locks and calls for commands which have devlink fallback */ @@ -713,7 +713,8 @@ ethtool_get_drvinfo(struct net_device *dev, struct ethtool_devlink_compat *rsp) struct device *parent = dev->dev.parent; rsp->info.cmd = ETHTOOL_GDRVINFO; - strscpy(rsp->info.version, UTS_RELEASE, sizeof(rsp->info.version)); + strscpy(rsp->info.version, init_uts_ns.name.release, + sizeof(rsp->info.version)); if (ops->get_drvinfo) { ops->get_drvinfo(dev, &rsp->info); if (!rsp->info.bus_info[0] && parent) @@ -1508,22 +1509,57 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) return 0; } +static void eee_to_keee(struct ethtool_keee *keee, + const struct ethtool_eee *eee) +{ + memset(keee, 0, sizeof(*keee)); + + keee->eee_enabled = eee->eee_enabled; + keee->tx_lpi_enabled = eee->tx_lpi_enabled; + keee->tx_lpi_timer = eee->tx_lpi_timer; + + ethtool_convert_legacy_u32_to_link_mode(keee->advertised, + eee->advertised); +} + +static void keee_to_eee(struct ethtool_eee *eee, + const struct ethtool_keee *keee) +{ + bool overflow; + + memset(eee, 0, sizeof(*eee)); + + eee->eee_active = keee->eee_active; + eee->eee_enabled = keee->eee_enabled; + eee->tx_lpi_enabled = keee->tx_lpi_enabled; + eee->tx_lpi_timer = keee->tx_lpi_timer; + + overflow = !ethtool_convert_link_mode_to_legacy_u32(&eee->supported, + keee->supported); + ethtool_convert_link_mode_to_legacy_u32(&eee->advertised, + keee->advertised); + ethtool_convert_link_mode_to_legacy_u32(&eee->lp_advertised, + keee->lp_advertised); + if (overflow) + pr_warn("Ethtool ioctl interface doesn't support passing EEE linkmodes beyond bit 32\n"); +} + static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) { - struct ethtool_eee edata; + struct ethtool_keee keee; + struct ethtool_eee eee; int rc; if (!dev->ethtool_ops->get_eee) return -EOPNOTSUPP; - memset(&edata, 0, sizeof(struct ethtool_eee)); - edata.cmd = ETHTOOL_GEEE; - rc = dev->ethtool_ops->get_eee(dev, &edata); - + memset(&keee, 0, sizeof(keee)); + rc = dev->ethtool_ops->get_eee(dev, &keee); if (rc) return rc; - if (copy_to_user(useraddr, &edata, sizeof(edata))) + keee_to_eee(&eee, &keee); + if (copy_to_user(useraddr, &eee, sizeof(eee))) return -EFAULT; return 0; @@ -1531,16 +1567,18 @@ static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) static int ethtool_set_eee(struct net_device *dev, char __user *useraddr) { - struct ethtool_eee edata; + struct ethtool_keee keee; + struct ethtool_eee eee; int ret; if (!dev->ethtool_ops->set_eee) return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) + if (copy_from_user(&eee, useraddr, sizeof(eee))) return -EFAULT; - ret = dev->ethtool_ops->set_eee(dev, &edata); + eee_to_keee(&keee, &eee); + ret = dev->ethtool_ops->set_eee(dev, &keee); if (!ret) ethtool_notify(dev, ETHTOOL_MSG_EEE_NTF, NULL); return ret; diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index fe3553f60bf3..bd04f28d5cf4 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -477,11 +477,7 @@ out: return ret; } -/* Default ->dumpit() handler for GET requests. Device iteration copied from - * rtnl_dump_ifinfo(); we have to be more careful about device hashtable - * persistence as we cannot guarantee to hold RTNL lock through the whole - * function as rtnetnlink does. - */ +/* Default ->dumpit() handler for GET requests. */ static int ethnl_default_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { @@ -490,14 +486,14 @@ static int ethnl_default_dumpit(struct sk_buff *skb, struct net_device *dev; int ret = 0; - rtnl_lock(); + rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->pos_ifindex) { dev_hold(dev); - rtnl_unlock(); + rcu_read_unlock(); ret = ethnl_default_dump_one(skb, dev, ctx, genl_info_dump(cb)); - rtnl_lock(); + rcu_read_lock(); dev_put(dev); if (ret < 0 && ret != -EOPNOTSUPP) { @@ -507,7 +503,7 @@ static int ethnl_default_dumpit(struct sk_buff *skb, } ret = 0; } - rtnl_unlock(); + rcu_read_unlock(); return ret; } diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 9d71b66183da..c98b5b71ad7c 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -28,29 +28,19 @@ static bool is_slave_up(struct net_device *dev) return dev && is_admin_up(dev) && netif_oper_up(dev); } -static void __hsr_set_operstate(struct net_device *dev, int transition) -{ - write_lock(&dev_base_lock); - if (dev->operstate != transition) { - dev->operstate = transition; - write_unlock(&dev_base_lock); - netdev_state_change(dev); - } else { - write_unlock(&dev_base_lock); - } -} - static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { - if (!is_admin_up(master->dev)) { - __hsr_set_operstate(master->dev, IF_OPER_DOWN); + struct net_device *dev = master->dev; + + if (!is_admin_up(dev)) { + netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) - __hsr_set_operstate(master->dev, IF_OPER_UP); + netdev_set_operstate(dev, IF_OPER_UP); else - __hsr_set_operstate(master->dev, IF_OPER_LOWERLAYERDOWN); + netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) @@ -78,14 +68,14 @@ static void hsr_check_announce(struct net_device *hsr_dev, hsr = netdev_priv(hsr_dev); - if (hsr_dev->operstate == IF_OPER_UP && old_operstate != IF_OPER_UP) { + if (READ_ONCE(hsr_dev->operstate) == IF_OPER_UP && old_operstate != IF_OPER_UP) { /* Went up */ hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } - if (hsr_dev->operstate != IF_OPER_UP && old_operstate == IF_OPER_UP) + if (READ_ONCE(hsr_dev->operstate) != IF_OPER_UP && old_operstate == IF_OPER_UP) /* Went down */ del_timer(&hsr->announce_timer); } @@ -100,7 +90,7 @@ void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ - old_operstate = master->dev->operstate; + old_operstate = READ_ONCE(master->dev->operstate); has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev, old_operstate); @@ -477,7 +467,7 @@ static const struct net_device_ops hsr_device_ops = { .ndo_set_rx_mode = hsr_set_rx_mode, }; -static struct device_type hsr_type = { +static const struct device_type hsr_type = { .name = "hsr", }; diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 2c087b7f17c5..77b4e92027c5 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -93,7 +93,7 @@ static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n) static int lowpan_get_iflink(const struct net_device *dev) { - return lowpan_802154_dev(dev)->wdev->ifindex; + return READ_ONCE(lowpan_802154_dev(dev)->wdev->ifindex); } static const struct net_device_ops lowpan_netdev_ops = { @@ -280,5 +280,6 @@ static void __exit lowpan_cleanup_module(void) module_init(lowpan_init_module); module_exit(lowpan_cleanup_module); +MODULE_DESCRIPTION("IPv6 over Low power Wireless Personal Area Network IEEE 802.15.4 core"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("lowpan"); diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 00302e8b9615..990a83455dcf 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -1137,4 +1137,5 @@ module_init(af_ieee802154_init); module_exit(af_ieee802154_remove); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("IEEE 802.15.4 socket interface"); MODULE_ALIAS_NETPROTO(PF_IEEE802154); diff --git a/net/ieee802154/sysfs.c b/net/ieee802154/sysfs.c index d2903933805c..6708160ebf9f 100644 --- a/net/ieee802154/sysfs.c +++ b/net/ieee802154/sysfs.c @@ -93,7 +93,7 @@ static SIMPLE_DEV_PM_OPS(wpan_phy_pm_ops, wpan_phy_suspend, wpan_phy_resume); #define WPAN_PHY_PM_OPS NULL #endif -struct class wpan_phy_class = { +const struct class wpan_phy_class = { .name = "ieee802154", .dev_release = wpan_phy_release, .dev_groups = pmib_groups, diff --git a/net/ieee802154/sysfs.h b/net/ieee802154/sysfs.h index 337545b639e9..69961e166257 100644 --- a/net/ieee802154/sysfs.h +++ b/net/ieee802154/sysfs.h @@ -5,6 +5,6 @@ int wpan_phy_sysfs_init(void); void wpan_phy_sysfs_exit(void); -extern struct class wpan_phy_class; +extern const struct class wpan_phy_class; #endif /* __IEEE802154_SYSFS_H */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index a5a820ee2026..55bd72997b31 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -119,6 +119,7 @@ #endif #include <net/l3mdev.h> #include <net/compat.h> +#include <net/rps.h> #include <trace/events/sock.h> @@ -1103,7 +1104,7 @@ const struct proto_ops inet_dgram_ops = { .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .splice_eof = inet_splice_eof, - .set_peek_off = sk_set_peek_off, + .set_peek_off = udp_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif @@ -1326,7 +1327,7 @@ int inet_sk_rebuild_header(struct sock *sk) fl4 = &inet->cork.fl.u.ip4; rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, - sk->sk_protocol, RT_CONN_FLAGS(sk), + sk->sk_protocol, ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (!IS_ERR(rt)) { err = 0; @@ -1751,19 +1752,6 @@ static const struct net_protocol igmp_protocol = { }; #endif -static const struct net_protocol tcp_protocol = { - .handler = tcp_v4_rcv, - .err_handler = tcp_v4_err, - .no_policy = 1, - .icmp_strict_tag_validation = 1, -}; - -static const struct net_protocol udp_protocol = { - .handler = udp_rcv, - .err_handler = udp_err, - .no_policy = 1, -}; - static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, @@ -1904,14 +1892,6 @@ static int ipv4_proc_init(void); * IP protocol layer initialiser */ -static struct packet_offload ip_packet_offload __read_mostly = { - .type = cpu_to_be16(ETH_P_IP), - .callbacks = { - .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, - .gro_complete = inet_gro_complete, - }, -}; static const struct net_offload ipip_offload = { .callbacks = { @@ -1938,7 +1918,15 @@ static int __init ipv4_offload_init(void) if (ipip_offload_init() < 0) pr_crit("%s: Cannot add IPIP protocol offload\n", __func__); - dev_add_offload(&ip_packet_offload); + net_hotdata.ip_packet_offload = (struct packet_offload) { + .type = cpu_to_be16(ETH_P_IP), + .callbacks = { + .gso_segment = inet_gso_segment, + .gro_receive = inet_gro_receive, + .gro_complete = inet_gro_complete, + }, + }; + dev_add_offload(&net_hotdata.ip_packet_offload); return 0; } @@ -1992,9 +1980,22 @@ static int __init inet_init(void) if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0) pr_crit("%s: Cannot add ICMP protocol\n", __func__); - if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0) + + net_hotdata.udp_protocol = (struct net_protocol) { + .handler = udp_rcv, + .err_handler = udp_err, + .no_policy = 1, + }; + if (inet_add_protocol(&net_hotdata.udp_protocol, IPPROTO_UDP) < 0) pr_crit("%s: Cannot add UDP protocol\n", __func__); - if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0) + + net_hotdata.tcp_protocol = (struct net_protocol) { + .handler = tcp_v4_rcv, + .err_handler = tcp_v4_err, + .no_policy = 1, + .icmp_strict_tag_validation = 1, + }; + if (inet_add_protocol(&net_hotdata.tcp_protocol, IPPROTO_TCP) < 0) pr_crit("%s: Cannot add TCP protocol\n", __func__); #ifdef CONFIG_IP_MULTICAST if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0) diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index ae8b15e6896f..7f518ea5f4ac 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -12,7 +12,7 @@ #include <net/bpf_sk_storage.h> /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ -extern struct bpf_struct_ops bpf_tcp_congestion_ops; +static struct bpf_struct_ops bpf_tcp_congestion_ops; static u32 unsupported_ops[] = { offsetof(struct tcp_congestion_ops, get_info), @@ -20,6 +20,7 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; +static const struct btf_type *tcp_congestion_ops_type; static int bpf_tcp_ca_init(struct btf *btf) { @@ -36,6 +37,11 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); + type_id = btf_find_by_name_kind(btf, "tcp_congestion_ops", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + tcp_congestion_ops_type = btf_type_by_id(btf, type_id); + return 0; } @@ -149,7 +155,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog) u32 midx; midx = prog->expected_attach_type; - t = bpf_tcp_congestion_ops.type; + t = tcp_congestion_ops_type; m = &btf_type_member(t)[midx]; return __btf_member_bit_offset(t, m) / 8; @@ -191,17 +197,17 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } -BTF_SET8_START(bpf_tcp_ca_check_kfunc_ids) +BTF_KFUNCS_START(bpf_tcp_ca_check_kfunc_ids) BTF_ID_FLAGS(func, tcp_reno_ssthresh) BTF_ID_FLAGS(func, tcp_reno_cong_avoid) BTF_ID_FLAGS(func, tcp_reno_undo_cwnd) BTF_ID_FLAGS(func, tcp_slow_start) BTF_ID_FLAGS(func, tcp_cong_avoid_ai) -BTF_SET8_END(bpf_tcp_ca_check_kfunc_ids) +BTF_KFUNCS_END(bpf_tcp_ca_check_kfunc_ids) static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = { .owner = THIS_MODULE, @@ -339,7 +345,7 @@ static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = { .release = __bpf_tcp_ca_release, }; -struct bpf_struct_ops bpf_tcp_congestion_ops = { +static struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, @@ -350,10 +356,16 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .validate = bpf_tcp_ca_validate, .name = "tcp_congestion_ops", .cfi_stubs = &__bpf_ops_tcp_congestion_ops, + .owner = THIS_MODULE, }; static int __init bpf_tcp_ca_kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops); + + return ret; } late_initcall(bpf_tcp_ca_kfunc_init); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index d048aa833293..8b17d83e5fde 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -864,11 +864,8 @@ static int cipso_v4_map_cat_rbm_ntoh(const struct cipso_v4_doi *doi_def, net_clen_bits, net_spot + 1, 1); - if (net_spot < 0) { - if (net_spot == -2) - return -EFAULT; + if (net_spot < 0) return 0; - } switch (doi_def->type) { case CIPSO_V4_MAP_PASS: diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 2cc50cbfc2a3..cc6d0bd7b0a9 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -119,7 +119,7 @@ void ip4_datagram_release_cb(struct sock *sk) rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + ip_sock_rt_tos(sk), sk->sk_bound_dev_if); dst = !IS_ERR(rt) ? &rt->dst : NULL; sk_dst_set(sk, dst); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index bc74f131fe4d..7a437f0d4190 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -713,34 +713,37 @@ static void check_lifetime(struct work_struct *work) rcu_read_lock(); hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) { - unsigned long age; + unsigned long age, tstamp; + u32 preferred_lft; + u32 valid_lft; + u32 flags; - if (ifa->ifa_flags & IFA_F_PERMANENT) + flags = READ_ONCE(ifa->ifa_flags); + if (flags & IFA_F_PERMANENT) continue; + preferred_lft = READ_ONCE(ifa->ifa_preferred_lft); + valid_lft = READ_ONCE(ifa->ifa_valid_lft); + tstamp = READ_ONCE(ifa->ifa_tstamp); /* We try to batch several events at once. */ - age = (now - ifa->ifa_tstamp + + age = (now - tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; - if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && - age >= ifa->ifa_valid_lft) { + if (valid_lft != INFINITY_LIFE_TIME && + age >= valid_lft) { change_needed = true; - } else if (ifa->ifa_preferred_lft == + } else if (preferred_lft == INFINITY_LIFE_TIME) { continue; - } else if (age >= ifa->ifa_preferred_lft) { - if (time_before(ifa->ifa_tstamp + - ifa->ifa_valid_lft * HZ, next)) - next = ifa->ifa_tstamp + - ifa->ifa_valid_lft * HZ; + } else if (age >= preferred_lft) { + if (time_before(tstamp + valid_lft * HZ, next)) + next = tstamp + valid_lft * HZ; - if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) + if (!(flags & IFA_F_DEPRECATED)) change_needed = true; - } else if (time_before(ifa->ifa_tstamp + - ifa->ifa_preferred_lft * HZ, + } else if (time_before(tstamp + preferred_lft * HZ, next)) { - next = ifa->ifa_tstamp + - ifa->ifa_preferred_lft * HZ; + next = tstamp + preferred_lft * HZ; } } rcu_read_unlock(); @@ -804,24 +807,26 @@ static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, __u32 prefered_lft) { unsigned long timeout; + u32 flags; - ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); + flags = ifa->ifa_flags & ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) - ifa->ifa_valid_lft = timeout; + WRITE_ONCE(ifa->ifa_valid_lft, timeout); else - ifa->ifa_flags |= IFA_F_PERMANENT; + flags |= IFA_F_PERMANENT; timeout = addrconf_timeout_fixup(prefered_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) - ifa->ifa_flags |= IFA_F_DEPRECATED; - ifa->ifa_preferred_lft = timeout; + flags |= IFA_F_DEPRECATED; + WRITE_ONCE(ifa->ifa_preferred_lft, timeout); } - ifa->ifa_tstamp = jiffies; + WRITE_ONCE(ifa->ifa_flags, flags); + WRITE_ONCE(ifa->ifa_tstamp, jiffies); if (!ifa->ifa_cstamp) - ifa->ifa_cstamp = ifa->ifa_tstamp; + WRITE_ONCE(ifa->ifa_cstamp, ifa->ifa_tstamp); } static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, @@ -1312,7 +1317,7 @@ static __be32 in_dev_select_addr(const struct in_device *in_dev, const struct in_ifaddr *ifa; in_dev_for_each_ifa_rcu(ifa, in_dev) { - if (ifa->ifa_flags & IFA_F_SECONDARY) + if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) @@ -1340,7 +1345,7 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) localnet_scope = RT_SCOPE_LINK; in_dev_for_each_ifa_rcu(ifa, in_dev) { - if (ifa->ifa_flags & IFA_F_SECONDARY) + if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) continue; if (min(ifa->ifa_scope, localnet_scope) > scope) continue; @@ -1671,11 +1676,12 @@ static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); } -static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, +static int inet_fill_ifaddr(struct sk_buff *skb, const struct in_ifaddr *ifa, struct inet_fill_args *args) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; + unsigned long tstamp; u32 preferred, valid; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), @@ -1686,7 +1692,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; - ifm->ifa_flags = ifa->ifa_flags; + ifm->ifa_flags = READ_ONCE(ifa->ifa_flags); ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; @@ -1694,11 +1700,12 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto nla_put_failure; + tstamp = READ_ONCE(ifa->ifa_tstamp); if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { - preferred = ifa->ifa_preferred_lft; - valid = ifa->ifa_valid_lft; + preferred = READ_ONCE(ifa->ifa_preferred_lft); + valid = READ_ONCE(ifa->ifa_valid_lft); if (preferred != INFINITY_LIFE_TIME) { - long tval = (jiffies - ifa->ifa_tstamp) / HZ; + long tval = (jiffies - tstamp) / HZ; if (preferred > tval) preferred -= tval; @@ -1725,10 +1732,10 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || (ifa->ifa_proto && nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) || - nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) || + nla_put_u32(skb, IFA_FLAGS, ifm->ifa_flags) || (ifa->ifa_rt_priority && nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) || - put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, + put_cacheinfo(skb, READ_ONCE(ifa->ifa_cstamp), tstamp, preferred, valid)) goto nla_put_failure; @@ -1798,15 +1805,15 @@ static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, } static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, - struct netlink_callback *cb, int s_ip_idx, + struct netlink_callback *cb, int *s_ip_idx, struct inet_fill_args *fillargs) { struct in_ifaddr *ifa; int ip_idx = 0; int err; - in_dev_for_each_ifa_rtnl(ifa, in_dev) { - if (ip_idx < s_ip_idx) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (ip_idx < *s_ip_idx) { ip_idx++; continue; } @@ -1818,9 +1825,9 @@ static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, ip_idx++; } err = 0; - + ip_idx = 0; done: - cb->args[2] = ip_idx; + *s_ip_idx = ip_idx; return err; } @@ -1830,7 +1837,7 @@ done: static u32 inet_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv4.dev_addr_genid) + - net->dev_base_seq; + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. @@ -1852,75 +1859,51 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) }; struct net *net = sock_net(skb->sk); struct net *tgt_net = net; - int h, s_h; - int idx, s_idx; - int s_ip_idx; - struct net_device *dev; + struct { + unsigned long ifindex; + int ip_idx; + } *ctx = (void *)cb->ctx; struct in_device *in_dev; - struct hlist_head *head; + struct net_device *dev; int err = 0; - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - s_ip_idx = cb->args[2]; - + rcu_read_lock(); if (cb->strict_check) { err = inet_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) - goto put_tgt_net; + goto done; - err = 0; if (fillargs.ifindex) { - dev = __dev_get_by_index(tgt_net, fillargs.ifindex); - if (!dev) { - err = -ENODEV; - goto put_tgt_net; - } - - in_dev = __in_dev_get_rtnl(dev); - if (in_dev) { - err = in_dev_dump_addr(in_dev, skb, cb, s_ip_idx, - &fillargs); - } - goto put_tgt_net; - } - } - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &tgt_net->dev_index_head[h]; - rcu_read_lock(); - cb->seq = inet_base_seq(tgt_net); - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - if (h > s_h || idx > s_idx) - s_ip_idx = 0; + err = -ENODEV; + dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); + if (!dev) + goto done; in_dev = __in_dev_get_rcu(dev); if (!in_dev) - goto cont; - - err = in_dev_dump_addr(in_dev, skb, cb, s_ip_idx, - &fillargs); - if (err < 0) { - rcu_read_unlock(); goto done; - } -cont: - idx++; + err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, + &fillargs); + goto done; } - rcu_read_unlock(); } + cb->seq = inet_base_seq(tgt_net); + + for_each_netdev_dump(net, dev, ctx->ifindex) { + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + continue; + err = in_dev_dump_addr(in_dev, skb, cb, &ctx->ip_idx, + &fillargs); + if (err < 0) + goto done; + } done: - cb->args[0] = h; - cb->args[1] = idx; -put_tgt_net: if (fillargs.netnsid >= 0) put_net(tgt_net); - - return skb->len ? : err; + rcu_read_unlock(); + return err; } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, @@ -1982,7 +1965,7 @@ static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) - ((u32 *) nla_data(nla))[i] = in_dev->cnf.data[i]; + ((u32 *) nla_data(nla))[i] = READ_ONCE(in_dev->cnf.data[i]); return 0; } @@ -2068,9 +2051,9 @@ static int inet_netconf_msgsize_devconf(int type) } static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, - struct ipv4_devconf *devconf, u32 portid, - u32 seq, int event, unsigned int flags, - int type) + const struct ipv4_devconf *devconf, + u32 portid, u32 seq, int event, + unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; @@ -2095,27 +2078,28 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, - IPV4_DEVCONF(*devconf, FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_RP_FILTER) && nla_put_s32(skb, NETCONFA_RP_FILTER, - IPV4_DEVCONF(*devconf, RP_FILTER)) < 0) + IPV4_DEVCONF_RO(*devconf, RP_FILTER)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, - IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_BC_FORWARDING) && nla_put_s32(skb, NETCONFA_BC_FORWARDING, - IPV4_DEVCONF(*devconf, BC_FORWARDING)) < 0) + IPV4_DEVCONF_RO(*devconf, BC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, - IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) + IPV4_DEVCONF_RO(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, - IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) + IPV4_DEVCONF_RO(*devconf, + IGNORE_ROUTES_WITH_LINKDOWN)) < 0) goto nla_put_failure; out: @@ -2204,21 +2188,20 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); - struct nlattr *tb[NETCONFA_MAX+1]; + struct nlattr *tb[NETCONFA_MAX + 1]; + const struct ipv4_devconf *devconf; + struct in_device *in_dev = NULL; + struct net_device *dev = NULL; struct sk_buff *skb; - struct ipv4_devconf *devconf; - struct in_device *in_dev; - struct net_device *dev; int ifindex; int err; err = inet_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err) - goto errout; + return err; - err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) - goto errout; + return -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { @@ -2229,10 +2212,10 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, devconf = net->ipv4.devconf_dflt; break; default: - dev = __dev_get_by_index(net, ifindex); - if (!dev) - goto errout; - in_dev = __in_dev_get_rtnl(dev); + err = -ENODEV; + dev = dev_get_by_index(net, ifindex); + if (dev) + in_dev = in_dev_get(dev); if (!in_dev) goto errout; devconf = &in_dev->cnf; @@ -2256,6 +2239,9 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: + if (in_dev) + in_dev_put(in_dev); + dev_put(dev); return err; } @@ -2264,11 +2250,13 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); - int h, s_h; - int idx, s_idx; + struct { + unsigned long ifindex; + unsigned int all_default; + } *ctx = (void *)cb->ctx; + const struct in_device *in_dev; struct net_device *dev; - struct in_device *in_dev; - struct hlist_head *head; + int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; @@ -2285,64 +2273,45 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, } } - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - rcu_read_lock(); - cb->seq = inet_base_seq(net); - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - in_dev = __in_dev_get_rcu(dev); - if (!in_dev) - goto cont; - - if (inet_netconf_fill_devconf(skb, dev->ifindex, - &in_dev->cnf, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, - NLM_F_MULTI, - NETCONFA_ALL) < 0) { - rcu_read_unlock(); - goto done; - } - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } - rcu_read_unlock(); + rcu_read_lock(); + for_each_netdev_dump(net, dev, ctx->ifindex) { + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + continue; + err = inet_netconf_fill_devconf(skb, dev->ifindex, + &in_dev->cnf, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) + goto done; } - if (h == NETDEV_HASHENTRIES) { - if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, - net->ipv4.devconf_all, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, NLM_F_MULTI, - NETCONFA_ALL) < 0) + if (ctx->all_default == 0) { + err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, + net->ipv4.devconf_all, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) goto done; - else - h++; - } - if (h == NETDEV_HASHENTRIES + 1) { - if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, - net->ipv4.devconf_dflt, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, NLM_F_MULTI, - NETCONFA_ALL) < 0) + ctx->all_default++; + } + if (ctx->all_default == 1) { + err = inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, + net->ipv4.devconf_dflt, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) goto done; - else - h++; + ctx->all_default++; } done: - cb->args[0] = h; - cb->args[1] = idx; - - return skb->len; + rcu_read_unlock(); + return err; } #ifdef CONFIG_SYSCTL @@ -2823,7 +2792,9 @@ void __init devinet_init(void) rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, 0); rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, 0); - rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, 0); + rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, + RTNL_FLAG_DUMP_UNLOCKED); rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf, - inet_netconf_dump_devconf, 0); + inet_netconf_dump_devconf, + RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 390f4be7f7be..48741352a88a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -916,7 +916,8 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct rtmsg *rtm; int err, i; - ASSERT_RTNL(); + if (filter->rtnl_held) + ASSERT_RTNL(); if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request"); @@ -961,7 +962,10 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, break; case RTA_OIF: ifindex = nla_get_u32(tb[i]); - filter->dev = __dev_get_by_index(net, ifindex); + if (filter->rtnl_held) + filter->dev = __dev_get_by_index(net, ifindex); + else + filter->dev = dev_get_by_index_rcu(net, ifindex); if (!filter->dev) return -ENODEV; break; @@ -983,20 +987,24 @@ EXPORT_SYMBOL_GPL(ip_valid_fib_dump_req); static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { - struct fib_dump_filter filter = { .dump_routes = true, - .dump_exceptions = true }; + struct fib_dump_filter filter = { + .dump_routes = true, + .dump_exceptions = true, + .rtnl_held = false, + }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_head *head; - int dumped = 0, err; + int dumped = 0, err = 0; + rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) - return err; + goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); @@ -1005,29 +1013,26 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) /* ipv4 does not use prefix flag */ if (filter.flags & RTM_F_PREFIX) - return skb->len; + goto unlock; if (filter.table_id) { tb = fib_get_table(net, filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET) - return skb->len; + goto unlock; NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist"); - return -ENOENT; + err = -ENOENT; + goto unlock; } - - rcu_read_lock(); err = fib_table_dump(tb, skb, cb, &filter); - rcu_read_unlock(); - return skb->len ? : err; + goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; - rcu_read_lock(); - + err = 0; for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; @@ -1038,25 +1043,20 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); err = fib_table_dump(tb, skb, cb, &filter); - if (err < 0) { - if (likely(skb->len)) - goto out; - - goto out_err; - } + if (err < 0) + goto out; dumped = 1; next: e++; } } out: - err = skb->len; -out_err: - rcu_read_unlock(); cb->args[1] = e; cb->args[0] = h; +unlock: + rcu_read_unlock(); return err; } @@ -1659,5 +1659,6 @@ void __init ip_fib_init(void) rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0); rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0); - rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, 0); + rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, + RTNL_FLAG_DUMP_UNLOCKED); } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 3ff35f811765..f474106464d2 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -501,7 +501,7 @@ static void tnode_free(struct key_vector *tn) if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) { tnode_free_size = 0; - synchronize_rcu(); + synchronize_net(); } } @@ -2368,7 +2368,7 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, * and key == 0 means the dump has wrapped around and we are done. */ if (count && !key) - return skb->len; + return 0; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { int err; @@ -2394,7 +2394,7 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, cb->args[3] = key; cb->args[2] = count; - return skb->len; + return 0; } void __init fib_trie_init(void) diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c index 4da03bf45c9b..06e5572f296f 100644 --- a/net/ipv4/fou_bpf.c +++ b/net/ipv4/fou_bpf.c @@ -100,10 +100,10 @@ __bpf_kfunc int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx, __bpf_kfunc_end_defs(); -BTF_SET8_START(fou_kfunc_set) +BTF_KFUNCS_START(fou_kfunc_set) BTF_ID_FLAGS(func, bpf_skb_set_fou_encap) BTF_ID_FLAGS(func, bpf_skb_get_fou_encap) -BTF_SET8_END(fou_kfunc_set) +BTF_KFUNCS_END(fou_kfunc_set) static const struct btf_kfunc_id_set fou_bpf_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index 0c41076e31ed..a8494f796dca 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -351,7 +351,7 @@ static struct sk_buff *gue_gro_receive(struct sock *sk, optlen = guehdr->hlen << 2; len += optlen; - if (skb_gro_header_hard(skb, len)) { + if (!skb_gro_may_pull(skb, len)) { guehdr = skb_gro_header_slow(skb, len, off); if (unlikely(!guehdr)) goto out; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 311e70bfce40..5028c72d494a 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -174,7 +174,7 @@ static struct sk_buff *gre_gro_receive(struct list_head *head, grehlen += GRE_HEADER_SECTION; hlen = off + grehlen; - if (skb_gro_header_hard(skb, hlen)) { + if (!skb_gro_may_pull(skb, hlen)) { greh = skb_gro_header_slow(skb, hlen, off); if (unlikely(!greh)) goto out; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index efeeca2b1328..717e97a389a8 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -120,12 +120,12 @@ */ #define IGMP_V1_SEEN(in_dev) \ - (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ + (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ - (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ + (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 459af1f89739..7d8090f109ef 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -906,8 +906,9 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req, 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)); + unsafe_memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, + req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end), + /* alloc is larger than struct, see above */); sk_node_init(&nreq_sk->sk_node); nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; @@ -1467,7 +1468,7 @@ static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *f rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) rt = NULL; if (rt) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8e6b6aa0579e..7adace541fe2 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -32,7 +32,7 @@ #include <linux/inet_diag.h> #include <linux/sock_diag.h> -static const struct inet_diag_handler **inet_diag_table; +static const struct inet_diag_handler __rcu **inet_diag_table; struct inet_diag_entry { const __be32 *saddr; @@ -48,28 +48,28 @@ struct inet_diag_entry { #endif }; -static DEFINE_MUTEX(inet_diag_table_mutex); - static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { - if (proto < 0 || proto >= IPPROTO_MAX) { - mutex_lock(&inet_diag_table_mutex); - return ERR_PTR(-ENOENT); - } + const struct inet_diag_handler *handler; - if (!inet_diag_table[proto]) + if (proto < 0 || proto >= IPPROTO_MAX) + return NULL; + + if (!READ_ONCE(inet_diag_table[proto])) sock_load_diag_module(AF_INET, proto); - mutex_lock(&inet_diag_table_mutex); - if (!inet_diag_table[proto]) - return ERR_PTR(-ENOENT); + rcu_read_lock(); + handler = rcu_dereference(inet_diag_table[proto]); + if (handler && !try_module_get(handler->owner)) + handler = NULL; + rcu_read_unlock(); - return inet_diag_table[proto]; + return handler; } static void inet_diag_unlock_handler(const struct inet_diag_handler *handler) { - mutex_unlock(&inet_diag_table_mutex); + module_put(handler->owner); } void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk) @@ -104,9 +104,12 @@ static size_t inet_sk_attr_size(struct sock *sk, const struct inet_diag_handler *handler; size_t aux = 0; - handler = inet_diag_table[req->sdiag_protocol]; + rcu_read_lock(); + handler = rcu_dereference(inet_diag_table[req->sdiag_protocol]); + DEBUG_NET_WARN_ON_ONCE(!handler); if (handler && handler->idiag_get_aux_size) aux = handler->idiag_get_aux_size(sk, net_admin); + rcu_read_unlock(); return nla_total_size(sizeof(struct tcp_info)) + nla_total_size(sizeof(struct inet_diag_msg)) @@ -244,10 +247,16 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct nlmsghdr *nlh; struct nlattr *attr; void *info = NULL; + int protocol; cb_data = cb->data; - handler = inet_diag_table[inet_diag_get_protocol(req, cb_data)]; - BUG_ON(!handler); + protocol = inet_diag_get_protocol(req, cb_data); + + /* inet_diag_lock_handler() made sure inet_diag_table[] is stable. */ + handler = rcu_dereference_protected(inet_diag_table[protocol], 1); + DEBUG_NET_WARN_ON_ONCE(!handler); + if (!handler) + return -ENXIO; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); @@ -605,9 +614,10 @@ static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, protocol = inet_diag_get_protocol(req, &dump_data); handler = inet_diag_lock_handler(protocol); - if (IS_ERR(handler)) { - err = PTR_ERR(handler); - } else if (cmd == SOCK_DIAG_BY_FAMILY) { + if (!handler) + return -ENOENT; + + if (cmd == SOCK_DIAG_BY_FAMILY) { struct netlink_callback cb = { .nlh = nlh, .skb = in_skb, @@ -1035,6 +1045,10 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, num = 0; ilb = &hashinfo->lhash2[i]; + if (hlist_nulls_empty(&ilb->nulls_head)) { + s_num = 0; + continue; + } spin_lock(&ilb->lock); sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); @@ -1099,6 +1113,10 @@ resume_bind_walk: accum = 0; ibb = &hashinfo->bhash2[i]; + if (hlist_empty(&ibb->chain)) { + s_num = 0; + continue; + } spin_lock_bh(&ibb->lock); inet_bind_bucket_for_each(tb2, &ibb->chain) { if (!net_eq(ib2_net(tb2), net)) @@ -1259,12 +1277,12 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, again: prev_min_dump_alloc = cb->min_dump_alloc; handler = inet_diag_lock_handler(protocol); - if (!IS_ERR(handler)) + if (handler) { handler->dump(skb, cb, r); - else - err = PTR_ERR(handler); - inet_diag_unlock_handler(handler); - + inet_diag_unlock_handler(handler); + } else { + err = -ENOENT; + } /* The skb is not large enough to fit one sk info and * inet_sk_diag_fill() has requested for a larger skb. */ @@ -1457,10 +1475,9 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) } handler = inet_diag_lock_handler(sk->sk_protocol); - if (IS_ERR(handler)) { - inet_diag_unlock_handler(handler); + if (!handler) { nlmsg_cancel(skb, nlh); - return PTR_ERR(handler); + return -ENOENT; } attr = handler->idiag_info_size @@ -1479,6 +1496,7 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk) } static const struct sock_diag_handler inet_diag_handler = { + .owner = THIS_MODULE, .family = AF_INET, .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, @@ -1486,6 +1504,7 @@ static const struct sock_diag_handler inet_diag_handler = { }; static const struct sock_diag_handler inet6_diag_handler = { + .owner = THIS_MODULE, .family = AF_INET6, .dump = inet_diag_handler_cmd, .get_info = inet_diag_handler_get_info, @@ -1495,20 +1514,12 @@ static const struct sock_diag_handler inet6_diag_handler = { int inet_diag_register(const struct inet_diag_handler *h) { const __u16 type = h->idiag_type; - int err = -EINVAL; if (type >= IPPROTO_MAX) - goto out; + return -EINVAL; - mutex_lock(&inet_diag_table_mutex); - err = -EEXIST; - if (!inet_diag_table[type]) { - inet_diag_table[type] = h; - err = 0; - } - mutex_unlock(&inet_diag_table_mutex); -out: - return err; + return !cmpxchg((const struct inet_diag_handler **)&inet_diag_table[type], + NULL, h) ? 0 : -EEXIST; } EXPORT_SYMBOL_GPL(inet_diag_register); @@ -1519,12 +1530,16 @@ void inet_diag_unregister(const struct inet_diag_handler *h) if (type >= IPPROTO_MAX) return; - mutex_lock(&inet_diag_table_mutex); - inet_diag_table[type] = NULL; - mutex_unlock(&inet_diag_table_mutex); + xchg((const struct inet_diag_handler **)&inet_diag_table[type], + NULL); } EXPORT_SYMBOL_GPL(inet_diag_unregister); +static const struct sock_diag_inet_compat inet_diag_compat = { + .owner = THIS_MODULE, + .fn = inet_diag_rcv_msg_compat, +}; + static int __init inet_diag_init(void) { const int inet_diag_table_size = (IPPROTO_MAX * @@ -1543,7 +1558,7 @@ static int __init inet_diag_init(void) if (err) goto out_free_inet; - sock_diag_register_inet_compat(inet_diag_rcv_msg_compat); + sock_diag_register_inet_compat(&inet_diag_compat); out: return err; @@ -1558,7 +1573,7 @@ static void __exit inet_diag_exit(void) { sock_diag_unregister(&inet6_diag_handler); sock_diag_unregister(&inet_diag_handler); - sock_diag_unregister_inet_compat(inet_diag_rcv_msg_compat); + sock_diag_unregister_inet_compat(&inet_diag_compat); kfree(inet_diag_table); } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 308ff34002ea..7498af320164 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -24,6 +24,7 @@ #include <net/inet6_hashtables.h> #endif #include <net/secure_seq.h> +#include <net/hotdata.h> #include <net/ip.h> #include <net/tcp.h> #include <net/sock_reuseport.h> @@ -32,8 +33,6 @@ u32 inet_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { - static u32 inet_ehash_secret __read_mostly; - net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e9fed83e9b3c..5bd759963451 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -81,10 +81,7 @@ void __init inet_initpeers(void) inet_peer_threshold = clamp_val(nr_entries, 4096, 65536 + 128); - peer_cachep = kmem_cache_create("inet_peer_cache", - sizeof(struct inet_peer), - 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, - NULL); + peer_cachep = KMEM_CACHE(inet_peer, SLAB_HWCACHE_ALIGN | SLAB_PANIC); } /* Called with rcu_read_lock() or base->lock held */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 6b9cf5a24c19..7b16c211b904 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1025,14 +1025,16 @@ static int __net_init ipgre_init_net(struct net *net) return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } -static void __net_exit ipgre_exit_batch_net(struct list_head *list_net) +static void __net_exit ipgre_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops); + ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops, + dev_to_kill); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, - .exit_batch = ipgre_exit_batch_net, + .exit_batch_rtnl = ipgre_exit_batch_rtnl, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1697,14 +1699,16 @@ static int __net_init ipgre_tap_init_net(struct net *net) return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } -static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net) +static void __net_exit ipgre_tap_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops); + ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops, + dev_to_kill); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, - .exit_batch = ipgre_tap_exit_batch_net, + .exit_batch_rtnl = ipgre_tap_exit_batch_rtnl, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1715,14 +1719,16 @@ static int __net_init erspan_init_net(struct net *net) &erspan_link_ops, "erspan0"); } -static void __net_exit erspan_exit_batch_net(struct list_head *net_list) +static void __net_exit erspan_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops); + ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops, + dev_to_kill); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, - .exit_batch = erspan_exit_batch_net, + .exit_batch_rtnl = erspan_exit_batch_rtnl, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 67d846622365..33f93dc730a3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -493,7 +493,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_CONN_FLAGS_TOS(sk, tos), + RT_TOS(tos), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; @@ -1458,6 +1458,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); skb->mark = cork->mark; skb->tstamp = cork->transmit_time; + skb->mono_delivery_time = !!skb->tstamp; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 21d2ffa919e9..cf377377b52d 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -894,7 +894,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); - int val = 0, err; + int val = 0, err, retv; bool needs_rtnl = setsockopt_needs_rtnl(optname); switch (optname) { @@ -938,8 +938,12 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, /* If optlen==0, it is equivalent to val == 0 */ - if (optname == IP_ROUTER_ALERT) - return ip_ra_control(sk, val ? 1 : 0, NULL); + if (optname == IP_ROUTER_ALERT) { + retv = ip_ra_control(sk, val ? 1 : 0, NULL); + if (retv == 0) + inet_assign_bit(RTALERT, sk, val); + return retv; + } if (ip_mroute_opt(optname)) return ip_mroute_setsockopt(sk, optname, optval, optlen); @@ -1575,6 +1579,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_BIND_ADDRESS_NO_PORT: val = inet_test_bit(BIND_ADDRESS_NO_PORT, sk); goto copyval; + case IP_ROUTER_ALERT: + val = inet_test_bit(RTALERT, sk); + goto copyval; case IP_TTL: val = READ_ONCE(inet->uc_ttl); if (val < 0) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 1b6981de3f29..1b8d8ff9a237 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -102,10 +102,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else - cand = t; + cand = t; } hlist_for_each_entry_rcu(t, head, hash_node) { @@ -117,9 +116,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else if (!cand) + if (!cand) cand = t; } @@ -137,9 +136,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, if (!ip_tunnel_key_match(&t->parms, flags, key)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else if (!cand) + if (!cand) cand = t; } @@ -150,9 +149,9 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, !(t->dev->flags & IFF_UP)) continue; - if (t->parms.link == link) + if (READ_ONCE(t->parms.link) == link) return t; - else if (!cand) + if (!cand) cand = t; } @@ -221,7 +220,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn, hlist_for_each_entry_rcu(t, head, hash_node) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && - link == t->parms.link && + link == READ_ONCE(t->parms.link) && type == t->dev->type && ip_tunnel_key_match(&t->parms, flags, key)) break; @@ -378,7 +377,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, bool log_ecn_error) { const struct iphdr *iph = ip_hdr(skb); - int err; + int nh, err; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { @@ -404,8 +403,21 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + iph = (struct iphdr *)(skb->head + nh); + err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -761,7 +773,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), - dev_net(dev), tunnel->parms.link, + dev_net(dev), READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) @@ -881,7 +893,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (t->parms.link != p->link || t->fwmark != fwmark) { int mtu; - t->parms.link = p->link; + WRITE_ONCE(t->parms.link, p->link); t->fwmark = fwmark; mtu = ip_tunnel_bind_dev(dev); if (set_mtu) @@ -1071,9 +1083,9 @@ EXPORT_SYMBOL(ip_tunnel_get_link_net); int ip_tunnel_get_iflink(const struct net_device *dev) { - struct ip_tunnel *tunnel = netdev_priv(dev); + const struct ip_tunnel *tunnel = netdev_priv(dev); - return tunnel->parms.link; + return READ_ONCE(tunnel->parms.link); } EXPORT_SYMBOL(ip_tunnel_get_iflink); @@ -1144,19 +1156,17 @@ static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn, } void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, - struct rtnl_link_ops *ops) + struct rtnl_link_ops *ops, + struct list_head *dev_to_kill) { struct ip_tunnel_net *itn; struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) { itn = net_generic(net, id); - ip_tunnel_destroy(net, itn, &list, ops); + ip_tunnel_destroy(net, itn, dev_to_kill, ops); } - unregister_netdevice_many(&list); - rtnl_unlock(); } EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); @@ -1285,6 +1295,7 @@ int ip_tunnel_init(struct net_device *dev) if (tunnel->collect_md) netif_keep_dst(dev); + netdev_lockdep_set_classes(dev); return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index d1d6bb28ed6e..ee587adb169f 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -510,14 +510,16 @@ static int __net_init vti_init_net(struct net *net) return 0; } -static void __net_exit vti_exit_batch_net(struct list_head *list_net) +static void __net_exit vti_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops); + ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops, + dev_to_kill); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, - .exit_batch = vti_exit_batch_net, + .exit_batch_rtnl = vti_exit_batch_rtnl, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 03afa3871efc..f2696eaadbe6 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -592,14 +592,16 @@ static int __net_init ipip_init_net(struct net *net) return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0"); } -static void __net_exit ipip_exit_batch_net(struct list_head *list_net) +static void __net_exit ipip_exit_batch_rtnl(struct list_head *list_net, + struct list_head *dev_to_kill) { - ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops); + ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops, + dev_to_kill); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, - .exit_batch = ipip_exit_batch_net, + .exit_batch_rtnl = ipip_exit_batch_rtnl, .id = &ipip_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 362229836510..fd5c01c8489f 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1603,9 +1603,11 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; - olr = min_t(unsigned int, olr, sizeof(int)); if (olr < 0) return -EINVAL; + + olr = min_t(unsigned int, olr, sizeof(int)); + if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, olr)) @@ -2587,7 +2589,9 @@ errout_free: static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { - struct fib_dump_filter filter = {}; + struct fib_dump_filter filter = { + .rtnl_held = true, + }; int err; if (cb->strict_check) { @@ -3139,10 +3143,7 @@ int __init ip_mr_init(void) { int err; - mrt_cachep = kmem_cache_create("ip_mrt_cache", - sizeof(struct mfc_cache), - 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, - NULL); + mrt_cachep = KMEM_CACHE(mfc_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC); err = register_pernet_subsys(&ipmr_net_ops); if (err) diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index f71a7e9a7de6..8f6e950163a7 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -10,6 +10,10 @@ config NF_DEFRAG_IPV4 tristate default n +# old sockopt interface and eval loop +config IP_NF_IPTABLES_LEGACY + tristate + config NF_SOCKET_IPV4 tristate "IPv4 socket lookup support" help @@ -152,7 +156,7 @@ config IP_NF_MATCH_ECN config IP_NF_MATCH_RPFILTER tristate '"rpfilter" reverse path filter match support' depends on NETFILTER_ADVANCED - depends on IP_NF_MANGLE || IP_NF_RAW + depends on IP_NF_MANGLE || IP_NF_RAW || NFT_COMPAT help This option allows you to match packets whose replies would go out via the interface the packet came in. @@ -173,6 +177,7 @@ config IP_NF_MATCH_TTL config IP_NF_FILTER tristate "Packet filtering" default m if NETFILTER_ADVANCED=n + select IP_NF_IPTABLES_LEGACY help Packet filtering defines a table `filter', which has a series of rules for simple packet filtering at local input, forwarding and @@ -182,7 +187,7 @@ config IP_NF_FILTER config IP_NF_TARGET_REJECT tristate "REJECT target support" - depends on IP_NF_FILTER + depends on IP_NF_FILTER || NFT_COMPAT select NF_REJECT_IPV4 default m if NETFILTER_ADVANCED=n help @@ -212,6 +217,7 @@ config IP_NF_NAT default m if NETFILTER_ADVANCED=n select NF_NAT select NETFILTER_XT_NAT + select IP_NF_IPTABLES_LEGACY help This enables the `nat' table in iptables. This allows masquerading, port forwarding and other forms of full Network Address Port @@ -252,6 +258,7 @@ endif # IP_NF_NAT config IP_NF_MANGLE tristate "Packet mangling" default m if NETFILTER_ADVANCED=n + select IP_NF_IPTABLES_LEGACY help This option adds a `mangle' table to iptables: see the man page for iptables(8). This table is used for various packet alterations @@ -261,7 +268,7 @@ config IP_NF_MANGLE config IP_NF_TARGET_ECN tristate "ECN target support" - depends on IP_NF_MANGLE + depends on IP_NF_MANGLE || NFT_COMPAT depends on NETFILTER_ADVANCED help This option adds a `ECN' target, which can be used in the iptables mangle @@ -286,6 +293,7 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' + select IP_NF_IPTABLES_LEGACY help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING @@ -299,6 +307,7 @@ config IP_NF_SECURITY tristate "Security table" depends on SECURITY depends on NETFILTER_ADVANCED + select IP_NF_IPTABLES_LEGACY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. @@ -309,36 +318,35 @@ endif # IP_NF_IPTABLES # ARP tables config IP_NF_ARPTABLES - tristate "ARP tables support" - select NETFILTER_XTABLES - select NETFILTER_FAMILY_ARP - depends on NETFILTER_ADVANCED - help - arptables is a general, extensible packet identification framework. - The ARP packet filtering and mangling (manipulation)subsystems - use this: say Y or M here if you want to use either of those. - - To compile it as a module, choose M here. If unsure, say N. + tristate -if IP_NF_ARPTABLES +config NFT_COMPAT_ARP + tristate + depends on NF_TABLES_ARP && NFT_COMPAT + default m if NFT_COMPAT=m + default y if NFT_COMPAT=y config IP_NF_ARPFILTER - tristate "ARP packet filtering" + tristate "arptables-legacy packet filtering support" + select IP_NF_ARPTABLES + depends on NETFILTER_XTABLES help ARP packet filtering defines a table `filter', which has a series of rules for simple ARP packet filtering at local input and - local output. On a bridge, you can also specify filtering rules - for forwarded ARP packets. See the man page for arptables(8). + local output. This is only needed for arptables-legacy(8). + Neither arptables-nft nor nftables need this to work. To compile it as a module, choose M here. If unsure, say N. config IP_NF_ARP_MANGLE tristate "ARP payload mangling" + depends on IP_NF_ARPTABLES || NFT_COMPAT_ARP help Allows altering the ARP packet payload: source and destination hardware and network addresses. -endif # IP_NF_ARPTABLES + This option is needed by both arptables-legacy and arptables-nft. + It is not used by nftables. endmenu diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 5a26f9de1ab9..85502d4dfbb4 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -25,7 +25,7 @@ obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o # generic IP tables -obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o +obj-$(CONFIG_IP_NF_IPTABLES_LEGACY) += ip_tables.o # the three instances of ip_tables obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index bbff68b5b5d4..74928a9d1aa4 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -26,6 +26,9 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) +#define NHA_OP_FLAGS_DUMP_ALL (NHA_OP_FLAG_DUMP_STATS | \ + NHA_OP_FLAG_DUMP_HW_STATS) + static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, @@ -37,10 +40,17 @@ static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_RES_GROUP] = { .type = NLA_NESTED }, + [NHA_HW_STATS_ENABLE] = NLA_POLICY_MAX(NLA_U32, true), }; static const struct nla_policy rtm_nh_policy_get[] = { [NHA_ID] = { .type = NLA_U32 }, + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, + NHA_OP_FLAGS_DUMP_ALL), +}; + +static const struct nla_policy rtm_nh_policy_del[] = { + [NHA_ID] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_dump[] = { @@ -48,6 +58,8 @@ static const struct nla_policy rtm_nh_policy_dump[] = { [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, + NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_res_policy_new[] = { @@ -92,6 +104,7 @@ __nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, else if (nh_info->gw_family == AF_INET6) nh_info->ipv6 = nhi->fib_nhc.nhc_gw.ipv6; + nh_info->id = nhi->nh_parent->id; nh_info->is_reject = nhi->reject_nh; nh_info->is_fdb = nhi->fdb_nh; nh_info->has_encap = !!nhi->fib_nhc.nhc_lwtstate; @@ -131,13 +144,13 @@ static int nh_notifier_mpath_info_init(struct nh_notifier_info *info, info->nh_grp->num_nh = num_nh; info->nh_grp->is_fdb = nhg->fdb_nh; + info->nh_grp->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi; nhi = rtnl_dereference(nhge->nh->nh_info); - info->nh_grp->nh_entries[i].id = nhge->nh->id; info->nh_grp->nh_entries[i].weight = nhge->weight; __nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh, nhi); @@ -162,6 +175,7 @@ static int nh_notifier_res_table_info_init(struct nh_notifier_info *info, return -ENOMEM; info->nh_res_table->num_nh_buckets = num_nh_buckets; + info->nh_res_table->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; @@ -393,6 +407,7 @@ static int call_nexthop_res_table_notifiers(struct net *net, struct nexthop *nh, struct nh_notifier_info info = { .net = net, .extack = extack, + .id = nh->id, }; struct nh_group *nhg; int err; @@ -474,6 +489,7 @@ static void nexthop_free_group(struct nexthop *nh) struct nh_grp_entry *nhge = &nhg->nh_entries[i]; WARN_ON(!list_empty(&nhge->nh_list)); + free_percpu(nhge->stats); nexthop_put(nhge->nh); } @@ -654,8 +670,202 @@ nla_put_failure: return -EMSGSIZE; } -static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) +static void nh_grp_entry_stats_inc(struct nh_grp_entry *nhge) +{ + struct nh_grp_entry_stats *cpu_stats; + + cpu_stats = get_cpu_ptr(nhge->stats); + u64_stats_update_begin(&cpu_stats->syncp); + u64_stats_inc(&cpu_stats->packets); + u64_stats_update_end(&cpu_stats->syncp); + put_cpu_ptr(cpu_stats); +} + +static void nh_grp_entry_stats_read(struct nh_grp_entry *nhge, + u64 *ret_packets) { + int i; + + *ret_packets = 0; + + for_each_possible_cpu(i) { + struct nh_grp_entry_stats *cpu_stats; + unsigned int start; + u64 packets; + + cpu_stats = per_cpu_ptr(nhge->stats, i); + do { + start = u64_stats_fetch_begin(&cpu_stats->syncp); + packets = u64_stats_read(&cpu_stats->packets); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + *ret_packets += packets; + } +} + +static int nh_notifier_grp_hw_stats_init(struct nh_notifier_info *info, + const struct nexthop *nh) +{ + struct nh_group *nhg; + int i; + + ASSERT_RTNL(); + nhg = rtnl_dereference(nh->nh_grp); + + info->id = nh->id; + info->type = NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS; + info->nh_grp_hw_stats = kzalloc(struct_size(info->nh_grp_hw_stats, + stats, nhg->num_nh), + GFP_KERNEL); + if (!info->nh_grp_hw_stats) + return -ENOMEM; + + info->nh_grp_hw_stats->num_nh = nhg->num_nh; + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + info->nh_grp_hw_stats->stats[i].id = nhge->nh->id; + } + + return 0; +} + +static void nh_notifier_grp_hw_stats_fini(struct nh_notifier_info *info) +{ + kfree(info->nh_grp_hw_stats); +} + +void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, + unsigned int nh_idx, + u64 delta_packets) +{ + info->hw_stats_used = true; + info->stats[nh_idx].packets += delta_packets; +} +EXPORT_SYMBOL(nh_grp_hw_stats_report_delta); + +static void nh_grp_hw_stats_apply_update(struct nexthop *nh, + struct nh_notifier_info *info) +{ + struct nh_group *nhg; + int i; + + ASSERT_RTNL(); + nhg = rtnl_dereference(nh->nh_grp); + + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + nhge->packets_hw += info->nh_grp_hw_stats->stats[i].packets; + } +} + +static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used) +{ + struct nh_notifier_info info = { + .net = nh->net, + }; + struct net *net = nh->net; + int err; + + if (nexthop_notifiers_is_empty(net)) + return 0; + + err = nh_notifier_grp_hw_stats_init(&info, nh); + if (err) + return err; + + err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, + NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, + &info); + + /* Cache whatever we got, even if there was an error, otherwise the + * successful stats retrievals would get lost. + */ + nh_grp_hw_stats_apply_update(nh, &info); + *hw_stats_used = info.nh_grp_hw_stats->hw_stats_used; + + nh_notifier_grp_hw_stats_fini(&info); + return notifier_to_errno(err); +} + +static int nla_put_nh_group_stats_entry(struct sk_buff *skb, + struct nh_grp_entry *nhge, + u32 op_flags) +{ + struct nlattr *nest; + u64 packets; + + nh_grp_entry_stats_read(nhge, &packets); + + nest = nla_nest_start(skb, NHA_GROUP_STATS_ENTRY); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, NHA_GROUP_STATS_ENTRY_ID, nhge->nh->id) || + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS, + packets + nhge->packets_hw)) + goto nla_put_failure; + + if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS_HW, + nhge->packets_hw)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh, + u32 op_flags) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + struct nlattr *nest; + bool hw_stats_used; + int err; + int i; + + if (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats)) + goto err_out; + + if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && + nhg->hw_stats) { + err = nh_grp_hw_stats_update(nh, &hw_stats_used); + if (err) + goto out; + + if (nla_put_u32(skb, NHA_HW_STATS_USED, hw_stats_used)) + goto err_out; + } + + nest = nla_nest_start(skb, NHA_GROUP_STATS); + if (!nest) + goto err_out; + + for (i = 0; i < nhg->num_nh; i++) + if (nla_put_nh_group_stats_entry(skb, &nhg->nh_entries[i], + op_flags)) + goto cancel_out; + + nla_nest_end(skb, nest); + return 0; + +cancel_out: + nla_nest_cancel(skb, nest); +err_out: + err = -EMSGSIZE; +out: + return err; +} + +static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, + u32 op_flags) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; @@ -684,6 +894,11 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) goto nla_put_failure; + if (op_flags & NHA_OP_FLAG_DUMP_STATS && + (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats) || + nla_put_nh_group_stats(skb, nh, op_flags))) + goto nla_put_failure; + return 0; nla_put_failure: @@ -691,7 +906,8 @@ nla_put_failure: } static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, - int event, u32 portid, u32 seq, unsigned int nlflags) + int event, u32 portid, u32 seq, unsigned int nlflags, + u32 op_flags) { struct fib6_nh *fib6_nh; struct fib_nh *fib_nh; @@ -718,7 +934,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; - if (nla_put_nh_group(skb, nhg)) + if (nla_put_nh_group(skb, nh, op_flags)) goto nla_put_failure; goto out; } @@ -849,7 +1065,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) if (!skb) goto errout; - err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags); + err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags, 0); if (err < 0) { /* -EMSGSIZE implies BUG in nh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1104,6 +1320,7 @@ static int nh_check_attr_group(struct net *net, if (!tb[i]) continue; switch (i) { + case NHA_HW_STATS_ENABLE: case NHA_FDB: continue; case NHA_RES_GROUP: @@ -1176,6 +1393,7 @@ static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; + nh_grp_entry_stats_inc(nhge); return nhge->nh; } @@ -1185,7 +1403,7 @@ static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) { - struct nexthop *rc = NULL; + struct nh_grp_entry *nhge0 = NULL; int i; if (nhg->fdb_nh) @@ -1200,16 +1418,20 @@ static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) if (!nexthop_is_good_nh(nhge->nh)) continue; - if (!rc) - rc = nhge->nh; + if (!nhge0) + nhge0 = nhge; if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; + nh_grp_entry_stats_inc(nhge); return nhge->nh; } - return rc ? : nhg->nh_entries[0].nh; + if (!nhge0) + nhge0 = &nhg->nh_entries[0]; + nh_grp_entry_stats_inc(nhge0); + return nhge0->nh; } static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) @@ -1225,6 +1447,7 @@ static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) bucket = &res_table->nh_buckets[bucket_index]; nh_res_bucket_set_busy(bucket); nhge = rcu_dereference(bucket->nh_entry); + nh_grp_entry_stats_inc(nhge); return nhge->nh; } @@ -1798,6 +2021,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, newg->has_v4 = true; list_del(&nhges[i].nh_list); + new_nhges[j].stats = nhges[i].stats; new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; new_nhges[j].weight = nhges[i].weight; @@ -1813,6 +2037,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); + free_percpu(nhge->stats); nexthop_put(nhge->nh); /* Removal of a NH from a resilient group is notified through @@ -2477,6 +2702,13 @@ static struct nexthop *nexthop_create_group(struct net *net, if (nhi->family == AF_INET) nhg->has_v4 = true; + nhg->nh_entries[i].stats = + netdev_alloc_pcpu_stats(struct nh_grp_entry_stats); + if (!nhg->nh_entries[i].stats) { + err = -ENOMEM; + nexthop_put(nhe); + goto out_no_nh; + } nhg->nh_entries[i].nh = nhe; nhg->nh_entries[i].weight = entry[i].weight + 1; list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); @@ -2509,6 +2741,9 @@ static struct nexthop *nexthop_create_group(struct net *net, if (cfg->nh_fdb) nhg->fdb_nh = 1; + if (cfg->nh_hw_stats) + nhg->hw_stats = true; + rcu_assign_pointer(nh->nh_grp, nhg); return nh; @@ -2516,6 +2751,7 @@ static struct nexthop *nexthop_create_group(struct net *net, out_no_nh: for (i--; i >= 0; --i) { list_del(&nhg->nh_entries[i].nh_list); + free_percpu(nhg->nh_entries[i].stats); nexthop_put(nhg->nh_entries[i].nh); } @@ -2850,6 +3086,9 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, err = rtm_to_nh_config_grp_res(tb[NHA_RES_GROUP], cfg, extack); + if (tb[NHA_HW_STATS_ENABLE]) + cfg->nh_hw_stats = nla_get_u32(tb[NHA_HW_STATS_ENABLE]); + /* no other attributes should be set */ goto out; } @@ -2941,6 +3180,10 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, goto out; } + if (tb[NHA_HW_STATS_ENABLE]) { + NL_SET_ERR_MSG(extack, "Cannot enable nexthop hardware statistics for non-group nexthops"); + goto out; + } err = 0; out: @@ -2966,9 +3209,9 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, return err; } -static int __nh_valid_get_del_req(const struct nlmsghdr *nlh, - struct nlattr **tb, u32 *id, - struct netlink_ext_ack *extack) +static int nh_valid_get_del_req(const struct nlmsghdr *nlh, + struct nlattr **tb, u32 *id, u32 *op_flags, + struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); @@ -2988,28 +3231,21 @@ static int __nh_valid_get_del_req(const struct nlmsghdr *nlh, return -EINVAL; } - return 0; -} - -static int nh_valid_get_del_req(const struct nlmsghdr *nlh, u32 *id, - struct netlink_ext_ack *extack) -{ - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; - int err; - - err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, - ARRAY_SIZE(rtm_nh_policy_get) - 1, - rtm_nh_policy_get, extack); - if (err < 0) - return err; + if (op_flags) { + if (tb[NHA_OP_FLAGS]) + *op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); + else + *op_flags = 0; + } - return __nh_valid_get_del_req(nlh, tb, id, extack); + return 0; } /* rtnl */ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_del)]; struct net *net = sock_net(skb->sk); struct nl_info nlinfo = { .nlh = nlh, @@ -3020,7 +3256,13 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, int err; u32 id; - err = nh_valid_get_del_req(nlh, &id, extack); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_del) - 1, rtm_nh_policy_del, + extack); + if (err < 0) + return err; + + err = nh_valid_get_del_req(nlh, tb, &id, NULL, extack); if (err) return err; @@ -3037,13 +3279,21 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; struct net *net = sock_net(in_skb->sk); struct sk_buff *skb = NULL; struct nexthop *nh; + u32 op_flags; int err; u32 id; - err = nh_valid_get_del_req(nlh, &id, extack); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_get) - 1, rtm_nh_policy_get, + extack); + if (err < 0) + return err; + + err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; @@ -3058,7 +3308,7 @@ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout_free; err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); + nlh->nlmsg_seq, 0, op_flags); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; @@ -3079,6 +3329,7 @@ struct nh_dump_filter { bool group_filter; bool fdb_filter; u32 res_bucket_nh_id; + u32 op_flags; }; static bool nh_dump_filtered(struct nexthop *nh, @@ -3166,6 +3417,11 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, if (err < 0) return err; + if (tb[NHA_OP_FLAGS]) + filter->op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); + else + filter->op_flags = 0; + return __nh_valid_dump_req(nlh, tb, filter, cb->extack); } @@ -3223,7 +3479,7 @@ static int rtm_dump_nexthop_cb(struct sk_buff *skb, struct netlink_callback *cb, return nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); + cb->nlh->nlmsg_seq, NLM_F_MULTI, filter->op_flags); } /* rtnl */ @@ -3241,10 +3497,6 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) err = rtm_dump_walk_nexthops(skb, cb, root, ctx, &rtm_dump_nexthop_cb, &filter); - if (err < 0) { - if (likely(skb->len)) - err = skb->len; - } cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -3439,11 +3691,6 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, &rtm_dump_nexthop_bucket_cb, &dd); } - if (err < 0) { - if (likely(skb->len)) - err = skb->len; - } - cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; @@ -3483,7 +3730,7 @@ static int nh_valid_get_bucket_req(const struct nlmsghdr *nlh, if (err < 0) return err; - err = __nh_valid_get_del_req(nlh, tb, id, extack); + err = nh_valid_get_del_req(nlh, tb, id, NULL, extack); if (err) return err; @@ -3631,17 +3878,24 @@ unlock: } EXPORT_SYMBOL(register_nexthop_notifier); -int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) +int __unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { int err; - rtnl_lock(); err = blocking_notifier_chain_unregister(&net->nexthop.notifier_chain, nb); - if (err) - goto unlock; - nexthops_dump(net, nb, NEXTHOP_EVENT_DEL, NULL); -unlock: + if (!err) + nexthops_dump(net, nb, NEXTHOP_EVENT_DEL, NULL); + return err; +} +EXPORT_SYMBOL(__unregister_nexthop_notifier); + +int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = __unregister_nexthop_notifier(net, nb); rtnl_unlock(); return err; } @@ -3737,16 +3991,20 @@ out: } EXPORT_SYMBOL(nexthop_res_grp_activity_update); -static void __net_exit nexthop_net_exit_batch(struct list_head *net_list) +static void __net_exit nexthop_net_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { struct net *net; - rtnl_lock(); - list_for_each_entry(net, net_list, exit_list) { + ASSERT_RTNL(); + list_for_each_entry(net, net_list, exit_list) flush_all_nexthops(net); - kfree(net->nexthop.devhash); - } - rtnl_unlock(); +} + +static void __net_exit nexthop_net_exit(struct net *net) +{ + kfree(net->nexthop.devhash); + net->nexthop.devhash = NULL; } static int __net_init nexthop_net_init(struct net *net) @@ -3764,7 +4022,8 @@ static int __net_init nexthop_net_init(struct net *net) static struct pernet_operations nexthop_net_ops = { .init = nexthop_net_init, - .exit_batch = nexthop_net_exit_batch, + .exit = nexthop_net_exit, + .exit_batch_rtnl = nexthop_net_exit_batch_rtnl, }; static int __init nexthop_init(void) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 5f4654ebff48..914bc9c35cc7 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -395,7 +395,7 @@ static int snmp_seq_show_ipstats(struct seq_file *seq, void *v) seq_printf(seq, " %s", snmp4_ipstats_list[i].name); seq_printf(seq, "\nIp: %d %d", - IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2, + IPV4_DEVCONF_ALL_RO(net, FORWARDING) ? 1 : 2, READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index aea89326c697..42ac434cfcfa 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -175,6 +175,13 @@ static int raw_v4_input(struct net *net, struct sk_buff *skb, if (!raw_v4_match(net, sk, iph->protocol, iph->saddr, iph->daddr, dif, sdif)) continue; + + if (atomic_read(&sk->sk_rmem_alloc) >= + READ_ONCE(sk->sk_rcvbuf)) { + atomic_inc(&sk->sk_drops); + continue; + } + delivered = 1; if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) && ip_mc_sf_allow(sk, iph->daddr, iph->saddr, @@ -310,7 +317,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) } nf_reset_ct(skb); - skb_push(skb, skb->data - skb_network_header(skb)); + skb_push(skb, -skb_network_offset(skb)); raw_rcv_skb(sk, skb); return 0; @@ -353,6 +360,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; + skb->mono_delivery_time = !!skb->tstamp; skb_dst_set(skb, &rt->dst); *rtp = NULL; @@ -815,7 +823,7 @@ static int raw_geticmpfilter(struct sock *sk, char __user *optval, int __user *o out: return ret; } -static int do_raw_setsockopt(struct sock *sk, int level, int optname, +static int do_raw_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { if (optname == ICMP_FILTER) { @@ -832,11 +840,11 @@ static int raw_setsockopt(struct sock *sk, int level, int optname, { if (level != SOL_RAW) return ip_setsockopt(sk, level, optname, optval, optlen); - return do_raw_setsockopt(sk, level, optname, optval, optlen); + return do_raw_setsockopt(sk, optname, optval, optlen); } -static int do_raw_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) +static int do_raw_getsockopt(struct sock *sk, int optname, + char __user *optval, int __user *optlen) { if (optname == ICMP_FILTER) { if (inet_sk(sk)->inet_num != IPPROTO_ICMP) @@ -852,7 +860,7 @@ static int raw_getsockopt(struct sock *sk, int level, int optname, { if (level != SOL_RAW) return ip_getsockopt(sk, level, optname, optval, optlen); - return do_raw_getsockopt(sk, level, optname, optval, optlen); + return do_raw_getsockopt(sk, optname, optval, optlen); } static int raw_ioctl(struct sock *sk, int cmd, int *karg) diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index fe2140c8375c..cc793bd8de25 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -213,6 +213,7 @@ static int raw_diag_destroy(struct sk_buff *in_skb, #endif static const struct inet_diag_handler raw_diag_handler = { + .owner = THIS_MODULE, .dump = raw_diag_dump, .dump_one = raw_diag_dump_one, .idiag_get_info = raw_diag_get_info, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 16615d107cf0..c8f76f56dc16 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2313,7 +2313,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (IN_DEV_BFORWARD(in_dev)) goto make_route; /* not do cache if bc_forwarding is enabled */ - if (IPV4_DEVCONF_ALL(net, BC_FORWARDING)) + if (IPV4_DEVCONF_ALL_RO(net, BC_FORWARDING)) do_cache = false; goto brd_input; } @@ -2993,7 +2993,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, #ifdef CONFIG_IP_MROUTE if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && - IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { + IPV4_DEVCONF_ALL_RO(net, MC_FORWARDING)) { int err = ipmr_get_route(net, skb, fl4->saddr, fl4->daddr, r, portid); @@ -3693,9 +3693,8 @@ int __init ip_rt_init(void) panic("IP: failed to allocate ip_rt_acct\n"); #endif - ipv4_dst_ops.kmem_cachep = - kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + ipv4_dst_ops.kmem_cachep = KMEM_CACHE(rtable, + SLAB_HWCACHE_ALIGN | SLAB_PANIC); ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 61f1c96cfe63..7972ad3d7c73 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -51,15 +51,6 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, count, &syncookie_secret[c]); } -/* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */ -static u64 tcp_ns_to_ts(bool usec_ts, u64 val) -{ - if (usec_ts) - return div_u64(val, NSEC_PER_USEC); - - return div_u64(val, NSEC_PER_MSEC); -} - /* * when syncookies are in effect and tcp timestamps are enabled we encode * tcp options in the lower bits of the timestamp value that will be @@ -304,6 +295,24 @@ static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb, return 0; } +#if IS_ENABLED(CONFIG_BPF) +struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb) +{ + struct request_sock *req = inet_reqsk(skb->sk); + + skb->sk = NULL; + skb->destructor = NULL; + + if (cookie_tcp_reqsk_init(sk, skb, req)) { + reqsk_free(req); + req = NULL; + } + + return req; +} +EXPORT_SYMBOL_GPL(cookie_bpf_check); +#endif + struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk, struct sk_buff *skb, struct tcp_options_received *tcp_opt, @@ -399,16 +408,23 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) struct rtable *rt; __u8 rcv_wscale; int full_space; + SKB_DR(reason); if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) || !th->ack || th->rst) goto out; - req = cookie_tcp_check(net, sk, skb); - if (IS_ERR(req)) - goto out; - if (!req) + if (cookie_bpf_ok(skb)) { + req = cookie_bpf_check(sk, skb); + } else { + req = cookie_tcp_check(net, sk, skb); + if (IS_ERR(req)) + goto out; + } + if (!req) { + SKB_DR_SET(reason, NO_SOCKET); goto out_drop; + } ireq = inet_rsk(req); @@ -420,8 +436,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) */ RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); - if (security_inet_conn_request(sk, skb, req)) + if (security_inet_conn_request(sk, skb, req)) { + SKB_DR_SET(reason, SECURITY_HOOK); goto out_free; + } tcp_ao_syncookie(sk, skb, req, AF_INET); @@ -438,8 +456,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid); security_req_classify_flow(req, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) + if (IS_ERR(rt)) { + SKB_DR_SET(reason, IP_OUTNOROUTES); goto out_free; + } /* Try to redo what tcp_v4_send_synack did. */ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); @@ -454,19 +474,24 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); - ireq->rcv_wscale = rcv_wscale; + if (!req->syncookie) + ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst); ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst); /* ip_queue_xmit() depends on our flow being setup * Normal sockets get it right from inet_csk_route_child_sock() */ - if (ret) - inet_sk(ret)->cork.fl.u.ip4 = fl4; + if (!ret) { + SKB_DR_SET(reason, NO_SOCKET); + goto out_drop; + } + inet_sk(ret)->cork.fl.u.ip4 = fl4; out: return ret; out_free: reqsk_free(req); out_drop: + kfree_skb_reason(skb, reason); return NULL; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c82dc42f57c6..d20b62d52171 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> +#include <net/rps.h> /* Track pending CMSGs. */ enum { @@ -974,7 +975,7 @@ int tcp_wmem_schedule(struct sock *sk, int copy) * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0] * to guarantee some progress. */ - left = sock_net(sk)->ipv4.sysctl_tcp_wmem[0] - sk->sk_wmem_queued; + left = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[0]) - sk->sk_wmem_queued; if (left > 0) sk_forced_mem_schedule(sk, min(left, copy)); return min(copy, sk->sk_forward_alloc); @@ -4010,11 +4011,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; @@ -4651,7 +4652,7 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 113); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 105); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 87db432c6bb4..3afeeb68e8a7 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -509,9 +509,9 @@ static int tcp_ao_hash_header(struct tcp_sigpool *hp, bool exclude_options, u8 *hash, int hash_offset, int hash_len) { - int err, len = th->doff << 2; struct scatterlist sg; u8 *hdr = hp->scratch; + int err, len; /* We are not allowed to change tcphdr, make a local copy */ if (exclude_options) { diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 22358032dd48..05dc2d05bc7c 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1155,7 +1155,7 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .set_state = bbr_set_state, }; -BTF_SET8_START(tcp_bbr_check_kfunc_ids) +BTF_KFUNCS_START(tcp_bbr_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, bbr_init) @@ -1168,7 +1168,7 @@ BTF_ID_FLAGS(func, bbr_min_tso_segs) BTF_ID_FLAGS(func, bbr_set_state) #endif #endif -BTF_SET8_END(tcp_bbr_check_kfunc_ids) +BTF_KFUNCS_END(tcp_bbr_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 1b34050a7538..28ffcfbeef14 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -146,11 +146,7 @@ EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_congestion_ops *old_ca) { struct tcp_congestion_ops *existing; - int ret; - - ret = tcp_validate_congestion_control(ca); - if (ret) - return ret; + int ret = 0; ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name)); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 0fd78ecb67e7..44869ea089e3 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -485,7 +485,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .name = "cubic", }; -BTF_SET8_START(tcp_cubic_check_kfunc_ids) +BTF_KFUNCS_START(tcp_cubic_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, cubictcp_init) @@ -496,7 +496,7 @@ BTF_ID_FLAGS(func, cubictcp_cwnd_event) BTF_ID_FLAGS(func, cubictcp_acked) #endif #endif -BTF_SET8_END(tcp_cubic_check_kfunc_ids) +BTF_KFUNCS_END(tcp_cubic_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index bb23bb5b387a..e33fbe4933e4 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -260,7 +260,7 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = { .name = "dctcp-reno", }; -BTF_SET8_START(tcp_dctcp_check_kfunc_ids) +BTF_KFUNCS_START(tcp_dctcp_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID_FLAGS(func, dctcp_init) @@ -271,7 +271,7 @@ BTF_ID_FLAGS(func, dctcp_cwnd_undo) BTF_ID_FLAGS(func, dctcp_state) #endif #endif -BTF_SET8_END(tcp_dctcp_check_kfunc_ids) +BTF_KFUNCS_END(tcp_dctcp_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_dctcp_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 4cbe4b44425a..f428ecf9120f 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -222,6 +222,7 @@ static int tcp_diag_destroy(struct sk_buff *in_skb, #endif static const struct inet_diag_handler tcp_diag_handler = { + .owner = THIS_MODULE, .dump = tcp_diag_dump, .dump_one = tcp_diag_dump_one, .idiag_get_info = tcp_diag_get_info, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index df7b13f0e5e0..5d874817a78d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1164,7 +1164,7 @@ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, * L|R 1 - orig is lost, retransmit is in flight. * S|R 1 - orig reached receiver, retrans is still in flight. * (L|S|R is logically valid, it could occur when L|R is sacked, - * but it is equivalent to plain S and code short-curcuits it to S. + * but it is equivalent to plain S and code short-circuits it to S. * L|S is logically invalid, it would mean -1 packet in flight 8)) * * These 6 states form finite state machine, controlled by the following events: @@ -6361,6 +6361,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, TCP_TIMEOUT_MIN, TCP_RTO_MAX); + SKB_DR_SET(reason, TCP_INVALID_ACK_SEQUENCE); goto reset_and_undo; } @@ -6369,6 +6370,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_time_stamp_ts(tp))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); + SKB_DR_SET(reason, TCP_RFC7323_PAWS); goto reset_and_undo; } @@ -6572,7 +6574,8 @@ discard_and_undo: reset_and_undo: tcp_clear_options(&tp->rx_opt); tp->rx_opt.mss_clamp = saved_clamp; - return 1; + /* we can reuse/return @reason to its caller to handle the exception */ + return reason; } static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) @@ -6616,14 +6619,14 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) * address independent. */ -int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) +enum skb_drop_reason +tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); const struct tcphdr *th = tcp_hdr(skb); struct request_sock *req; int queued = 0; - bool acceptable; SKB_DR(reason); switch (sk->sk_state) { @@ -6633,7 +6636,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_LISTEN: if (th->ack) - return 1; + return SKB_DROP_REASON_TCP_FLAGS; if (th->rst) { SKB_DR_SET(reason, TCP_RESET); @@ -6649,12 +6652,10 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) */ rcu_read_lock(); local_bh_disable(); - acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0; + icsk->icsk_af_ops->conn_request(sk, skb); local_bh_enable(); rcu_read_unlock(); - if (!acceptable) - return 1; consume_skb(skb); return 0; } @@ -6699,17 +6700,25 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) return 0; /* step 5: check the ACK field */ - acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | - FLAG_UPDATE_TS_RECENT | - FLAG_NO_CHALLENGE_ACK) > 0; - - if (!acceptable) { - if (sk->sk_state == TCP_SYN_RECV) - return 1; /* send one RST */ - tcp_send_challenge_ack(sk); - SKB_DR_SET(reason, TCP_OLD_ACK); - goto discard; + reason = tcp_ack(sk, skb, FLAG_SLOWPATH | + FLAG_UPDATE_TS_RECENT | + FLAG_NO_CHALLENGE_ACK); + + if ((int)reason <= 0) { + if (sk->sk_state == TCP_SYN_RECV) { + /* send one RST */ + if (!reason) + return SKB_DROP_REASON_TCP_OLD_ACK; + return -reason; + } + /* accept old ack during closing */ + if ((int)reason < 0) { + tcp_send_challenge_ack(sk); + reason = -reason; + goto discard; + } } + SKB_DR_SET(reason, NOT_SPECIFIED); switch (sk->sk_state) { case TCP_SYN_RECV: tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */ @@ -6777,7 +6786,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (READ_ONCE(tp->linger2) < 0) { tcp_done(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); - return 1; + return SKB_DROP_REASON_TCP_ABORT_ON_DATA; } if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) { @@ -6786,7 +6795,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_fastopen_active_disable(sk); tcp_done(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); - return 1; + return SKB_DROP_REASON_TCP_ABORT_ON_DATA; } tmo = tcp_fin_time(sk); @@ -6851,7 +6860,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); tcp_reset(sk, skb); - return 1; + return SKB_DROP_REASON_TCP_ABORT_ON_DATA; } } fallthrough; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0c50c5a32b84..a22ee5838751 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1907,7 +1907,6 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } - reason = SKB_DROP_REASON_NOT_SPECIFIED; if (tcp_checksum_complete(skb)) goto csum_err; @@ -1915,9 +1914,10 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) struct sock *nsk = tcp_v4_cookie_check(sk, skb); if (!nsk) - goto discard; + return 0; if (nsk != sk) { - if (tcp_child_process(sk, nsk, skb)) { + reason = tcp_child_process(sk, nsk, skb); + if (reason) { rsk = nsk; goto reset; } @@ -1926,7 +1926,8 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb)) { + reason = tcp_rcv_state_process(sk, skb); + if (reason) { rsk = sk; goto reset; } @@ -2275,10 +2276,12 @@ process: if (nsk == sk) { reqsk_put(req); tcp_v4_restore_cb(skb); - } else if (tcp_child_process(sk, nsk, skb)) { - tcp_v4_send_reset(nsk, skb); - goto discard_and_relse; } else { + drop_reason = tcp_child_process(sk, nsk, skb); + if (drop_reason) { + tcp_v4_send_reset(nsk, skb); + goto discard_and_relse; + } sock_put(sk); return 0; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 9e85f2a0bddd..52040b0e2616 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -911,11 +911,11 @@ EXPORT_SYMBOL(tcp_check_req); * be created. */ -int tcp_child_process(struct sock *parent, struct sock *child, - struct sk_buff *skb) +enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, + struct sk_buff *skb) __releases(&((child)->sk_lock.slock)) { - int ret = 0; + enum skb_drop_reason reason = SKB_NOT_DROPPED_YET; int state = child->sk_state; /* record sk_napi_id and sk_rx_queue_mapping of child. */ @@ -923,7 +923,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, tcp_segs_in(tcp_sk(child), skb); if (!sock_owned_by_user(child)) { - ret = tcp_rcv_state_process(child, skb); + reason = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) parent->sk_data_ready(parent); @@ -937,6 +937,6 @@ int tcp_child_process(struct sock *parent, struct sock *child, bh_unlock_sock(child); sock_put(child); - return ret; + return reason; } EXPORT_SYMBOL(tcp_child_process); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 8311c38267b5..ebe4722bb020 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -204,7 +204,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb) goto out; hlen = off + thlen; - if (skb_gro_header_hard(skb, hlen)) { + if (!skb_gro_may_pull(skb, hlen)) { th = skb_gro_header_slow(skb, hlen, off); if (unlikely(!th)) goto out; @@ -299,18 +299,20 @@ out: void tcp_gro_complete(struct sk_buff *skb) { struct tcphdr *th = tcp_hdr(skb); + struct skb_shared_info *shinfo; + + if (skb->encapsulation) + skb->inner_transport_header = skb->transport_header; skb->csum_start = (unsigned char *)th - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; - skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + shinfo = skb_shinfo(skb); + shinfo->gso_segs = NAPI_GRO_CB(skb)->count; if (th->cwr) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; - - if (skb->encapsulation) - skb->inner_transport_header = skb->transport_header; + shinfo->gso_type |= SKB_GSO_TCP_ECN; } EXPORT_SYMBOL(tcp_gro_complete); @@ -335,24 +337,22 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; - if (NAPI_GRO_CB(skb)->is_atomic) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4 | + (NAPI_GRO_CB(skb)->is_atomic * SKB_GSO_TCP_FIXEDID); tcp_gro_complete(skb); return 0; } -static const struct net_offload tcpv4_offload = { - .callbacks = { - .gso_segment = tcp4_gso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, - }, -}; - int __init tcpv4_offload_init(void) { - return inet_add_offload(&tcpv4_offload, IPPROTO_TCP); + net_hotdata.tcpv4_offload = (struct net_offload) { + .callbacks = { + .gso_segment = tcp4_gso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, + }, + }; + return inet_add_offload(&net_hotdata.tcpv4_offload, IPPROTO_TCP); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e474b201900f..661d0e0d273f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -411,8 +411,6 @@ INDIRECT_CALLABLE_SCOPE u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { - static u32 udp_ehash_secret __read_mostly; - net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, @@ -1589,7 +1587,8 @@ int udp_init_sock(struct sock *sk) void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { - sk_peek_offset_bwd(sk, len); + if (unlikely(READ_ONCE(udp_sk(sk)->peeking_with_offset))) + sk_peek_offset_bwd(sk, len); if (!skb_unref(skb)) return; @@ -2569,11 +2568,12 @@ int udp_v4_early_demux(struct sk_buff *skb) uh->source, iph->saddr, dif, sdif); } - if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) + if (!sk) return 0; skb->sk = sk; - skb->destructor = sock_efree; + DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); + skb->destructor = sock_pfree; dst = rcu_dereference(sk->sk_rx_dst); if (dst) @@ -2792,11 +2792,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case UDP_CORK: val = udp_test_bit(CORK, sk); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index dc41a22ee80e..38cb3a28e4ed 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -237,6 +237,7 @@ static int udplite_diag_destroy(struct sk_buff *in_skb, #endif static const struct inet_diag_handler udp_diag_handler = { + .owner = THIS_MODULE, .dump = udp_diag_dump, .dump_one = udp_diag_dump_one, .idiag_get_info = udp_diag_get_info, @@ -260,6 +261,7 @@ static int udplite_diag_dump_one(struct netlink_callback *cb, } static const struct inet_diag_handler udplite_diag_handler = { + .owner = THIS_MODULE, .dump = udplite_diag_dump, .dump_one = udplite_diag_dump_one, .idiag_get_info = udp_diag_get_info, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6c95d28d0c4a..b9880743765c 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -737,15 +737,14 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } -static const struct net_offload udpv4_offload = { - .callbacks = { - .gso_segment = udp4_ufo_fragment, - .gro_receive = udp4_gro_receive, - .gro_complete = udp4_gro_complete, - }, -}; - int __init udpv4_offload_init(void) { - return inet_add_offload(&udpv4_offload, IPPROTO_UDP); + net_hotdata.udpv4_offload = (struct net_offload) { + .callbacks = { + .gso_segment = udp4_ufo_fragment, + .gro_receive = udp4_gro_receive, + .gro_complete = udp4_gro_complete, + }, + }; + return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP); } diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index c54676998eb6..dae35101d189 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -58,7 +58,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) return -iph->protocol; #endif - __skb_push(skb, skb->data - skb_network_header(skb)); + __skb_push(skb, -skb_network_offset(skb)); iph->tot_len = htons(skb->len); ip_send_check(iph); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 055230b669cf..247bd4d8ee45 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -195,6 +195,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, + .regen_min_advance = REGEN_MIN_ADVANCE, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, @@ -257,6 +258,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, + .regen_min_advance = REGEN_MIN_ADVANCE, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, @@ -549,7 +551,8 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, goto out; if ((all || type == NETCONFA_FORWARDING) && - nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0) + nla_put_s32(skb, NETCONFA_FORWARDING, + READ_ONCE(devconf->forwarding)) < 0) goto nla_put_failure; #ifdef CONFIG_IPV6_MROUTE if ((all || type == NETCONFA_MC_FORWARDING) && @@ -558,12 +561,13 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, goto nla_put_failure; #endif if ((all || type == NETCONFA_PROXY_NEIGH) && - nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0) + nla_put_s32(skb, NETCONFA_PROXY_NEIGH, + READ_ONCE(devconf->proxy_ndp)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, - devconf->ignore_routes_with_linkdown) < 0) + READ_ONCE(devconf->ignore_routes_with_linkdown)) < 0) goto nla_put_failure; out: @@ -713,7 +717,7 @@ errout: static u32 inet6_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv6.dev_addr_genid) + - net->dev_base_seq; + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. @@ -723,17 +727,18 @@ static u32 inet6_base_seq(const struct net *net) return res; } - static int inet6_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); - int h, s_h; - int idx, s_idx; + struct { + unsigned long ifindex; + unsigned int all_default; + } *ctx = (void *)cb->ctx; struct net_device *dev; struct inet6_dev *idev; - struct hlist_head *head; + int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; @@ -750,64 +755,46 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, } } - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - rcu_read_lock(); - cb->seq = inet6_base_seq(net); - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - idev = __in6_dev_get(dev); - if (!idev) - goto cont; - - if (inet6_netconf_fill_devconf(skb, dev->ifindex, - &idev->cnf, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, - NLM_F_MULTI, - NETCONFA_ALL) < 0) { - rcu_read_unlock(); - goto done; - } - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } - rcu_read_unlock(); + rcu_read_lock(); + for_each_netdev_dump(net, dev, ctx->ifindex) { + idev = __in6_dev_get(dev); + if (!idev) + continue; + err = inet6_netconf_fill_devconf(skb, dev->ifindex, + &idev->cnf, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, + NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) + goto done; } - if (h == NETDEV_HASHENTRIES) { - if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, - net->ipv6.devconf_all, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, NLM_F_MULTI, - NETCONFA_ALL) < 0) + if (ctx->all_default == 0) { + err = inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) goto done; - else - h++; - } - if (h == NETDEV_HASHENTRIES + 1) { - if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, - net->ipv6.devconf_dflt, - NETLINK_CB(cb->skb).portid, - nlh->nlmsg_seq, - RTM_NEWNETCONF, NLM_F_MULTI, - NETCONFA_ALL) < 0) + ctx->all_default++; + } + if (ctx->all_default == 1) { + err = inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt, + NETLINK_CB(cb->skb).portid, + nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + NETCONFA_ALL); + if (err < 0) goto done; - else - h++; + ctx->all_default++; } done: - cb->args[0] = h; - cb->args[1] = idx; - - return skb->len; + rcu_read_unlock(); + return err; } #ifdef CONFIG_SYSCTL @@ -867,7 +854,8 @@ static void addrconf_forward_change(struct net *net, __s32 newf) idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!newf); - idev->cnf.forwarding = newf; + + WRITE_ONCE(idev->cnf.forwarding, newf); if (changed) dev_forward_change(idev); } @@ -884,7 +872,7 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) net = (struct net *)table->extra2; old = *p; - *p = newf; + WRITE_ONCE(*p, newf); if (p == &net->ipv6.devconf_dflt->forwarding) { if ((!newf) ^ (!old)) @@ -899,7 +887,7 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) if (p == &net->ipv6.devconf_all->forwarding) { int old_dflt = net->ipv6.devconf_dflt->forwarding; - net->ipv6.devconf_dflt->forwarding = newf; + WRITE_ONCE(net->ipv6.devconf_dflt->forwarding, newf); if ((!newf) ^ (!old_dflt)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, @@ -931,7 +919,7 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf) if (idev) { int changed = (!idev->cnf.ignore_routes_with_linkdown) ^ (!newf); - idev->cnf.ignore_routes_with_linkdown = newf; + WRITE_ONCE(idev->cnf.ignore_routes_with_linkdown, newf); if (changed) inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, @@ -952,7 +940,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) net = (struct net *)table->extra2; old = *p; - *p = newf; + WRITE_ONCE(*p, newf); if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) { if ((!newf) ^ (!old)) @@ -966,7 +954,7 @@ static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) } if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) { - net->ipv6.devconf_dflt->ignore_routes_with_linkdown = newf; + WRITE_ONCE(net->ipv6.devconf_dflt->ignore_routes_with_linkdown, newf); addrconf_linkdown_change(net, newf); if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, @@ -1270,6 +1258,7 @@ static void cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt, bool del_peer) { + struct fib6_table *table; struct fib6_info *f6i; f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr, @@ -1279,8 +1268,15 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, if (del_rt) ip6_del_rt(dev_net(ifp->idev->dev), f6i, false); else { - if (!(f6i->fib6_flags & RTF_EXPIRES)) + if (!(f6i->fib6_flags & RTF_EXPIRES)) { + table = f6i->fib6_table; + spin_lock_bh(&table->tb6_lock); + fib6_set_expires(f6i, expires); + fib6_add_gc_list(f6i); + + spin_unlock_bh(&table->tb6_lock); + } fib6_info_release(f6i); } } @@ -1346,12 +1342,21 @@ out: in6_ifa_put(ifp); } +static unsigned long ipv6_get_regen_advance(const struct inet6_dev *idev) +{ + return READ_ONCE(idev->cnf.regen_min_advance) + + READ_ONCE(idev->cnf.regen_max_retry) * + READ_ONCE(idev->cnf.dad_transmits) * + max(NEIGH_VAR(idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; +} + static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block) { struct inet6_dev *idev = ifp->idev; unsigned long tmp_tstamp, age; unsigned long regen_advance; unsigned long now = jiffies; + u32 if_public_preferred_lft; s32 cnf_temp_preferred_lft; struct inet6_ifaddr *ift; struct ifa6_config cfg; @@ -1363,7 +1368,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block) retry: in6_dev_hold(idev); - if (idev->cnf.use_tempaddr <= 0) { + if (READ_ONCE(idev->cnf.use_tempaddr) <= 0) { write_unlock_bh(&idev->lock); pr_info("%s: use_tempaddr is disabled\n", __func__); in6_dev_put(idev); @@ -1371,8 +1376,8 @@ retry: goto out; } spin_lock_bh(&ifp->lock); - if (ifp->regen_count++ >= idev->cnf.regen_max_retry) { - idev->cnf.use_tempaddr = -1; /*XXX*/ + if (ifp->regen_count++ >= READ_ONCE(idev->cnf.regen_max_retry)) { + WRITE_ONCE(idev->cnf.use_tempaddr, -1); /*XXX*/ spin_unlock_bh(&ifp->lock); write_unlock_bh(&idev->lock); pr_warn("%s: regeneration time exceeded - disabled temporary address support\n", @@ -1387,16 +1392,14 @@ retry: age = (now - ifp->tstamp) / HZ; - regen_advance = idev->cnf.regen_max_retry * - idev->cnf.dad_transmits * - max(NEIGH_VAR(idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; + regen_advance = ipv6_get_regen_advance(idev); /* recalculate max_desync_factor each time and update * idev->desync_factor if it's larger */ cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft); max_desync_factor = min_t(long, - idev->cnf.max_desync_factor, + READ_ONCE(idev->cnf.max_desync_factor), cnf_temp_preferred_lft - regen_advance); if (unlikely(idev->desync_factor > max_desync_factor)) { @@ -1409,11 +1412,13 @@ retry: } } + if_public_preferred_lft = ifp->prefered_lft; + memset(&cfg, 0, sizeof(cfg)); cfg.valid_lft = min_t(__u32, ifp->valid_lft, - idev->cnf.temp_valid_lft + age); + READ_ONCE(idev->cnf.temp_valid_lft) + age); cfg.preferred_lft = cnf_temp_preferred_lft + age - idev->desync_factor; - cfg.preferred_lft = min_t(__u32, ifp->prefered_lft, cfg.preferred_lft); + cfg.preferred_lft = min_t(__u32, if_public_preferred_lft, cfg.preferred_lft); cfg.preferred_lft = min_t(__u32, cfg.valid_lft, cfg.preferred_lft); cfg.plen = ifp->prefix_len; @@ -1422,19 +1427,41 @@ retry: write_unlock_bh(&idev->lock); - /* A temporary address is created only if this calculated Preferred - * Lifetime is greater than REGEN_ADVANCE time units. In particular, - * an implementation must not create a temporary address with a zero - * Preferred Lifetime. + /* From RFC 4941: + * + * A temporary address is created only if this calculated Preferred + * Lifetime is greater than REGEN_ADVANCE time units. In + * particular, an implementation must not create a temporary address + * with a zero Preferred Lifetime. + * + * ... + * + * When creating a temporary address, the lifetime values MUST be + * derived from the corresponding prefix as follows: + * + * ... + * + * * Its Preferred Lifetime is the lower of the Preferred Lifetime + * of the public address or TEMP_PREFERRED_LIFETIME - + * DESYNC_FACTOR. + * + * To comply with the RFC's requirements, clamp the preferred lifetime + * to a minimum of regen_advance, unless that would exceed valid_lft or + * ifp->prefered_lft. + * * Use age calculation as in addrconf_verify to avoid unnecessary * temporary addresses being generated. */ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (cfg.preferred_lft <= regen_advance + age) { - in6_ifa_put(ifp); - in6_dev_put(idev); - ret = -1; - goto out; + cfg.preferred_lft = regen_advance + age + 1; + if (cfg.preferred_lft > cfg.valid_lft || + cfg.preferred_lft > if_public_preferred_lft) { + in6_ifa_put(ifp); + in6_dev_put(idev); + ret = -1; + goto out; + } } cfg.ifa_flags = IFA_F_TEMPORARY; @@ -1513,15 +1540,17 @@ static inline int ipv6_saddr_preferred(int type) return 0; } -static bool ipv6_use_optimistic_addr(struct net *net, - struct inet6_dev *idev) +static bool ipv6_use_optimistic_addr(const struct net *net, + const struct inet6_dev *idev) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (!idev) return false; - if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad) + if (!READ_ONCE(net->ipv6.devconf_all->optimistic_dad) && + !READ_ONCE(idev->cnf.optimistic_dad)) return false; - if (!net->ipv6.devconf_all->use_optimistic && !idev->cnf.use_optimistic) + if (!READ_ONCE(net->ipv6.devconf_all->use_optimistic) && + !READ_ONCE(idev->cnf.use_optimistic)) return false; return true; @@ -1530,13 +1559,14 @@ static bool ipv6_use_optimistic_addr(struct net *net, #endif } -static bool ipv6_allow_optimistic_dad(struct net *net, - struct inet6_dev *idev) +static bool ipv6_allow_optimistic_dad(const struct net *net, + const struct inet6_dev *idev) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (!idev) return false; - if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad) + if (!READ_ONCE(net->ipv6.devconf_all->optimistic_dad) && + !READ_ONCE(idev->cnf.optimistic_dad)) return false; return true; @@ -1642,7 +1672,7 @@ static int ipv6_get_saddr_eval(struct net *net, */ int preftmp = dst->prefs & (IPV6_PREFER_SRC_PUBLIC|IPV6_PREFER_SRC_TMP) ? !!(dst->prefs & IPV6_PREFER_SRC_TMP) : - score->ifa->idev->cnf.use_tempaddr >= 2; + READ_ONCE(score->ifa->idev->cnf.use_tempaddr) >= 2; ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ preftmp; break; } @@ -1818,7 +1848,7 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, idev = __in6_dev_get(dst_dev); if ((dst_type & IPV6_ADDR_MULTICAST) || dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL || - (idev && idev->cnf.use_oif_addrs_only)) { + (idev && READ_ONCE(idev->cnf.use_oif_addrs_only))) { use_oif_addr = true; } } @@ -2125,6 +2155,7 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net *net = dev_net(idev->dev); + int max_addresses; if (addrconf_dad_end(ifp)) { in6_ifa_put(ifp); @@ -2162,9 +2193,9 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) spin_unlock_bh(&ifp->lock); - if (idev->cnf.max_addresses && - ipv6_count_addresses(idev) >= - idev->cnf.max_addresses) + max_addresses = READ_ONCE(idev->cnf.max_addresses); + if (max_addresses && + ipv6_count_addresses(idev) >= max_addresses) goto lock_errdad; net_info_ratelimited("%s: generating new stable privacy address because of DAD conflict\n", @@ -2561,11 +2592,11 @@ static void manage_tempaddrs(struct inet6_dev *idev, * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR), respectively. */ age = (now - ift->cstamp) / HZ; - max_valid = idev->cnf.temp_valid_lft - age; + max_valid = READ_ONCE(idev->cnf.temp_valid_lft) - age; if (max_valid < 0) max_valid = 0; - max_prefered = idev->cnf.temp_prefered_lft - + max_prefered = READ_ONCE(idev->cnf.temp_prefered_lft) - idev->desync_factor - age; if (max_prefered < 0) max_prefered = 0; @@ -2598,7 +2629,7 @@ static void manage_tempaddrs(struct inet6_dev *idev, if (list_empty(&idev->tempaddr_list) && (valid_lft || prefered_lft)) create = true; - if (create && idev->cnf.use_tempaddr > 0) { + if (create && READ_ONCE(idev->cnf.use_tempaddr) > 0) { /* When a new public address is created as described * in [ADDRCONF], also create a new temporary address. */ @@ -2626,7 +2657,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, int create = 0, update_lft = 0; if (!ifp && valid_lft) { - int max_addresses = in6_dev->cnf.max_addresses; + int max_addresses = READ_ONCE(in6_dev->cnf.max_addresses); struct ifa6_config cfg = { .pfx = addr, .plen = pinfo->prefix_len, @@ -2638,8 +2669,8 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, }; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD - if ((net->ipv6.devconf_all->optimistic_dad || - in6_dev->cnf.optimistic_dad) && + if ((READ_ONCE(net->ipv6.devconf_all->optimistic_dad) || + READ_ONCE(in6_dev->cnf.optimistic_dad)) && !net->ipv6.devconf_all->forwarding && sllao) cfg.ifa_flags |= IFA_F_OPTIMISTIC; #endif @@ -2688,7 +2719,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, */ update_lft = !create && stored_lft; - if (update_lft && !in6_dev->cnf.ra_honor_pio_life) { + if (update_lft && !READ_ONCE(in6_dev->cnf.ra_honor_pio_life)) { const u32 minimum_lft = min_t(u32, stored_lft, MIN_VALID_LIFETIME); valid_lft = max(valid_lft, minimum_lft); @@ -2697,7 +2728,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, if (update_lft) { ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; - ifp->tstamp = now; + WRITE_ONCE(ifp->tstamp, now); flags = ifp->flags; ifp->flags &= ~IFA_F_DEPRECATED; spin_unlock_bh(&ifp->lock); @@ -2721,6 +2752,7 @@ EXPORT_SYMBOL_GPL(addrconf_prefix_rcv_add_addr); void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) { struct prefix_info *pinfo; + struct fib6_table *table; __u32 valid_lft; __u32 prefered_lft; int addr_type, err; @@ -2797,11 +2829,20 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) if (valid_lft == 0) { ip6_del_rt(net, rt, false); rt = NULL; - } else if (addrconf_finite_timeout(rt_expires)) { - /* not infinity */ - fib6_set_expires(rt, jiffies + rt_expires); } else { - fib6_clean_expires(rt); + table = rt->fib6_table; + spin_lock_bh(&table->tb6_lock); + + if (addrconf_finite_timeout(rt_expires)) { + /* not infinity */ + fib6_set_expires(rt, jiffies + rt_expires); + fib6_add_gc_list(rt); + } else { + fib6_clean_expires(rt); + fib6_remove_gc_list(rt); + } + + spin_unlock_bh(&table->tb6_lock); } } else if (valid_lft) { clock_t expires = 0; @@ -3262,8 +3303,8 @@ void addrconf_add_linklocal(struct inet6_dev *idev, struct inet6_ifaddr *ifp; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD - if ((dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad || - idev->cnf.optimistic_dad) && + if ((READ_ONCE(dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad) || + READ_ONCE(idev->cnf.optimistic_dad)) && !dev_net(idev->dev)->ipv6.devconf_all->forwarding) cfg.ifa_flags |= IFA_F_OPTIMISTIC; #endif @@ -3442,7 +3483,8 @@ static void addrconf_dev_config(struct net_device *dev) /* this device type has no EUI support */ if (dev->type == ARPHRD_NONE && idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) - idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM; + WRITE_ONCE(idev->cnf.addr_gen_mode, + IN6_ADDR_GEN_MODE_RANDOM); addrconf_addr_gen(idev, false); } @@ -3620,7 +3662,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (idev) { rt6_mtu_change(dev, dev->mtu); - idev->cnf.mtu6 = dev->mtu; + WRITE_ONCE(idev->cnf.mtu6, dev->mtu); break; } @@ -3712,9 +3754,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (idev->cnf.mtu6 != dev->mtu && dev->mtu >= IPV6_MIN_MTU) { rt6_mtu_change(dev, dev->mtu); - idev->cnf.mtu6 = dev->mtu; + WRITE_ONCE(idev->cnf.mtu6, dev->mtu); } - idev->tstamp = jiffies; + WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); /* @@ -3834,10 +3876,10 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister) */ if (!unregister && !idev->cnf.disable_ipv6) { /* aggregate the system setting and interface setting */ - int _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; + int _keep_addr = READ_ONCE(net->ipv6.devconf_all->keep_addr_on_down); if (!_keep_addr) - _keep_addr = idev->cnf.keep_addr_on_down; + _keep_addr = READ_ONCE(idev->cnf.keep_addr_on_down); keep_addr = (_keep_addr > 0); } @@ -3956,7 +3998,7 @@ restart: ipv6_mc_down(idev); } - idev->tstamp = jiffies; + WRITE_ONCE(idev->tstamp, jiffies); idev->ra_mtu = 0; /* Last: Shot the device (if unregistered) */ @@ -3974,6 +4016,7 @@ static void addrconf_rs_timer(struct timer_list *t) struct inet6_dev *idev = from_timer(idev, t, rs_timer); struct net_device *dev = idev->dev; struct in6_addr lladdr; + int rtr_solicits; write_lock(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) @@ -3986,7 +4029,9 @@ static void addrconf_rs_timer(struct timer_list *t) if (idev->if_flags & IF_RA_RCVD) goto out; - if (idev->rs_probes++ < idev->cnf.rtr_solicits || idev->cnf.rtr_solicits < 0) { + rtr_solicits = READ_ONCE(idev->cnf.rtr_solicits); + + if (idev->rs_probes++ < rtr_solicits || rtr_solicits < 0) { write_unlock(&idev->lock); if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) ndisc_send_rs(dev, &lladdr, @@ -3996,11 +4041,12 @@ static void addrconf_rs_timer(struct timer_list *t) write_lock(&idev->lock); idev->rs_interval = rfc3315_s14_backoff_update( - idev->rs_interval, idev->cnf.rtr_solicit_max_interval); + idev->rs_interval, + READ_ONCE(idev->cnf.rtr_solicit_max_interval)); /* The wait after the last probe can be shorter */ addrconf_mod_rs_timer(idev, (idev->rs_probes == - idev->cnf.rtr_solicits) ? - idev->cnf.rtr_solicit_delay : + READ_ONCE(idev->cnf.rtr_solicits)) ? + READ_ONCE(idev->cnf.rtr_solicit_delay) : idev->rs_interval); } else { /* @@ -4021,24 +4067,25 @@ put: */ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) { - unsigned long rand_num; struct inet6_dev *idev = ifp->idev; + unsigned long rand_num; u64 nonce; if (ifp->flags & IFA_F_OPTIMISTIC) rand_num = 0; else - rand_num = get_random_u32_below(idev->cnf.rtr_solicit_delay ? : 1); + rand_num = get_random_u32_below( + READ_ONCE(idev->cnf.rtr_solicit_delay) ? : 1); nonce = 0; - if (idev->cnf.enhanced_dad || - dev_net(idev->dev)->ipv6.devconf_all->enhanced_dad) { + if (READ_ONCE(idev->cnf.enhanced_dad) || + READ_ONCE(dev_net(idev->dev)->ipv6.devconf_all->enhanced_dad)) { do get_random_bytes(&nonce, 6); while (nonce == 0); } ifp->dad_nonce = nonce; - ifp->dad_probes = idev->cnf.dad_transmits; + ifp->dad_probes = READ_ONCE(idev->cnf.dad_transmits); addrconf_mod_dad_work(ifp, rand_num); } @@ -4058,8 +4105,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) net = dev_net(dev); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || - (net->ipv6.devconf_all->accept_dad < 1 && - idev->cnf.accept_dad < 1) || + (READ_ONCE(net->ipv6.devconf_all->accept_dad) < 1 && + READ_ONCE(idev->cnf.accept_dad) < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { bool send_na = false; @@ -4151,8 +4198,8 @@ static void addrconf_dad_work(struct work_struct *w) action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; - if ((dev_net(idev->dev)->ipv6.devconf_all->accept_dad > 1 || - idev->cnf.accept_dad > 1) && + if ((READ_ONCE(dev_net(idev->dev)->ipv6.devconf_all->accept_dad) > 1 || + READ_ONCE(idev->cnf.accept_dad) > 1) && !idev->cnf.disable_ipv6 && !(ifp->flags & IFA_F_STABLE_PRIVACY)) { struct in6_addr addr; @@ -4163,7 +4210,7 @@ static void addrconf_dad_work(struct work_struct *w) if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && ipv6_addr_equal(&ifp->addr, &addr)) { /* DAD failed for link-local based on MAC */ - idev->cnf.disable_ipv6 = 1; + WRITE_ONCE(idev->cnf.disable_ipv6, 1); pr_info("%s: IPv6 being disabled!\n", ifp->idev->dev->name); @@ -4277,7 +4324,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp); send_rs = send_mld && ipv6_accept_ra(ifp->idev) && - ifp->idev->cnf.rtr_solicits != 0 && + READ_ONCE(ifp->idev->cnf.rtr_solicits) != 0 && (dev->flags & IFF_LOOPBACK) == 0 && (dev->type != ARPHRD_TUNNEL) && !netif_is_team_port(dev); @@ -4291,8 +4338,8 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, /* send unsolicited NA if enabled */ if (send_na && - (ifp->idev->cnf.ndisc_notify || - dev_net(dev)->ipv6.devconf_all->ndisc_notify)) { + (READ_ONCE(ifp->idev->cnf.ndisc_notify) || + READ_ONCE(dev_net(dev)->ipv6.devconf_all->ndisc_notify))) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifp->addr, /*router=*/ !!ifp->idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, @@ -4312,7 +4359,7 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, write_lock_bh(&ifp->idev->lock); spin_lock(&ifp->lock); ifp->idev->rs_interval = rfc3315_s14_backoff_init( - ifp->idev->cnf.rtr_solicit_interval); + READ_ONCE(ifp->idev->cnf.rtr_solicit_interval)); ifp->idev->rs_probes = 1; ifp->idev->if_flags |= IF_RS_SENT; addrconf_mod_rs_timer(ifp->idev, ifp->idev->rs_interval); @@ -4592,9 +4639,7 @@ restart: !ifp->regen_count && ifp->ifpub) { /* This is a non-regenerated temporary addr. */ - unsigned long regen_advance = ifp->idev->cnf.regen_max_retry * - ifp->idev->cnf.dad_transmits * - max(NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; + unsigned long regen_advance = ipv6_get_regen_advance(ifp->idev); if (age + regen_advance >= ifp->prefered_lft) { struct inet6_ifaddr *ifpub = ifp->ifpub; @@ -4756,6 +4801,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, u32 flags, bool modify_peer) { + struct fib6_table *table; struct fib6_info *f6i; u32 prio; @@ -4776,10 +4822,18 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } else { - if (!expires) + table = f6i->fib6_table; + spin_lock_bh(&table->tb6_lock); + + if (!(flags & RTF_EXPIRES)) { fib6_clean_expires(f6i); - else + fib6_remove_gc_list(f6i); + } else { fib6_set_expires(f6i, expires); + fib6_add_gc_list(f6i); + } + + spin_unlock_bh(&table->tb6_lock); fib6_info_release(f6i); } @@ -4842,13 +4896,13 @@ static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE); ifp->flags |= cfg->ifa_flags; - ifp->tstamp = jiffies; - ifp->valid_lft = cfg->valid_lft; - ifp->prefered_lft = cfg->preferred_lft; - ifp->ifa_proto = cfg->ifa_proto; + WRITE_ONCE(ifp->tstamp, jiffies); + WRITE_ONCE(ifp->valid_lft, cfg->valid_lft); + WRITE_ONCE(ifp->prefered_lft, cfg->preferred_lft); + WRITE_ONCE(ifp->ifa_proto, cfg->ifa_proto); if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) - ifp->rt_priority = cfg->rt_priority; + WRITE_ONCE(ifp->rt_priority, cfg->rt_priority); if (new_peer) ifp->peer_addr = *cfg->peer_pfx; @@ -5069,17 +5123,21 @@ struct inet6_fill_args { enum addr_type_t type; }; -static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, +static int inet6_fill_ifaddr(struct sk_buff *skb, + const struct inet6_ifaddr *ifa, struct inet6_fill_args *args) { - struct nlmsghdr *nlh; + struct nlmsghdr *nlh; u32 preferred, valid; + u32 flags, priority; + u8 proto; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; + flags = READ_ONCE(ifa->flags); put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), ifa->idev->dev->ifindex); @@ -5087,13 +5145,14 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto error; - spin_lock_bh(&ifa->lock); - if (!((ifa->flags&IFA_F_PERMANENT) && - (ifa->prefered_lft == INFINITY_LIFE_TIME))) { - preferred = ifa->prefered_lft; - valid = ifa->valid_lft; + preferred = READ_ONCE(ifa->prefered_lft); + valid = READ_ONCE(ifa->valid_lft); + + if (!((flags & IFA_F_PERMANENT) && + (preferred == INFINITY_LIFE_TIME))) { if (preferred != INFINITY_LIFE_TIME) { - long tval = (jiffies - ifa->tstamp)/HZ; + long tval = (jiffies - READ_ONCE(ifa->tstamp)) / HZ; + if (preferred > tval) preferred -= tval; else @@ -5109,28 +5168,29 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } - spin_unlock_bh(&ifa->lock); if (!ipv6_addr_any(&ifa->peer_addr)) { if (nla_put_in6_addr(skb, IFA_LOCAL, &ifa->addr) < 0 || nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->peer_addr) < 0) goto error; - } else + } else { if (nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->addr) < 0) goto error; + } - if (ifa->rt_priority && - nla_put_u32(skb, IFA_RT_PRIORITY, ifa->rt_priority)) + priority = READ_ONCE(ifa->rt_priority); + if (priority && nla_put_u32(skb, IFA_RT_PRIORITY, priority)) goto error; - if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) + if (put_cacheinfo(skb, ifa->cstamp, READ_ONCE(ifa->tstamp), + preferred, valid) < 0) goto error; - if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) + if (nla_put_u32(skb, IFA_FLAGS, flags) < 0) goto error; - if (ifa->ifa_proto && - nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) + proto = READ_ONCE(ifa->ifa_proto); + if (proto && nla_put_u8(skb, IFA_PROTO, proto)) goto error; nlmsg_end(skb, nlh); @@ -5141,12 +5201,13 @@ error: return -EMSGSIZE; } -static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, +static int inet6_fill_ifmcaddr(struct sk_buff *skb, + const struct ifmcaddr6 *ifmca, struct inet6_fill_args *args) { - struct nlmsghdr *nlh; - u8 scope = RT_SCOPE_UNIVERSE; int ifindex = ifmca->idev->dev->ifindex; + u8 scope = RT_SCOPE_UNIVERSE; + struct nlmsghdr *nlh; if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; @@ -5164,7 +5225,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || - put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, + put_cacheinfo(skb, ifmca->mca_cstamp, READ_ONCE(ifmca->mca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -5174,13 +5235,14 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, return 0; } -static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, +static int inet6_fill_ifacaddr(struct sk_buff *skb, + const struct ifacaddr6 *ifaca, struct inet6_fill_args *args) { struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); int ifindex = dev ? dev->ifindex : 1; - struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; + struct nlmsghdr *nlh; if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; @@ -5198,7 +5260,7 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || - put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, + put_cacheinfo(skb, ifaca->aca_cstamp, READ_ONCE(ifaca->aca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -5209,24 +5271,23 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, } /* called with rcu_read_lock() */ -static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, - struct netlink_callback *cb, int s_ip_idx, +static int in6_dump_addrs(const struct inet6_dev *idev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, struct inet6_fill_args *fillargs) { - struct ifmcaddr6 *ifmca; - struct ifacaddr6 *ifaca; + const struct ifmcaddr6 *ifmca; + const struct ifacaddr6 *ifaca; int ip_idx = 0; - int err = 1; + int err = 0; - read_lock_bh(&idev->lock); switch (fillargs->type) { case UNICAST_ADDR: { - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; fillargs->event = RTM_NEWADDR; /* unicast address incl. temp addr */ - list_for_each_entry(ifa, &idev->addr_list, if_list) { - if (ip_idx < s_ip_idx) + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { + if (ip_idx < *s_ip_idx) goto next; err = inet6_fill_ifaddr(skb, ifa, fillargs); if (err < 0) @@ -5238,27 +5299,25 @@ next: break; } case MULTICAST_ADDR: - read_unlock_bh(&idev->lock); fillargs->event = RTM_GETMULTICAST; /* multicast address */ - for (ifmca = rtnl_dereference(idev->mc_list); + for (ifmca = rcu_dereference(idev->mc_list); ifmca; - ifmca = rtnl_dereference(ifmca->next), ip_idx++) { - if (ip_idx < s_ip_idx) + ifmca = rcu_dereference(ifmca->next), ip_idx++) { + if (ip_idx < *s_ip_idx) continue; err = inet6_fill_ifmcaddr(skb, ifmca, fillargs); if (err < 0) break; } - read_lock_bh(&idev->lock); break; case ANYCAST_ADDR: fillargs->event = RTM_GETANYCAST; /* anycast address */ - for (ifaca = idev->ac_list; ifaca; - ifaca = ifaca->aca_next, ip_idx++) { - if (ip_idx < s_ip_idx) + for (ifaca = rcu_dereference(idev->ac_list); ifaca; + ifaca = rcu_dereference(ifaca->aca_next), ip_idx++) { + if (ip_idx < *s_ip_idx) continue; err = inet6_fill_ifacaddr(skb, ifaca, fillargs); if (err < 0) @@ -5268,8 +5327,7 @@ next: default: break; } - read_unlock_bh(&idev->lock); - cb->args[2] = ip_idx; + *s_ip_idx = err ? ip_idx : 0; return err; } @@ -5332,6 +5390,7 @@ static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { + struct net *tgt_net = sock_net(skb->sk); const struct nlmsghdr *nlh = cb->nlh; struct inet6_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, @@ -5340,72 +5399,52 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, .netnsid = -1, .type = type, }; - struct net *tgt_net = sock_net(skb->sk); - int idx, s_idx, s_ip_idx; - int h, s_h; + struct { + unsigned long ifindex; + int ip_idx; + } *ctx = (void *)cb->ctx; struct net_device *dev; struct inet6_dev *idev; - struct hlist_head *head; int err = 0; - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - s_ip_idx = cb->args[2]; - + rcu_read_lock(); if (cb->strict_check) { err = inet6_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) - goto put_tgt_net; + goto done; err = 0; if (fillargs.ifindex) { - dev = __dev_get_by_index(tgt_net, fillargs.ifindex); - if (!dev) { - err = -ENODEV; - goto put_tgt_net; - } + err = -ENODEV; + dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); + if (!dev) + goto done; idev = __in6_dev_get(dev); - if (idev) { - err = in6_dump_addrs(idev, skb, cb, s_ip_idx, + if (idev) + err = in6_dump_addrs(idev, skb, cb, + &ctx->ip_idx, &fillargs); - if (err > 0) - err = 0; - } - goto put_tgt_net; + goto done; } } - rcu_read_lock(); cb->seq = inet6_base_seq(tgt_net); - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &tgt_net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - if (h > s_h || idx > s_idx) - s_ip_idx = 0; - idev = __in6_dev_get(dev); - if (!idev) - goto cont; - - if (in6_dump_addrs(idev, skb, cb, s_ip_idx, - &fillargs) < 0) - goto done; -cont: - idx++; - } + for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { + idev = __in6_dev_get(dev); + if (!idev) + continue; + err = in6_dump_addrs(idev, skb, cb, &ctx->ip_idx, + &fillargs); + if (err < 0) + goto done; } done: rcu_read_unlock(); - cb->args[0] = h; - cb->args[1] = idx; -put_tgt_net: if (fillargs.netnsid >= 0) put_net(tgt_net); - return skb->len ? : err; + return err; } static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) @@ -5578,87 +5617,97 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); } -static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, - __s32 *array, int bytes) +static void ipv6_store_devconf(const struct ipv6_devconf *cnf, + __s32 *array, int bytes) { BUG_ON(bytes < (DEVCONF_MAX * 4)); memset(array, 0, bytes); - array[DEVCONF_FORWARDING] = cnf->forwarding; - array[DEVCONF_HOPLIMIT] = cnf->hop_limit; - array[DEVCONF_MTU6] = cnf->mtu6; - array[DEVCONF_ACCEPT_RA] = cnf->accept_ra; - array[DEVCONF_ACCEPT_REDIRECTS] = cnf->accept_redirects; - array[DEVCONF_AUTOCONF] = cnf->autoconf; - array[DEVCONF_DAD_TRANSMITS] = cnf->dad_transmits; - array[DEVCONF_RTR_SOLICITS] = cnf->rtr_solicits; + array[DEVCONF_FORWARDING] = READ_ONCE(cnf->forwarding); + array[DEVCONF_HOPLIMIT] = READ_ONCE(cnf->hop_limit); + array[DEVCONF_MTU6] = READ_ONCE(cnf->mtu6); + array[DEVCONF_ACCEPT_RA] = READ_ONCE(cnf->accept_ra); + array[DEVCONF_ACCEPT_REDIRECTS] = READ_ONCE(cnf->accept_redirects); + array[DEVCONF_AUTOCONF] = READ_ONCE(cnf->autoconf); + array[DEVCONF_DAD_TRANSMITS] = READ_ONCE(cnf->dad_transmits); + array[DEVCONF_RTR_SOLICITS] = READ_ONCE(cnf->rtr_solicits); array[DEVCONF_RTR_SOLICIT_INTERVAL] = - jiffies_to_msecs(cnf->rtr_solicit_interval); + jiffies_to_msecs(READ_ONCE(cnf->rtr_solicit_interval)); array[DEVCONF_RTR_SOLICIT_MAX_INTERVAL] = - jiffies_to_msecs(cnf->rtr_solicit_max_interval); + jiffies_to_msecs(READ_ONCE(cnf->rtr_solicit_max_interval)); array[DEVCONF_RTR_SOLICIT_DELAY] = - jiffies_to_msecs(cnf->rtr_solicit_delay); - array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version; + jiffies_to_msecs(READ_ONCE(cnf->rtr_solicit_delay)); + array[DEVCONF_FORCE_MLD_VERSION] = READ_ONCE(cnf->force_mld_version); array[DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL] = - jiffies_to_msecs(cnf->mldv1_unsolicited_report_interval); + jiffies_to_msecs(READ_ONCE(cnf->mldv1_unsolicited_report_interval)); array[DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL] = - jiffies_to_msecs(cnf->mldv2_unsolicited_report_interval); - array[DEVCONF_USE_TEMPADDR] = cnf->use_tempaddr; - array[DEVCONF_TEMP_VALID_LFT] = cnf->temp_valid_lft; - array[DEVCONF_TEMP_PREFERED_LFT] = cnf->temp_prefered_lft; - array[DEVCONF_REGEN_MAX_RETRY] = cnf->regen_max_retry; - array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; - array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; - array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; - array[DEVCONF_RA_DEFRTR_METRIC] = cnf->ra_defrtr_metric; - array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit; - array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; + jiffies_to_msecs(READ_ONCE(cnf->mldv2_unsolicited_report_interval)); + array[DEVCONF_USE_TEMPADDR] = READ_ONCE(cnf->use_tempaddr); + array[DEVCONF_TEMP_VALID_LFT] = READ_ONCE(cnf->temp_valid_lft); + array[DEVCONF_TEMP_PREFERED_LFT] = READ_ONCE(cnf->temp_prefered_lft); + array[DEVCONF_REGEN_MAX_RETRY] = READ_ONCE(cnf->regen_max_retry); + array[DEVCONF_MAX_DESYNC_FACTOR] = READ_ONCE(cnf->max_desync_factor); + array[DEVCONF_MAX_ADDRESSES] = READ_ONCE(cnf->max_addresses); + array[DEVCONF_ACCEPT_RA_DEFRTR] = READ_ONCE(cnf->accept_ra_defrtr); + array[DEVCONF_RA_DEFRTR_METRIC] = READ_ONCE(cnf->ra_defrtr_metric); + array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = + READ_ONCE(cnf->accept_ra_min_hop_limit); + array[DEVCONF_ACCEPT_RA_PINFO] = READ_ONCE(cnf->accept_ra_pinfo); #ifdef CONFIG_IPV6_ROUTER_PREF - array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref; + array[DEVCONF_ACCEPT_RA_RTR_PREF] = READ_ONCE(cnf->accept_ra_rtr_pref); array[DEVCONF_RTR_PROBE_INTERVAL] = - jiffies_to_msecs(cnf->rtr_probe_interval); + jiffies_to_msecs(READ_ONCE(cnf->rtr_probe_interval)); #ifdef CONFIG_IPV6_ROUTE_INFO - array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen; - array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen; + array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = + READ_ONCE(cnf->accept_ra_rt_info_min_plen); + array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = + READ_ONCE(cnf->accept_ra_rt_info_max_plen); #endif #endif - array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp; - array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route; + array[DEVCONF_PROXY_NDP] = READ_ONCE(cnf->proxy_ndp); + array[DEVCONF_ACCEPT_SOURCE_ROUTE] = + READ_ONCE(cnf->accept_source_route); #ifdef CONFIG_IPV6_OPTIMISTIC_DAD - array[DEVCONF_OPTIMISTIC_DAD] = cnf->optimistic_dad; - array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic; + array[DEVCONF_OPTIMISTIC_DAD] = READ_ONCE(cnf->optimistic_dad); + array[DEVCONF_USE_OPTIMISTIC] = READ_ONCE(cnf->use_optimistic); #endif #ifdef CONFIG_IPV6_MROUTE array[DEVCONF_MC_FORWARDING] = atomic_read(&cnf->mc_forwarding); #endif - array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; - array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; - array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; - array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify; - array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; - array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; - array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu; - array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = cnf->ignore_routes_with_linkdown; + array[DEVCONF_DISABLE_IPV6] = READ_ONCE(cnf->disable_ipv6); + array[DEVCONF_ACCEPT_DAD] = READ_ONCE(cnf->accept_dad); + array[DEVCONF_FORCE_TLLAO] = READ_ONCE(cnf->force_tllao); + array[DEVCONF_NDISC_NOTIFY] = READ_ONCE(cnf->ndisc_notify); + array[DEVCONF_SUPPRESS_FRAG_NDISC] = + READ_ONCE(cnf->suppress_frag_ndisc); + array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = + READ_ONCE(cnf->accept_ra_from_local); + array[DEVCONF_ACCEPT_RA_MTU] = READ_ONCE(cnf->accept_ra_mtu); + array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = + READ_ONCE(cnf->ignore_routes_with_linkdown); /* we omit DEVCONF_STABLE_SECRET for now */ - array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; - array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; - array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; - array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; - array[DEVCONF_SEG6_ENABLED] = cnf->seg6_enabled; + array[DEVCONF_USE_OIF_ADDRS_ONLY] = READ_ONCE(cnf->use_oif_addrs_only); + array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = + READ_ONCE(cnf->drop_unicast_in_l2_multicast); + array[DEVCONF_DROP_UNSOLICITED_NA] = READ_ONCE(cnf->drop_unsolicited_na); + array[DEVCONF_KEEP_ADDR_ON_DOWN] = READ_ONCE(cnf->keep_addr_on_down); + array[DEVCONF_SEG6_ENABLED] = READ_ONCE(cnf->seg6_enabled); #ifdef CONFIG_IPV6_SEG6_HMAC - array[DEVCONF_SEG6_REQUIRE_HMAC] = cnf->seg6_require_hmac; + array[DEVCONF_SEG6_REQUIRE_HMAC] = READ_ONCE(cnf->seg6_require_hmac); #endif - array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; - array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; - array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; - array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass; - array[DEVCONF_RPL_SEG_ENABLED] = cnf->rpl_seg_enabled; - array[DEVCONF_IOAM6_ENABLED] = cnf->ioam6_enabled; - array[DEVCONF_IOAM6_ID] = cnf->ioam6_id; - array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; - array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; - array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na; - array[DEVCONF_ACCEPT_RA_MIN_LFT] = cnf->accept_ra_min_lft; + array[DEVCONF_ENHANCED_DAD] = READ_ONCE(cnf->enhanced_dad); + array[DEVCONF_ADDR_GEN_MODE] = READ_ONCE(cnf->addr_gen_mode); + array[DEVCONF_DISABLE_POLICY] = READ_ONCE(cnf->disable_policy); + array[DEVCONF_NDISC_TCLASS] = READ_ONCE(cnf->ndisc_tclass); + array[DEVCONF_RPL_SEG_ENABLED] = READ_ONCE(cnf->rpl_seg_enabled); + array[DEVCONF_IOAM6_ENABLED] = READ_ONCE(cnf->ioam6_enabled); + array[DEVCONF_IOAM6_ID] = READ_ONCE(cnf->ioam6_id); + array[DEVCONF_IOAM6_ID_WIDE] = READ_ONCE(cnf->ioam6_id_wide); + array[DEVCONF_NDISC_EVICT_NOCARRIER] = + READ_ONCE(cnf->ndisc_evict_nocarrier); + array[DEVCONF_ACCEPT_UNTRACKED_NA] = + READ_ONCE(cnf->accept_untracked_na); + array[DEVCONF_ACCEPT_RA_MIN_LFT] = READ_ONCE(cnf->accept_ra_min_lft); } static inline size_t inet6_ifla6_size(void) @@ -5738,13 +5787,14 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, u32 ext_filter_mask) { - struct nlattr *nla; struct ifla_cacheinfo ci; + struct nlattr *nla; + u32 ra_mtu; - if (nla_put_u32(skb, IFLA_INET6_FLAGS, idev->if_flags)) + if (nla_put_u32(skb, IFLA_INET6_FLAGS, READ_ONCE(idev->if_flags))) goto nla_put_failure; ci.max_reasm_len = IPV6_MAXPLEN; - ci.tstamp = cstamp_delta(idev->tstamp); + ci.tstamp = cstamp_delta(READ_ONCE(idev->tstamp)); ci.reachable_time = jiffies_to_msecs(idev->nd_parms->reachable_time); ci.retrans_time = jiffies_to_msecs(NEIGH_VAR(idev->nd_parms, RETRANS_TIME)); if (nla_put(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci)) @@ -5776,11 +5826,12 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, memcpy(nla_data(nla), idev->token.s6_addr, nla_len(nla)); read_unlock_bh(&idev->lock); - if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->cnf.addr_gen_mode)) + if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, + READ_ONCE(idev->cnf.addr_gen_mode))) goto nla_put_failure; - if (idev->ra_mtu && - nla_put_u32(skb, IFLA_INET6_RA_MTU, idev->ra_mtu)) + ra_mtu = READ_ONCE(idev->ra_mtu); + if (ra_mtu && nla_put_u32(skb, IFLA_INET6_RA_MTU, ra_mtu)) goto nla_put_failure; return 0; @@ -5842,7 +5893,7 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token, return -EINVAL; } - if (idev->cnf.rtr_solicits == 0) { + if (READ_ONCE(idev->cnf.rtr_solicits) == 0) { NL_SET_ERR_MSG(extack, "Router solicitation is disabled on device"); return -EINVAL; @@ -5875,7 +5926,7 @@ update_lft: if (update_rs) { idev->if_flags |= IF_RS_SENT; idev->rs_interval = rfc3315_s14_backoff_init( - idev->cnf.rtr_solicit_interval); + READ_ONCE(idev->cnf.rtr_solicit_interval)); idev->rs_probes = 1; addrconf_mod_rs_timer(idev, idev->rs_interval); } @@ -5981,7 +6032,7 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla, if (tb[IFLA_INET6_ADDR_GEN_MODE]) { u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); - idev->cnf.addr_gen_mode = mode; + WRITE_ONCE(idev->cnf.addr_gen_mode, mode); } return 0; @@ -5993,6 +6044,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, struct net_device *dev = idev->dev; struct ifinfomsg *hdr; struct nlmsghdr *nlh; + int ifindex, iflink; void *protoinfo; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); @@ -6003,18 +6055,20 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, hdr->ifi_family = AF_INET6; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; - hdr->ifi_index = dev->ifindex; + ifindex = READ_ONCE(dev->ifindex); + hdr->ifi_index = ifindex; hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; + iflink = dev_get_iflink(dev); if (nla_put_string(skb, IFLA_IFNAME, dev->name) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || - nla_put_u32(skb, IFLA_MTU, dev->mtu) || - (dev->ifindex != dev_get_iflink(dev) && - nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) || + nla_put_u32(skb, IFLA_MTU, READ_ONCE(dev->mtu)) || + (ifindex != iflink && + nla_put_u32(skb, IFLA_LINK, iflink)) || nla_put_u8(skb, IFLA_OPERSTATE, - netif_running(dev) ? dev->operstate : IF_OPER_DOWN)) + netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN)) goto nla_put_failure; protoinfo = nla_nest_start_noflag(skb, IFLA_PROTINFO); if (!protoinfo) @@ -6060,50 +6114,39 @@ static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh, static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - int h, s_h; - int idx = 0, s_idx; + struct { + unsigned long ifindex; + } *ctx = (void *)cb->ctx; struct net_device *dev; struct inet6_dev *idev; - struct hlist_head *head; + int err; /* only requests using strict checking can pass data to * influence the dump */ if (cb->strict_check) { - int err = inet6_valid_dump_ifinfo(cb->nlh, cb->extack); + err = inet6_valid_dump_ifinfo(cb->nlh, cb->extack); if (err < 0) return err; } - s_h = cb->args[0]; - s_idx = cb->args[1]; - + err = 0; rcu_read_lock(); - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - idev = __in6_dev_get(dev); - if (!idev) - goto cont; - if (inet6_fill_ifinfo(skb, idev, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWLINK, NLM_F_MULTI) < 0) - goto out; -cont: - idx++; - } + for_each_netdev_dump(net, dev, ctx->ifindex) { + idev = __in6_dev_get(dev); + if (!idev) + continue; + err = inet6_fill_ifinfo(skb, idev, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWLINK, NLM_F_MULTI); + if (err < 0) + break; } -out: rcu_read_unlock(); - cb->args[1] = idx; - cb->args[0] = h; - return skb->len; + return err; } void inet6_ifinfo_notify(int event, struct inet6_dev *idev) @@ -6324,7 +6367,8 @@ static void addrconf_disable_change(struct net *net, __s32 newf) idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); - idev->cnf.disable_ipv6 = newf; + + WRITE_ONCE(idev->cnf.disable_ipv6, newf); if (changed) dev_disable_change(idev); } @@ -6333,23 +6377,22 @@ static void addrconf_disable_change(struct net *net, __s32 newf) static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) { - struct net *net; + struct net *net = (struct net *)table->extra2; int old; + if (p == &net->ipv6.devconf_dflt->disable_ipv6) { + WRITE_ONCE(*p, newf); + return 0; + } + if (!rtnl_trylock()) return restart_syscall(); - net = (struct net *)table->extra2; old = *p; - *p = newf; - - if (p == &net->ipv6.devconf_dflt->disable_ipv6) { - rtnl_unlock(); - return 0; - } + WRITE_ONCE(*p, newf); if (p == &net->ipv6.devconf_all->disable_ipv6) { - net->ipv6.devconf_dflt->disable_ipv6 = newf; + WRITE_ONCE(net->ipv6.devconf_dflt->disable_ipv6, newf); addrconf_disable_change(net, newf); } else if ((!newf) ^ (!old)) dev_disable_change((struct inet6_dev *)table->extra1); @@ -6460,24 +6503,25 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, } if (idev->cnf.addr_gen_mode != new_val) { - idev->cnf.addr_gen_mode = new_val; + WRITE_ONCE(idev->cnf.addr_gen_mode, new_val); addrconf_init_auto_addrs(idev->dev); } } else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) { struct net_device *dev; - net->ipv6.devconf_dflt->addr_gen_mode = new_val; + WRITE_ONCE(net->ipv6.devconf_dflt->addr_gen_mode, new_val); for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev && idev->cnf.addr_gen_mode != new_val) { - idev->cnf.addr_gen_mode = new_val; + WRITE_ONCE(idev->cnf.addr_gen_mode, + new_val); addrconf_init_auto_addrs(idev->dev); } } } - *((u32 *)ctl->data) = new_val; + WRITE_ONCE(*((u32 *)ctl->data), new_val); } out: @@ -6536,14 +6580,15 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, struct inet6_dev *idev = __in6_dev_get(dev); if (idev) { - idev->cnf.addr_gen_mode = - IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + WRITE_ONCE(idev->cnf.addr_gen_mode, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY); } } } else { struct inet6_dev *idev = ctl->extra1; - idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + WRITE_ONCE(idev->cnf.addr_gen_mode, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY); } out: @@ -6623,20 +6668,19 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) static int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val) { + struct net *net = (struct net *)ctl->extra2; struct inet6_dev *idev; - struct net *net; - if (!rtnl_trylock()) - return restart_syscall(); - - *valp = val; - - net = (struct net *)ctl->extra2; if (valp == &net->ipv6.devconf_dflt->disable_policy) { - rtnl_unlock(); + WRITE_ONCE(*valp, val); return 0; } + if (!rtnl_trylock()) + return restart_syscall(); + + WRITE_ONCE(*valp, val); + if (valp == &net->ipv6.devconf_all->disable_policy) { struct net_device *dev; @@ -6806,6 +6850,13 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, { + .procname = "regen_min_advance", + .data = &ipv6_devconf.regen_min_advance, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "regen_max_retry", .data = &ipv6_devconf.regen_max_retry, .maxlen = sizeof(int), @@ -7365,7 +7416,8 @@ int __init addrconf_init(void) if (err < 0) goto out_addrlabel; - addrconf_wq = create_workqueue("ipv6_addrconf"); + /* All works using addrconf_wq need to lock rtnl. */ + addrconf_wq = create_singlethread_workqueue("ipv6_addrconf"); if (!addrconf_wq) { err = -ENOMEM; goto out_nowq; @@ -7388,7 +7440,7 @@ int __init addrconf_init(void) rtnl_af_register(&inet6_ops); err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETLINK, - NULL, inet6_dump_ifinfo, 0); + NULL, inet6_dump_ifinfo, RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; @@ -7402,21 +7454,25 @@ int __init addrconf_init(void) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, inet6_dump_ifaddr, - RTNL_FLAG_DOIT_UNLOCKED); + RTNL_FLAG_DOIT_UNLOCKED | + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETMULTICAST, - NULL, inet6_dump_ifmcaddr, 0); + NULL, inet6_dump_ifmcaddr, + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETANYCAST, - NULL, inet6_dump_ifacaddr, 0); + NULL, inet6_dump_ifacaddr, + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, inet6_netconf_dump_devconf, - RTNL_FLAG_DOIT_UNLOCKED); + RTNL_FLAG_DOIT_UNLOCKED | + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = ipv6_addr_label_rtnl_register(); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 959bfd9f6344..8041dc181bd4 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -64,6 +64,7 @@ #include <net/xfrm.h> #include <net/ioam6.h> #include <net/rawv6.h> +#include <net/rps.h> #include <linux/uaccess.h> #include <linux/mroute6.h> @@ -736,7 +737,7 @@ const struct proto_ops inet6_dgram_ops = { .recvmsg = inet6_recvmsg, /* retpoline's sake */ .read_skb = udp_read_skb, .mmap = sock_no_mmap, - .set_peek_off = sk_set_peek_off, + .set_peek_off = udp_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index bb17f484ee2c..0f2506e35359 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -296,7 +296,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) goto out; } - for (aca = idev->ac_list; aca; aca = aca->aca_next) { + for (aca = rtnl_dereference(idev->ac_list); aca; + aca = rtnl_dereference(aca->aca_next)) { if (ipv6_addr_equal(&aca->aca_addr, addr)) { aca->aca_users++; err = 0; @@ -317,13 +318,13 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) goto out; } - aca->aca_next = idev->ac_list; - idev->ac_list = aca; - /* Hold this for addrconf_join_solict() below before we unlock, * it is already exposed via idev->ac_list. */ aca_get(aca); + aca->aca_next = idev->ac_list; + rcu_assign_pointer(idev->ac_list, aca); + write_unlock_bh(&idev->lock); ipv6_add_acaddr_hash(net, aca); @@ -350,7 +351,8 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) write_lock_bh(&idev->lock); prev_aca = NULL; - for (aca = idev->ac_list; aca; aca = aca->aca_next) { + for (aca = rtnl_dereference(idev->ac_list); aca; + aca = rtnl_dereference(aca->aca_next)) { if (ipv6_addr_equal(&aca->aca_addr, addr)) break; prev_aca = aca; @@ -364,9 +366,9 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) return 0; } if (prev_aca) - prev_aca->aca_next = aca->aca_next; + rcu_assign_pointer(prev_aca->aca_next, aca->aca_next); else - idev->ac_list = aca->aca_next; + rcu_assign_pointer(idev->ac_list, aca->aca_next); write_unlock_bh(&idev->lock); ipv6_del_acaddr_hash(aca); addrconf_leave_solict(idev, &aca->aca_addr); @@ -392,8 +394,8 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev) struct ifacaddr6 *aca; write_lock_bh(&idev->lock); - while ((aca = idev->ac_list) != NULL) { - idev->ac_list = aca->aca_next; + while ((aca = rtnl_dereference(idev->ac_list)) != NULL) { + rcu_assign_pointer(idev->ac_list, aca->aca_next); write_unlock_bh(&idev->lock); ipv6_del_acaddr_hash(aca); @@ -420,11 +422,10 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad idev = __in6_dev_get(dev); if (idev) { - read_lock_bh(&idev->lock); - for (aca = idev->ac_list; aca; aca = aca->aca_next) + for (aca = rcu_dereference(idev->ac_list); aca; + aca = rcu_dereference(aca->aca_next)) if (ipv6_addr_equal(&aca->aca_addr, addr)) break; - read_unlock_bh(&idev->lock); return aca != NULL; } return false; @@ -477,30 +478,25 @@ bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, struct ac6_iter_state { struct seq_net_private p; struct net_device *dev; - struct inet6_dev *idev; }; #define ac6_seq_private(seq) ((struct ac6_iter_state *)(seq)->private) static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) { - struct ifacaddr6 *im = NULL; struct ac6_iter_state *state = ac6_seq_private(seq); struct net *net = seq_file_net(seq); + struct ifacaddr6 *im = NULL; - state->idev = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; + idev = __in6_dev_get(state->dev); if (!idev) continue; - read_lock_bh(&idev->lock); - im = idev->ac_list; - if (im) { - state->idev = idev; + im = rcu_dereference(idev->ac_list); + if (im) break; - } - read_unlock_bh(&idev->lock); } return im; } @@ -508,22 +504,17 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im) { struct ac6_iter_state *state = ac6_seq_private(seq); + struct inet6_dev *idev; - im = im->aca_next; + im = rcu_dereference(im->aca_next); while (!im) { - if (likely(state->idev != NULL)) - read_unlock_bh(&state->idev->lock); - state->dev = next_net_device_rcu(state->dev); - if (!state->dev) { - state->idev = NULL; + if (!state->dev) break; - } - state->idev = __in6_dev_get(state->dev); - if (!state->idev) + idev = __in6_dev_get(state->dev); + if (!idev) continue; - read_lock_bh(&state->idev->lock); - im = state->idev->ac_list; + im = rcu_dereference(idev->ac_list); } return im; } @@ -555,12 +546,6 @@ static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ac6_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { - struct ac6_iter_state *state = ac6_seq_private(seq); - - if (likely(state->idev != NULL)) { - read_unlock_bh(&state->idev->lock); - state->idev = NULL; - } rcu_read_unlock(); } diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 1578ed9e97d8..eb8ee1e9373a 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -657,11 +657,8 @@ static int calipso_map_cat_ntoh(const struct calipso_doi *doi_def, net_clen_bits, spot + 1, 1); - if (spot < 0) { - if (spot == -2) - return -EFAULT; + if (spot < 0) return 0; - } ret_val = netlbl_catmap_setbit(&secattr->attr.mls.cat, spot, diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 02e9ffb63af1..6789623b2b0d 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -50,6 +50,7 @@ #endif #include <net/rpl.h> #include <linux/ioam6.h> +#include <linux/ioam6_genl.h> #include <net/ioam6.h> #include <net/dst_metadata.h> @@ -378,9 +379,8 @@ static int ipv6_srh_rcv(struct sk_buff *skb) idev = __in6_dev_get(skb->dev); - accept_seg6 = net->ipv6.devconf_all->seg6_enabled; - if (accept_seg6 > idev->cnf.seg6_enabled) - accept_seg6 = idev->cnf.seg6_enabled; + accept_seg6 = min(READ_ONCE(net->ipv6.devconf_all->seg6_enabled), + READ_ONCE(idev->cnf.seg6_enabled)); if (!accept_seg6) { kfree_skb(skb); @@ -654,10 +654,13 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) struct ipv6_rt_hdr *hdr; struct rt0_hdr *rthdr; struct net *net = dev_net(skb->dev); - int accept_source_route = net->ipv6.devconf_all->accept_source_route; + int accept_source_route; - if (idev && accept_source_route > idev->cnf.accept_source_route) - accept_source_route = idev->cnf.accept_source_route; + accept_source_route = READ_ONCE(net->ipv6.devconf_all->accept_source_route); + + if (idev) + accept_source_route = min(accept_source_route, + READ_ONCE(idev->cnf.accept_source_route)); if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + @@ -801,7 +804,7 @@ looped_back: ip6_route_input(skb); if (skb_dst(skb)->error) { - skb_push(skb, skb->data - skb_network_header(skb)); + skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; } @@ -818,7 +821,7 @@ looped_back: goto looped_back; } - skb_push(skb, skb->data - skb_network_header(skb)); + skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; @@ -880,14 +883,6 @@ void ipv6_exthdrs_exit(void) Hop-by-hop options. **********************************/ -/* - * Note: we cannot rely on skb_dst(skb) before we assign it in ip6_route_input(). - */ -static inline struct net *ipv6_skb_net(struct sk_buff *skb) -{ - return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev); -} - /* Router Alert as of RFC 2711 */ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) @@ -918,7 +913,7 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) goto drop; /* Ignore if IOAM is not enabled on ingress */ - if (!__in6_dev_get(skb->dev)->cnf.ioam6_enabled) + if (!READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_enabled)) goto ignore; /* Truncated Option header */ @@ -938,7 +933,7 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) goto drop; /* Ignore if the IOAM namespace is unknown */ - ns = ioam6_namespace(ipv6_skb_net(skb), trace->namespace_id); + ns = ioam6_namespace(dev_net(skb->dev), trace->namespace_id); if (!ns) goto ignore; @@ -954,6 +949,9 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) + optoff + sizeof(*hdr)); ioam6_fill_trace_data(skb, ns, trace, true); + + ioam6_event(IOAM6_EVENT_TRACE, dev_net(skb->dev), + GFP_ATOMIC, (void *)trace, hdr->opt_len - 2); break; default: break; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 7523c4baef35..52c04f0ac498 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -449,6 +449,11 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) + nla_total_size(16); /* src */ } +static void fib6_rule_flush_cache(struct fib_rules_ops *ops) +{ + rt_genid_bump_ipv6(ops->fro_net); +} + static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .family = AF_INET6, .rule_size = sizeof(struct fib6_rule), @@ -461,6 +466,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .compare = fib6_rule_compare, .fill = fib6_rule_fill, .nlmsg_payload = fib6_rule_nlmsg_payload, + .flush_cache = fib6_rule_flush_cache, .nlgroup = RTNLGRP_IPV6_RULE, .owner = THIS_MODULE, .fro_net = &init_net, diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b0e8d278e8a9..2e81383b663b 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -14,6 +14,7 @@ #include <linux/random.h> #include <net/addrconf.h> +#include <net/hotdata.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> @@ -25,16 +26,13 @@ u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) { - static u32 inet6_ehash_secret __read_mostly; - static u32 ipv6_hash_secret __read_mostly; - u32 lhash, fhash; net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret)); - net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); + net_get_random_once(&tcp_ipv6_hash_secret, sizeof(tcp_ipv6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; - fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret); + fhash = __ipv6_addr_jhash(faddr, tcp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, inet6_ehash_secret + net_hash_mix(net)); diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c index 571f0e4d9cf3..08c929513065 100644 --- a/net/ipv6/ioam6.c +++ b/net/ipv6/ioam6.c @@ -612,6 +612,68 @@ static const struct genl_ops ioam6_genl_ops[] = { }, }; +#define IOAM6_GENL_EV_GRP_OFFSET 0 + +static const struct genl_multicast_group ioam6_mcgrps[] = { + [IOAM6_GENL_EV_GRP_OFFSET] = { .name = IOAM6_GENL_EV_GRP_NAME, + .flags = GENL_MCAST_CAP_NET_ADMIN }, +}; + +static int ioam6_event_put_trace(struct sk_buff *skb, + struct ioam6_trace_hdr *trace, + unsigned int len) +{ + if (nla_put_u16(skb, IOAM6_EVENT_ATTR_TRACE_NAMESPACE, + be16_to_cpu(trace->namespace_id)) || + nla_put_u8(skb, IOAM6_EVENT_ATTR_TRACE_NODELEN, trace->nodelen) || + nla_put_u32(skb, IOAM6_EVENT_ATTR_TRACE_TYPE, + be32_to_cpu(trace->type_be32)) || + nla_put(skb, IOAM6_EVENT_ATTR_TRACE_DATA, + len - sizeof(struct ioam6_trace_hdr) - trace->remlen * 4, + trace->data + trace->remlen * 4)) + return 1; + + return 0; +} + +void ioam6_event(enum ioam6_event_type type, struct net *net, gfp_t gfp, + void *opt, unsigned int opt_len) +{ + struct nlmsghdr *nlh; + struct sk_buff *skb; + + if (!genl_has_listeners(&ioam6_genl_family, net, + IOAM6_GENL_EV_GRP_OFFSET)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); + if (!skb) + return; + + nlh = genlmsg_put(skb, 0, 0, &ioam6_genl_family, 0, type); + if (!nlh) + goto nla_put_failure; + + switch (type) { + case IOAM6_EVENT_UNSPEC: + WARN_ON_ONCE(1); + break; + case IOAM6_EVENT_TRACE: + if (ioam6_event_put_trace(skb, (struct ioam6_trace_hdr *)opt, + opt_len)) + goto nla_put_failure; + break; + } + + genlmsg_end(skb, nlh); + genlmsg_multicast_netns(&ioam6_genl_family, net, skb, 0, + IOAM6_GENL_EV_GRP_OFFSET, gfp); + return; + +nla_put_failure: + nlmsg_free(skb); +} + static struct genl_family ioam6_genl_family __ro_after_init = { .name = IOAM6_GENL_NAME, .version = IOAM6_GENL_VERSION, @@ -620,6 +682,8 @@ static struct genl_family ioam6_genl_family __ro_after_init = { .ops = ioam6_genl_ops, .n_ops = ARRAY_SIZE(ioam6_genl_ops), .resv_start_op = IOAM6_CMD_NS_SET_SCHEMA + 1, + .mcgrps = ioam6_mcgrps, + .n_mcgrps = ARRAY_SIZE(ioam6_mcgrps), .module = THIS_MODULE, }; @@ -663,7 +727,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (!skb->dev) raw16 = IOAM6_U16_UNAVAILABLE; else - raw16 = (__force u16)__in6_dev_get(skb->dev)->cnf.ioam6_id; + raw16 = (__force u16)READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_id); *(__be16 *)data = cpu_to_be16(raw16); data += sizeof(__be16); @@ -671,7 +735,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) raw16 = IOAM6_U16_UNAVAILABLE; else - raw16 = (__force u16)__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id; + raw16 = (__force u16)READ_ONCE(__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id); *(__be16 *)data = cpu_to_be16(raw16); data += sizeof(__be16); @@ -758,7 +822,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (!skb->dev) raw32 = IOAM6_U32_UNAVAILABLE; else - raw32 = __in6_dev_get(skb->dev)->cnf.ioam6_id_wide; + raw32 = READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_id_wide); *(__be32 *)data = cpu_to_be32(raw32); data += sizeof(__be32); @@ -766,7 +830,7 @@ static void __ioam6_fill_trace_data(struct sk_buff *skb, if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) raw32 = IOAM6_U32_UNAVAILABLE; else - raw32 = __in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id_wide; + raw32 = READ_ONCE(__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id_wide); *(__be32 *)data = cpu_to_be32(raw32); data += sizeof(__be32); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 4fc2cae0d116..5c558dc1c683 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -160,6 +160,8 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); + INIT_HLIST_NODE(&f6i->gc_link); + return f6i; } @@ -246,6 +248,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); + INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; @@ -617,8 +620,11 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { - struct rt6_rtnl_dump_arg arg = { .filter.dump_exceptions = true, - .filter.dump_routes = true }; + struct rt6_rtnl_dump_arg arg = { + .filter.dump_exceptions = true, + .filter.dump_routes = true, + .filter.rtnl_held = true, + }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int h, s_h; @@ -751,8 +757,6 @@ static struct fib6_node *fib6_add_1(struct net *net, int bit; __be32 dir = 0; - RT6_TRACE("fib6_add_1\n"); - /* insert node in tree */ fn = root; @@ -1057,6 +1061,9 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, lockdep_is_held(&table->tb6_lock)); } } + + fib6_clean_expires(rt); + fib6_remove_gc_list(rt); } /* @@ -1117,10 +1124,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, rt->fib6_nsiblings = 0; if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; - if (!(rt->fib6_flags & RTF_EXPIRES)) + if (!(rt->fib6_flags & RTF_EXPIRES)) { fib6_clean_expires(iter); - else + fib6_remove_gc_list(iter); + } else { fib6_set_expires(iter, rt->expires); + fib6_add_gc_list(iter); + } if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, @@ -1479,6 +1489,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); + + if (rt->fib6_flags & RTF_EXPIRES) + fib6_add_gc_list(rt); + fib6_start_gc(info->nl_net, rt); } @@ -1803,7 +1817,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_fn_leaf; - RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); + pr_debug("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); @@ -1866,7 +1880,8 @@ static struct fib6_node *fib6_repair_tree(struct net *net, FOR_WALKERS(net, w) { if (!child) { if (w->node == fn) { - RT6_TRACE("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); + pr_debug("W %p adjusted by delnode 1, s=%d/%d\n", + w, w->state, nstate); w->node = pn; w->state = nstate; } @@ -1874,10 +1889,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net, if (w->node == fn) { w->node = child; if (children&2) { - RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); + pr_debug("W %p adjusted by delnode 2, s=%d\n", + w, w->state); w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { - RT6_TRACE("W %p adjusted by delnode 2, s=%d\n", w, w->state); + pr_debug("W %p adjusted by delnode 2, s=%d\n", + w, w->state); w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } @@ -1905,8 +1922,6 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, struct net *net = info->nl_net; bool notify_del = false; - RT6_TRACE("fib6_del_route\n"); - /* If the deleted route is the first in the node and it is not part of * a multipath route, then we need to replace it with the next route * in the node, if exists. @@ -1955,7 +1970,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { - RT6_TRACE("walker %p adjusted by delroute\n", w); + pr_debug("walker %p adjusted by delroute\n", w); w->leaf = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); if (!w->leaf) @@ -2281,9 +2296,8 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -static int fib6_age(struct fib6_info *rt, void *arg) +static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { - struct fib6_gc_args *gc_args = arg; unsigned long now = jiffies; /* @@ -2293,7 +2307,7 @@ static int fib6_age(struct fib6_info *rt, void *arg) if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { if (time_after(now, rt->expires)) { - RT6_TRACE("expiring %p\n", rt); + pr_debug("expiring %p\n", rt); return -1; } gc_args->more++; @@ -2308,6 +2322,42 @@ static int fib6_age(struct fib6_info *rt, void *arg) return 0; } +static void fib6_gc_table(struct net *net, + struct fib6_table *tb6, + struct fib6_gc_args *gc_args) +{ + struct fib6_info *rt; + struct hlist_node *n; + struct nl_info info = { + .nl_net = net, + .skip_notify = false, + }; + + hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) + if (fib6_age(rt, gc_args) == -1) + fib6_del(rt, &info); +} + +static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) +{ + struct fib6_table *table; + struct hlist_head *head; + unsigned int h; + + rcu_read_lock(); + for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { + head = &net->ipv6.fib_table_hash[h]; + hlist_for_each_entry_rcu(table, head, tb6_hlist) { + spin_lock_bh(&table->tb6_lock); + + fib6_gc_table(net, table, gc_args); + + spin_unlock_bh(&table->tb6_lock); + } + } + rcu_read_unlock(); +} + void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; @@ -2323,7 +2373,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = 0; - fib6_clean_all(net, fib6_age, &gc_args); + fib6_gc_all(net, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; @@ -2383,6 +2433,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); + INIT_HLIST_HEAD(&net->ipv6.fib6_main_tbl->tb6_gc_hlist); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), @@ -2395,6 +2446,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); + INIT_HLIST_HEAD(&net->ipv6.fib6_local_tbl->tb6_gc_hlist); #endif fib6_tables_init(net); @@ -2444,10 +2496,8 @@ int __init fib6_init(void) { int ret = -ENOMEM; - fib6_node_kmem = kmem_cache_create("fib6_nodes", - sizeof(struct fib6_node), 0, - SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, - NULL); + fib6_node_kmem = KMEM_CACHE(fib6_node, + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT); if (!fib6_node_kmem) goto out; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 070d87abf7c0..5e97e0aa8e07 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1511,6 +1511,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) ip6gre_tnl_init_features(dev); netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_lockdep_set_classes(dev); return 0; cleanup_dst_cache_init: @@ -1632,21 +1633,19 @@ err_alloc_dev: return err; } -static void __net_exit ip6gre_exit_batch_net(struct list_head *net_list) +static void __net_exit ip6gre_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) - ip6gre_destroy_tunnels(net, &list); - unregister_netdevice_many(&list); - rtnl_unlock(); + ip6gre_destroy_tunnels(net, dev_to_kill); } static struct pernet_operations ip6gre_net_ops = { .init = ip6gre_init_net, - .exit_batch = ip6gre_exit_batch_net, + .exit_batch_rtnl = ip6gre_exit_batch_rtnl, .id = &ip6gre_net_id, .size = sizeof(struct ip6gre_net), }; @@ -1903,6 +1902,7 @@ static int ip6erspan_tap_init(struct net_device *dev) ip6erspan_tnl_link_config(tunnel, 1); netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_lockdep_set_classes(dev); return 0; cleanup_dst_cache_init: diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index b8378814532c..133610a49da6 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -168,9 +168,9 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, SKB_DR_SET(reason, NOT_SPECIFIED); if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL || - !idev || unlikely(idev->cnf.disable_ipv6)) { + !idev || unlikely(READ_ONCE(idev->cnf.disable_ipv6))) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); - if (idev && unlikely(idev->cnf.disable_ipv6)) + if (idev && unlikely(READ_ONCE(idev->cnf.disable_ipv6))) SKB_DR_SET(reason, IPV6DISABLED); goto drop; } @@ -236,7 +236,7 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, if (!ipv6_addr_is_multicast(&hdr->daddr) && (skb->pkt_type == PACKET_BROADCAST || skb->pkt_type == PACKET_MULTICAST) && - idev->cnf.drop_unicast_in_l2_multicast) { + READ_ONCE(idev->cnf.drop_unicast_in_l2_multicast)) { SKB_DR_SET(reason, UNICAST_IN_L2_MULTICAST); goto err; } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index cca64c7809be..b41e35af69ea 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -419,14 +419,6 @@ static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff) return inet_gro_complete(skb, nhoff); } -static struct packet_offload ipv6_packet_offload __read_mostly = { - .type = cpu_to_be16(ETH_P_IPV6), - .callbacks = { - .gso_segment = ipv6_gso_segment, - .gro_receive = ipv6_gro_receive, - .gro_complete = ipv6_gro_complete, - }, -}; static struct sk_buff *sit_gso_segment(struct sk_buff *skb, netdev_features_t features) @@ -486,7 +478,15 @@ static int __init ipv6_offload_init(void) if (ipv6_exthdrs_offload_init() < 0) pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); - dev_add_offload(&ipv6_packet_offload); + net_hotdata.ipv6_packet_offload = (struct packet_offload) { + .type = cpu_to_be16(ETH_P_IPV6), + .callbacks = { + .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = ipv6_gro_complete, + }, + }; + dev_add_offload(&net_hotdata.ipv6_packet_offload); inet_add_offload(&sit_offload, IPPROTO_IPV6); inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 31b86fe661aa..02eeca5492cd 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -234,7 +234,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; - if (unlikely(idev->cnf.disable_ipv6)) { + if (unlikely(READ_ONCE(idev->cnf.disable_ipv6))) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED); return 0; @@ -501,7 +501,7 @@ int ip6_forward(struct sk_buff *skb) u32 mtu; idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); - if (net->ipv6.devconf_all->forwarding == 0) + if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) goto error; if (skb->pkt_type != PACKET_HOST) @@ -513,8 +513,8 @@ int ip6_forward(struct sk_buff *skb) if (skb_warn_if_lro(skb)) goto drop; - if (!net->ipv6.devconf_all->disable_policy && - (!idev || !idev->cnf.disable_policy) && + if (!READ_ONCE(net->ipv6.devconf_all->disable_policy) && + (!idev || !READ_ONCE(idev->cnf.disable_policy)) && !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; @@ -552,7 +552,7 @@ int ip6_forward(struct sk_buff *skb) } /* XXX: idev->cnf.proxy_ndp? */ - if (net->ipv6.devconf_all->proxy_ndp && + if (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); if (proxied > 0) { @@ -1925,7 +1925,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = cork->base.mark; skb->tstamp = cork->base.transmit_time; - + skb->mono_delivery_time = !!skb->tstamp; ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9bbabf750a21..e9cc315832cb 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -247,7 +247,6 @@ static void ip6_dev_free(struct net_device *dev) gro_cells_destroy(&t->gro_cells); dst_cache_destroy(&t->dst_cache); - free_percpu(dev->tstats); } static int ip6_tnl_create2(struct net_device *dev) @@ -1756,7 +1755,7 @@ int ip6_tnl_get_iflink(const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - return t->parms.link; + return READ_ONCE(t->parms.link); } EXPORT_SYMBOL(ip6_tnl_get_iflink); @@ -1848,6 +1847,7 @@ static void ip6_tnl_dev_setup(struct net_device *dev) dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->features |= NETIF_F_LLTX; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); dev->features |= IPXIPX_FEATURES; @@ -1873,13 +1873,10 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t->dev = dev; t->net = dev_net(dev); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; ret = dst_cache_init(&t->dst_cache, GFP_KERNEL); if (ret) - goto free_stats; + return ret; ret = gro_cells_init(&t->gro_cells, dev); if (ret) @@ -1898,13 +1895,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev) dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); + netdev_lockdep_set_classes(dev); return 0; destroy_dst: dst_cache_destroy(&t->dst_cache); -free_stats: - free_percpu(dev->tstats); - dev->tstats = NULL; return ret; } @@ -2282,21 +2277,19 @@ err_alloc_dev: return err; } -static void __net_exit ip6_tnl_exit_batch_net(struct list_head *net_list) +static void __net_exit ip6_tnl_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) - ip6_tnl_destroy_tunnels(net, &list); - unregister_netdevice_many(&list); - rtnl_unlock(); + ip6_tnl_destroy_tunnels(net, dev_to_kill); } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, - .exit_batch = ip6_tnl_exit_batch_net, + .exit_batch_rtnl = ip6_tnl_exit_batch_rtnl, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), }; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index e550240c85e1..7f4f976aa24a 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -935,6 +935,7 @@ static inline int vti6_dev_init_gen(struct net_device *dev) if (!dev->tstats) return -ENOMEM; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); + netdev_lockdep_set_classes(dev); return 0; } @@ -1174,24 +1175,22 @@ err_alloc_dev: return err; } -static void __net_exit vti6_exit_batch_net(struct list_head *net_list) +static void __net_exit vti6_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { struct vti6_net *ip6n; struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) { ip6n = net_generic(net, vti6_net_id); - vti6_destroy_tunnels(ip6n, &list); + vti6_destroy_tunnels(ip6n, dev_to_kill); } - unregister_netdevice_many(&list); - rtnl_unlock(); } static struct pernet_operations vti6_net_ops = { .init = vti6_init_net, - .exit_batch = vti6_exit_batch_net, + .exit_batch_rtnl = vti6_exit_batch_rtnl, .id = &vti6_net_id, .size = sizeof(struct vti6_net), }; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 9782c180fee6..cb0ee81a068a 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1373,10 +1373,7 @@ int __init ip6_mr_init(void) { int err; - mrt_cachep = kmem_cache_create("ip6_mrt_cache", - sizeof(struct mfc6_cache), - 0, SLAB_HWCACHE_ALIGN, - NULL); + mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN); if (!mrt_cachep) return -ENOMEM; @@ -2595,7 +2592,9 @@ static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; - struct fib_dump_filter filter = {}; + struct fib_dump_filter filter = { + .rtnl_held = true, + }; int err; if (cb->strict_check) { diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 56c3c467f9de..d4c28ec1bc51 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -948,6 +948,8 @@ done: if (optlen < sizeof(int)) goto e_inval; retv = ip6_ra_control(sk, val); + if (retv == 0) + inet6_assign_bit(RTALERT, sk, valbool); break; case IPV6_FLOWLABEL_MGR: retv = ipv6_flowlabel_opt(sk, optval, optlen); @@ -1346,7 +1348,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, } if (val < 0) - val = sock_net(sk)->ipv6.devconf_all->hop_limit; + val = READ_ONCE(sock_net(sk)->ipv6.devconf_all->hop_limit); break; } @@ -1445,6 +1447,10 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->rxopt.bits.recvfragsize; break; + case IPV6_ROUTER_ALERT: + val = inet6_test_bit(RTALERT, sk); + break; + case IPV6_ROUTER_ALERT_ISOLATE: val = inet6_test_bit(RTALERT_ISOLATE, sk); break; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index bc6e0a0bad3c..7ba01d8cfbae 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -159,9 +159,9 @@ static int unsolicited_report_interval(struct inet6_dev *idev) int iv; if (mld_in_v1_mode(idev)) - iv = idev->cnf.mldv1_unsolicited_report_interval; + iv = READ_ONCE(idev->cnf.mldv1_unsolicited_report_interval); else - iv = idev->cnf.mldv2_unsolicited_report_interval; + iv = READ_ONCE(idev->cnf.mldv2_unsolicited_report_interval); return iv > 0 ? iv : 1; } @@ -1202,15 +1202,15 @@ static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, static int mld_force_mld_version(const struct inet6_dev *idev) { + const struct net *net = dev_net(idev->dev); + int all_force; + + all_force = READ_ONCE(net->ipv6.devconf_all->force_mld_version); /* Normally, both are 0 here. If enforcement to a particular is * being used, individual device enforcement will have a lower * precedence over 'all' device (.../conf/all/force_mld_version). */ - - if (dev_net(idev->dev)->ipv6.devconf_all->force_mld_version != 0) - return dev_net(idev->dev)->ipv6.devconf_all->force_mld_version; - else - return idev->cnf.force_mld_version; + return all_force ?: READ_ONCE(idev->cnf.force_mld_version); } static bool mld_in_v2_mode_only(const struct inet6_dev *idev) @@ -2719,7 +2719,6 @@ void ipv6_mc_down(struct inet6_dev *idev) /* Should stop work after group drop. or we will * start work again in mld_ifc_event() */ - synchronize_net(); mld_query_stop_work(idev); mld_report_stop_work(idev); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index a19999b30bc0..ae134634c323 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -451,7 +451,7 @@ static void ip6_nd_hdr(struct sk_buff *skb, rcu_read_lock(); idev = __in6_dev_get(skb->dev); - tclass = idev ? idev->cnf.ndisc_tclass : 0; + tclass = idev ? READ_ONCE(idev->cnf.ndisc_tclass) : 0; rcu_read_unlock(); skb_push(skb, sizeof(*hdr)); @@ -535,7 +535,7 @@ void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) override = false; - inc_opt |= ifp->idev->cnf.force_tllao; + inc_opt |= READ_ONCE(ifp->idev->cnf.force_tllao); in6_ifa_put(ifp); } else { if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, @@ -903,8 +903,9 @@ have_ifp: } if (ipv6_chk_acast_addr(net, dev, &msg->target) || - (idev->cnf.forwarding && - (net->ipv6.devconf_all->proxy_ndp || idev->cnf.proxy_ndp) && + (READ_ONCE(idev->cnf.forwarding) && + (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) || + READ_ONCE(idev->cnf.proxy_ndp)) && (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && @@ -929,7 +930,7 @@ have_ifp: } if (is_router < 0) - is_router = idev->cnf.forwarding; + is_router = READ_ONCE(idev->cnf.forwarding); if (dad) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target, @@ -973,7 +974,7 @@ static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr) { struct inet6_dev *idev = __in6_dev_get(dev); - switch (idev->cnf.accept_untracked_na) { + switch (READ_ONCE(idev->cnf.accept_untracked_na)) { case 0: /* Don't accept untracked na (absent in neighbor cache) */ return 0; case 1: /* Create new entries from na if currently untracked */ @@ -1024,7 +1025,7 @@ static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) * drop_unsolicited_na takes precedence over accept_untracked_na */ if (!msg->icmph.icmp6_solicited && idev && - idev->cnf.drop_unsolicited_na) + READ_ONCE(idev->cnf.drop_unsolicited_na)) return reason; if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) @@ -1080,7 +1081,7 @@ static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) * Note that we don't do a (daddr == all-routers-mcast) check. */ new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE; - if (!neigh && lladdr && idev && idev->cnf.forwarding) { + if (!neigh && lladdr && idev && READ_ONCE(idev->cnf.forwarding)) { if (accept_untracked_na(dev, saddr)) { neigh = neigh_create(&nd_tbl, &msg->target, dev); new_state = NUD_STALE; @@ -1100,7 +1101,8 @@ static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) * has already sent a NA to us. */ if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && - net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp && + READ_ONCE(net->ipv6.devconf_all->forwarding) && + READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { /* XXX: idev->cnf.proxy_ndp */ goto out; @@ -1148,7 +1150,7 @@ static enum skb_drop_reason ndisc_recv_rs(struct sk_buff *skb) } /* Don't accept RS if we're not in router mode */ - if (!idev->cnf.forwarding) + if (!READ_ONCE(idev->cnf.forwarding)) goto out; /* @@ -1237,6 +1239,7 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) struct ndisc_options ndopts; struct fib6_info *rt = NULL; struct inet6_dev *in6_dev; + struct fib6_table *table; u32 defrtr_usr_metric; unsigned int pref = 0; __u32 old_if_flags; @@ -1317,7 +1320,7 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) if (old_if_flags != in6_dev->if_flags) send_ifinfo_notify = true; - if (!in6_dev->cnf.accept_ra_defrtr) { + if (!READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) { ND_PRINTK(2, info, "RA: %s, defrtr is false for dev: %s\n", __func__, skb->dev->name); @@ -1325,7 +1328,8 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) } lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); - if (lifetime != 0 && lifetime < in6_dev->cnf.accept_ra_min_lft) { + if (lifetime != 0 && + lifetime < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) { ND_PRINTK(2, info, "RA: router lifetime (%ds) is too short: %s\n", lifetime, skb->dev->name); @@ -1336,7 +1340,7 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) * accept_ra_from_local is set to true. */ net = dev_net(in6_dev->dev); - if (!in6_dev->cnf.accept_ra_from_local && + if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: default router ignored\n", @@ -1348,7 +1352,7 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ if (pref == ICMPV6_ROUTER_PREF_INVALID || - !in6_dev->cnf.accept_ra_rtr_pref) + !READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref)) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif /* routes added from RAs do not use nexthop objects */ @@ -1382,7 +1386,8 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) neigh_release(neigh); rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, - skb->dev, pref, defrtr_usr_metric); + skb->dev, pref, defrtr_usr_metric, + lifetime); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", @@ -1409,12 +1414,21 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE); } - if (rt) + if (rt) { + table = rt->fib6_table; + spin_lock_bh(&table->tb6_lock); + fib6_set_expires(rt, jiffies + (HZ * lifetime)); - if (in6_dev->cnf.accept_ra_min_hop_limit < 256 && + fib6_add_gc_list(rt); + + spin_unlock_bh(&table->tb6_lock); + } + if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) < 256 && ra_msg->icmph.icmp6_hop_limit) { - if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) { - in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + if (READ_ONCE(in6_dev->cnf.accept_ra_min_hop_limit) <= + ra_msg->icmph.icmp6_hop_limit) { + WRITE_ONCE(in6_dev->cnf.hop_limit, + ra_msg->icmph.icmp6_hop_limit); fib6_metric_set(rt, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); } else { @@ -1496,7 +1510,7 @@ skip_linkparms: } #ifdef CONFIG_IPV6_ROUTE_INFO - if (!in6_dev->cnf.accept_ra_from_local && + if (!READ_ONCE(in6_dev->cnf.accept_ra_from_local) && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, @@ -1505,7 +1519,7 @@ skip_linkparms: goto skip_routeinfo; } - if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { + if (READ_ONCE(in6_dev->cnf.accept_ra_rtr_pref) && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_ri; p; @@ -1517,14 +1531,14 @@ skip_linkparms: continue; #endif if (ri->prefix_len == 0 && - !in6_dev->cnf.accept_ra_defrtr) + !READ_ONCE(in6_dev->cnf.accept_ra_defrtr)) continue; if (ri->lifetime != 0 && - ntohl(ri->lifetime) < in6_dev->cnf.accept_ra_min_lft) + ntohl(ri->lifetime) < READ_ONCE(in6_dev->cnf.accept_ra_min_lft)) continue; - if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen) + if (ri->prefix_len < READ_ONCE(in6_dev->cnf.accept_ra_rt_info_min_plen)) continue; - if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) + if (ri->prefix_len > READ_ONCE(in6_dev->cnf.accept_ra_rt_info_max_plen)) continue; rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, &ipv6_hdr(skb)->saddr); @@ -1544,7 +1558,7 @@ skip_routeinfo: } #endif - if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) { + if (READ_ONCE(in6_dev->cnf.accept_ra_pinfo) && ndopts.nd_opts_pi) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_pi; p; @@ -1555,7 +1569,7 @@ skip_routeinfo: } } - if (ndopts.nd_opts_mtu && in6_dev->cnf.accept_ra_mtu) { + if (ndopts.nd_opts_mtu && READ_ONCE(in6_dev->cnf.accept_ra_mtu)) { __be32 n; u32 mtu; @@ -1569,8 +1583,8 @@ skip_routeinfo: if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); - } else if (in6_dev->cnf.mtu6 != mtu) { - in6_dev->cnf.mtu6 = mtu; + } else if (READ_ONCE(in6_dev->cnf.mtu6) != mtu) { + WRITE_ONCE(in6_dev->cnf.mtu6, mtu); fib6_metric_set(rt, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } @@ -1804,7 +1818,7 @@ static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) if (!idev) return true; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED && - idev->cnf.suppress_frag_ndisc) { + READ_ONCE(idev->cnf.suppress_frag_ndisc)) { net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n"); return true; } @@ -1881,8 +1895,8 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, idev = in6_dev_get(dev); if (!idev) break; - if (idev->cnf.ndisc_notify || - net->ipv6.devconf_all->ndisc_notify) + if (READ_ONCE(idev->cnf.ndisc_notify) || + READ_ONCE(net->ipv6.devconf_all->ndisc_notify)) ndisc_send_unsol_na(dev); in6_dev_put(idev); break; @@ -1891,8 +1905,8 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, if (!idev) evict_nocarrier = true; else { - evict_nocarrier = idev->cnf.ndisc_evict_nocarrier && - net->ipv6.devconf_all->ndisc_evict_nocarrier; + evict_nocarrier = READ_ONCE(idev->cnf.ndisc_evict_nocarrier) && + READ_ONCE(net->ipv6.devconf_all->ndisc_evict_nocarrier); in6_dev_put(idev); } @@ -1966,7 +1980,7 @@ int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void *buffer, if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)) idev->nd_parms->reachable_time = neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)); - idev->tstamp = jiffies; + WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); } diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 0ba62f4868f9..f3c8e2d918e1 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -6,6 +6,10 @@ menu "IPv6: Netfilter Configuration" depends on INET && IPV6 && NETFILTER +# old sockopt interface and eval loop +config IP6_NF_IPTABLES_LEGACY + tristate + config NF_SOCKET_IPV6 tristate "IPv6 socket lookup support" help @@ -147,7 +151,7 @@ config IP6_NF_MATCH_MH config IP6_NF_MATCH_RPFILTER tristate '"rpfilter" reverse path filter match support' depends on NETFILTER_ADVANCED - depends on IP6_NF_MANGLE || IP6_NF_RAW + depends on IP6_NF_MANGLE || IP6_NF_RAW || NFT_COMPAT help This option allows you to match packets whose replies would go out via the interface the packet came in. @@ -186,6 +190,8 @@ config IP6_NF_TARGET_HL config IP6_NF_FILTER tristate "Packet filtering" default m if NETFILTER_ADVANCED=n + select IP6_NF_IPTABLES_LEGACY + tristate help Packet filtering defines a table `filter', which has a series of rules for simple packet filtering at local input, forwarding and @@ -195,7 +201,7 @@ config IP6_NF_FILTER config IP6_NF_TARGET_REJECT tristate "REJECT target support" - depends on IP6_NF_FILTER + depends on IP6_NF_FILTER || NFT_COMPAT select NF_REJECT_IPV6 default m if NETFILTER_ADVANCED=n help @@ -221,6 +227,7 @@ config IP6_NF_TARGET_SYNPROXY config IP6_NF_MANGLE tristate "Packet mangling" default m if NETFILTER_ADVANCED=n + select IP6_NF_IPTABLES_LEGACY help This option adds a `mangle' table to iptables: see the man page for iptables(8). This table is used for various packet alterations @@ -230,6 +237,7 @@ config IP6_NF_MANGLE config IP6_NF_RAW tristate 'raw table support (required for TRACE)' + select IP6_NF_IPTABLES_LEGACY help This option adds a `raw' table to ip6tables. This table is the very first in the netfilter framework and hooks in at the PREROUTING @@ -243,6 +251,7 @@ config IP6_NF_SECURITY tristate "Security table" depends on SECURITY depends on NETFILTER_ADVANCED + select IP6_NF_IPTABLES_LEGACY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. @@ -254,6 +263,7 @@ config IP6_NF_NAT depends on NF_CONNTRACK depends on NETFILTER_ADVANCED select NF_NAT + select IP6_NF_IPTABLES_LEGACY select NETFILTER_XT_NAT help This enables the `nat' table in ip6tables. This allows masquerading, @@ -262,25 +272,23 @@ config IP6_NF_NAT To compile it as a module, choose M here. If unsure, say N. -if IP6_NF_NAT - config IP6_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" select NETFILTER_XT_TARGET_MASQUERADE + depends on IP6_NF_NAT help This is a backwards-compat option for the user's convenience (e.g. when running oldconfig). It selects NETFILTER_XT_TARGET_MASQUERADE. config IP6_NF_TARGET_NPT tristate "NPT (Network Prefix translation) target support" + depends on IP6_NF_NAT || NFT_COMPAT help This option adds the `SNPT' and `DNPT' target, which perform stateless IPv6-to-IPv6 Network Prefix Translation per RFC 6296. To compile it as a module, choose M here. If unsure, say N. -endif # IP6_NF_NAT - endif # IP6_NF_IPTABLES endmenu diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index b8d6dc9aeeb6..66ce6fa5b2f5 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -4,7 +4,7 @@ # # Link order matters here. -obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o +obj-$(CONFIG_IP6_NF_IPTABLES_LEGACY) += ip6_tables.o obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b2dd48911c8d..1a51a44571c3 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -327,9 +327,9 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, if (!reasm_data) goto err; - payload_len = ((skb->data - skb_network_header(skb)) - + payload_len = -skb_network_offset(skb) - sizeof(struct ipv6hdr) + fq->q.len - - sizeof(struct frag_hdr)); + sizeof(struct frag_hdr); if (payload_len > IPV6_MAXPLEN) { net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", payload_len); diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 196dd4ecb5e2..dedee264b8f6 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -83,7 +83,7 @@ struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net, skb_reserve(nskb, LL_MAX_HEADER); nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, - net->ipv6.devconf_all->hop_limit); + READ_ONCE(net->ipv6.devconf_all->hop_limit)); nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen); nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr)); @@ -124,7 +124,7 @@ struct sk_buff *nf_reject_skb_v6_unreach(struct net *net, skb_reserve(nskb, LL_MAX_HEADER); nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6, - net->ipv6.devconf_all->hop_limit); + READ_ONCE(net->ipv6.devconf_all->hop_limit)); skb_reset_transport_header(nskb); icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr)); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index b5205311f372..806d4b5dd1e6 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -111,9 +111,9 @@ int ip6_dst_hoplimit(struct dst_entry *dst) rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) - hoplimit = idev->cnf.hop_limit; + hoplimit = READ_ONCE(idev->cnf.hop_limit); else - hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit; + hoplimit = READ_ONCE(dev_net(dev)->ipv6.devconf_all->hop_limit); rcu_read_unlock(); } return hoplimit; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 03dbb874c363..ca49e6617afa 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -160,6 +160,13 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) if (!raw_v6_match(net, sk, nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb))) continue; + + if (atomic_read(&sk->sk_rmem_alloc) >= + READ_ONCE(sk->sk_rcvbuf)) { + atomic_inc(&sk->sk_drops); + continue; + } + delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: @@ -288,8 +295,7 @@ out: } static void rawv6_err(struct sock *sk, struct sk_buff *skb, - struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { bool recverr = inet6_test_bit(RECVERR6, sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -344,7 +350,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, if (!raw_v6_match(net, sk, nexthdr, &ip6h->saddr, &ip6h->daddr, inet6_iif(skb), inet6_iif(skb))) continue; - rawv6_err(sk, skb, NULL, type, code, inner_offset, info); + rawv6_err(sk, skb, type, code, inner_offset, info); } rcu_read_unlock(); } @@ -616,7 +622,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; - + skb->mono_delivery_time = !!skb->tstamp; skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); @@ -935,7 +941,7 @@ do_confirm: goto done; } -static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, +static int rawv6_seticmpfilter(struct sock *sk, int optname, sockptr_t optval, int optlen) { switch (optname) { @@ -952,7 +958,7 @@ static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, return 0; } -static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, +static int rawv6_geticmpfilter(struct sock *sk, int optname, char __user *optval, int __user *optlen) { int len; @@ -1038,7 +1044,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; - return rawv6_seticmpfilter(sk, level, optname, optval, optlen); + return rawv6_seticmpfilter(sk, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) @@ -1099,7 +1105,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; - return rawv6_geticmpfilter(sk, level, optname, optval, optlen); + return rawv6_geticmpfilter(sk, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 5ebc47da1000..acb4f119e11f 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -272,9 +272,9 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, if (!reasm_data) goto out_oom; - payload_len = ((skb->data - skb_network_header(skb)) - + payload_len = -skb_network_offset(skb) - sizeof(struct ipv6hdr) + fq->q.len - - sizeof(struct frag_hdr)); + sizeof(struct frag_hdr); if (payload_len > IPV6_MAXPLEN) goto out_oversize; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ef815ba583a8..1f4b935a0e57 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -645,14 +645,15 @@ static void rt6_probe(struct fib6_nh *fib6_nh) write_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, - neigh->updated + idev->cnf.rtr_probe_interval)) { + neigh->updated + + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) __neigh_set_probe_once(neigh); } write_unlock_bh(&neigh->lock); } else if (time_after(jiffies, last_probe + - idev->cnf.rtr_probe_interval)) { + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); } @@ -931,6 +932,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, struct net *net = dev_net(dev); struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; + struct fib6_table *table; unsigned int pref; unsigned long lifetime; struct fib6_info *rt; @@ -989,10 +991,18 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { - if (!addrconf_finite_timeout(lifetime)) + table = rt->fib6_table; + spin_lock_bh(&table->tb6_lock); + + if (!addrconf_finite_timeout(lifetime)) { fib6_clean_expires(rt); - else + fib6_remove_gc_list(rt); + } else { fib6_set_expires(rt, jiffies + HZ * lifetime); + fib6_add_gc_list(rt); + } + + spin_unlock_bh(&table->tb6_lock); fib6_info_release(rt); } @@ -1587,7 +1597,7 @@ static unsigned int fib6_mtu(const struct fib6_result *res) rcu_read_lock(); idev = __in6_dev_get(dev); - mtu = idev->cnf.mtu6; + mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); } @@ -2085,12 +2095,12 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, */ if (!(rt->rt6i_flags & RTF_EXPIRES)) { if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { - RT6_TRACE("aging clone %p\n", rt); + pr_debug("aging clone %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } else if (time_after(jiffies, rt->dst.expires)) { - RT6_TRACE("purging expired route %p\n", rt); + pr_debug("purging expired route %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } @@ -2101,8 +2111,8 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (!(neigh && (neigh->flags & NTF_ROUTER))) { - RT6_TRACE("purging route %p via non-router but gateway\n", - rt); + pr_debug("purging route %p via non-router but gateway\n", + rt); rt6_remove_exception(bucket, rt6_ex); return; } @@ -2211,7 +2221,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, strict |= flags & RT6_LOOKUP_F_IFACE; strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE; - if (net->ipv6.devconf_all->forwarding == 0) + if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) strict |= RT6_LOOKUP_F_REACHABLE; rcu_read_lock(); @@ -3240,8 +3250,8 @@ u32 ip6_mtu_from_fib6(const struct fib6_result *res, mtu = IPV6_MIN_MTU; idev = __in6_dev_get(dev); - if (idev && idev->cnf.mtu6 > mtu) - mtu = idev->cnf.mtu6; + if (idev) + mtu = max_t(u32, mtu, READ_ONCE(idev->cnf.mtu6)); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); @@ -3765,8 +3775,6 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, if (cfg->fc_flags & RTF_EXPIRES) fib6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); - else - fib6_clean_expires(rt); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; @@ -4142,7 +4150,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) return; - if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_redirects) + if (READ_ONCE(in6_dev->cnf.forwarding) || + !READ_ONCE(in6_dev->cnf.accept_redirects)) return; /* RFC2461 8.1: @@ -4355,7 +4364,8 @@ struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, - u32 defrtr_usr_metric) + u32 defrtr_usr_metric, + int lifetime) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, @@ -4368,6 +4378,7 @@ struct fib6_info *rt6_add_dflt_router(struct net *net, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, + .fc_expires = jiffies_to_clock_t(lifetime * HZ), }; cfg.fc_gateway = *gwaddr; @@ -4574,8 +4585,8 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net, f6i->dst_nocount = true; if (!anycast && - (net->ipv6.devconf_all->disable_policy || - idev->cnf.disable_policy)) + (READ_ONCE(net->ipv6.devconf_all->disable_policy) || + READ_ONCE(idev->cnf.disable_policy))) f6i->dst_nopolicy = true; } diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index d43c50a7310d..861e0366f549 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -241,6 +241,7 @@ bool seg6_hmac_validate_skb(struct sk_buff *skb) struct sr6_tlv_hmac *tlv; struct ipv6_sr_hdr *srh; struct inet6_dev *idev; + int require_hmac; idev = __in6_dev_get(skb->dev); @@ -248,16 +249,17 @@ bool seg6_hmac_validate_skb(struct sk_buff *skb) tlv = seg6_get_tlv_hmac(srh); + require_hmac = READ_ONCE(idev->cnf.seg6_require_hmac); /* mandatory check but no tlv */ - if (idev->cnf.seg6_require_hmac > 0 && !tlv) + if (require_hmac > 0 && !tlv) return false; /* no check */ - if (idev->cnf.seg6_require_hmac < 0) + if (require_hmac < 0) return true; /* check only if present */ - if (idev->cnf.seg6_require_hmac == 0 && !tlv) + if (require_hmac == 0 && !tlv) return true; /* now, seg6_require_hmac >= 0 && tlv */ diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 5e9f625b76e3..655c9b1a19b8 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1398,7 +1398,6 @@ static const struct net_device_ops ipip6_netdev_ops = { .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, .ndo_siocdevprivate = ipip6_tunnel_siocdevprivate, - .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipip6_tunnel_ctl, }; @@ -1408,7 +1407,6 @@ static void ipip6_dev_free(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); dst_cache_destroy(&tunnel->dst_cache); - free_percpu(dev->tstats); } #define SIT_FEATURES (NETIF_F_SG | \ @@ -1437,6 +1435,8 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->features |= NETIF_F_LLTX; dev->features |= SIT_FEATURES; dev->hw_features |= SIT_FEATURES; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; + } static int ipip6_tunnel_init(struct net_device *dev) @@ -1449,17 +1449,13 @@ static int ipip6_tunnel_init(struct net_device *dev) strcpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); - if (err) { - free_percpu(dev->tstats); - dev->tstats = NULL; + if (err) return err; - } + netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_lockdep_set_classes(dev); return 0; } @@ -1875,22 +1871,19 @@ err_alloc_dev: return err; } -static void __net_exit sit_exit_batch_net(struct list_head *net_list) +static void __net_exit sit_exit_batch_rtnl(struct list_head *net_list, + struct list_head *dev_to_kill) { - LIST_HEAD(list); struct net *net; - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) - sit_destroy_tunnels(net, &list); - - unregister_netdevice_many(&list); - rtnl_unlock(); + sit_destroy_tunnels(net, dev_to_kill); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, - .exit_batch = sit_exit_batch_net, + .exit_batch_rtnl = sit_exit_batch_rtnl, .id = &sit_net_id, .size = sizeof(struct sit_net), }; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index c8d2ca27220c..8bad0a44a0a6 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -177,24 +177,33 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) struct sock *ret = sk; __u8 rcv_wscale; int full_space; + SKB_DR(reason); if (!READ_ONCE(net->ipv4.sysctl_tcp_syncookies) || !th->ack || th->rst) goto out; - req = cookie_tcp_check(net, sk, skb); - if (IS_ERR(req)) - goto out; - if (!req) + if (cookie_bpf_ok(skb)) { + req = cookie_bpf_check(sk, skb); + } else { + req = cookie_tcp_check(net, sk, skb); + if (IS_ERR(req)) + goto out; + } + if (!req) { + SKB_DR_SET(reason, NO_SOCKET); goto out_drop; + } ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; - if (security_inet_conn_request(sk, skb, req)) + if (security_inet_conn_request(sk, skb, req)) { + SKB_DR_SET(reason, SECURITY_HOOK); goto out_free; + } if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || @@ -231,8 +240,10 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) security_req_classify_flow(req, flowi6_to_flowi_common(&fl6)); dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p); - if (IS_ERR(dst)) + if (IS_ERR(dst)) { + SKB_DR_SET(reason, IP_OUTNOROUTES); goto out_free; + } } req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); @@ -247,14 +258,20 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); - ireq->rcv_wscale = rcv_wscale; + if (!req->syncookie) + ireq->rcv_wscale = rcv_wscale; ireq->ecn_ok &= cookie_ecn_ok(net, dst); ret = tcp_get_cookie_sock(sk, skb, req, dst); + if (!ret) { + SKB_DR_SET(reason, NO_SOCKET); + goto out_drop; + } out: return ret; out_free: reqsk_free(req); out_drop: + kfree_skb_reason(skb, reason); return NULL; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 57b25b1fc9d9..3f4cba49e9ee 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -58,6 +58,7 @@ #include <net/timewait_sock.h> #include <net/inet_common.h> #include <net/secure_seq.h> +#include <net/hotdata.h> #include <net/busy_poll.h> #include <linux/proc_fs.h> @@ -1623,7 +1624,6 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (np->rxopt.all) opt_skb = skb_clone_and_charge_r(skb, sk); - reason = SKB_DROP_REASON_NOT_SPECIFIED; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; @@ -1653,12 +1653,12 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v6_cookie_check(sk, skb); - if (!nsk) - goto discard; - if (nsk != sk) { - if (tcp_child_process(sk, nsk, skb)) - goto reset; + if (nsk) { + reason = tcp_child_process(sk, nsk, skb); + if (reason) + goto reset; + } if (opt_skb) __kfree_skb(opt_skb); return 0; @@ -1666,7 +1666,8 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb)) + reason = tcp_rcv_state_process(sk, skb); + if (reason) goto reset; if (opt_skb) goto ipv6_pktoptions; @@ -1856,10 +1857,12 @@ process: if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); - } else if (tcp_child_process(sk, nsk, skb)) { - tcp_v6_send_reset(nsk, skb); - goto discard_and_relse; } else { + drop_reason = tcp_child_process(sk, nsk, skb); + if (drop_reason) { + tcp_v6_send_reset(nsk, skb); + goto discard_and_relse; + } sock_put(sk); return 0; } @@ -2365,11 +2368,6 @@ struct proto tcpv6_prot = { }; EXPORT_SYMBOL_GPL(tcpv6_prot); -static const struct inet6_protocol tcpv6_protocol = { - .handler = tcp_v6_rcv, - .err_handler = tcp_v6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; static struct inet_protosw tcpv6_protosw = { .type = SOCK_STREAM, @@ -2406,7 +2404,12 @@ int __init tcpv6_init(void) { int ret; - ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP); + net_hotdata.tcpv6_protocol = (struct inet6_protocol) { + .handler = tcp_v6_rcv, + .err_handler = tcp_v6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + }; + ret = inet6_add_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); if (ret) goto out; @@ -2431,7 +2434,7 @@ out_tcpv6_pernet_subsys: out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); out_tcpv6_protocol: - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); + inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); goto out; } @@ -2439,5 +2442,5 @@ void tcpv6_exit(void) { unregister_pernet_subsys(&tcpv6_net_ops); inet6_unregister_protosw(&tcpv6_protosw); - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); + inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index bf0c957e4b5e..4b07d1e6c952 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -66,15 +66,15 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, return tcp_gso_segment(skb, features); } -static const struct net_offload tcpv6_offload = { - .callbacks = { - .gso_segment = tcp6_gso_segment, - .gro_receive = tcp6_gro_receive, - .gro_complete = tcp6_gro_complete, - }, -}; int __init tcpv6_offload_init(void) { - return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); + net_hotdata.tcpv6_offload = (struct net_offload) { + .callbacks = { + .gso_segment = tcp6_gso_segment, + .gro_receive = tcp6_gro_receive, + .gro_complete = tcp6_gro_complete, + }, + }; + return inet6_add_offload(&net_hotdata.tcpv6_offload, IPPROTO_TCP); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3f2249b4cd5f..7c1e6469d091 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -79,9 +79,6 @@ u32 udp6_ehashfn(const struct net *net, const struct in6_addr *faddr, const __be16 fport) { - static u32 udp6_ehash_secret __read_mostly; - static u32 udp_ipv6_hash_secret __read_mostly; - u32 lhash, fhash; net_get_random_once(&udp6_ehash_secret, @@ -1101,11 +1098,12 @@ void udp_v6_early_demux(struct sk_buff *skb) else return; - if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) + if (!sk) return; skb->sk = sk; - skb->destructor = sock_efree; + DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); + skb->destructor = sock_pfree; dst = rcu_dereference(sk->sk_rx_dst); if (dst) @@ -1702,11 +1700,6 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname, return ipv6_getsockopt(sk, level, optname, optval, optlen); } -static const struct inet6_protocol udpv6_protocol = { - .handler = udpv6_rcv, - .err_handler = udpv6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS @@ -1803,7 +1796,12 @@ int __init udpv6_init(void) { int ret; - ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP); + net_hotdata.udpv6_protocol = (struct inet6_protocol) { + .handler = udpv6_rcv, + .err_handler = udpv6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + }; + ret = inet6_add_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); if (ret) goto out; @@ -1814,12 +1812,12 @@ out: return ret; out_udpv6_protocol: - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); goto out; } void udpv6_exit(void) { inet6_unregister_protosw(&udpv6_protosw); - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); } diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 6b95ba241ebe..312bcaeea96f 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -192,20 +192,19 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb); } -static const struct net_offload udpv6_offload = { - .callbacks = { - .gso_segment = udp6_ufo_fragment, - .gro_receive = udp6_gro_receive, - .gro_complete = udp6_gro_complete, - }, -}; - -int udpv6_offload_init(void) +int __init udpv6_offload_init(void) { - return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); + net_hotdata.udpv6_offload = (struct net_offload) { + .callbacks = { + .gso_segment = udp6_ufo_fragment, + .gro_receive = udp6_gro_receive, + .gro_complete = udp6_gro_complete, + }, + }; + return inet6_add_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } int udpv6_offload_exit(void) { - return inet6_del_offload(&udpv6_offload, IPPROTO_UDP); + return inet6_del_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 6e36e5047fba..a17d783dc7c0 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -43,7 +43,7 @@ static int xfrm6_transport_finish2(struct net *net, struct sock *sk, int xfrm6_transport_finish(struct sk_buff *skb, int async) { struct xfrm_offload *xo = xfrm_offload(skb); - int nhlen = skb->data - skb_network_header(skb); + int nhlen = -skb_network_offset(skb); skb_network_header(skb)[IP6CB(skb)->nhoff] = XFRM_MODE_SKB_CB(skb)->protocol; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f6cb94f82cc3..bf140ef781c1 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -355,10 +355,7 @@ static int __init xfrm6_tunnel_init(void) { int rv; - xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi", - sizeof(struct xfrm6_tunnel_spi), - 0, SLAB_HWCACHE_ALIGN, - NULL); + xfrm6_tunnel_spi_kmem = KMEM_CACHE(xfrm6_tunnel_spi, SLAB_HWCACHE_ALIGN); if (!xfrm6_tunnel_spi_kmem) return -ENOMEM; rv = register_pernet_subsys(&xfrm6_tunnel_net_ops); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 498a0c35b7bb..4aa1c72e6c49 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1060,13 +1060,12 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, int i; /* skip iucv_array lying in the headroom */ - iba[0].address = (u32)(addr_t)skb->data; + iba[0].address = (u32)virt_to_phys(skb->data); iba[0].length = (u32)skb_headlen(skb); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - iba[i + 1].address = - (u32)(addr_t)skb_frag_address(frag); + iba[i + 1].address = (u32)virt_to_phys(skb_frag_address(frag)); iba[i + 1].length = (u32)skb_frag_size(frag); } err = pr_iucv->message_send(iucv->path, &txmsg, @@ -1162,13 +1161,12 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, struct iucv_array *iba = (struct iucv_array *)skb->head; int i; - iba[0].address = (u32)(addr_t)skb->data; + iba[0].address = (u32)virt_to_phys(skb->data); iba[0].length = (u32)skb_headlen(skb); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - iba[i + 1].address = - (u32)(addr_t)skb_frag_address(frag); + iba[i + 1].address = (u32)virt_to_phys(skb_frag_address(frag)); iba[i + 1].length = (u32)skb_frag_size(frag); } rc = pr_iucv->message_receive(path, msg, diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index b0b3e9c5af44..5b56ae6612dd 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -286,6 +286,7 @@ static union iucv_param *iucv_param_irq[NR_CPUS]; */ static inline int __iucv_call_b2f0(int command, union iucv_param *parm) { + unsigned long reg1 = virt_to_phys(parm); int cc; asm volatile( @@ -296,7 +297,7 @@ static inline int __iucv_call_b2f0(int command, union iucv_param *parm) " srl %[cc],28\n" : [cc] "=&d" (cc), "+m" (*parm) : [reg0] "d" ((unsigned long)command), - [reg1] "d" ((unsigned long)parm) + [reg1] "d" (reg1) : "cc", "0", "1"); return cc; } @@ -1123,7 +1124,7 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, parm = iucv_param[smp_processor_id()]; memset(parm, 0, sizeof(union iucv_param)); - parm->db.ipbfadr1 = (u32)(addr_t) buffer; + parm->db.ipbfadr1 = (u32)virt_to_phys(buffer); parm->db.ipbfln1f = (u32) size; parm->db.ipmsgid = msg->id; parm->db.ippathid = path->pathid; @@ -1241,7 +1242,7 @@ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg, parm->dpl.iptrgcls = msg->class; memcpy(parm->dpl.iprmmsg, reply, min_t(size_t, size, 8)); } else { - parm->db.ipbfadr1 = (u32)(addr_t) reply; + parm->db.ipbfadr1 = (u32)virt_to_phys(reply); parm->db.ipbfln1f = (u32) size; parm->db.ippathid = path->pathid; parm->db.ipflags1 = flags; @@ -1293,7 +1294,7 @@ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg, parm->dpl.ipmsgtag = msg->tag; memcpy(parm->dpl.iprmmsg, buffer, 8); } else { - parm->db.ipbfadr1 = (u32)(addr_t) buffer; + parm->db.ipbfadr1 = (u32)virt_to_phys(buffer); parm->db.ipbfln1f = (u32) size; parm->db.ippathid = path->pathid; parm->db.ipflags1 = flags | IUCV_IPNORPY; @@ -1378,7 +1379,7 @@ int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg, parm->dpl.iptrgcls = msg->class; parm->dpl.ipsrccls = srccls; parm->dpl.ipmsgtag = msg->tag; - parm->dpl.ipbfadr2 = (u32)(addr_t) answer; + parm->dpl.ipbfadr2 = (u32)virt_to_phys(answer); parm->dpl.ipbfln2f = (u32) asize; memcpy(parm->dpl.iprmmsg, buffer, 8); } else { @@ -1387,9 +1388,9 @@ int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg, parm->db.iptrgcls = msg->class; parm->db.ipsrccls = srccls; parm->db.ipmsgtag = msg->tag; - parm->db.ipbfadr1 = (u32)(addr_t) buffer; + parm->db.ipbfadr1 = (u32)virt_to_phys(buffer); parm->db.ipbfln1f = (u32) size; - parm->db.ipbfadr2 = (u32)(addr_t) answer; + parm->db.ipbfadr2 = (u32)virt_to_phys(answer); parm->db.ipbfln2f = (u32) asize; } rc = iucv_call_b2f0(IUCV_SEND, parm); diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 1184d40167b8..2f191e50d4fc 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -627,7 +627,8 @@ retry: skb = txm->frag_skb; } - if (WARN_ON(!skb_shinfo(skb)->nr_frags)) { + if (WARN_ON(!skb_shinfo(skb)->nr_frags) || + WARN_ON_ONCE(!skb_frag_page(&skb_shinfo(skb)->frags[0]))) { ret = -EINVAL; goto out; } @@ -637,8 +638,8 @@ retry: msize += skb_frag_size(&skb_shinfo(skb)->frags[i]); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, - skb_shinfo(skb)->frags, skb_shinfo(skb)->nr_frags, - msize); + (const struct bio_vec *)skb_shinfo(skb)->frags, + skb_shinfo(skb)->nr_frags, msize); iov_iter_advance(&msg.msg_iter, txm->frag_offset); do { @@ -1152,10 +1153,11 @@ static int kcm_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case KCM_RECV_DISABLE: val = kcm->rx_disabled; @@ -1877,15 +1879,11 @@ static int __init kcm_init(void) { int err = -ENOMEM; - kcm_muxp = kmem_cache_create("kcm_mux_cache", - sizeof(struct kcm_mux), 0, - SLAB_HWCACHE_ALIGN, NULL); + kcm_muxp = KMEM_CACHE(kcm_mux, SLAB_HWCACHE_ALIGN); if (!kcm_muxp) goto fail; - kcm_psockp = kmem_cache_create("kcm_psock_cache", - sizeof(struct kcm_psock), 0, - SLAB_HWCACHE_ALIGN, NULL); + kcm_psockp = KMEM_CACHE(kcm_psock, SLAB_HWCACHE_ALIGN); if (!kcm_psockp) goto fail; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 25ca89f80414..39e487ccc468 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -100,7 +100,7 @@ static const struct net_device_ops l2tp_eth_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, }; -static struct device_type l2tpeth_type = { +static const struct device_type l2tpeth_type = { .name = "l2tpeth", }; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 9a2a9ed3ba47..970af3983d11 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -478,7 +478,7 @@ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, - sk->sk_protocol, RT_CONN_FLAGS(sk), + sk->sk_protocol, ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index f011af6601c9..6146e4e67bbb 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1356,11 +1356,11 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + err = -ENOTCONN; if (!sk->sk_user_data) goto end; diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 4406b4f8f3b9..a33884967f21 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -29,7 +29,7 @@ mac80211-y := \ spectmgmt.o \ tx.o \ key.o \ - util.o \ + util.o parse.o \ wme.o \ chan.o \ trace.o mlme.o \ diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index b8a278355e18..21d55dc539f6 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -616,7 +616,7 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, return -EINVAL; if (!pubsta->deflink.ht_cap.ht_supported && - sta->sdata->vif.bss_conf.chandef.chan->band != NL80211_BAND_6GHZ) + sta->sdata->vif.bss_conf.chanreq.oper.chan->band != NL80211_BAND_6GHZ) return -EINVAL; if (WARN_ON_ONCE(!local->ops->ampdu_action)) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 327682995c92..f03452dc716d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -886,33 +886,32 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy, { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; - int ret = 0; + struct ieee80211_chan_req chanreq = { .oper = *chandef }; + int ret; lockdep_assert_wiphy(local->hw.wiphy); - if (cfg80211_chandef_identical(&local->monitor_chandef, chandef)) + if (cfg80211_chandef_identical(&local->monitor_chanreq.oper, + &chanreq.oper)) return 0; - if (local->use_chanctx) { - sdata = wiphy_dereference(local->hw.wiphy, - local->monitor_sdata); - if (sdata) { - ieee80211_link_release_channel(&sdata->deflink); - ret = ieee80211_link_use_channel(&sdata->deflink, - chandef, - IEEE80211_CHANCTX_EXCLUSIVE); - } - } else { - if (local->open_count == local->monitors) { - local->_oper_chandef = *chandef; - ieee80211_hw_config(local, 0); - } - } + sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); + if (!sdata) + goto done; - if (ret == 0) - local->monitor_chandef = *chandef; + if (cfg80211_chandef_identical(&sdata->vif.bss_conf.chanreq.oper, + &chanreq.oper)) + return 0; - return ret; + ieee80211_link_release_channel(&sdata->deflink); + ret = ieee80211_link_use_channel(&sdata->deflink, &chanreq, + IEEE80211_CHANCTX_EXCLUSIVE); + if (ret) + return ret; +done: + local->monitor_chanreq = chanreq; + return 0; } static int @@ -953,7 +952,8 @@ ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata, struct cfg80211_fils_discovery *params, struct ieee80211_link_data *link, - struct ieee80211_bss_conf *link_conf) + struct ieee80211_bss_conf *link_conf, + u64 *changed) { struct fils_discovery_data *new, *old = NULL; struct ieee80211_fils_discovery *fd; @@ -980,7 +980,8 @@ static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata, RCU_INIT_POINTER(link->u.ap.fils_discovery, NULL); } - return BSS_CHANGED_FILS_DISCOVERY; + *changed |= BSS_CHANGED_FILS_DISCOVERY; + return 0; } static int @@ -1240,6 +1241,30 @@ ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, return 0; } +static u8 ieee80211_num_beaconing_links(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_link_data *link; + u8 link_id, num = 0; + + if (sdata->vif.type != NL80211_IFTYPE_AP && + sdata->vif.type != NL80211_IFTYPE_P2P_GO) + return num; + + if (!sdata->vif.valid_links) + return num; + + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + link = sdata_dereference(sdata->link[link_id], sdata); + if (!link) + continue; + + if (sdata_dereference(link->u.ap.beacon, sdata)) + num++; + } + + return num; +} + static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_settings *params) { @@ -1258,6 +1283,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id = params->beacon.link_id; struct ieee80211_link_data *link; struct ieee80211_bss_conf *link_conf; + struct ieee80211_chan_req chanreq = { .oper = params->chandef }; lockdep_assert_wiphy(local->hw.wiphy); @@ -1341,8 +1367,6 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, return -EOPNOTSUPP; link_conf->eht_support = true; - link_conf->eht_puncturing = params->punct_bitmap; - changed |= BSS_CHANGED_EHT_PUNCTURING; link_conf->eht_su_beamformer = params->eht_cap->fixed.phy_cap_info[0] & @@ -1370,7 +1394,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, return err; } - err = ieee80211_link_use_channel(link, ¶ms->chandef, + err = ieee80211_link_use_channel(link, &chanreq, IEEE80211_CHANCTX_SHARED); if (!err) ieee80211_link_copy_chanctx_to_vlans(link, false); @@ -1445,10 +1469,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, goto error; err = ieee80211_set_fils_discovery(sdata, ¶ms->fils_discovery, - link, link_conf); + link, link_conf, &changed); if (err < 0) goto error; - changed |= err; err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, @@ -1471,7 +1494,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, ieee80211_vif_cfg_change_notify(sdata, BSS_CHANGED_SSID); ieee80211_link_info_change_notify(sdata, link, changed); - netif_carrier_on(dev); + if (ieee80211_num_beaconing_links(sdata) <= 1) + netif_carrier_on(dev); + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_on(vlan->dev); @@ -1519,10 +1544,9 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, return err; err = ieee80211_set_fils_discovery(sdata, ¶ms->fils_discovery, - link, link_conf); + link, link_conf, &changed); if (err < 0) return err; - changed |= err; err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, @@ -1565,6 +1589,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); struct ieee80211_bss_conf *link_conf = link->conf; + LIST_HEAD(keys); lockdep_assert_wiphy(local->hw.wiphy); @@ -1582,10 +1607,10 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, /* abort any running channel switch or color change */ link_conf->csa_active = false; link_conf->color_change_active = false; - if (link->csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - link->csa_block_tx = false; + sdata->csa_blocked_tx = false; } ieee80211_free_next_beacon(link); @@ -1593,7 +1618,9 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, /* turn off carrier for this interface and dependent VLANs */ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_off(vlan->dev); - netif_carrier_off(dev); + + if (ieee80211_num_beaconing_links(sdata) <= 1) + netif_carrier_off(dev); /* remove beacon and probe response */ sdata->u.ap.active = false; @@ -1618,8 +1645,13 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, link_conf->ema_ap = false; link_conf->bssid_indicator = 0; - __sta_info_flush(sdata, true); - ieee80211_free_keys(sdata, true); + __sta_info_flush(sdata, true, link_id); + + ieee80211_remove_link_keys(link, &keys); + if (!list_empty(&keys)) { + synchronize_net(); + ieee80211_free_key_list(local, &keys); + } link_conf->enable_beacon = false; sdata->beacon_rate_set = false; @@ -1629,7 +1661,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_BEACON_ENABLED); if (sdata->wdev.cac_started) { - chandef = link_conf->chandef; + chandef = link_conf->chanreq.oper; wiphy_delayed_work_cancel(wiphy, &link->dfs_cac_timer_work); cfg80211_cac_event(sdata->dev, &chandef, NL80211_RADAR_CAC_ABORTED, @@ -1829,7 +1861,7 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, if (params->supported_rates && params->supported_rates_len) { - ieee80211_parse_bitrates(link->conf->chandef.width, + ieee80211_parse_bitrates(link->conf->chanreq.oper.width, sband, params->supported_rates, params->supported_rates_len, &link_sta->pub->supp_rates[sband->band]); @@ -1869,7 +1901,7 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, sband->band); } - ieee80211_sta_set_rx_nss(link_sta); + ieee80211_sta_init_nss(link_sta); return ret; } @@ -1944,6 +1976,9 @@ static int sta_apply_parameters(struct ieee80211_local *local, clear_sta_flag(sta, WLAN_STA_TDLS_PEER); } + if (mask & BIT(NL80211_STA_FLAG_SPP_AMSDU)) + sta->sta.spp_amsdu = set & BIT(NL80211_STA_FLAG_SPP_AMSDU); + /* mark TDLS channel switch support, if the AP allows it */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && !sdata->deflink.u.mgd.tdls_chan_switch_prohibited && @@ -2095,7 +2130,7 @@ static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, if (params->mac) return sta_info_destroy_addr_bss(sdata, params->mac); - sta_info_flush(sdata); + sta_info_flush(sdata, params->link_id); return 0; } @@ -2602,6 +2637,7 @@ static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev, const struct mesh_setup *setup) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_chan_req chanreq = { .oper = setup->chandef }; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; int err; @@ -2618,7 +2654,7 @@ static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev, sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; sdata->deflink.needed_rx_chains = sdata->local->rx_chains; - err = ieee80211_link_use_channel(&sdata->deflink, &setup->chandef, + err = ieee80211_link_use_channel(&sdata->deflink, &chanreq, IEEE80211_CHANCTX_SHARED); if (err) return err; @@ -2661,7 +2697,7 @@ static int ieee80211_change_bss(struct wiphy *wiphy, return -EINVAL; if (params->basic_rates) { - if (!ieee80211_parse_bitrates(link->conf->chandef.width, + if (!ieee80211_parse_bitrates(link->conf->chanreq.oper.width, wiphy->bands[sband->band], params->basic_rates, params->basic_rates_len, @@ -3083,7 +3119,7 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy, if (local->ops->get_txpower) return drv_get_txpower(local, sdata, dbm); - if (!local->use_chanctx) + if (local->emulate_chanctx) *dbm = local->hw.conf.power_level; else *dbm = sdata->vif.bss_conf.txpower; @@ -3153,8 +3189,7 @@ int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION)) return -EINVAL; - if (ieee80211_vif_is_mld(&sdata->vif) && - !(sdata->vif.active_links & BIT(link->link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) return 0; old_req = link->u.mgd.req_smps; @@ -3176,7 +3211,7 @@ int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, * the new value until we associate. */ if (!sdata->u.mgd.associated || - link->conf->chandef.width == NL80211_CHAN_WIDTH_20_NOHT) + link->conf->chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT) return 0; ap = sdata->vif.cfg.ap_addr; @@ -3207,7 +3242,7 @@ int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, if (err) link->u.mgd.req_smps = old_req; else if (smps_mode != IEEE80211_SMPS_OFF && tdls_peer_found) - ieee80211_teardown_tdls_peers(sdata); + ieee80211_teardown_tdls_peers(link); return err; } @@ -3254,33 +3289,57 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, return 0; } +static void ieee80211_set_cqm_rssi_link(struct ieee80211_sub_if_data *sdata, + struct ieee80211_link_data *link, + s32 rssi_thold, u32 rssi_hyst, + s32 rssi_low, s32 rssi_high) +{ + struct ieee80211_bss_conf *conf; + + if (!link || !link->conf) + return; + + conf = link->conf; + + if (rssi_thold && rssi_hyst && + rssi_thold == conf->cqm_rssi_thold && + rssi_hyst == conf->cqm_rssi_hyst) + return; + + conf->cqm_rssi_thold = rssi_thold; + conf->cqm_rssi_hyst = rssi_hyst; + conf->cqm_rssi_low = rssi_low; + conf->cqm_rssi_high = rssi_high; + link->u.mgd.last_cqm_event_signal = 0; + + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) + return; + + if (sdata->u.mgd.associated && + (sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) + ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_CQM); +} + static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy, struct net_device *dev, s32 rssi_thold, u32 rssi_hyst) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_vif *vif = &sdata->vif; - struct ieee80211_bss_conf *bss_conf = &vif->bss_conf; - - if (rssi_thold == bss_conf->cqm_rssi_thold && - rssi_hyst == bss_conf->cqm_rssi_hyst) - return 0; + int link_id; - if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER && - !(sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) + if (vif->driver_flags & IEEE80211_VIF_BEACON_FILTER && + !(vif->driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) return -EOPNOTSUPP; - bss_conf->cqm_rssi_thold = rssi_thold; - bss_conf->cqm_rssi_hyst = rssi_hyst; - bss_conf->cqm_rssi_low = 0; - bss_conf->cqm_rssi_high = 0; - sdata->deflink.u.mgd.last_cqm_event_signal = 0; + /* For MLD, handle CQM change on all the active links */ + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + struct ieee80211_link_data *link = + sdata_dereference(sdata->link[link_id], sdata); - /* tell the driver upon association, unless already associated */ - if (sdata->u.mgd.associated && - sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI) - ieee80211_link_info_change_notify(sdata, &sdata->deflink, - BSS_CHANGED_CQM); + ieee80211_set_cqm_rssi_link(sdata, link, rssi_thold, rssi_hyst, + 0, 0); + } return 0; } @@ -3291,22 +3350,19 @@ static int ieee80211_set_cqm_rssi_range_config(struct wiphy *wiphy, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_vif *vif = &sdata->vif; - struct ieee80211_bss_conf *bss_conf = &vif->bss_conf; + int link_id; - if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER) + if (vif->driver_flags & IEEE80211_VIF_BEACON_FILTER) return -EOPNOTSUPP; - bss_conf->cqm_rssi_low = rssi_low; - bss_conf->cqm_rssi_high = rssi_high; - bss_conf->cqm_rssi_thold = 0; - bss_conf->cqm_rssi_hyst = 0; - sdata->deflink.u.mgd.last_cqm_event_signal = 0; + /* For MLD, handle CQM change on all the active links */ + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + struct ieee80211_link_data *link = + sdata_dereference(sdata->link[link_id], sdata); - /* tell the driver upon association, unless already associated */ - if (sdata->u.mgd.associated && - sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI) - ieee80211_link_info_change_notify(sdata, &sdata->deflink, - BSS_CHANGED_CQM); + ieee80211_set_cqm_rssi_link(sdata, link, 0, 0, + rssi_low, rssi_high); + } return 0; } @@ -3331,9 +3387,11 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, * so at a basic rate so that all clients can receive it. */ if (rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) && - sdata->vif.bss_conf.chandef.chan) { + sdata->vif.bss_conf.chanreq.oper.chan) { u32 basic_rates = sdata->vif.bss_conf.basic_rates; - enum nl80211_band band = sdata->vif.bss_conf.chandef.chan->band; + enum nl80211_band band; + + band = sdata->vif.bss_conf.chanreq.oper.chan->band; if (!(mask->control[band].legacy & basic_rates)) return -EINVAL; @@ -3385,6 +3443,7 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy, u32 cac_time_ms) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_chan_req chanreq = { .oper = *chandef }; struct ieee80211_local *local = sdata->local; int err; @@ -3399,7 +3458,7 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy, sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; sdata->deflink.needed_rx_chains = local->rx_chains; - err = ieee80211_link_use_channel(&sdata->deflink, chandef, + err = ieee80211_link_use_channel(&sdata->deflink, &chanreq, IEEE80211_CHANCTX_SHARED); if (err) goto out_unlock; @@ -3542,13 +3601,24 @@ cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) return new_beacon; } -void ieee80211_csa_finish(struct ieee80211_vif *vif) +void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; + struct ieee80211_link_data *link_data; + + if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) + return; rcu_read_lock(); + link_data = rcu_dereference(sdata->link[link_id]); + if (WARN_ON(!link_data)) { + rcu_read_unlock(); + return; + } + + /* TODO: MBSSID with MLO changes */ if (vif->mbssid_tx_vif == vif) { /* Trigger ieee80211_csa_finish() on the non-transmitting * interfaces when channel switch is received on @@ -3567,7 +3637,7 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif) &iter->deflink.csa_finalize_work); } } - wiphy_work_queue(local->hw.wiphy, &sdata->deflink.csa_finalize_work); + wiphy_work_queue(local->hw.wiphy, &link_data->csa_finalize_work); rcu_read_unlock(); } @@ -3579,26 +3649,27 @@ void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, bool block_t struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - sdata->deflink.csa_block_tx = block_tx; + sdata->csa_blocked_tx = block_tx; sdata_info(sdata, "channel switch failed, disconnecting\n"); wiphy_work_queue(local->hw.wiphy, &ifmgd->csa_connection_drop_work); } EXPORT_SYMBOL(ieee80211_channel_switch_disconnect); -static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata, +static int ieee80211_set_after_csa_beacon(struct ieee80211_link_data *link_data, u64 *changed) { + struct ieee80211_sub_if_data *sdata = link_data->sdata; int err; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: - if (!sdata->deflink.u.ap.next_beacon) + if (!link_data->u.ap.next_beacon) return -EINVAL; - err = ieee80211_assign_beacon(sdata, &sdata->deflink, - sdata->deflink.u.ap.next_beacon, + err = ieee80211_assign_beacon(sdata, link_data, + link_data->u.ap.next_beacon, NULL, NULL, changed); - ieee80211_free_next_beacon(&sdata->deflink); + ieee80211_free_next_beacon(link_data); if (err < 0) return err; @@ -3627,6 +3698,7 @@ static int __ieee80211_csa_finalize(struct ieee80211_link_data *link_data) { struct ieee80211_sub_if_data *sdata = link_data->sdata; struct ieee80211_local *local = sdata->local; + struct ieee80211_bss_conf *link_conf = link_data->conf; u64 changed = 0; int err; @@ -3648,40 +3720,33 @@ static int __ieee80211_csa_finalize(struct ieee80211_link_data *link_data) if (link_data->reserved_ready) return 0; - return ieee80211_link_use_reserved_context(&sdata->deflink); + return ieee80211_link_use_reserved_context(link_data); } - if (!cfg80211_chandef_identical(&link_data->conf->chandef, - &link_data->csa_chandef)) + if (!cfg80211_chandef_identical(&link_conf->chanreq.oper, + &link_data->csa_chanreq.oper)) return -EINVAL; - sdata->vif.bss_conf.csa_active = false; + link_conf->csa_active = false; - err = ieee80211_set_after_csa_beacon(sdata, &changed); + err = ieee80211_set_after_csa_beacon(link_data, &changed); if (err) return err; - if (sdata->vif.bss_conf.eht_puncturing != sdata->vif.bss_conf.csa_punct_bitmap) { - sdata->vif.bss_conf.eht_puncturing = - sdata->vif.bss_conf.csa_punct_bitmap; - changed |= BSS_CHANGED_EHT_PUNCTURING; - } - ieee80211_link_info_change_notify(sdata, link_data, changed); - if (link_data->csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - link_data->csa_block_tx = false; + sdata->csa_blocked_tx = false; } err = drv_post_channel_switch(link_data); if (err) return err; - cfg80211_ch_switch_notify(sdata->dev, &link_data->csa_chandef, - link_data->link_id, - link_data->conf->eht_puncturing); + cfg80211_ch_switch_notify(sdata->dev, &link_data->csa_chanreq.oper, + link_data->link_id); return 0; } @@ -3691,7 +3756,8 @@ static void ieee80211_csa_finalize(struct ieee80211_link_data *link_data) struct ieee80211_sub_if_data *sdata = link_data->sdata; if (__ieee80211_csa_finalize(link_data)) { - sdata_info(sdata, "failed to finalize CSA, disconnecting\n"); + sdata_info(sdata, "failed to finalize CSA on link %d, disconnecting\n", + link_data->link_id); cfg80211_stop_iface(sdata->local->hw.wiphy, &sdata->wdev, GFP_KERNEL); } @@ -3716,18 +3782,19 @@ void ieee80211_csa_finalize_work(struct wiphy *wiphy, struct wiphy_work *work) ieee80211_csa_finalize(link); } -static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, +static int ieee80211_set_csa_beacon(struct ieee80211_link_data *link_data, struct cfg80211_csa_settings *params, u64 *changed) { + struct ieee80211_sub_if_data *sdata = link_data->sdata; struct ieee80211_csa_settings csa = {}; int err; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: - sdata->deflink.u.ap.next_beacon = + link_data->u.ap.next_beacon = cfg80211_beacon_dup(¶ms->beacon_after); - if (!sdata->deflink.u.ap.next_beacon) + if (!link_data->u.ap.next_beacon) return -ENOMEM; /* @@ -3753,7 +3820,7 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, IEEE80211_MAX_CNTDWN_COUNTERS_NUM) || (params->n_counter_offsets_presp > IEEE80211_MAX_CNTDWN_COUNTERS_NUM)) { - ieee80211_free_next_beacon(&sdata->deflink); + ieee80211_free_next_beacon(link_data); return -EINVAL; } @@ -3763,11 +3830,11 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, csa.n_counter_offsets_presp = params->n_counter_offsets_presp; csa.count = params->count; - err = ieee80211_assign_beacon(sdata, &sdata->deflink, + err = ieee80211_assign_beacon(sdata, link_data, ¶ms->beacon_csa, &csa, NULL, changed); if (err < 0) { - ieee80211_free_next_beacon(&sdata->deflink); + ieee80211_free_next_beacon(link_data); return err; } @@ -3814,7 +3881,7 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; /* changes into another band are not supported */ - if (sdata->vif.bss_conf.chandef.chan->band != + if (sdata->vif.bss_conf.chanreq.oper.chan->band != params->chandef.chan->band) return -EINVAL; @@ -3862,11 +3929,17 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_chan_req chanreq = { .oper = params->chandef }; struct ieee80211_local *local = sdata->local; - struct ieee80211_channel_switch ch_switch; + struct ieee80211_channel_switch ch_switch = { + .link_id = params->link_id, + }; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *chanctx; + struct ieee80211_bss_conf *link_conf; + struct ieee80211_link_data *link_data; u64 changed = 0; + u8 link_id = params->link_id; int err; lockdep_assert_wiphy(local->hw.wiphy); @@ -3877,16 +3950,23 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, if (sdata->wdev.cac_started) return -EBUSY; - if (cfg80211_chandef_identical(¶ms->chandef, - &sdata->vif.bss_conf.chandef)) + if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) + return -EINVAL; + + link_data = wiphy_dereference(wiphy, sdata->link[link_id]); + if (!link_data) + return -ENOLINK; + + link_conf = link_data->conf; + + if (chanreq.oper.punctured && !link_conf->eht_support) return -EINVAL; /* don't allow another channel switch if one is already active. */ - if (sdata->vif.bss_conf.csa_active) + if (link_conf->csa_active) return -EBUSY; - conf = rcu_dereference_protected(sdata->vif.bss_conf.chanctx_conf, - lockdep_is_held(&local->hw.wiphy->mtx)); + conf = wiphy_dereference(wiphy, link_conf->chanctx_conf); if (!conf) { err = -EBUSY; goto out; @@ -3903,14 +3983,14 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, ch_switch.timestamp = 0; ch_switch.device_timestamp = 0; ch_switch.block_tx = params->block_tx; - ch_switch.chandef = params->chandef; + ch_switch.chandef = chanreq.oper; ch_switch.count = params->count; err = drv_pre_channel_switch(sdata, &ch_switch); if (err) goto out; - err = ieee80211_link_reserve_chanctx(&sdata->deflink, ¶ms->chandef, + err = ieee80211_link_reserve_chanctx(link_data, &chanreq, chanctx->mode, params->radar_required); if (err) @@ -3919,44 +3999,40 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, /* if reservation is invalid then this will fail */ err = ieee80211_check_combinations(sdata, NULL, chanctx->mode, 0); if (err) { - ieee80211_link_unreserve_chanctx(&sdata->deflink); + ieee80211_link_unreserve_chanctx(link_data); goto out; } /* if there is a color change in progress, abort it */ - if (sdata->vif.bss_conf.color_change_active) + if (link_conf->color_change_active) ieee80211_color_change_abort(sdata); - err = ieee80211_set_csa_beacon(sdata, params, &changed); + err = ieee80211_set_csa_beacon(link_data, params, &changed); if (err) { - ieee80211_link_unreserve_chanctx(&sdata->deflink); + ieee80211_link_unreserve_chanctx(link_data); goto out; } - if (params->punct_bitmap && !sdata->vif.bss_conf.eht_support) - goto out; + link_data->csa_chanreq = chanreq; + link_conf->csa_active = true; - sdata->deflink.csa_chandef = params->chandef; - sdata->deflink.csa_block_tx = params->block_tx; - sdata->vif.bss_conf.csa_active = true; - sdata->vif.bss_conf.csa_punct_bitmap = params->punct_bitmap; - - if (sdata->deflink.csa_block_tx) + if (params->block_tx && + !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) { ieee80211_stop_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_blocked_tx = true; + } cfg80211_ch_switch_started_notify(sdata->dev, - &sdata->deflink.csa_chandef, 0, - params->count, params->block_tx, - sdata->vif.bss_conf.csa_punct_bitmap); + &link_data->csa_chanreq.oper, 0, + params->count, params->block_tx); if (changed) { - ieee80211_link_info_change_notify(sdata, &sdata->deflink, - changed); - drv_channel_switch_beacon(sdata, ¶ms->chandef); + ieee80211_link_info_change_notify(sdata, link_data, changed); + drv_channel_switch_beacon(sdata, &link_data->csa_chanreq.oper); } else { /* if the beacon didn't change, we can finalize immediately */ - ieee80211_csa_finalize(&sdata->deflink); + ieee80211_csa_finalize(link_data); } out: @@ -4206,15 +4282,12 @@ static int ieee80211_cfg_get_channel(struct wiphy *wiphy, chanctx_conf = rcu_dereference(link->conf->chanctx_conf); if (chanctx_conf) { - *chandef = link->conf->chandef; + *chandef = link->conf->chanreq.oper; ret = 0; } else if (local->open_count > 0 && local->open_count == local->monitors && sdata->vif.type == NL80211_IFTYPE_MONITOR) { - if (local->use_chanctx) - *chandef = local->monitor_chandef; - else - *chandef = local->_oper_chandef; + *chandef = local->monitor_chanreq.oper; ret = 0; } out: @@ -4262,12 +4335,13 @@ static int ieee80211_set_ap_chanwidth(struct wiphy *wiphy, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link; + struct ieee80211_chan_req chanreq = { .oper = *chandef }; int ret; u64 changed = 0; link = sdata_dereference(sdata->link[link_id], sdata); - ret = ieee80211_link_change_bandwidth(link, chandef, &changed); + ret = ieee80211_link_change_chanreq(link, &chanreq, &changed); if (ret == 0) ieee80211_link_info_change_notify(sdata, link, changed); @@ -4749,7 +4823,7 @@ EXPORT_SYMBOL_GPL(ieee80211_color_change_finish); void ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, - u64 color_bitmap, gfp_t gfp) + u64 color_bitmap) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_link_data *link = &sdata->deflink; @@ -4968,6 +5042,17 @@ static int ieee80211_set_hw_timestamp(struct wiphy *wiphy, return local->ops->set_hw_timestamp(&local->hw, &sdata->vif, hwts); } +static int +ieee80211_set_ttlm(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_ttlm_params *params) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + lockdep_assert_wiphy(sdata->local->hw.wiphy); + + return ieee80211_req_neg_ttlm(sdata, params); +} + const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -5080,4 +5165,5 @@ const struct cfg80211_ops mac80211_config_ops = { .mod_link_station = ieee80211_mod_link_station, .del_link_station = ieee80211_del_link_station, .set_hw_timestamp = ieee80211_set_hw_timestamp, + .set_ttlm = ieee80211_set_ttlm, }; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index ef4c2cebc080..80e4b9784131 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * mac80211 - channel management - * Copyright 2020 - 2022 Intel Corporation + * Copyright 2020 - 2024 Intel Corporation */ #include <linux/nl80211.h> @@ -81,87 +81,122 @@ ieee80211_link_get_chanctx(struct ieee80211_link_data *link) return container_of(conf, struct ieee80211_chanctx, conf); } -static const struct cfg80211_chan_def * -ieee80211_chanctx_reserved_chandef(struct ieee80211_local *local, +bool ieee80211_chanreq_identical(const struct ieee80211_chan_req *a, + const struct ieee80211_chan_req *b) +{ + if (!cfg80211_chandef_identical(&a->oper, &b->oper)) + return false; + if (!a->ap.chan && !b->ap.chan) + return true; + return cfg80211_chandef_identical(&a->ap, &b->ap); +} + +static const struct ieee80211_chan_req * +ieee80211_chanreq_compatible(const struct ieee80211_chan_req *a, + const struct ieee80211_chan_req *b, + struct ieee80211_chan_req *tmp) +{ + const struct cfg80211_chan_def *compat; + + if (a->ap.chan && b->ap.chan && + !cfg80211_chandef_identical(&a->ap, &b->ap)) + return NULL; + + compat = cfg80211_chandef_compatible(&a->oper, &b->oper); + if (!compat) + return NULL; + + /* Note: later code assumes this always fills & returns tmp if compat */ + tmp->oper = *compat; + tmp->ap = a->ap.chan ? a->ap : b->ap; + return tmp; +} + +static const struct ieee80211_chan_req * +ieee80211_chanctx_compatible(struct ieee80211_chanctx *ctx, + const struct ieee80211_chan_req *req, + struct ieee80211_chan_req *tmp) +{ + const struct ieee80211_chan_req *ret; + struct ieee80211_chan_req tmp2; + + *tmp = (struct ieee80211_chan_req){ + .oper = ctx->conf.def, + .ap = ctx->conf.ap, + }; + + ret = ieee80211_chanreq_compatible(tmp, req, &tmp2); + if (!ret) + return NULL; + *tmp = *ret; + return tmp; +} + +static const struct ieee80211_chan_req * +ieee80211_chanctx_reserved_chanreq(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, - const struct cfg80211_chan_def *compat) + const struct ieee80211_chan_req *req, + struct ieee80211_chan_req *tmp) { struct ieee80211_link_data *link; lockdep_assert_wiphy(local->hw.wiphy); - list_for_each_entry(link, &ctx->reserved_links, - reserved_chanctx_list) { - if (!compat) - compat = &link->reserved_chandef; + if (WARN_ON(!req)) + return NULL; - compat = cfg80211_chandef_compatible(&link->reserved_chandef, - compat); - if (!compat) + list_for_each_entry(link, &ctx->reserved_links, reserved_chanctx_list) { + req = ieee80211_chanreq_compatible(&link->reserved, req, tmp); + if (!req) break; } - return compat; + return req; } -static const struct cfg80211_chan_def * +static const struct ieee80211_chan_req * ieee80211_chanctx_non_reserved_chandef(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, - const struct cfg80211_chan_def *compat) + const struct ieee80211_chan_req *compat, + struct ieee80211_chan_req *tmp) { struct ieee80211_link_data *link; + const struct ieee80211_chan_req *comp_def = compat; lockdep_assert_wiphy(local->hw.wiphy); - list_for_each_entry(link, &ctx->assigned_links, - assigned_chanctx_list) { + list_for_each_entry(link, &ctx->assigned_links, assigned_chanctx_list) { struct ieee80211_bss_conf *link_conf = link->conf; if (link->reserved_chanctx) continue; - if (!compat) - compat = &link_conf->chandef; - - compat = cfg80211_chandef_compatible( - &link_conf->chandef, compat); - if (!compat) + comp_def = ieee80211_chanreq_compatible(&link_conf->chanreq, + comp_def, tmp); + if (!comp_def) break; } - return compat; -} - -static const struct cfg80211_chan_def * -ieee80211_chanctx_combined_chandef(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx, - const struct cfg80211_chan_def *compat) -{ - lockdep_assert_wiphy(local->hw.wiphy); - - compat = ieee80211_chanctx_reserved_chandef(local, ctx, compat); - if (!compat) - return NULL; - - compat = ieee80211_chanctx_non_reserved_chandef(local, ctx, compat); - if (!compat) - return NULL; - - return compat; + return comp_def; } static bool -ieee80211_chanctx_can_reserve_chandef(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx, - const struct cfg80211_chan_def *def) +ieee80211_chanctx_can_reserve(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + const struct ieee80211_chan_req *req) { + struct ieee80211_chan_req tmp; + lockdep_assert_wiphy(local->hw.wiphy); - if (ieee80211_chanctx_combined_chandef(local, ctx, def)) - return true; + if (!ieee80211_chanctx_reserved_chanreq(local, ctx, req, &tmp)) + return false; + + if (!ieee80211_chanctx_non_reserved_chandef(local, ctx, req, &tmp)) + return false; if (!list_empty(&ctx->reserved_links) && - ieee80211_chanctx_reserved_chandef(local, ctx, def)) + ieee80211_chanctx_reserved_chanreq(local, ctx, req, &tmp)) return true; return false; @@ -169,7 +204,7 @@ ieee80211_chanctx_can_reserve_chandef(struct ieee80211_local *local, static struct ieee80211_chanctx * ieee80211_find_reservation_chanctx(struct ieee80211_local *local, - const struct cfg80211_chan_def *chandef, + const struct ieee80211_chan_req *chanreq, enum ieee80211_chanctx_mode mode) { struct ieee80211_chanctx *ctx; @@ -186,8 +221,7 @@ ieee80211_find_reservation_chanctx(struct ieee80211_local *local, if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) continue; - if (!ieee80211_chanctx_can_reserve_chandef(local, ctx, - chandef)) + if (!ieee80211_chanctx_can_reserve(local, ctx, chanreq)) continue; return ctx; @@ -202,7 +236,7 @@ static enum nl80211_chan_width ieee80211_get_sta_bw(struct sta_info *sta, enum ieee80211_sta_rx_bandwidth width; struct link_sta_info *link_sta; - link_sta = rcu_dereference(sta->link[link_id]); + link_sta = wiphy_dereference(sta->local->hw.wiphy, sta->link[link_id]); /* no effect if this STA has no presence on this link */ if (!link_sta) @@ -240,9 +274,10 @@ static enum nl80211_chan_width ieee80211_get_sta_bw(struct sta_info *sta, } static enum nl80211_chan_width -ieee80211_get_max_required_bw(struct ieee80211_sub_if_data *sdata, - unsigned int link_id) +ieee80211_get_max_required_bw(struct ieee80211_link_data *link) { + struct ieee80211_sub_if_data *sdata = link->sdata; + unsigned int link_id = link->link_id; enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; struct sta_info *sta; @@ -258,31 +293,25 @@ ieee80211_get_max_required_bw(struct ieee80211_sub_if_data *sdata, } static enum nl80211_chan_width -ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, - struct ieee80211_chanctx *ctx, - struct ieee80211_link_data *rsvd_for) +ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { + struct ieee80211_sub_if_data *sdata; + struct ieee80211_link_data *link; enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; - struct ieee80211_vif *vif = &sdata->vif; - int link_id; - rcu_read_lock(); - for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { + for_each_sdata_link(local, link) { enum nl80211_chan_width width = NL80211_CHAN_WIDTH_20_NOHT; - struct ieee80211_link_data *link = - rcu_dereference(sdata->link[link_id]); - - if (!link) - continue; if (link != rsvd_for && rcu_access_pointer(link->conf->chanctx_conf) != &ctx->conf) continue; - switch (vif->type) { + switch (link->sdata->vif.type) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: - width = ieee80211_get_max_required_bw(sdata, link_id); + width = ieee80211_get_max_required_bw(link); break; case NL80211_IFTYPE_STATION: /* @@ -290,8 +319,8 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, * point, so take the width from the chandef, but * account also for TDLS peers */ - width = max(link->conf->chandef.width, - ieee80211_get_max_required_bw(sdata, link_id)); + width = max(link->conf->chanreq.oper.width, + ieee80211_get_max_required_bw(link)); break; case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: @@ -299,7 +328,7 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_OCB: - width = link->conf->chandef.width; + width = link->conf->chanreq.oper.width; break; case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_UNSPECIFIED: @@ -312,40 +341,13 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, max_bw = max(max_bw, width); } - rcu_read_unlock(); - - return max_bw; -} - -static enum nl80211_chan_width -ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx, - struct ieee80211_link_data *rsvd_for) -{ - struct ieee80211_sub_if_data *sdata; - enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; - - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - enum nl80211_chan_width width; - - if (!ieee80211_sdata_running(sdata)) - continue; - - width = ieee80211_get_chanctx_vif_max_required_bw(sdata, ctx, - rsvd_for); - - max_bw = max(max_bw, width); - } /* use the configured bandwidth in case of monitor interface */ - sdata = rcu_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (sdata && rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) == &ctx->conf) max_bw = max(max_bw, ctx->conf.def.width); - rcu_read_unlock(); - return max_bw; } @@ -382,7 +384,7 @@ _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, /* downgrade chandef up to max_bw */ min_def = ctx->conf.def; while (min_def.width > max_bw) - ieee80211_chandef_downgrade(&min_def); + ieee80211_chandef_downgrade(&min_def, NULL); if (cfg80211_chandef_identical(&ctx->conf.min_def, &min_def)) return 0; @@ -395,7 +397,7 @@ _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, } /* calling this function is assuming that station vif is updated to - * lates changes by calling ieee80211_link_update_chandef + * lates changes by calling ieee80211_link_update_chanreq */ static void ieee80211_chan_bw_change(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, @@ -475,10 +477,15 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, static void _ieee80211_change_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, struct ieee80211_chanctx *old_ctx, - const struct cfg80211_chan_def *chandef, + const struct ieee80211_chan_req *chanreq, struct ieee80211_link_data *rsvd_for) { - u32 changed; + const struct cfg80211_chan_def *chandef = &chanreq->oper; + struct ieee80211_chan_req ctx_req = { + .oper = ctx->conf.def, + .ap = ctx->conf.ap, + }; + u32 changed = 0; /* expected to handle only 20/40/80/160/320 channel widths */ switch (chandef->width) { @@ -500,47 +507,52 @@ static void _ieee80211_change_chanctx(struct ieee80211_local *local, */ ieee80211_chan_bw_change(local, old_ctx, true); - if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) { + if (ieee80211_chanreq_identical(&ctx_req, chanreq)) { ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); return; } - WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef)); + WARN_ON(ieee80211_chanctx_refcount(local, ctx) > 1 && + !cfg80211_chandef_compatible(&ctx->conf.def, &chanreq->oper)); ieee80211_remove_wbrf(local, &ctx->conf.def); + if (!cfg80211_chandef_identical(&ctx->conf.def, &chanreq->oper)) { + if (ctx->conf.def.width != chanreq->oper.width) + changed |= IEEE80211_CHANCTX_CHANGE_WIDTH; + if (ctx->conf.def.punctured != chanreq->oper.punctured) + changed |= IEEE80211_CHANCTX_CHANGE_PUNCTURING; + } + if (!cfg80211_chandef_identical(&ctx->conf.ap, &chanreq->ap)) + changed |= IEEE80211_CHANCTX_CHANGE_AP; ctx->conf.def = *chandef; + ctx->conf.ap = chanreq->ap; /* check if min chanctx also changed */ - changed = IEEE80211_CHANCTX_CHANGE_WIDTH | - _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); + changed |= _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); ieee80211_add_wbrf(local, &ctx->conf.def); drv_change_chanctx(local, ctx, changed); - if (!local->use_chanctx) { - local->_oper_chandef = *chandef; - ieee80211_hw_config(local, 0); - } - - /* check is BW wider */ + /* check if BW is wider */ ieee80211_chan_bw_change(local, old_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) + const struct ieee80211_chan_req *chanreq) { - _ieee80211_change_chanctx(local, ctx, old_ctx, chandef, NULL); + _ieee80211_change_chanctx(local, ctx, old_ctx, chanreq, NULL); } static struct ieee80211_chanctx * ieee80211_find_chanctx(struct ieee80211_local *local, - const struct cfg80211_chan_def *chandef, + const struct ieee80211_chan_req *chanreq, enum ieee80211_chanctx_mode mode) { + struct ieee80211_chan_req tmp; struct ieee80211_chanctx *ctx; lockdep_assert_wiphy(local->hw.wiphy); @@ -549,7 +561,7 @@ ieee80211_find_chanctx(struct ieee80211_local *local, return NULL; list_for_each_entry(ctx, &local->chanctx_list, list) { - const struct cfg80211_chan_def *compat; + const struct ieee80211_chan_req *compat; if (ctx->replace_state != IEEE80211_CHANCTX_REPLACE_NONE) continue; @@ -557,12 +569,12 @@ ieee80211_find_chanctx(struct ieee80211_local *local, if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) continue; - compat = cfg80211_chandef_compatible(&ctx->conf.def, chandef); + compat = ieee80211_chanctx_compatible(ctx, chanreq, &tmp); if (!compat) continue; - compat = ieee80211_chanctx_reserved_chandef(local, ctx, - compat); + compat = ieee80211_chanctx_reserved_chanreq(local, ctx, + compat, &tmp); if (!compat) continue; @@ -576,26 +588,14 @@ ieee80211_find_chanctx(struct ieee80211_local *local, bool ieee80211_is_radar_required(struct ieee80211_local *local) { - struct ieee80211_sub_if_data *sdata; + struct ieee80211_link_data *link; lockdep_assert_wiphy(local->hw.wiphy); - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - unsigned int link_id; - - for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { - struct ieee80211_link_data *link; - - link = rcu_dereference(sdata->link[link_id]); - - if (link && link->radar_required) { - rcu_read_unlock(); - return true; - } - } + for_each_sdata_link(local, link) { + if (link->radar_required) + return true; } - rcu_read_unlock(); return false; } @@ -605,43 +605,24 @@ ieee80211_chanctx_radar_required(struct ieee80211_local *local, struct ieee80211_chanctx *ctx) { struct ieee80211_chanctx_conf *conf = &ctx->conf; - struct ieee80211_sub_if_data *sdata; - bool required = false; + struct ieee80211_link_data *link; lockdep_assert_wiphy(local->hw.wiphy); - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - unsigned int link_id; - - if (!ieee80211_sdata_running(sdata)) + for_each_sdata_link(local, link) { + if (rcu_access_pointer(link->conf->chanctx_conf) != conf) continue; - for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { - struct ieee80211_link_data *link; - - link = rcu_dereference(sdata->link[link_id]); - if (!link) - continue; - - if (rcu_access_pointer(link->conf->chanctx_conf) != conf) - continue; - if (!link->radar_required) - continue; - required = true; - break; - } - - if (required) - break; + if (!link->radar_required) + continue; + return true; } - rcu_read_unlock(); - return required; + return false; } static struct ieee80211_chanctx * ieee80211_alloc_chanctx(struct ieee80211_local *local, - const struct cfg80211_chan_def *chandef, + const struct ieee80211_chan_req *chanreq, enum ieee80211_chanctx_mode mode) { struct ieee80211_chanctx *ctx; @@ -654,7 +635,8 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local, INIT_LIST_HEAD(&ctx->assigned_links); INIT_LIST_HEAD(&ctx->reserved_links); - ctx->conf.def = *chandef; + ctx->conf.def = chanreq->oper; + ctx->conf.ap = chanreq->ap; ctx->conf.rx_chains_static = 1; ctx->conf.rx_chains_dynamic = 1; ctx->mode = mode; @@ -674,23 +656,15 @@ static int ieee80211_add_chanctx(struct ieee80211_local *local, ieee80211_add_wbrf(local, &ctx->conf.def); - if (!local->use_chanctx) - local->hw.conf.radar_enabled = ctx->conf.radar_enabled; - /* turn idle off *before* setting channel -- some drivers need that */ changed = ieee80211_idle_off(local); if (changed) ieee80211_hw_config(local, changed); - if (!local->use_chanctx) { - local->_oper_chandef = ctx->conf.def; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - } else { - err = drv_add_chanctx(local, ctx); - if (err) { - ieee80211_recalc_idle(local); - return err; - } + err = drv_add_chanctx(local, ctx); + if (err) { + ieee80211_recalc_idle(local); + return err; } return 0; @@ -698,7 +672,7 @@ static int ieee80211_add_chanctx(struct ieee80211_local *local, static struct ieee80211_chanctx * ieee80211_new_chanctx(struct ieee80211_local *local, - const struct cfg80211_chan_def *chandef, + const struct ieee80211_chan_req *chanreq, enum ieee80211_chanctx_mode mode) { struct ieee80211_chanctx *ctx; @@ -706,7 +680,7 @@ ieee80211_new_chanctx(struct ieee80211_local *local, lockdep_assert_wiphy(local->hw.wiphy); - ctx = ieee80211_alloc_chanctx(local, chandef, mode); + ctx = ieee80211_alloc_chanctx(local, chanreq, mode); if (!ctx) return ERR_PTR(-ENOMEM); @@ -725,32 +699,7 @@ static void ieee80211_del_chanctx(struct ieee80211_local *local, { lockdep_assert_wiphy(local->hw.wiphy); - if (!local->use_chanctx) { - struct cfg80211_chan_def *chandef = &local->_oper_chandef; - /* S1G doesn't have 20MHz, so get the correct width for the - * current channel. - */ - if (chandef->chan->band == NL80211_BAND_S1GHZ) - chandef->width = - ieee80211_s1g_channel_width(chandef->chan); - else - chandef->width = NL80211_CHAN_WIDTH_20_NOHT; - chandef->center_freq1 = chandef->chan->center_freq; - chandef->freq1_offset = chandef->chan->freq_offset; - chandef->center_freq2 = 0; - - /* NOTE: Disabling radar is only valid here for - * single channel context. To be sure, check it ... - */ - WARN_ON(local->hw.conf.radar_enabled && - !list_empty(&local->chanctx_list)); - - local->hw.conf.radar_enabled = false; - - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - } else { - drv_remove_chanctx(local, ctx); - } + drv_remove_chanctx(local, ctx); ieee80211_recalc_idle(local); @@ -773,64 +722,53 @@ void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, struct ieee80211_chanctx *ctx) { struct ieee80211_chanctx_conf *conf = &ctx->conf; - struct ieee80211_sub_if_data *sdata; - const struct cfg80211_chan_def *compat = NULL; + const struct ieee80211_chan_req *compat = NULL; + struct ieee80211_link_data *link; + struct ieee80211_chan_req tmp; struct sta_info *sta; lockdep_assert_wiphy(local->hw.wiphy); - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - int link_id; + for_each_sdata_link(local, link) { + struct ieee80211_bss_conf *link_conf; - if (!ieee80211_sdata_running(sdata)) + if (link->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) continue; - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - continue; + link_conf = link->conf; - for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { - struct ieee80211_bss_conf *link_conf = - rcu_dereference(sdata->vif.link_conf[link_id]); - - if (!link_conf) - continue; - - if (rcu_access_pointer(link_conf->chanctx_conf) != conf) - continue; + if (rcu_access_pointer(link_conf->chanctx_conf) != conf) + continue; - if (!compat) - compat = &link_conf->chandef; + if (!compat) + compat = &link_conf->chanreq; - compat = cfg80211_chandef_compatible(&link_conf->chandef, - compat); - if (WARN_ON_ONCE(!compat)) - break; - } + compat = ieee80211_chanreq_compatible(&link_conf->chanreq, + compat, &tmp); + if (WARN_ON_ONCE(!compat)) + return; } - if (WARN_ON_ONCE(!compat)) { - rcu_read_unlock(); + if (WARN_ON_ONCE(!compat)) return; - } /* TDLS peers can sometimes affect the chandef width */ - list_for_each_entry_rcu(sta, &local->sta_list, list) { + list_for_each_entry(sta, &local->sta_list, list) { + struct ieee80211_chan_req tdls_chanreq = {}; if (!sta->uploaded || !test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW) || !test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->tdls_chandef.chan) continue; - compat = cfg80211_chandef_compatible(&sta->tdls_chandef, - compat); + tdls_chanreq.oper = sta->tdls_chandef; + + /* note this always fills and returns &tmp if compat */ + compat = ieee80211_chanreq_compatible(&tdls_chanreq, + compat, &tmp); if (WARN_ON_ONCE(!compat)) - break; + return; } - rcu_read_unlock(); - - if (!compat) - return; ieee80211_change_chanctx(local, ctx, ctx, compat); } @@ -849,11 +787,6 @@ static void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local, chanctx->conf.radar_enabled = radar_enabled; - if (!local->use_chanctx) { - local->hw.conf.radar_enabled = chanctx->conf.radar_enabled; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); - } - drv_change_chanctx(local, chanctx, IEEE80211_CHANCTX_CHANGE_RADAR); } @@ -924,23 +857,19 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, { struct ieee80211_sub_if_data *sdata; u8 rx_chains_static, rx_chains_dynamic; + struct ieee80211_link_data *link; lockdep_assert_wiphy(local->hw.wiphy); rx_chains_static = 1; rx_chains_dynamic = 1; - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) { + for_each_sdata_link(local, link) { u8 needed_static, needed_dynamic; - unsigned int link_id; - if (!ieee80211_sdata_running(sdata)) - continue; - - switch (sdata->vif.type) { + switch (link->sdata->vif.type) { case NL80211_IFTYPE_STATION: - if (!sdata->u.mgd.associated) + if (!link->sdata->u.mgd.associated) continue; break; case NL80211_IFTYPE_AP: @@ -952,59 +881,38 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, continue; } - for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { - struct ieee80211_link_data *link; - - link = rcu_dereference(sdata->link[link_id]); - - if (!link) - continue; - - if (rcu_access_pointer(link->conf->chanctx_conf) != &chanctx->conf) - continue; - - switch (link->smps_mode) { - default: - WARN_ONCE(1, "Invalid SMPS mode %d\n", - link->smps_mode); - fallthrough; - case IEEE80211_SMPS_OFF: - needed_static = link->needed_rx_chains; - needed_dynamic = link->needed_rx_chains; - break; - case IEEE80211_SMPS_DYNAMIC: - needed_static = 1; - needed_dynamic = link->needed_rx_chains; - break; - case IEEE80211_SMPS_STATIC: - needed_static = 1; - needed_dynamic = 1; - break; - } + if (rcu_access_pointer(link->conf->chanctx_conf) != &chanctx->conf) + continue; - rx_chains_static = max(rx_chains_static, needed_static); - rx_chains_dynamic = max(rx_chains_dynamic, needed_dynamic); + switch (link->smps_mode) { + default: + WARN_ONCE(1, "Invalid SMPS mode %d\n", + link->smps_mode); + fallthrough; + case IEEE80211_SMPS_OFF: + needed_static = link->needed_rx_chains; + needed_dynamic = link->needed_rx_chains; + break; + case IEEE80211_SMPS_DYNAMIC: + needed_static = 1; + needed_dynamic = link->needed_rx_chains; + break; + case IEEE80211_SMPS_STATIC: + needed_static = 1; + needed_dynamic = 1; + break; } + + rx_chains_static = max(rx_chains_static, needed_static); + rx_chains_dynamic = max(rx_chains_dynamic, needed_dynamic); } /* Disable SMPS for the monitor interface */ - sdata = rcu_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (sdata && rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) == &chanctx->conf) rx_chains_dynamic = rx_chains_static = local->rx_chains; - rcu_read_unlock(); - - if (!local->use_chanctx) { - if (rx_chains_static > 1) - local->smps_mode = IEEE80211_SMPS_OFF; - else if (rx_chains_dynamic > 1) - local->smps_mode = IEEE80211_SMPS_DYNAMIC; - else - local->smps_mode = IEEE80211_SMPS_STATIC; - ieee80211_hw_config(local, 0); - } - if (rx_chains_static == chanctx->conf.rx_chains_static && rx_chains_dynamic == chanctx->conf.rx_chains_dynamic) return; @@ -1043,17 +951,16 @@ __ieee80211_link_copy_chanctx_to_vlans(struct ieee80211_link_data *link, if (clear) conf = NULL; - rcu_read_lock(); list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { struct ieee80211_bss_conf *vlan_conf; - vlan_conf = rcu_dereference(vlan->vif.link_conf[link_id]); + vlan_conf = wiphy_dereference(local->hw.wiphy, + vlan->vif.link_conf[link_id]); if (WARN_ON(!vlan_conf)) continue; rcu_assign_pointer(vlan_conf->chanctx_conf, conf); } - rcu_read_unlock(); } void ieee80211_link_copy_chanctx_to_vlans(struct ieee80211_link_data *link, @@ -1103,7 +1010,7 @@ int ieee80211_link_unreserve_chanctx(struct ieee80211_link_data *link) } int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, - const struct cfg80211_chan_def *chandef, + const struct ieee80211_chan_req *chanreq, enum ieee80211_chanctx_mode mode, bool radar_required) { @@ -1114,13 +1021,13 @@ int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, lockdep_assert_wiphy(local->hw.wiphy); curr_ctx = ieee80211_link_get_chanctx(link); - if (curr_ctx && local->use_chanctx && !local->ops->switch_vif_chanctx) + if (curr_ctx && !local->ops->switch_vif_chanctx) return -EOPNOTSUPP; - new_ctx = ieee80211_find_reservation_chanctx(local, chandef, mode); + new_ctx = ieee80211_find_reservation_chanctx(local, chanreq, mode); if (!new_ctx) { if (ieee80211_can_create_new_chanctx(local)) { - new_ctx = ieee80211_new_chanctx(local, chandef, mode); + new_ctx = ieee80211_new_chanctx(local, chanreq, mode); if (IS_ERR(new_ctx)) return PTR_ERR(new_ctx); } else { @@ -1174,7 +1081,7 @@ int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, !list_empty(&curr_ctx->reserved_links)) return -EBUSY; - new_ctx = ieee80211_alloc_chanctx(local, chandef, mode); + new_ctx = ieee80211_alloc_chanctx(local, chanreq, mode); if (!new_ctx) return -ENOMEM; @@ -1192,7 +1099,7 @@ int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, list_add(&link->reserved_chanctx_list, &new_ctx->reserved_links); link->reserved_chanctx = new_ctx; - link->reserved_chandef = *chandef; + link->reserved = *chanreq; link->reserved_radar_required = radar_required; link->reserved_ready = false; @@ -1231,29 +1138,28 @@ ieee80211_link_chanctx_reservation_complete(struct ieee80211_link_data *link) } static void -ieee80211_link_update_chandef(struct ieee80211_link_data *link, - const struct cfg80211_chan_def *chandef) +ieee80211_link_update_chanreq(struct ieee80211_link_data *link, + const struct ieee80211_chan_req *chanreq) { struct ieee80211_sub_if_data *sdata = link->sdata; unsigned int link_id = link->link_id; struct ieee80211_sub_if_data *vlan; - link->conf->chandef = *chandef; + link->conf->chanreq = *chanreq; if (sdata->vif.type != NL80211_IFTYPE_AP) return; - rcu_read_lock(); list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { struct ieee80211_bss_conf *vlan_conf; - vlan_conf = rcu_dereference(vlan->vif.link_conf[link_id]); + vlan_conf = wiphy_dereference(sdata->local->hw.wiphy, + vlan->vif.link_conf[link_id]); if (WARN_ON(!vlan_conf)) continue; - vlan_conf->chandef = *chandef; + vlan_conf->chanreq = *chanreq; } - rcu_read_unlock(); } static int @@ -1264,7 +1170,8 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) struct ieee80211_local *local = sdata->local; struct ieee80211_vif_chanctx_switch vif_chsw[1] = {}; struct ieee80211_chanctx *old_ctx, *new_ctx; - const struct cfg80211_chan_def *chandef; + const struct ieee80211_chan_req *chanreq; + struct ieee80211_chan_req tmp; u64 changed = 0; int err; @@ -1286,17 +1193,18 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) IEEE80211_CHANCTX_REPLACES_OTHER)) return -EINVAL; - chandef = ieee80211_chanctx_non_reserved_chandef(local, new_ctx, - &link->reserved_chandef); - if (WARN_ON(!chandef)) + chanreq = ieee80211_chanctx_non_reserved_chandef(local, new_ctx, + &link->reserved, + &tmp); + if (WARN_ON(!chanreq)) return -EINVAL; - if (link_conf->chandef.width != link->reserved_chandef.width) + if (link_conf->chanreq.oper.width != link->reserved.oper.width) changed = BSS_CHANGED_BANDWIDTH; - ieee80211_link_update_chandef(link, &link->reserved_chandef); + ieee80211_link_update_chanreq(link, &link->reserved); - _ieee80211_change_chanctx(local, new_ctx, old_ctx, chandef, link); + _ieee80211_change_chanctx(local, new_ctx, old_ctx, chanreq, link); vif_chsw[0].vif = &sdata->vif; vif_chsw[0].old_ctx = &old_ctx->conf; @@ -1344,7 +1252,8 @@ ieee80211_link_use_reserved_assign(struct ieee80211_link_data *link) struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx *old_ctx, *new_ctx; - const struct cfg80211_chan_def *chandef; + const struct ieee80211_chan_req *chanreq; + struct ieee80211_chan_req tmp; int err; old_ctx = ieee80211_link_get_chanctx(link); @@ -1363,12 +1272,13 @@ ieee80211_link_use_reserved_assign(struct ieee80211_link_data *link) IEEE80211_CHANCTX_REPLACES_OTHER)) return -EINVAL; - chandef = ieee80211_chanctx_non_reserved_chandef(local, new_ctx, - &link->reserved_chandef); - if (WARN_ON(!chandef)) + chanreq = ieee80211_chanctx_non_reserved_chandef(local, new_ctx, + &link->reserved, + &tmp); + if (WARN_ON(!chanreq)) return -EINVAL; - ieee80211_change_chanctx(local, new_ctx, new_ctx, chandef); + ieee80211_change_chanctx(local, new_ctx, new_ctx, chanreq); list_del(&link->reserved_chanctx_list); link->reserved_chanctx = NULL; @@ -1412,24 +1322,6 @@ ieee80211_link_has_in_place_reservation(struct ieee80211_link_data *link) return true; } -static int ieee80211_chsw_switch_hwconf(struct ieee80211_local *local, - struct ieee80211_chanctx *new_ctx) -{ - const struct cfg80211_chan_def *chandef; - - lockdep_assert_wiphy(local->hw.wiphy); - - chandef = ieee80211_chanctx_reserved_chandef(local, new_ctx, NULL); - if (WARN_ON(!chandef)) - return -EINVAL; - - local->hw.conf.radar_enabled = new_ctx->conf.radar_enabled; - local->_oper_chandef = *chandef; - ieee80211_hw_config(local, 0); - - return 0; -} - static int ieee80211_chsw_switch_vifs(struct ieee80211_local *local, int n_vifs) { @@ -1518,7 +1410,6 @@ err: static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) { struct ieee80211_chanctx *ctx, *ctx_tmp, *old_ctx; - struct ieee80211_chanctx *new_ctx = NULL; int err, n_assigned, n_reserved, n_ready; int n_ctx = 0, n_vifs_switch = 0, n_vifs_assign = 0, n_vifs_ctxless = 0; @@ -1551,9 +1442,6 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) goto err; } - if (!local->use_chanctx) - new_ctx = ctx; - n_ctx++; n_assigned = 0; @@ -1607,9 +1495,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) if (WARN_ON(n_ctx == 0) || WARN_ON(n_vifs_switch == 0 && n_vifs_assign == 0 && - n_vifs_ctxless == 0) || - WARN_ON(n_ctx > 1 && !local->use_chanctx) || - WARN_ON(!new_ctx && !local->use_chanctx)) { + n_vifs_ctxless == 0)) { err = -EINVAL; goto err; } @@ -1619,20 +1505,14 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) * reservations and driver capabilities. */ - if (local->use_chanctx) { - if (n_vifs_switch > 0) { - err = ieee80211_chsw_switch_vifs(local, n_vifs_switch); - if (err) - goto err; - } + if (n_vifs_switch > 0) { + err = ieee80211_chsw_switch_vifs(local, n_vifs_switch); + if (err) + goto err; + } - if (n_vifs_assign > 0 || n_vifs_ctxless > 0) { - err = ieee80211_chsw_switch_ctxs(local); - if (err) - goto err; - } - } else { - err = ieee80211_chsw_switch_hwconf(local, new_ctx); + if (n_vifs_assign > 0 || n_vifs_ctxless > 0) { + err = ieee80211_chsw_switch_ctxs(local); if (err) goto err; } @@ -1672,10 +1552,10 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) link->radar_required = link->reserved_radar_required; - if (link_conf->chandef.width != link->reserved_chandef.width) + if (link_conf->chanreq.oper.width != link->reserved.oper.width) changed = BSS_CHANGED_BANDWIDTH; - ieee80211_link_update_chandef(link, &link->reserved_chandef); + ieee80211_link_update_chanreq(link, &link->reserved); if (changed) ieee80211_link_info_change_notify(sdata, link, @@ -1810,7 +1690,7 @@ static void __ieee80211_link_release_channel(struct ieee80211_link_data *link) } int ieee80211_link_use_channel(struct ieee80211_link_data *link, - const struct cfg80211_chan_def *chandef, + const struct ieee80211_chan_req *chanreq, enum ieee80211_chanctx_mode mode) { struct ieee80211_sub_if_data *sdata = link->sdata; @@ -1821,38 +1701,37 @@ int ieee80211_link_use_channel(struct ieee80211_link_data *link, lockdep_assert_wiphy(local->hw.wiphy); - if (sdata->vif.active_links && - !(sdata->vif.active_links & BIT(link->link_id))) { - ieee80211_link_update_chandef(link, chandef); + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) { + ieee80211_link_update_chanreq(link, chanreq); return 0; } ret = cfg80211_chandef_dfs_required(local->hw.wiphy, - chandef, + &chanreq->oper, sdata->wdev.iftype); if (ret < 0) goto out; if (ret > 0) - radar_detect_width = BIT(chandef->width); + radar_detect_width = BIT(chanreq->oper.width); link->radar_required = ret; - ret = ieee80211_check_combinations(sdata, chandef, mode, + ret = ieee80211_check_combinations(sdata, &chanreq->oper, mode, radar_detect_width); if (ret < 0) goto out; __ieee80211_link_release_channel(link); - ctx = ieee80211_find_chanctx(local, chandef, mode); + ctx = ieee80211_find_chanctx(local, chanreq, mode); if (!ctx) - ctx = ieee80211_new_chanctx(local, chandef, mode); + ctx = ieee80211_new_chanctx(local, chanreq, mode); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); goto out; } - ieee80211_link_update_chandef(link, chandef); + ieee80211_link_update_chanreq(link, chanreq); ret = ieee80211_assign_link_chanctx(link, ctx); if (ret) { @@ -1932,28 +1811,79 @@ int ieee80211_link_use_reserved_context(struct ieee80211_link_data *link) return 0; } -int ieee80211_link_change_bandwidth(struct ieee80211_link_data *link, - const struct cfg80211_chan_def *chandef, - u64 *changed) +/* + * This is similar to ieee80211_chanctx_compatible(), but rechecks + * against all the links actually using it (except the one that's + * passed, since that one is changing). + * This is done in order to allow changes to the AP's bandwidth for + * wider bandwidth OFDMA purposes, which wouldn't be treated as + * compatible by ieee80211_chanctx_recheck() but is OK if the link + * requesting the update is the only one using it. + */ +static const struct ieee80211_chan_req * +ieee80211_chanctx_recheck(struct ieee80211_local *local, + struct ieee80211_link_data *skip_link, + struct ieee80211_chanctx *ctx, + const struct ieee80211_chan_req *req, + struct ieee80211_chan_req *tmp) +{ + const struct ieee80211_chan_req *ret = req; + struct ieee80211_link_data *link; + + lockdep_assert_wiphy(local->hw.wiphy); + + for_each_sdata_link(local, link) { + if (link == skip_link) + continue; + + if (rcu_access_pointer(link->conf->chanctx_conf) == &ctx->conf) { + ret = ieee80211_chanreq_compatible(ret, + &link->conf->chanreq, + tmp); + if (!ret) + return NULL; + } + + if (link->reserved_chanctx == ctx) { + ret = ieee80211_chanreq_compatible(ret, + &link->reserved, + tmp); + if (!ret) + return NULL; + } + } + + *tmp = *ret; + return tmp; +} + +int ieee80211_link_change_chanreq(struct ieee80211_link_data *link, + const struct ieee80211_chan_req *chanreq, + u64 *changed) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_bss_conf *link_conf = link->conf; struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *ctx; - const struct cfg80211_chan_def *compat; + const struct ieee80211_chan_req *compat; + struct ieee80211_chan_req tmp; lockdep_assert_wiphy(local->hw.wiphy); - if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef, + if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, + &chanreq->oper, IEEE80211_CHAN_DISABLED)) return -EINVAL; - if (cfg80211_chandef_identical(chandef, &link_conf->chandef)) + /* for non-HT 20 MHz the rest doesn't matter */ + if (chanreq->oper.width == NL80211_CHAN_WIDTH_20_NOHT && + cfg80211_chandef_identical(&chanreq->oper, &link_conf->chanreq.oper)) return 0; - if (chandef->width == NL80211_CHAN_WIDTH_20_NOHT || - link_conf->chandef.width == NL80211_CHAN_WIDTH_20_NOHT) + /* but you cannot switch to/from it */ + if (chanreq->oper.width == NL80211_CHAN_WIDTH_20_NOHT || + link_conf->chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT) return -EINVAL; conf = rcu_dereference_protected(link_conf->chanctx_conf, @@ -1963,13 +1893,14 @@ int ieee80211_link_change_bandwidth(struct ieee80211_link_data *link, ctx = container_of(conf, struct ieee80211_chanctx, conf); - compat = cfg80211_chandef_compatible(&conf->def, chandef); + compat = ieee80211_chanctx_recheck(local, link, ctx, chanreq, &tmp); if (!compat) return -EINVAL; switch (ctx->replace_state) { case IEEE80211_CHANCTX_REPLACE_NONE: - if (!ieee80211_chanctx_reserved_chandef(local, ctx, compat)) + if (!ieee80211_chanctx_reserved_chanreq(local, ctx, compat, + &tmp)) return -EBUSY; break; case IEEE80211_CHANCTX_WILL_BE_REPLACED: @@ -1984,7 +1915,7 @@ int ieee80211_link_change_bandwidth(struct ieee80211_link_data *link, break; } - ieee80211_link_update_chandef(link, chandef); + ieee80211_link_update_chanreq(link, chanreq); ieee80211_recalc_chanctx_chantype(local, ctx); @@ -2019,12 +1950,11 @@ void ieee80211_link_vlan_copy_chanctx(struct ieee80211_link_data *link) ap = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); - rcu_read_lock(); - ap_conf = rcu_dereference(ap->vif.link_conf[link_id]); - conf = rcu_dereference_protected(ap_conf->chanctx_conf, - lockdep_is_held(&local->hw.wiphy->mtx)); + ap_conf = wiphy_dereference(local->hw.wiphy, + ap->vif.link_conf[link_id]); + conf = wiphy_dereference(local->hw.wiphy, + ap_conf->chanctx_conf); rcu_assign_pointer(link_conf->chanctx_conf, conf); - rcu_read_unlock(); } void ieee80211_iter_chan_contexts_atomic( diff --git a/net/mac80211/debug.h b/net/mac80211/debug.h index d49894df2351..49da401c5340 100644 --- a/net/mac80211/debug.h +++ b/net/mac80211/debug.h @@ -152,16 +152,17 @@ do { \ else \ _sdata_err((link)->sdata, fmt, ##__VA_ARGS__); \ } while (0) -#define link_dbg(link, fmt, ...) \ +#define _link_id_dbg(print, sdata, link_id, fmt, ...) \ do { \ - if (ieee80211_vif_is_mld(&(link)->sdata->vif)) \ - _sdata_dbg(1, (link)->sdata, "[link %d] " fmt, \ - (link)->link_id, \ - ##__VA_ARGS__); \ + if (ieee80211_vif_is_mld(&(sdata)->vif)) \ + _sdata_dbg(print, sdata, "[link %d] " fmt, \ + link_id, ##__VA_ARGS__); \ else \ - _sdata_dbg(1, (link)->sdata, fmt, \ - ##__VA_ARGS__); \ + _sdata_dbg(1, sdata, fmt, ##__VA_ARGS__); \ } while (0) +#define link_dbg(link, fmt, ...) \ + _link_id_dbg(1, (link)->sdata, (link)->link_id, \ + fmt, ##__VA_ARGS__) #define ht_dbg(sdata, fmt, ...) \ _sdata_dbg(MAC80211_HT_DEBUG, \ @@ -226,6 +227,9 @@ do { \ #define mlme_dbg(sdata, fmt, ...) \ _sdata_dbg(MAC80211_MLME_DEBUG, \ sdata, fmt, ##__VA_ARGS__) +#define mlme_link_id_dbg(sdata, link_id, fmt, ...) \ + _link_id_dbg(MAC80211_MLME_DEBUG, sdata, link_id, \ + fmt, ##__VA_ARGS__) #define mlme_dbg_ratelimited(sdata, fmt, ...) \ _sdata_dbg(MAC80211_MLME_DEBUG && net_ratelimit(), \ diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 74be49191e70..2f68e92a7404 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -4,7 +4,7 @@ * * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018 - 2019, 2021-2023 Intel Corporation + * Copyright (C) 2018 - 2019, 2021-2024 Intel Corporation */ #include <linux/debugfs.h> @@ -498,6 +498,7 @@ static const char *hw_flag_names[] = { FLAG(DETECTS_COLOR_COLLISION), FLAG(MLO_MCAST_MULTI_LINK_TX), FLAG(DISALLOW_PUNCTURING), + FLAG(HANDLES_QUIET_CSA), #undef FLAG }; diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index 3b7f70073fc3..dce37ba8ebe3 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2015 Intel Deutschland GmbH - * Copyright (C) 2022-2023 Intel Corporation + * Copyright (C) 2022-2024 Intel Corporation */ #include <net/mac80211.h> #include "ieee80211_i.h" @@ -214,8 +214,7 @@ int drv_conf_tx(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return -EIO; - if (sdata->vif.active_links && - !(sdata->vif.active_links & BIT(link->link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) return 0; if (params->cw_min == 0 || params->cw_min > params->cw_max) { @@ -315,8 +314,7 @@ int drv_assign_vif_chanctx(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return -EIO; - if (sdata->vif.active_links && - !(sdata->vif.active_links & BIT(link_conf->link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link_conf->link_id)) return 0; trace_drv_assign_vif_chanctx(local, sdata, link_conf, ctx); @@ -343,8 +341,7 @@ void drv_unassign_vif_chanctx(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return; - if (sdata->vif.active_links && - !(sdata->vif.active_links & BIT(link_conf->link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link_conf->link_id)) return; trace_drv_unassign_vif_chanctx(local, sdata, link_conf, ctx); @@ -461,8 +458,7 @@ void drv_link_info_changed(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return; - if (sdata->vif.active_links && - !(sdata->vif.active_links & BIT(link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link_id)) return; trace_drv_link_info_changed(local, sdata, info, changed); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index eb482fb8c3af..5d078c0a2323 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, 2021 - 2023 Intel Corporation +* Copyright (C) 2018-2019, 2021-2024 Intel Corporation */ #ifndef __MAC80211_DRIVER_OPS @@ -1180,8 +1180,9 @@ drv_post_channel_switch(struct ieee80211_link_data *link) } static inline void -drv_abort_channel_switch(struct ieee80211_sub_if_data *sdata) +drv_abort_channel_switch(struct ieee80211_link_data *link) { + struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; might_sleep(); @@ -1193,7 +1194,8 @@ drv_abort_channel_switch(struct ieee80211_sub_if_data *sdata) trace_drv_abort_channel_switch(local, sdata); if (local->ops->abort_channel_switch) - local->ops->abort_channel_switch(&local->hw, &sdata->vif); + local->ops->abort_channel_switch(&local->hw, &sdata->vif, + link->conf); } static inline void @@ -1695,4 +1697,23 @@ int drv_change_sta_links(struct ieee80211_local *local, struct ieee80211_sta *sta, u16 old_links, u16 new_links); +static inline enum ieee80211_neg_ttlm_res +drv_can_neg_ttlm(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_neg_ttlm *neg_ttlm) +{ + enum ieee80211_neg_ttlm_res res = NEG_TTLM_RES_REJECT; + + might_sleep(); + if (!check_sdata_in_driver(sdata)) + return -EIO; + + trace_drv_can_neg_ttlm(local, sdata, neg_ttlm); + if (local->ops->can_neg_ttlm) + res = local->ops->can_neg_ttlm(&local->hw, &sdata->vif, + neg_ttlm); + trace_drv_neg_ttlm_res(local, sdata, res, neg_ttlm); + + return res; +} #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 749f4ecab990..c3330aea4da3 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) 2020-2023 Intel Corporation + * Copyright(c) 2020-2024 Intel Corporation */ #include <linux/ieee80211.h> @@ -257,7 +257,7 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, if (WARN_ON(!link_conf)) width = NL80211_CHAN_WIDTH_20_NOHT; else - width = link_conf->chandef.width; + width = link_conf->chanreq.oper.width; switch (width) { default: @@ -603,6 +603,8 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, unsigned int link_id, if (WARN_ON(!link)) goto out; + trace_api_request_smps(sdata->local, sdata, link, smps_mode); + if (link->u.mgd.driver_smps_mode == smps_mode) goto out; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 8f2b445a5ec3..7ace5cdc6c26 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -223,7 +223,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt; struct cfg80211_bss *bss; u64 bss_change; - struct cfg80211_chan_def chandef; + struct ieee80211_chan_req chanreq = {}; struct ieee80211_channel *chan; struct beacon_data *presp; struct cfg80211_inform_bss bss_meta = {}; @@ -237,7 +237,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, drv_reset_tsf(local, sdata); if (!ether_addr_equal(ifibss->bssid, bssid)) - sta_info_flush(sdata); + sta_info_flush(sdata, -1); /* if merging, indicate to driver that we leave the old IBSS */ if (sdata->vif.cfg.ibss_joined) { @@ -257,22 +257,22 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, kfree_rcu(presp, rcu_head); /* make a copy of the chandef, it could be modified below. */ - chandef = *req_chandef; - chan = chandef.chan; - if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef, + chanreq.oper = *req_chandef; + chan = chanreq.oper.chan; + if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chanreq.oper, NL80211_IFTYPE_ADHOC)) { - if (chandef.width == NL80211_CHAN_WIDTH_5 || - chandef.width == NL80211_CHAN_WIDTH_10 || - chandef.width == NL80211_CHAN_WIDTH_20_NOHT || - chandef.width == NL80211_CHAN_WIDTH_20) { + if (chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + chanreq.oper.width == NL80211_CHAN_WIDTH_10 || + chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT || + chanreq.oper.width == NL80211_CHAN_WIDTH_20) { sdata_info(sdata, "Failed to join IBSS, beacons forbidden\n"); return; } - chandef.width = NL80211_CHAN_WIDTH_20; - chandef.center_freq1 = chan->center_freq; + chanreq.oper.width = NL80211_CHAN_WIDTH_20; + chanreq.oper.center_freq1 = chan->center_freq; /* check again for downgraded chandef */ - if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef, + if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chanreq.oper, NL80211_IFTYPE_ADHOC)) { sdata_info(sdata, "Failed to join IBSS, beacons forbidden\n"); @@ -281,7 +281,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, } err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy, - &chandef, NL80211_IFTYPE_ADHOC); + &chanreq.oper, NL80211_IFTYPE_ADHOC); if (err < 0) { sdata_info(sdata, "Failed to join IBSS, invalid chandef\n"); @@ -295,7 +295,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, radar_required = err; - if (ieee80211_link_use_channel(&sdata->deflink, &chandef, + if (ieee80211_link_use_channel(&sdata->deflink, &chanreq, ifibss->fixed_channel ? IEEE80211_CHANCTX_SHARED : IEEE80211_CHANCTX_EXCLUSIVE)) { @@ -307,7 +307,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, memcpy(ifibss->bssid, bssid, ETH_ALEN); presp = ieee80211_ibss_build_presp(sdata, beacon_int, basic_rates, - capability, tsf, &chandef, + capability, tsf, &chanreq.oper, &have_higher_than_11mbit, NULL); if (!presp) return; @@ -533,12 +533,12 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata, u64 *changed) IEEE80211_PRIVACY(ifibss->privacy)); /* XXX: should not really modify cfg80211 data */ if (cbss) { - cbss->channel = sdata->deflink.csa_chandef.chan; + cbss->channel = sdata->deflink.csa_chanreq.oper.chan; cfg80211_put_bss(sdata->local->hw.wiphy, cbss); } } - ifibss->chandef = sdata->deflink.csa_chandef; + ifibss->chandef = sdata->deflink.csa_chanreq.oper; /* generate the beacon */ return ieee80211_ibss_csa_beacon(sdata, NULL, changed); @@ -682,7 +682,7 @@ static void ieee80211_ibss_disconnect(struct ieee80211_sub_if_data *sdata) ifibss->state = IEEE80211_IBSS_MLME_SEARCH; - sta_info_flush(sdata); + sta_info_flush(sdata, -1); spin_lock_bh(&ifibss->incomplete_lock); while (!list_empty(&ifibss->incomplete_stations)) { @@ -757,21 +757,22 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_ibss *ifibss = &sdata->u.ibss; enum nl80211_channel_type ch_type; int err; - ieee80211_conn_flags_t conn_flags; + struct ieee80211_conn_settings conn = { + .mode = IEEE80211_CONN_MODE_HT, + .bw_limit = IEEE80211_CONN_BW_LIMIT_40, + }; u32 vht_cap_info = 0; lockdep_assert_wiphy(sdata->local->hw.wiphy); - conn_flags = IEEE80211_CONN_DISABLE_VHT; - switch (ifibss->chandef.width) { case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: case NL80211_CHAN_WIDTH_20_NOHT: - conn_flags |= IEEE80211_CONN_DISABLE_HT; + conn.mode = IEEE80211_CONN_MODE_LEGACY; fallthrough; case NL80211_CHAN_WIDTH_20: - conn_flags |= IEEE80211_CONN_DISABLE_40MHZ; + conn.bw_limit = IEEE80211_CONN_BW_LIMIT_20; break; default: break; @@ -783,8 +784,8 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); err = ieee80211_parse_ch_switch_ie(sdata, elems, ifibss->chandef.chan->band, - vht_cap_info, - conn_flags, ifibss->bssid, &csa_ie); + vht_cap_info, &conn, + ifibss->bssid, &csa_ie); /* can't switch to destination channel, fail */ if (err < 0) goto disconnect; @@ -798,7 +799,7 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, goto disconnect; params.count = csa_ie.count; - params.chandef = csa_ie.chandef; + params.chandef = csa_ie.chanreq.oper; switch (ifibss->chandef.width) { case NL80211_CHAN_WIDTH_20_NOHT: @@ -857,7 +858,7 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, params.radar_required = err; if (cfg80211_chandef_identical(¶ms.chandef, - &sdata->vif.bss_conf.chandef)) { + &sdata->vif.bss_conf.chanreq.oper)) { ibss_dbg(sdata, "received csa with an identical chandef, ignoring\n"); return true; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 0b2b53550bd9..b6fead612b66 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) 2018-2022 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #ifndef IEEE80211_I_H @@ -370,19 +370,32 @@ enum ieee80211_sta_flags { IEEE80211_STA_ENABLE_RRM = BIT(15), }; -typedef u32 __bitwise ieee80211_conn_flags_t; - -enum ieee80211_conn_flags { - IEEE80211_CONN_DISABLE_HT = (__force ieee80211_conn_flags_t)BIT(0), - IEEE80211_CONN_DISABLE_40MHZ = (__force ieee80211_conn_flags_t)BIT(1), - IEEE80211_CONN_DISABLE_VHT = (__force ieee80211_conn_flags_t)BIT(2), - IEEE80211_CONN_DISABLE_80P80MHZ = (__force ieee80211_conn_flags_t)BIT(3), - IEEE80211_CONN_DISABLE_160MHZ = (__force ieee80211_conn_flags_t)BIT(4), - IEEE80211_CONN_DISABLE_HE = (__force ieee80211_conn_flags_t)BIT(5), - IEEE80211_CONN_DISABLE_EHT = (__force ieee80211_conn_flags_t)BIT(6), - IEEE80211_CONN_DISABLE_320MHZ = (__force ieee80211_conn_flags_t)BIT(7), +enum ieee80211_conn_mode { + IEEE80211_CONN_MODE_S1G, + IEEE80211_CONN_MODE_LEGACY, + IEEE80211_CONN_MODE_HT, + IEEE80211_CONN_MODE_VHT, + IEEE80211_CONN_MODE_HE, + IEEE80211_CONN_MODE_EHT, }; +#define IEEE80211_CONN_MODE_HIGHEST IEEE80211_CONN_MODE_EHT + +enum ieee80211_conn_bw_limit { + IEEE80211_CONN_BW_LIMIT_20, + IEEE80211_CONN_BW_LIMIT_40, + IEEE80211_CONN_BW_LIMIT_80, + IEEE80211_CONN_BW_LIMIT_160, /* also 80+80 */ + IEEE80211_CONN_BW_LIMIT_320, +}; + +struct ieee80211_conn_settings { + enum ieee80211_conn_mode mode; + enum ieee80211_conn_bw_limit bw_limit; +}; + +extern const struct ieee80211_conn_settings ieee80211_conn_settings_unlimited; + struct ieee80211_mgd_auth_data { struct cfg80211_bss *bss; unsigned long timeout; @@ -416,7 +429,7 @@ struct ieee80211_mgd_assoc_data { size_t elems_len; u8 *elems; /* pointing to inside ie[] below */ - ieee80211_conn_flags_t conn_flags; + struct ieee80211_conn_settings conn; u16 status; @@ -441,6 +454,7 @@ struct ieee80211_mgd_assoc_data { bool timeout_started; bool comeback; /* whether the AP has requested association comeback */ bool s1g; + bool spp_amsdu; unsigned int assoc_link_id; @@ -509,6 +523,8 @@ struct ieee80211_if_managed { unsigned int flags; + u16 mcast_seq_last; + bool status_acked; bool status_received; __le16 status_fc; @@ -579,6 +595,10 @@ struct ieee80211_if_managed { /* TID-to-link mapping support */ struct wiphy_delayed_work ttlm_work; struct ieee80211_adv_ttlm_info ttlm_info; + + /* dialog token enumerator for neg TTLM request */ + u8 dialog_token_alloc; + struct wiphy_delayed_work neg_ttlm_timeout_work; }; struct ieee80211_if_ibss { @@ -866,6 +886,9 @@ struct ieee80211_chanctx { enum ieee80211_chanctx_mode mode; bool driver_present; + /* temporary data for search algorithm etc. */ + struct ieee80211_chan_req req; + struct ieee80211_chanctx_conf conf; }; @@ -938,7 +961,7 @@ struct ieee80211_link_data_managed { enum ieee80211_smps_mode req_smps, /* requested smps mode */ driver_smps_mode; /* smps mode request */ - ieee80211_conn_flags_t conn_flags; + struct ieee80211_conn_settings conn; s16 p2p_noa_index; @@ -983,8 +1006,6 @@ struct ieee80211_link_data_managed { int mu_edca_last_param_set; u8 bss_param_ch_cnt; - - struct cfg80211_bss *bss; }; struct ieee80211_link_data_ap { @@ -1013,11 +1034,10 @@ struct ieee80211_link_data { struct ieee80211_key __rcu *default_beacon_key; struct wiphy_work csa_finalize_work; - bool csa_block_tx; bool operating_11g_mode; - struct cfg80211_chan_def csa_chandef; + struct ieee80211_chan_req csa_chanreq; struct wiphy_work color_change_finalize_work; struct delayed_work color_collision_detect_work; @@ -1025,7 +1045,7 @@ struct ieee80211_link_data { /* context reservation -- protected with wiphy mutex */ struct ieee80211_chanctx *reserved_chanctx; - struct cfg80211_chan_def reserved_chandef; + struct ieee80211_chan_req reserved; bool reserved_radar_required; bool reserved_ready; @@ -1072,6 +1092,8 @@ struct ieee80211_sub_if_data { unsigned long state; + bool csa_blocked_tx; + char name[IFNAMSIZ]; struct ieee80211_fragment_cache frags; @@ -1160,6 +1182,19 @@ struct ieee80211_sub_if_data *vif_to_sdata(struct ieee80211_vif *p) #define sdata_dereference(p, sdata) \ wiphy_dereference(sdata->local->hw.wiphy, p) +#define for_each_sdata_link(_local, _link) \ + /* outer loop just to define the variables ... */ \ + for (struct ieee80211_sub_if_data *___sdata = NULL; \ + !___sdata; \ + ___sdata = (void *)~0 /* always stop */) \ + list_for_each_entry(___sdata, &(_local)->interfaces, list) \ + if (ieee80211_sdata_running(___sdata)) \ + for (int ___link_id = 0; \ + ___link_id < ARRAY_SIZE(___sdata->link); \ + ___link_id++) \ + if ((_link = wiphy_dereference((local)->hw.wiphy, \ + ___sdata->link[___link_id]))) + static inline int ieee80211_get_mbssid_beacon_len(struct cfg80211_mbssid_elems *elems, struct cfg80211_rnr_elems *rnr_elems, @@ -1330,7 +1365,8 @@ struct ieee80211_local { bool wiphy_ciphers_allocated; - bool use_chanctx; + struct cfg80211_chan_def dflt_chandef; + bool emulate_chanctx; /* protects the aggregated multicast list and filter calls */ spinlock_t filter_lock; @@ -1456,8 +1492,6 @@ struct ieee80211_local { enum mac80211_scan_state next_scan_state; struct wiphy_delayed_work scan_work; struct ieee80211_sub_if_data __rcu *scan_sdata; - /* For backward compatibility only -- do not use */ - struct cfg80211_chan_def _oper_chandef; /* Temporary remain-on-channel for off-channel operations */ struct ieee80211_channel *tmp_channel; @@ -1531,8 +1565,6 @@ struct ieee80211_local { int user_power_level; /* in dBm, for all interfaces */ - enum ieee80211_smps_mode smps_mode; - struct work_struct restart_work; #ifdef CONFIG_MAC80211_DEBUGFS @@ -1559,7 +1591,7 @@ struct ieee80211_local { /* virtual monitor interface */ struct ieee80211_sub_if_data __rcu *monitor_sdata; - struct cfg80211_chan_def monitor_chandef; + struct ieee80211_chan_req monitor_chanreq; /* extended capabilities provided by mac80211 */ u8 ext_capa[8]; @@ -1624,7 +1656,7 @@ ieee80211_get_link_sband(struct ieee80211_link_data *link) /* this struct holds the value parsing from channel switch IE */ struct ieee80211_csa_ie { - struct cfg80211_chan_def chandef; + struct ieee80211_chan_req chanreq; u8 mode; u8 count; u8 ttl; @@ -1633,6 +1665,14 @@ struct ieee80211_csa_ie { u32 max_switch_time; }; +enum ieee80211_elems_parse_error { + IEEE80211_PARSE_ERR_INVALID_END = BIT(0), + IEEE80211_PARSE_ERR_DUP_ELEM = BIT(1), + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE = BIT(2), + IEEE80211_PARSE_ERR_UNEXPECTED_ELEM = BIT(3), + IEEE80211_PARSE_ERR_DUP_NEST_ML_BASIC = BIT(4), +}; + /* Parsed Information Elements */ struct ieee802_11_elems { const u8 *ie_start; @@ -1727,12 +1767,6 @@ struct ieee802_11_elems { size_t ml_basic_len; size_t ml_reconf_len; - /* The basic Multi-Link element in the original IEs */ - const struct element *ml_basic_elem; - - /* The reconfiguration Multi-Link element in the original IEs */ - const struct element *ml_reconf_elem; - u8 ttlm_num; /* @@ -1743,16 +1777,8 @@ struct ieee802_11_elems { struct ieee80211_mle_per_sta_profile *prof; size_t sta_prof_len; - /* whether a parse error occurred while retrieving these elements */ - bool parse_error; - - /* - * scratch buffer that can be used for various element parsing related - * tasks, e.g., element de-fragmentation etc. - */ - size_t scratch_len; - u8 *scratch_pos; - u8 scratch[] __counted_by(scratch_len); + /* whether/which parse error occurred while retrieving these elements */ + u8 parse_error; }; static inline struct ieee80211_local *hw_to_local( @@ -1801,6 +1827,8 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, unsigned int mpdu_len, unsigned int mpdu_offset); int ieee80211_hw_config(struct ieee80211_local *local, u32 changed); +int ieee80211_hw_conf_chan(struct ieee80211_local *local); +void ieee80211_hw_conf_init(struct ieee80211_local *local); void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx); void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, u64 changed); @@ -2112,7 +2140,7 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta); enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta); -void ieee80211_sta_set_rx_nss(struct link_sta_info *link_sta); +void ieee80211_sta_init_nss(struct link_sta_info *link_sta); enum ieee80211_sta_rx_bandwidth ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width); enum nl80211_chan_width @@ -2166,9 +2194,8 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, * @elems: parsed 802.11 elements received with the frame * @current_band: indicates the current band * @vht_cap_info: VHT capabilities of the transmitter - * @conn_flags: contains information about own capabilities and restrictions - * to decide which channel switch announcements can be accepted, using - * flags from &enum ieee80211_conn_flags. + * @conn: contains information about own capabilities and restrictions + * to decide which channel switch announcements can be accepted * @bssid: the currently connected bssid (for reporting) * @csa_ie: parsed 802.11 csa elements on count, mode, chandef and mesh ttl. * All of them will be filled with if success only. @@ -2178,7 +2205,8 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, enum nl80211_band current_band, u32 vht_cap_info, - ieee80211_conn_flags_t conn_flags, u8 *bssid, + struct ieee80211_conn_settings *conn, + u8 *bssid, struct ieee80211_csa_ie *csa_ie); /* Suspend/resume and hw reconfiguration */ @@ -2202,6 +2230,9 @@ static inline int __ieee80211_resume(struct ieee80211_hw *hw) /* utility functions/constants */ extern const void *const mac80211_wiphy_privid; /* for wiphy privid */ +const char *ieee80211_conn_mode_str(enum ieee80211_conn_mode mode); +enum ieee80211_conn_bw_limit +ieee80211_min_bw_limit_from_chandef(struct cfg80211_chan_def *chandef); int ieee80211_frame_duration(enum nl80211_band band, size_t len, int rate, int erp, int short_preamble); void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, @@ -2243,6 +2274,7 @@ static inline void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, /** * struct ieee80211_elems_parse_params - element parsing parameters + * @mode: connection mode for parsing * @start: pointer to the elements * @len: length of the elements * @action: %true if the elements came from an action frame @@ -2260,6 +2292,7 @@ static inline void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, * for EHT capabilities parsing) */ struct ieee80211_elems_parse_params { + enum ieee80211_conn_mode mode; const u8 *start; size_t len; bool action; @@ -2279,6 +2312,7 @@ ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, struct cfg80211_bss *bss) { struct ieee80211_elems_parse_params params = { + .mode = IEEE80211_CONN_MODE_HIGHEST, .start = start, .len = len, .action = action, @@ -2408,7 +2442,6 @@ void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, const u8 *da, const u8 *bssid, u16 stype, u16 reason, bool send_frame, u8 *frame_buf); -u8 *ieee80211_write_he_6ghz_cap(u8 *pos, __le16 cap, u8 *end); enum { IEEE80211_PROBE_FLAG_DIRECTED = BIT(0), @@ -2453,32 +2486,36 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, u32 cap); u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, const struct cfg80211_chan_def *chandef); -u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype); -u8 *ieee80211_ie_build_he_cap(ieee80211_conn_flags_t disable_flags, u8 *pos, - const struct ieee80211_sta_he_cap *he_cap, - u8 *end); -void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, - enum ieee80211_smps_mode smps_mode, - struct sk_buff *skb); +u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata); u8 *ieee80211_ie_build_he_oper(u8 *pos, struct cfg80211_chan_def *chandef); u8 *ieee80211_ie_build_eht_oper(u8 *pos, struct cfg80211_chan_def *chandef, const struct ieee80211_sta_eht_cap *eht_cap); int ieee80211_parse_bitrates(enum nl80211_chan_width width, const struct ieee80211_supported_band *sband, const u8 *srates, int srates_len, u32 *rates); -int ieee80211_add_srates_ie(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, bool need_basic, - enum nl80211_band band); -int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, bool need_basic, - enum nl80211_band band); u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo); void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta_s1g_cap *caps, struct sk_buff *skb); void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); -u8 *ieee80211_ie_build_s1g_cap(u8 *pos, struct ieee80211_sta_s1g_cap *s1g_cap); + +/* element building in SKBs */ +int ieee80211_put_srates_elem(struct sk_buff *skb, + const struct ieee80211_supported_band *sband, + u32 basic_rates, u32 rate_flags, u32 masked_rates, + u8 element_id); +int ieee80211_put_he_cap(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata, + const struct ieee80211_supported_band *sband, + const struct ieee80211_conn_settings *conn); +int ieee80211_put_he_6ghz_cap(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata, + enum ieee80211_smps_mode smps_mode); +int ieee80211_put_eht_cap(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata, + const struct ieee80211_supported_band *sband, + const struct ieee80211_conn_settings *conn); /* channel management */ bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper, @@ -2488,23 +2525,36 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, u32 vht_cap_info, const struct ieee80211_ht_operation *htop, struct cfg80211_chan_def *chandef); void ieee80211_chandef_eht_oper(const struct ieee80211_eht_operation_info *info, - bool support_160, bool support_320, struct cfg80211_chan_def *chandef); -bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, +bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_local *local, const struct ieee80211_he_operation *he_oper, const struct ieee80211_eht_operation *eht_oper, struct cfg80211_chan_def *chandef); bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper, struct cfg80211_chan_def *chandef); -ieee80211_conn_flags_t ieee80211_chandef_downgrade(struct cfg80211_chan_def *c); +void ieee80211_chandef_downgrade(struct cfg80211_chan_def *chandef, + struct ieee80211_conn_settings *conn); +static inline void +ieee80211_chanreq_downgrade(struct ieee80211_chan_req *chanreq, + struct ieee80211_conn_settings *conn) +{ + ieee80211_chandef_downgrade(&chanreq->oper, conn); + if (WARN_ON(!conn)) + return; + if (conn->mode < IEEE80211_CONN_MODE_EHT) + chanreq->ap.chan = NULL; +} + +bool ieee80211_chanreq_identical(const struct ieee80211_chan_req *a, + const struct ieee80211_chan_req *b); int __must_check ieee80211_link_use_channel(struct ieee80211_link_data *link, - const struct cfg80211_chan_def *chandef, + const struct ieee80211_chan_req *req, enum ieee80211_chanctx_mode mode); int __must_check ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, - const struct cfg80211_chan_def *chandef, + const struct ieee80211_chan_req *req, enum ieee80211_chanctx_mode mode, bool radar_required); int __must_check @@ -2512,9 +2562,9 @@ ieee80211_link_use_reserved_context(struct ieee80211_link_data *link); int ieee80211_link_unreserve_chanctx(struct ieee80211_link_data *link); int __must_check -ieee80211_link_change_bandwidth(struct ieee80211_link_data *link, - const struct cfg80211_chan_def *chandef, - u64 *changed); +ieee80211_link_change_chanreq(struct ieee80211_link_data *link, + const struct ieee80211_chan_req *req, + u64 *changed); void ieee80211_link_release_channel(struct ieee80211_link_data *link); void ieee80211_link_vlan_copy_chanctx(struct ieee80211_link_data *link); void ieee80211_link_copy_chanctx_to_vlans(struct ieee80211_link_data *link, @@ -2561,7 +2611,7 @@ int ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev, 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_teardown_tdls_peers(struct ieee80211_link_data *link); void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata, const u8 *peer, u16 reason); void @@ -2589,12 +2639,7 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache); void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache); -u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata, u8 iftype); -u8 *ieee80211_ie_build_eht_cap(u8 *pos, - const struct ieee80211_sta_he_cap *he_cap, - const struct ieee80211_sta_eht_cap *eht_cap, - u8 *end, - bool for_ap); +u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata); void ieee80211_eht_cap_ie_to_sta_eht_cap(struct ieee80211_sub_if_data *sdata, @@ -2603,6 +2648,12 @@ ieee80211_eht_cap_ie_to_sta_eht_cap(struct ieee80211_sub_if_data *sdata, const struct ieee80211_eht_cap_elem *eht_cap_ie_elem, u8 eht_cap_len, struct link_sta_info *link_sta); +void ieee80211_process_neg_ttlm_req(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len); +void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len); +int ieee80211_req_neg_ttlm(struct ieee80211_sub_if_data *sdata, + struct cfg80211_ttlm_params *params); void ieee80211_check_wbrf_support(struct ieee80211_local *local); void ieee80211_add_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 11c4caa4748e..395de62d9cb2 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -8,7 +8,7 @@ * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> @@ -511,7 +511,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do * would have removed them, but in other modes there shouldn't * be any stations. */ - flushed = sta_info_flush(sdata); + flushed = sta_info_flush(sdata, -1); WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN && flushed > 0); /* don't count this interface for allmulti while it is down */ @@ -544,10 +544,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do sdata->vif.bss_conf.csa_active = false; if (sdata->vif.type == NL80211_IFTYPE_STATION) sdata->deflink.u.mgd.csa_waiting_bcn = false; - if (sdata->deflink.csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->deflink.csa_block_tx = false; + sdata->csa_blocked_tx = false; } wiphy_work_cancel(local->hw.wiphy, &sdata->deflink.csa_finalize_work); @@ -557,7 +557,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do &sdata->deflink.dfs_cac_timer_work); if (sdata->wdev.cac_started) { - chandef = sdata->vif.bss_conf.chandef; + chandef = sdata->vif.bss_conf.chanreq.oper; WARN_ON(local->suspended); ieee80211_link_release_channel(&sdata->deflink); cfg80211_cac_event(sdata->dev, &chandef, @@ -1164,7 +1164,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) rcu_assign_pointer(local->monitor_sdata, sdata); mutex_unlock(&local->iflist_mtx); - ret = ieee80211_link_use_channel(&sdata->deflink, &local->monitor_chandef, + ret = ieee80211_link_use_channel(&sdata->deflink, &local->monitor_chanreq, IEEE80211_CHANCTX_EXCLUSIVE); if (ret) { mutex_lock(&local->iflist_mtx); @@ -1252,7 +1252,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) sdata->vif.cab_queue = master->vif.cab_queue; memcpy(sdata->vif.hw_queue, master->vif.hw_queue, sizeof(sdata->vif.hw_queue)); - sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef; + sdata->vif.bss_conf.chanreq = master->vif.bss_conf.chanreq; sdata->crypto_tx_tailroom_needed_cnt += master->crypto_tx_tailroom_needed_cnt; @@ -1288,8 +1288,6 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) res = drv_start(local); if (res) goto err_del_bss; - /* we're brought up, everything changes */ - hw_reconf_flags = ~0; ieee80211_led_radio(local, true); ieee80211_mod_tpt_led_trig(local, IEEE80211_TPT_LEDTRIG_FL_RADIO, 0); @@ -1436,7 +1434,9 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) if (coming_up) local->open_count++; - if (hw_reconf_flags) + if (local->open_count == 1) + ieee80211_hw_conf_init(local); + else if (hw_reconf_flags) ieee80211_hw_config(local, hw_reconf_flags); ieee80211_recalc_ps(local); @@ -1546,6 +1546,22 @@ static void ieee80211_iface_process_skb(struct ieee80211_local *local, default: break; } + } else if (ieee80211_is_action(mgmt->frame_control) && + mgmt->u.action.category == WLAN_CATEGORY_PROTECTED_EHT) { + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + switch (mgmt->u.action.u.ttlm_req.action_code) { + case WLAN_PROTECTED_EHT_ACTION_TTLM_REQ: + ieee80211_process_neg_ttlm_req(sdata, mgmt, + skb->len); + break; + case WLAN_PROTECTED_EHT_ACTION_TTLM_RES: + ieee80211_process_neg_ttlm_res(sdata, mgmt, + skb->len); + break; + default: + break; + } + } } else if (ieee80211_is_ext(mgmt->frame_control)) { if (sdata->vif.type == NL80211_IFTYPE_STATION) ieee80211_sta_rx_queued_ext(sdata, skb); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index af74d7f9d94d..eecdd2265eaa 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -6,7 +6,7 @@ * Copyright 2007-2008 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright 2018-2020, 2022-2023 Intel Corporation + * Copyright 2018-2020, 2022-2024 Intel Corporation */ #include <crypto/utils.h> @@ -925,6 +925,10 @@ int ieee80211_key_link(struct ieee80211_key *key, */ key->color = atomic_inc_return(&key_color); + /* keep this flag for easier access later */ + if (sta && sta->sta.spp_amsdu) + key->conf.flags |= IEEE80211_KEY_FLAG_SPP_AMSDU; + increment_tailroom_need_count(sdata); ret = ieee80211_key_replace(sdata, link, sta, pairwise, old_key, key); @@ -1368,12 +1372,19 @@ EXPORT_SYMBOL_GPL(ieee80211_remove_key); struct ieee80211_key_conf * ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, - struct ieee80211_key_conf *keyconf) + struct ieee80211_key_conf *keyconf, + int link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; int err; + struct ieee80211_link_data *link_data = + link_id < 0 ? &sdata->deflink : + sdata_dereference(sdata->link[link_id], sdata); + + if (WARN_ON(!link_data)) + return ERR_PTR(-EINVAL); if (WARN_ON(!local->wowlan)) return ERR_PTR(-EINVAL); @@ -1390,8 +1401,9 @@ ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, if (sdata->u.mgd.mfp != IEEE80211_MFP_DISABLED) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; - /* FIXME: this function needs to get a link ID */ - err = ieee80211_key_link(key, &sdata->deflink, NULL); + key->conf.link_id = link_id; + + err = ieee80211_key_link(key, link_data, NULL); if (err) return ERR_PTR(err); diff --git a/net/mac80211/link.c b/net/mac80211/link.c index d4f86955afa6..685ec66b4264 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -2,7 +2,7 @@ /* * MLO link handling * - * Copyright (C) 2022-2023 Intel Corporation + * Copyright (C) 2022-2024 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> @@ -73,6 +73,8 @@ void ieee80211_link_stop(struct ieee80211_link_data *link) ieee80211_mgd_stop_link(link); cancel_delayed_work_sync(&link->color_collision_detect_work); + wiphy_work_cancel(link->sdata->local->hw.wiphy, + &link->csa_finalize_work); ieee80211_link_release_channel(link); } @@ -354,7 +356,7 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, link = sdata_dereference(sdata->link[link_id], sdata); - /* FIXME: kill TDLS connections on the link */ + ieee80211_teardown_tdls_peers(link); ieee80211_link_release_channel(link); } @@ -402,7 +404,8 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, link = sdata_dereference(sdata->link[link_id], sdata); - ret = ieee80211_link_use_channel(link, &link->conf->chandef, + ret = ieee80211_link_use_channel(link, + &link->conf->chanreq, IEEE80211_CHANCTX_SHARED); WARN_ON_ONCE(ret); @@ -444,6 +447,9 @@ int ieee80211_set_active_links(struct ieee80211_vif *vif, u16 active_links) lockdep_assert_wiphy(local->hw.wiphy); + if (WARN_ON(!active_links)) + return -EINVAL; + if (!drv_can_activate_links(local, sdata, active_links)) return -EINVAL; @@ -472,6 +478,9 @@ void ieee80211_set_active_links_async(struct ieee80211_vif *vif, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + if (WARN_ON(!active_links)) + return; + if (!ieee80211_sdata_running(sdata)) return; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index f2ece7793573..4eaea0a9975b 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -93,16 +93,32 @@ static void ieee80211_reconfig_filter(struct wiphy *wiphy, ieee80211_configure_filter(local); } -static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local) +static u32 ieee80211_calc_hw_conf_chan(struct ieee80211_local *local, + struct ieee80211_chanctx_conf *ctx) { struct ieee80211_sub_if_data *sdata; struct cfg80211_chan_def chandef = {}; + struct cfg80211_chan_def *oper = NULL; + enum ieee80211_smps_mode smps_mode = IEEE80211_SMPS_STATIC; u32 changed = 0; int power; u32 offchannel_flag; + if (!local->emulate_chanctx) + return 0; + offchannel_flag = local->hw.conf.flags & IEEE80211_CONF_OFFCHANNEL; + if (ctx && !WARN_ON(!ctx->def.chan)) { + oper = &ctx->def; + if (ctx->rx_chains_static > 1) + smps_mode = IEEE80211_SMPS_OFF; + else if (ctx->rx_chains_dynamic > 1) + smps_mode = IEEE80211_SMPS_DYNAMIC; + else + smps_mode = IEEE80211_SMPS_STATIC; + } + if (local->scan_chandef.chan) { chandef = local->scan_chandef; } else if (local->tmp_channel) { @@ -110,25 +126,30 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local) chandef.width = NL80211_CHAN_WIDTH_20_NOHT; chandef.center_freq1 = chandef.chan->center_freq; chandef.freq1_offset = chandef.chan->freq_offset; - } else - chandef = local->_oper_chandef; + } else if (oper) { + chandef = *oper; + } else { + chandef = local->dflt_chandef; + } - WARN(!cfg80211_chandef_valid(&chandef), - "control:%d.%03d MHz width:%d center: %d.%03d/%d MHz", - chandef.chan->center_freq, chandef.chan->freq_offset, - chandef.width, chandef.center_freq1, chandef.freq1_offset, - chandef.center_freq2); + if (WARN(!cfg80211_chandef_valid(&chandef), + "control:%d.%03d MHz width:%d center: %d.%03d/%d MHz", + chandef.chan ? chandef.chan->center_freq : -1, + chandef.chan ? chandef.chan->freq_offset : 0, + chandef.width, chandef.center_freq1, chandef.freq1_offset, + chandef.center_freq2)) + return 0; - if (!cfg80211_chandef_identical(&chandef, &local->_oper_chandef)) + if (!oper || !cfg80211_chandef_identical(&chandef, oper)) local->hw.conf.flags |= IEEE80211_CONF_OFFCHANNEL; else local->hw.conf.flags &= ~IEEE80211_CONF_OFFCHANNEL; offchannel_flag ^= local->hw.conf.flags & IEEE80211_CONF_OFFCHANNEL; - if (offchannel_flag || - !cfg80211_chandef_identical(&local->hw.conf.chandef, - &local->_oper_chandef)) { + /* force it also for scanning, since drivers might config differently */ + if (offchannel_flag || local->scanning || + !cfg80211_chandef_identical(&local->hw.conf.chandef, &chandef)) { local->hw.conf.chandef = chandef; changed |= IEEE80211_CONF_CHANGE_CHANNEL; } @@ -140,8 +161,8 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local) * that otherwise STATIC is used. */ local->hw.conf.smps_mode = IEEE80211_SMPS_STATIC; - } else if (local->hw.conf.smps_mode != local->smps_mode) { - local->hw.conf.smps_mode = local->smps_mode; + } else if (local->hw.conf.smps_mode != smps_mode) { + local->hw.conf.smps_mode = smps_mode; changed |= IEEE80211_CONF_CHANGE_SMPS; } @@ -173,12 +194,9 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) might_sleep(); - if (!local->use_chanctx) - changed |= ieee80211_hw_conf_chan(local); - else - changed &= ~(IEEE80211_CONF_CHANGE_CHANNEL | - IEEE80211_CONF_CHANGE_POWER | - IEEE80211_CONF_CHANGE_SMPS); + WARN_ON(changed & (IEEE80211_CONF_CHANGE_CHANNEL | + IEEE80211_CONF_CHANGE_POWER | + IEEE80211_CONF_CHANGE_SMPS)); if (changed && local->open_count) { ret = drv_config(local, changed); @@ -202,13 +220,115 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) return ret; } +/* for scanning, offchannel and chanctx emulation only */ +static int _ieee80211_hw_conf_chan(struct ieee80211_local *local, + struct ieee80211_chanctx_conf *ctx) +{ + u32 changed; + + if (!local->open_count) + return 0; + + changed = ieee80211_calc_hw_conf_chan(local, ctx); + if (!changed) + return 0; + + return drv_config(local, changed); +} + +int ieee80211_hw_conf_chan(struct ieee80211_local *local) +{ + struct ieee80211_chanctx *ctx; + + ctx = list_first_entry_or_null(&local->chanctx_list, + struct ieee80211_chanctx, + list); + + return _ieee80211_hw_conf_chan(local, ctx ? &ctx->conf : NULL); +} + +void ieee80211_hw_conf_init(struct ieee80211_local *local) +{ + u32 changed = ~(IEEE80211_CONF_CHANGE_CHANNEL | + IEEE80211_CONF_CHANGE_POWER | + IEEE80211_CONF_CHANGE_SMPS); + + if (WARN_ON(!local->open_count)) + return; + + if (local->emulate_chanctx) { + struct ieee80211_chanctx *ctx; + + ctx = list_first_entry_or_null(&local->chanctx_list, + struct ieee80211_chanctx, + list); + + changed |= ieee80211_calc_hw_conf_chan(local, + ctx ? &ctx->conf : NULL); + } + + WARN_ON(drv_config(local, changed)); +} + +int ieee80211_emulate_add_chanctx(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *ctx) +{ + struct ieee80211_local *local = hw_to_local(hw); + + local->hw.conf.radar_enabled = ctx->radar_enabled; + + return _ieee80211_hw_conf_chan(local, ctx); +} +EXPORT_SYMBOL(ieee80211_emulate_add_chanctx); + +void ieee80211_emulate_remove_chanctx(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *ctx) +{ + struct ieee80211_local *local = hw_to_local(hw); + + local->hw.conf.radar_enabled = false; + + _ieee80211_hw_conf_chan(local, NULL); +} +EXPORT_SYMBOL(ieee80211_emulate_remove_chanctx); + +void ieee80211_emulate_change_chanctx(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *ctx, + u32 changed) +{ + struct ieee80211_local *local = hw_to_local(hw); + + local->hw.conf.radar_enabled = ctx->radar_enabled; + + _ieee80211_hw_conf_chan(local, ctx); +} +EXPORT_SYMBOL(ieee80211_emulate_change_chanctx); + +int ieee80211_emulate_switch_vif_chanctx(struct ieee80211_hw *hw, + struct ieee80211_vif_chanctx_switch *vifs, + int n_vifs, + enum ieee80211_chanctx_switch_mode mode) +{ + struct ieee80211_local *local = hw_to_local(hw); + + if (n_vifs <= 0) + return -EINVAL; + + local->hw.conf.radar_enabled = vifs[0].new_ctx->radar_enabled; + _ieee80211_hw_conf_chan(local, vifs[0].new_ctx); + + return 0; +} +EXPORT_SYMBOL(ieee80211_emulate_switch_vif_chanctx); + #define BSS_CHANGED_VIF_CFG_FLAGS (BSS_CHANGED_ASSOC |\ BSS_CHANGED_IDLE |\ BSS_CHANGED_PS |\ BSS_CHANGED_IBSS |\ BSS_CHANGED_ARP_FILTER |\ BSS_CHANGED_SSID |\ - BSS_CHANGED_MLD_VALID_LINKS) + BSS_CHANGED_MLD_VALID_LINKS |\ + BSS_CHANGED_MLD_TTLM) void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, u64 changed) @@ -644,7 +764,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, struct ieee80211_local *local; int priv_size, i; struct wiphy *wiphy; - bool use_chanctx; + bool emulate_chanctx; if (WARN_ON(!ops->tx || !ops->start || !ops->stop || !ops->config || !ops->add_interface || !ops->remove_interface || @@ -659,12 +779,26 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, return NULL; /* check all or no channel context operations exist */ - i = !!ops->add_chanctx + !!ops->remove_chanctx + - !!ops->change_chanctx + !!ops->assign_vif_chanctx + - !!ops->unassign_vif_chanctx; - if (WARN_ON(i != 0 && i != 5)) - return NULL; - use_chanctx = i == 5; + if (ops->add_chanctx == ieee80211_emulate_add_chanctx && + ops->remove_chanctx == ieee80211_emulate_remove_chanctx && + ops->change_chanctx == ieee80211_emulate_change_chanctx) { + if (WARN_ON(ops->assign_vif_chanctx || + ops->unassign_vif_chanctx)) + return NULL; + emulate_chanctx = true; + } else { + if (WARN_ON(ops->add_chanctx == ieee80211_emulate_add_chanctx || + ops->remove_chanctx == ieee80211_emulate_remove_chanctx || + ops->change_chanctx == ieee80211_emulate_change_chanctx)) + return NULL; + if (WARN_ON(!ops->add_chanctx || + !ops->remove_chanctx || + !ops->change_chanctx || + !ops->assign_vif_chanctx || + !ops->unassign_vif_chanctx)) + return NULL; + emulate_chanctx = false; + } /* Ensure 32-byte alignment of our private data and hw private data. * We use the wiphy priv data for both our ieee80211_local and for @@ -698,7 +832,7 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, WIPHY_FLAG_REPORTS_OBSS | WIPHY_FLAG_OFFCHAN_TX; - if (!use_chanctx || ops->remain_on_channel) + if (emulate_chanctx || ops->remain_on_channel) wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL; wiphy->features |= NL80211_FEATURE_SK_TX_STATUS | @@ -734,8 +868,11 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT); } - if (!ops->set_key) + if (!ops->set_key) { wiphy->flags |= WIPHY_FLAG_IBSS_RSN; + wiphy_ext_feature_set(wiphy, + NL80211_EXT_FEATURE_SPP_AMSDU_SUPPORT); + } wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_TXQS); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_RRM); @@ -752,7 +889,10 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, local->hw.priv = (char *)local + ALIGN(sizeof(*local), NETDEV_ALIGN); local->ops = ops; - local->use_chanctx = use_chanctx; + local->emulate_chanctx = emulate_chanctx; + + if (emulate_chanctx) + ieee80211_hw_set(&local->hw, CHANCTX_STA_CSA); /* * We need a bit of data queued to build aggregates properly, so @@ -829,7 +969,6 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, ieee80211_dfs_radar_detected_work); wiphy_work_init(&local->reconfig_filter, ieee80211_reconfig_filter); - local->smps_mode = IEEE80211_SMPS_OFF; wiphy_work_init(&local->dynamic_ps_enable_work, ieee80211_dynamic_ps_enable_work); @@ -980,7 +1119,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) * as much, e.g. monitoring beacons would be hard if we * might not even know which link is active at which time. */ - if (WARN_ON(!local->use_chanctx)) + if (WARN_ON(local->emulate_chanctx)) return -EINVAL; if (WARN_ON(!local->ops->link_info_changed)) @@ -1024,7 +1163,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) return -EINVAL; #endif - if (!local->use_chanctx) { + if (local->emulate_chanctx) { for (i = 0; i < local->hw.wiphy->n_iface_combinations; i++) { const struct ieee80211_iface_combination *comb; @@ -1090,11 +1229,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) &sband->channels[i], NL80211_CHAN_NO_HT); /* init channel we're on */ - if (!local->use_chanctx && !local->_oper_chandef.chan) { + local->monitor_chanreq.oper = dflt_chandef; + if (local->emulate_chanctx) { + local->dflt_chandef = dflt_chandef; local->hw.conf.chandef = dflt_chandef; - local->_oper_chandef = dflt_chandef; } - local->monitor_chandef = dflt_chandef; } channels += sband->n_channels; @@ -1115,8 +1254,26 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) supp_vht = supp_vht || sband->vht_cap.vht_supported; for_each_sband_iftype_data(sband, i, iftd) { + u8 he_40_mhz_cap; + supp_he = supp_he || iftd->he_cap.has_he; supp_eht = supp_eht || iftd->eht_cap.has_eht; + + if (band == NL80211_BAND_2GHZ) + he_40_mhz_cap = + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G; + else + he_40_mhz_cap = + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G; + + /* currently no support for HE client where HT has 40 MHz but not HT */ + if (iftd->he_cap.has_he && + iftd->types_mask & (BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_P2P_CLIENT)) && + sband->ht_cap.ht_supported && + sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 && + !(iftd->he_cap.he_cap_elem.phy_cap_info[0] & he_40_mhz_cap)) + return -EINVAL; } /* HT, VHT, HE require QoS, thus >= 4 queues */ diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index fccbcde3359a..32475da98d73 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, 2009 open80211s Ltd. - * Copyright (C) 2018 - 2023 Intel Corporation + * Copyright (C) 2018 - 2024 Intel Corporation * Authors: Luis Carlos Cobo <luisca@cozybit.com> * Javier Cardona <javier@cozybit.com> */ @@ -97,7 +97,7 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, if (sdata->vif.bss_conf.basic_rates != basic_rates) return false; - cfg80211_chandef_create(&sta_chan_def, sdata->vif.bss_conf.chandef.chan, + cfg80211_chandef_create(&sta_chan_def, sdata->vif.bss_conf.chanreq.oper.chan, NL80211_CHAN_NO_HT); ieee80211_chandef_ht_oper(ie->ht_operation, &sta_chan_def); @@ -107,10 +107,11 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, ieee80211_chandef_vht_oper(&sdata->local->hw, vht_cap_info, ie->vht_operation, ie->ht_operation, &sta_chan_def); - ieee80211_chandef_he_6ghz_oper(sdata, ie->he_operation, ie->eht_operation, + ieee80211_chandef_he_6ghz_oper(sdata->local, ie->he_operation, + ie->eht_operation, &sta_chan_def); - if (!cfg80211_chandef_compatible(&sdata->vif.bss_conf.chandef, + if (!cfg80211_chandef_compatible(&sdata->vif.bss_conf.chanreq.oper, &sta_chan_def)) return false; @@ -435,9 +436,9 @@ int mesh_add_ht_cap_ie(struct ieee80211_sub_if_data *sdata, return 0; if (!sband->ht_cap.ht_supported || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_10) return 0; if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_ht_cap)) @@ -476,16 +477,16 @@ int mesh_add_ht_oper_ie(struct ieee80211_sub_if_data *sdata, return 0; if (!ht_cap->ht_supported || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_10) return 0; if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_ht_operation)) return -ENOMEM; pos = skb_put(skb, 2 + sizeof(struct ieee80211_ht_operation)); - ieee80211_ie_build_ht_oper(pos, ht_cap, &sdata->vif.bss_conf.chandef, + ieee80211_ie_build_ht_oper(pos, ht_cap, &sdata->vif.bss_conf.chanreq.oper, sdata->vif.bss_conf.ht_operation_mode, false); @@ -507,9 +508,9 @@ int mesh_add_vht_cap_ie(struct ieee80211_sub_if_data *sdata, return 0; if (!sband->vht_cap.vht_supported || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_10) return 0; if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_vht_cap)) @@ -548,9 +549,9 @@ int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata, return 0; if (!vht_cap->vht_supported || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_10) return 0; if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_vht_operation)) @@ -558,7 +559,7 @@ int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata, pos = skb_put(skb, 2 + sizeof(struct ieee80211_vht_operation)); ieee80211_ie_build_vht_oper(pos, vht_cap, - &sdata->vif.bss_conf.chandef); + &sdata->vif.bss_conf.chanreq.oper); return 0; } @@ -566,29 +567,18 @@ int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata, int mesh_add_he_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u8 ie_len) { - const struct ieee80211_sta_he_cap *he_cap; struct ieee80211_supported_band *sband; - u8 *pos; sband = ieee80211_get_sband(sdata); if (!sband) return -EINVAL; - he_cap = ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT); - - if (!he_cap || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + if (sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_10) return 0; - if (skb_tailroom(skb) < ie_len) - return -ENOMEM; - - pos = skb_put(skb, ie_len); - ieee80211_ie_build_he_cap(0, pos, he_cap, pos + ie_len); - - return 0; + return ieee80211_put_he_cap(skb, sdata, sband, NULL); } int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, @@ -605,20 +595,20 @@ int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, he_cap = ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT); if (!he_cap || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_10) return 0; len = 2 + 1 + sizeof(struct ieee80211_he_operation); - if (sdata->vif.bss_conf.chandef.chan->band == NL80211_BAND_6GHZ) + if (sdata->vif.bss_conf.chanreq.oper.chan->band == NL80211_BAND_6GHZ) len += sizeof(struct ieee80211_he_6ghz_oper); if (skb_tailroom(skb) < len) return -ENOMEM; pos = skb_put(skb, len); - ieee80211_ie_build_he_oper(pos, &sdata->vif.bss_conf.chandef); + ieee80211_ie_build_he_oper(pos, &sdata->vif.bss_conf.chanreq.oper); return 0; } @@ -639,37 +629,25 @@ int mesh_add_he_6ghz_cap_ie(struct ieee80211_sub_if_data *sdata, if (!iftd) return 0; - ieee80211_ie_build_he_6ghz_cap(sdata, sdata->deflink.smps_mode, skb); + ieee80211_put_he_6ghz_cap(skb, sdata, sdata->deflink.smps_mode); return 0; } int mesh_add_eht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u8 ie_len) { - const struct ieee80211_sta_he_cap *he_cap; - const struct ieee80211_sta_eht_cap *eht_cap; struct ieee80211_supported_band *sband; - u8 *pos; sband = ieee80211_get_sband(sdata); if (!sband) return -EINVAL; - he_cap = ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT); - eht_cap = ieee80211_get_eht_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT); - if (!he_cap || !eht_cap || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + if (sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_10) return 0; - if (skb_tailroom(skb) < ie_len) - return -ENOMEM; - - pos = skb_put(skb, ie_len); - ieee80211_ie_build_eht_cap(pos, he_cap, eht_cap, pos + ie_len, false); - - return 0; + return ieee80211_put_eht_cap(skb, sdata, sband, NULL); } int mesh_add_eht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) @@ -685,9 +663,9 @@ int mesh_add_eht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *sk eht_cap = ieee80211_get_eht_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT); if (!eht_cap || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_10) return 0; len = 2 + 1 + offsetof(struct ieee80211_eht_operation, optional) + @@ -697,7 +675,7 @@ int mesh_add_eht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *sk return -ENOMEM; pos = skb_put(skb, len); - ieee80211_ie_build_eht_oper(pos, &sdata->vif.bss_conf.chandef, eht_cap); + ieee80211_ie_build_eht_oper(pos, &sdata->vif.bss_conf.chanreq.oper, eht_cap); return 0; } @@ -745,9 +723,9 @@ ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata, return; if (!ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT) || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 || - sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10) + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + sdata->vif.bss_conf.chanreq.oper.width == NL80211_CHAN_WIDTH_10) return; sdata->vif.bss_conf.he_support = true; @@ -966,24 +944,22 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) int head_len, tail_len; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; - struct ieee80211_chanctx_conf *chanctx_conf; struct mesh_csa_settings *csa; - enum nl80211_band band; + const struct ieee80211_supported_band *sband; u8 ie_len_he_cap, ie_len_eht_cap; u8 *pos; struct ieee80211_sub_if_data *sdata; int hdr_len = offsetofend(struct ieee80211_mgmt, u.beacon); + u32 rate_flags; sdata = container_of(ifmsh, struct ieee80211_sub_if_data, u.mesh); - rcu_read_lock(); - chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf); - band = chanctx_conf->def.chan->band; - rcu_read_unlock(); - ie_len_he_cap = ieee80211_ie_len_he_cap(sdata, - NL80211_IFTYPE_MESH_POINT); - ie_len_eht_cap = ieee80211_ie_len_eht_cap(sdata, - NL80211_IFTYPE_MESH_POINT); + sband = ieee80211_get_sband(sdata); + rate_flags = + ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chanreq.oper); + + ie_len_he_cap = ieee80211_ie_len_he_cap(sdata); + ie_len_eht_cap = ieee80211_ie_len_eht_cap(sdata); head_len = hdr_len + 2 + /* NULL SSID */ /* Channel Switch Announcement */ @@ -1107,7 +1083,9 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) } rcu_read_unlock(); - if (ieee80211_add_srates_ie(sdata, skb, true, band) || + if (ieee80211_put_srates_elem(skb, sband, + sdata->vif.bss_conf.basic_rates, + rate_flags, 0, WLAN_EID_SUPP_RATES) || mesh_add_ds_params_ie(sdata, skb)) goto out_free; @@ -1118,7 +1096,9 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh) skb_trim(skb, 0); bcn->tail = bcn->head + bcn->head_len; - if (ieee80211_add_ext_srates_ie(sdata, skb, true, band) || + if (ieee80211_put_srates_elem(skb, sband, + sdata->vif.bss_conf.basic_rates, + rate_flags, 0, WLAN_EID_EXT_SUPP_RATES) || mesh_add_rsn_ie(sdata, skb) || mesh_add_ht_cap_ie(sdata, skb) || mesh_add_ht_oper_ie(sdata, skb) || @@ -1234,7 +1214,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) netif_carrier_off(sdata->dev); /* flush STAs and mpaths on this iface */ - sta_info_flush(sdata); + sta_info_flush(sdata, -1); ieee80211_free_keys(sdata, true); mesh_path_flush_by_iface(sdata); @@ -1276,11 +1256,12 @@ static void ieee80211_mesh_csa_mark_radar(struct ieee80211_sub_if_data *sdata) * unavailable. */ err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy, - &sdata->vif.bss_conf.chandef, + &sdata->vif.bss_conf.chanreq.oper, NL80211_IFTYPE_MESH_POINT); if (err > 0) cfg80211_radar_event(sdata->local->hw.wiphy, - &sdata->vif.bss_conf.chandef, GFP_ATOMIC); + &sdata->vif.bss_conf.chanreq.oper, + GFP_ATOMIC); } static bool @@ -1292,7 +1273,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee80211_supported_band *sband; int err; - ieee80211_conn_flags_t conn_flags = 0; + struct ieee80211_conn_settings conn = ieee80211_conn_settings_unlimited; u32 vht_cap_info = 0; lockdep_assert_wiphy(sdata->local->hw.wiphy); @@ -1301,15 +1282,18 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, if (!sband) return false; - switch (sdata->vif.bss_conf.chandef.width) { + switch (sdata->vif.bss_conf.chanreq.oper.width) { case NL80211_CHAN_WIDTH_20_NOHT: - conn_flags |= IEEE80211_CONN_DISABLE_HT; - fallthrough; + conn.mode = IEEE80211_CONN_MODE_LEGACY; + conn.bw_limit = IEEE80211_CONN_BW_LIMIT_20; + break; case NL80211_CHAN_WIDTH_20: - conn_flags |= IEEE80211_CONN_DISABLE_40MHZ; - fallthrough; + conn.mode = IEEE80211_CONN_MODE_HT; + conn.bw_limit = IEEE80211_CONN_BW_LIMIT_20; + break; case NL80211_CHAN_WIDTH_40: - conn_flags |= IEEE80211_CONN_DISABLE_VHT; + conn.mode = IEEE80211_CONN_MODE_HT; + conn.bw_limit = IEEE80211_CONN_BW_LIMIT_40; break; default: break; @@ -1321,8 +1305,8 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); err = ieee80211_parse_ch_switch_ie(sdata, elems, sband->band, - vht_cap_info, - conn_flags, sdata->vif.addr, + vht_cap_info, &conn, + sdata->vif.addr, &csa_ie); if (err < 0) return false; @@ -1335,7 +1319,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, if (csa_ie.reason_code == WLAN_REASON_MESH_CHAN_REGULATORY) ieee80211_mesh_csa_mark_radar(sdata); - params.chandef = csa_ie.chandef; + params.chandef = csa_ie.chanreq.oper; params.count = csa_ie.count; if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, ¶ms.chandef, @@ -1371,7 +1355,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, params.radar_required = err; if (cfg80211_chandef_identical(¶ms.chandef, - &sdata->vif.bss_conf.chandef)) { + &sdata->vif.bss_conf.chanreq.oper)) { mcsa_dbg(sdata, "received csa with an identical chandef, ignoring\n"); return true; @@ -1551,7 +1535,7 @@ int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata, u64 *changed) *changed |= BSS_CHANGED_BEACON; mcsa_dbg(sdata, "complete switching to center freq %d MHz", - sdata->vif.bss_conf.chandef.chan->center_freq); + sdata->vif.bss_conf.chanreq.oper.chan->center_freq); return 0; } diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index ad8469293d71..d913ce7ba72e 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2008, 2009 open80211s Ltd. - * Copyright (C) 2023 Intel Corporation + * Copyright (C) 2023-2024 Intel Corporation * Authors: Luis Carlos Cobo <luisca@cozybit.com> * Javier Cardona <javier@cozybit.com> */ @@ -94,6 +94,7 @@ enum mesh_deferred_task_flags { * @is_root: the destination station of this path is a root node * @is_gate: the destination station of this path is a mesh gate * @path_change_count: the number of path changes to destination + * @fast_tx_check: timestamp of last fast-xmit enable attempt * * * The dst address is unique in the mesh path table. Since the mesh_path is diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 735edde1bd81..91b55d6a68b9 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -600,11 +600,10 @@ unlock_sta: void mesh_fast_tx_gc(struct ieee80211_sub_if_data *sdata) { unsigned long timeout = msecs_to_jiffies(MESH_FAST_TX_CACHE_TIMEOUT); - struct mesh_tx_cache *cache; + struct mesh_tx_cache *cache = &sdata->u.mesh.tx_cache; struct ieee80211_mesh_fast_tx *entry; struct hlist_node *n; - cache = &sdata->u.mesh.tx_cache; if (atomic_read(&cache->rht.nelems) < MESH_FAST_TX_CACHE_THRESHOLD_SIZE) return; @@ -622,7 +621,6 @@ void mesh_fast_tx_flush_mpath(struct mesh_path *mpath) struct ieee80211_mesh_fast_tx *entry; struct hlist_node *n; - cache = &sdata->u.mesh.tx_cache; spin_lock_bh(&cache->walk_lock); hlist_for_each_entry_safe(entry, n, &cache->walk_head, walk_list) if (entry->mpath == mpath) @@ -637,7 +635,6 @@ void mesh_fast_tx_flush_sta(struct ieee80211_sub_if_data *sdata, struct ieee80211_mesh_fast_tx *entry; struct hlist_node *n; - cache = &sdata->u.mesh.tx_cache; spin_lock_bh(&cache->walk_lock); hlist_for_each_entry_safe(entry, n, &cache->walk_head, walk_list) if (rcu_access_pointer(entry->mpath->next_hop) == sta) @@ -651,7 +648,6 @@ void mesh_fast_tx_flush_addr(struct ieee80211_sub_if_data *sdata, struct mesh_tx_cache *cache = &sdata->u.mesh.tx_cache; struct ieee80211_mesh_fast_tx *entry; - cache = &sdata->u.mesh.tx_cache; spin_lock_bh(&cache->walk_lock); entry = rhashtable_lookup_fast(&cache->rht, addr, fast_tx_rht_params); if (entry) diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 28bf794f67f8..8f2b492a9fe9 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, 2009 open80211s Ltd. - * Copyright (C) 2019, 2021-2023 Intel Corporation + * Copyright (C) 2019, 2021-2024 Intel Corporation * Author: Luis Carlos Cobo <luisca@cozybit.com> */ #include <linux/gfp.h> @@ -163,7 +163,7 @@ static u64 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) u16 ht_opmode; bool non_ht_sta = false, ht20_sta = false; - switch (sdata->vif.bss_conf.chandef.width) { + switch (sdata->vif.bss_conf.chanreq.oper.width) { case NL80211_CHAN_WIDTH_20_NOHT: case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: @@ -196,7 +196,7 @@ static u64 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) if (non_ht_sta) ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED; else if (ht20_sta && - sdata->vif.bss_conf.chandef.width > NL80211_CHAN_WIDTH_20) + sdata->vif.bss_conf.chanreq.oper.width > NL80211_CHAN_WIDTH_20) ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_20MHZ; else ht_opmode = IEEE80211_HT_OP_MODE_PROTECTION_NONE; @@ -226,10 +226,8 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.self_prot); int err = -ENOMEM; - ie_len_he_cap = ieee80211_ie_len_he_cap(sdata, - NL80211_IFTYPE_MESH_POINT); - ie_len_eht_cap = ieee80211_ie_len_eht_cap(sdata, - NL80211_IFTYPE_MESH_POINT); + ie_len_he_cap = ieee80211_ie_len_he_cap(sdata); + ie_len_eht_cap = ieee80211_ie_len_eht_cap(sdata); skb = dev_alloc_skb(local->tx_headroom + hdr_len + 2 + /* capability info */ @@ -266,14 +264,13 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, if (action != WLAN_SP_MESH_PEERING_CLOSE) { struct ieee80211_supported_band *sband; - enum nl80211_band band; + u32 rate_flags, basic_rates; sband = ieee80211_get_sband(sdata); if (!sband) { err = -EINVAL; goto free; } - band = sband->band; /* capability info */ pos = skb_put_zero(skb, 2); @@ -282,8 +279,17 @@ static int mesh_plink_frame_tx(struct ieee80211_sub_if_data *sdata, pos = skb_put(skb, 2); put_unaligned_le16(sta->sta.aid, pos); } - if (ieee80211_add_srates_ie(sdata, skb, true, band) || - ieee80211_add_ext_srates_ie(sdata, skb, true, band) || + + rate_flags = + ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chanreq.oper); + basic_rates = sdata->vif.bss_conf.basic_rates; + + if (ieee80211_put_srates_elem(skb, sband, basic_rates, + rate_flags, 0, + WLAN_EID_SUPP_RATES) || + ieee80211_put_srates_elem(skb, sband, basic_rates, + rate_flags, 0, + WLAN_EID_EXT_SUPP_RATES) || mesh_add_rsn_ie(sdata, skb) || mesh_add_meshid_ie(sdata, skb) || mesh_add_meshconf_ie(sdata, skb)) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 2022a26eb881..47a2cba8313f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -46,6 +46,8 @@ #define IEEE80211_ADV_TTLM_SAFETY_BUFFER_MS msecs_to_jiffies(100) #define IEEE80211_ADV_TTLM_ST_UNDERFLOW 0xff00 +#define IEEE80211_NEG_TTLM_REQ_TIMEOUT (HZ / 5) + static int max_nullfunc_tries = 2; module_param(max_nullfunc_tries, int, 0644); MODULE_PARM_DESC(max_nullfunc_tries, @@ -92,84 +94,6 @@ MODULE_PARM_DESC(probe_wait_ms, #define IEEE80211_SIGNAL_AVE_MIN_COUNT 4 /* - * Extract from the given disabled subchannel bitmap (raw format - * from the EHT Operation Element) the bits for the subchannel - * we're using right now. - */ -static u16 -ieee80211_extract_dis_subch_bmap(const struct ieee80211_eht_operation *eht_oper, - struct cfg80211_chan_def *chandef, u16 bitmap) -{ - struct ieee80211_eht_operation_info *info = (void *)eht_oper->optional; - struct cfg80211_chan_def ap_chandef = *chandef; - u32 ap_center_freq, local_center_freq; - u32 ap_bw, local_bw; - int ap_start_freq, local_start_freq; - u16 shift, mask; - - if (!(eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT) || - !(eht_oper->params & - IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)) - return 0; - - /* set 160/320 supported to get the full AP definition */ - ieee80211_chandef_eht_oper((const void *)eht_oper->optional, - true, true, &ap_chandef); - ap_center_freq = ap_chandef.center_freq1; - ap_bw = 20 * BIT(u8_get_bits(info->control, - IEEE80211_EHT_OPER_CHAN_WIDTH)); - ap_start_freq = ap_center_freq - ap_bw / 2; - local_center_freq = chandef->center_freq1; - local_bw = 20 * BIT(ieee80211_chan_width_to_rx_bw(chandef->width)); - local_start_freq = local_center_freq - local_bw / 2; - shift = (local_start_freq - ap_start_freq) / 20; - mask = BIT(local_bw / 20) - 1; - - return (bitmap >> shift) & mask; -} - -/* - * Handle the puncturing bitmap, possibly downgrading bandwidth to get a - * valid bitmap. - */ -static void -ieee80211_handle_puncturing_bitmap(struct ieee80211_link_data *link, - const struct ieee80211_eht_operation *eht_oper, - u16 bitmap, u64 *changed) -{ - struct cfg80211_chan_def *chandef = &link->conf->chandef; - struct ieee80211_local *local = link->sdata->local; - u16 extracted; - u64 _changed = 0; - - if (!changed) - changed = &_changed; - - while (chandef->width > NL80211_CHAN_WIDTH_40) { - extracted = - ieee80211_extract_dis_subch_bmap(eht_oper, chandef, - bitmap); - - if (cfg80211_valid_disable_subchannel_bitmap(&bitmap, - chandef) && - !(bitmap && ieee80211_hw_check(&local->hw, - DISALLOW_PUNCTURING))) - break; - link->u.mgd.conn_flags |= - ieee80211_chandef_downgrade(chandef); - *changed |= BSS_CHANGED_BANDWIDTH; - } - - if (chandef->width <= NL80211_CHAN_WIDTH_40) - extracted = 0; - - if (link->conf->eht_puncturing != extracted) { - link->conf->eht_puncturing = extracted; - *changed |= BSS_CHANGED_EHT_PUNCTURING; - } -} - -/* * We can have multiple work items (and connection probing) * scheduling this timer, but we need to take care to only * reschedule it when it should fire _earlier_ than it was @@ -223,77 +147,84 @@ static int ecw2cw(int ecw) return (1 << ecw) - 1; } -static ieee80211_conn_flags_t -ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, - struct ieee80211_link_data *link, - ieee80211_conn_flags_t conn_flags, - struct ieee80211_supported_band *sband, - struct ieee80211_channel *channel, - u32 vht_cap_info, - const struct ieee80211_ht_operation *ht_oper, - const struct ieee80211_vht_operation *vht_oper, - const struct ieee80211_he_operation *he_oper, - const struct ieee80211_eht_operation *eht_oper, - const struct ieee80211_s1g_oper_ie *s1g_oper, - struct cfg80211_chan_def *chandef, bool tracking) +static enum ieee80211_conn_mode +ieee80211_determine_ap_chan(struct ieee80211_sub_if_data *sdata, + struct ieee80211_channel *channel, + u32 vht_cap_info, + const struct ieee802_11_elems *elems, + bool ignore_ht_channel_mismatch, + const struct ieee80211_conn_settings *conn, + struct cfg80211_chan_def *chandef) { + const struct ieee80211_ht_operation *ht_oper = elems->ht_operation; + const struct ieee80211_vht_operation *vht_oper = elems->vht_operation; + const struct ieee80211_he_operation *he_oper = elems->he_operation; + const struct ieee80211_eht_operation *eht_oper = elems->eht_operation; + struct ieee80211_supported_band *sband = + sdata->local->hw.wiphy->bands[channel->band]; struct cfg80211_chan_def vht_chandef; - struct ieee80211_sta_ht_cap sta_ht_cap; - ieee80211_conn_flags_t ret; + bool no_vht = false; u32 ht_cfreq; - memset(chandef, 0, sizeof(struct cfg80211_chan_def)); - chandef->chan = channel; - chandef->width = NL80211_CHAN_WIDTH_20_NOHT; - chandef->center_freq1 = channel->center_freq; - chandef->freq1_offset = channel->freq_offset; + *chandef = (struct cfg80211_chan_def) { + .chan = channel, + .width = NL80211_CHAN_WIDTH_20_NOHT, + .center_freq1 = channel->center_freq, + .freq1_offset = channel->freq_offset, + }; - if (channel->band == NL80211_BAND_6GHZ) { - if (!ieee80211_chandef_he_6ghz_oper(sdata, he_oper, eht_oper, - chandef)) { - mlme_dbg(sdata, - "bad 6 GHz operation, disabling HT/VHT/HE/EHT\n"); - ret = IEEE80211_CONN_DISABLE_HT | - IEEE80211_CONN_DISABLE_VHT | - IEEE80211_CONN_DISABLE_HE | - IEEE80211_CONN_DISABLE_EHT; - } else { - ret = 0; - } - vht_chandef = *chandef; - goto out; - } else if (sband->band == NL80211_BAND_S1GHZ) { - if (!ieee80211_chandef_s1g_oper(s1g_oper, chandef)) { + /* get special S1G case out of the way */ + if (sband->band == NL80211_BAND_S1GHZ) { + if (!ieee80211_chandef_s1g_oper(elems->s1g_oper, chandef)) { sdata_info(sdata, "Missing S1G Operation Element? Trying operating == primary\n"); chandef->width = ieee80211_s1g_channel_width(channel); } - ret = IEEE80211_CONN_DISABLE_HT | IEEE80211_CONN_DISABLE_40MHZ | - IEEE80211_CONN_DISABLE_VHT | - IEEE80211_CONN_DISABLE_80P80MHZ | - IEEE80211_CONN_DISABLE_160MHZ; - goto out; + return IEEE80211_CONN_MODE_S1G; } - memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap)); - ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap); + /* get special 6 GHz case out of the way */ + if (sband->band == NL80211_BAND_6GHZ) { + enum ieee80211_conn_mode mode = IEEE80211_CONN_MODE_EHT; - if (!ht_oper || !sta_ht_cap.ht_supported) { - mlme_dbg(sdata, "HT operation missing / HT not supported\n"); - ret = IEEE80211_CONN_DISABLE_HT | - IEEE80211_CONN_DISABLE_VHT | - IEEE80211_CONN_DISABLE_HE | - IEEE80211_CONN_DISABLE_EHT; - goto out; + /* this is an error */ + if (conn->mode < IEEE80211_CONN_MODE_HE) + return IEEE80211_CONN_MODE_LEGACY; + + if (!elems->he_6ghz_capa || !elems->he_cap) { + sdata_info(sdata, + "HE 6 GHz AP is missing HE/HE 6 GHz band capability\n"); + return IEEE80211_CONN_MODE_LEGACY; + } + + if (!eht_oper || !elems->eht_cap) { + eht_oper = NULL; + mode = IEEE80211_CONN_MODE_HE; + } + + if (!ieee80211_chandef_he_6ghz_oper(sdata->local, he_oper, + eht_oper, chandef)) { + sdata_info(sdata, "bad HE/EHT 6 GHz operation\n"); + return IEEE80211_CONN_MODE_LEGACY; + } + + return mode; } + /* now we have the progression HT, VHT, ... */ + if (conn->mode < IEEE80211_CONN_MODE_HT) + return IEEE80211_CONN_MODE_LEGACY; + + if (!ht_oper || !elems->ht_cap_elem) + return IEEE80211_CONN_MODE_LEGACY; + chandef->width = NL80211_CHAN_WIDTH_20; ht_cfreq = ieee80211_channel_to_frequency(ht_oper->primary_chan, channel->band); /* check that channel matches the right operating channel */ - if (!tracking && channel->center_freq != ht_cfreq) { + if (!ignore_ht_channel_mismatch && channel->center_freq != ht_cfreq) { /* * It's possible that some APs are confused here; * Netgear WNDR3700 sometimes reports 4 higher than @@ -305,36 +236,22 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n", channel->center_freq, ht_cfreq, ht_oper->primary_chan, channel->band); - ret = IEEE80211_CONN_DISABLE_HT | - IEEE80211_CONN_DISABLE_VHT | - IEEE80211_CONN_DISABLE_HE | - IEEE80211_CONN_DISABLE_EHT; - goto out; + return IEEE80211_CONN_MODE_LEGACY; } - /* check 40 MHz support, if we have it */ - if (sta_ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40) { - ieee80211_chandef_ht_oper(ht_oper, chandef); - } else { - mlme_dbg(sdata, "40 MHz not supported\n"); - /* 40 MHz (and 80 MHz) must be supported for VHT */ - ret = IEEE80211_CONN_DISABLE_VHT; - /* also mark 40 MHz disabled */ - ret |= IEEE80211_CONN_DISABLE_40MHZ; - goto out; - } + ieee80211_chandef_ht_oper(ht_oper, chandef); - if (!vht_oper || !sband->vht_cap.vht_supported) { - mlme_dbg(sdata, "VHT operation missing / VHT not supported\n"); - ret = IEEE80211_CONN_DISABLE_VHT; - goto out; - } + if (conn->mode < IEEE80211_CONN_MODE_VHT) + return IEEE80211_CONN_MODE_HT; vht_chandef = *chandef; - if (!(conn_flags & IEEE80211_CONN_DISABLE_HE) && - he_oper && - (le32_to_cpu(he_oper->he_oper_params) & - IEEE80211_HE_OPERATION_VHT_OPER_INFO)) { + + /* + * having he_cap/he_oper parsed out implies we're at + * least operating as HE STA + */ + if (elems->he_cap && he_oper && + he_oper->he_oper_params & cpu_to_le32(IEEE80211_HE_OPERATION_VHT_OPER_INFO)) { struct ieee80211_vht_operation he_oper_vht_cap; /* @@ -347,253 +264,614 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, if (!ieee80211_chandef_vht_oper(&sdata->local->hw, vht_cap_info, &he_oper_vht_cap, ht_oper, &vht_chandef)) { - if (!(conn_flags & IEEE80211_CONN_DISABLE_HE)) - sdata_info(sdata, - "HE AP VHT information is invalid, disabling HE\n"); - ret = IEEE80211_CONN_DISABLE_HE | IEEE80211_CONN_DISABLE_EHT; - goto out; + sdata_info(sdata, + "HE AP VHT information is invalid, disabling HE\n"); + /* this will cause us to re-parse as VHT STA */ + return IEEE80211_CONN_MODE_VHT; } + } else if (!vht_oper || !elems->vht_cap_elem) { + if (sband->band == NL80211_BAND_5GHZ) { + sdata_info(sdata, + "VHT information is missing, disabling VHT\n"); + return IEEE80211_CONN_MODE_HT; + } + no_vht = true; + } else if (sband->band == NL80211_BAND_2GHZ) { + no_vht = true; } else if (!ieee80211_chandef_vht_oper(&sdata->local->hw, vht_cap_info, vht_oper, ht_oper, &vht_chandef)) { - if (!(conn_flags & IEEE80211_CONN_DISABLE_VHT)) - sdata_info(sdata, - "AP VHT information is invalid, disabling VHT\n"); - ret = IEEE80211_CONN_DISABLE_VHT; - goto out; + sdata_info(sdata, + "AP VHT information is invalid, disabling VHT\n"); + return IEEE80211_CONN_MODE_HT; } - if (!cfg80211_chandef_valid(&vht_chandef)) { - if (!(conn_flags & IEEE80211_CONN_DISABLE_VHT)) - sdata_info(sdata, - "AP VHT information is invalid, disabling VHT\n"); - ret = IEEE80211_CONN_DISABLE_VHT; - goto out; + if (!cfg80211_chandef_compatible(chandef, &vht_chandef)) { + sdata_info(sdata, + "AP VHT information doesn't match HT, disabling VHT\n"); + return IEEE80211_CONN_MODE_HT; } - if (cfg80211_chandef_identical(chandef, &vht_chandef)) { - ret = 0; - goto out; - } + *chandef = vht_chandef; - if (!cfg80211_chandef_compatible(chandef, &vht_chandef)) { - if (!(conn_flags & IEEE80211_CONN_DISABLE_VHT)) - sdata_info(sdata, - "AP VHT information doesn't match HT, disabling VHT\n"); - ret = IEEE80211_CONN_DISABLE_VHT; - goto out; + /* stick to current max mode if we or the AP don't have HE */ + if (conn->mode < IEEE80211_CONN_MODE_HE || + !elems->he_operation || !elems->he_cap) { + if (no_vht) + return IEEE80211_CONN_MODE_HT; + return IEEE80211_CONN_MODE_VHT; } - *chandef = vht_chandef; + /* stick to HE if we or the AP don't have EHT */ + if (conn->mode < IEEE80211_CONN_MODE_EHT || + !eht_oper || !elems->eht_cap) + return IEEE80211_CONN_MODE_HE; /* * handle the case that the EHT operation indicates that it holds EHT * operation information (in case that the channel width differs from * the channel width reported in HT/VHT/HE). */ - if (eht_oper && (eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT)) { + if (eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT) { struct cfg80211_chan_def eht_chandef = *chandef; ieee80211_chandef_eht_oper((const void *)eht_oper->optional, - eht_chandef.width == - NL80211_CHAN_WIDTH_160, - false, &eht_chandef); + &eht_chandef); + + eht_chandef.punctured = + ieee80211_eht_oper_dis_subchan_bitmap(eht_oper); if (!cfg80211_chandef_valid(&eht_chandef)) { - if (!(conn_flags & IEEE80211_CONN_DISABLE_EHT)) - sdata_info(sdata, - "AP EHT information is invalid, disabling EHT\n"); - ret = IEEE80211_CONN_DISABLE_EHT; - goto out; + sdata_info(sdata, + "AP EHT information is invalid, disabling EHT\n"); + return IEEE80211_CONN_MODE_HE; } if (!cfg80211_chandef_compatible(chandef, &eht_chandef)) { - if (!(conn_flags & IEEE80211_CONN_DISABLE_EHT)) - sdata_info(sdata, - "AP EHT information is incompatible, disabling EHT\n"); - ret = IEEE80211_CONN_DISABLE_EHT; - goto out; + sdata_info(sdata, + "AP EHT information doesn't match HT/VHT/HE, disabling EHT\n"); + return IEEE80211_CONN_MODE_HE; } *chandef = eht_chandef; } - ret = 0; + return IEEE80211_CONN_MODE_EHT; +} + +static bool +ieee80211_verify_peer_he_mcs_support(struct ieee80211_sub_if_data *sdata, + const struct ieee80211_he_cap_elem *he_cap, + const struct ieee80211_he_operation *he_op) +{ + struct ieee80211_he_mcs_nss_supp *he_mcs_nss_supp; + u16 mcs_80_map_tx, mcs_80_map_rx; + u16 ap_min_req_set; + int nss; + + if (!he_cap) + return false; + + /* mcs_nss is right after he_cap info */ + he_mcs_nss_supp = (void *)(he_cap + 1); + + mcs_80_map_tx = le16_to_cpu(he_mcs_nss_supp->tx_mcs_80); + mcs_80_map_rx = le16_to_cpu(he_mcs_nss_supp->rx_mcs_80); + + /* P802.11-REVme/D0.3 + * 27.1.1 Introduction to the HE PHY + * ... + * An HE STA shall support the following features: + * ... + * Single spatial stream HE-MCSs 0 to 7 (transmit and receive) in all + * supported channel widths for HE SU PPDUs + */ + if ((mcs_80_map_tx & 0x3) == IEEE80211_HE_MCS_NOT_SUPPORTED || + (mcs_80_map_rx & 0x3) == IEEE80211_HE_MCS_NOT_SUPPORTED) { + sdata_info(sdata, + "Missing mandatory rates for 1 Nss, rx 0x%x, tx 0x%x, disable HE\n", + mcs_80_map_tx, mcs_80_map_rx); + return false; + } + + if (!he_op) + return true; + + ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set); -out: /* - * When tracking the current AP, don't do any further checks if the - * new chandef is identical to the one we're currently using for the - * connection. This keeps us from playing ping-pong with regulatory, - * without it the following can happen (for example): - * - connect to an AP with 80 MHz, world regdom allows 80 MHz - * - AP advertises regdom US - * - CRDA loads regdom US with 80 MHz prohibited (old database) - * - the code below detects an unsupported channel, downgrades, and - * we disconnect from the AP in the caller - * - disconnect causes CRDA to reload world regdomain and the game - * starts anew. - * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881) + * Apparently iPhone 13 (at least iOS version 15.3.1) sets this to all + * zeroes, which is nonsense, and completely inconsistent with itself + * (it doesn't have 8 streams). Accept the settings in this case anyway. + */ + if (!ap_min_req_set) + return true; + + /* make sure the AP is consistent with itself * - * It seems possible that there are still scenarios with CSA or real - * bandwidth changes where a this could happen, but those cases are - * less common and wouldn't completely prevent using the AP. + * P802.11-REVme/D0.3 + * 26.17.1 Basic HE BSS operation + * + * A STA that is operating in an HE BSS shall be able to receive and + * transmit at each of the <HE-MCS, NSS> tuple values indicated by the + * Basic HE-MCS And NSS Set field of the HE Operation parameter of the + * MLME-START.request primitive and shall be able to receive at each of + * the <HE-MCS, NSS> tuple values indicated by the Supported HE-MCS and + * NSS Set field in the HE Capabilities parameter of the MLMESTART.request + * primitive */ - if (tracking && - cfg80211_chandef_identical(chandef, &link->conf->chandef)) - return ret; + for (nss = 8; nss > 0; nss--) { + u8 ap_op_val = (ap_min_req_set >> (2 * (nss - 1))) & 3; + u8 ap_rx_val; + u8 ap_tx_val; + + if (ap_op_val == IEEE80211_HE_MCS_NOT_SUPPORTED) + continue; - /* don't print the message below for VHT mismatch if VHT is disabled */ - if (ret & IEEE80211_CONN_DISABLE_VHT) - vht_chandef = *chandef; + ap_rx_val = (mcs_80_map_rx >> (2 * (nss - 1))) & 3; + ap_tx_val = (mcs_80_map_tx >> (2 * (nss - 1))) & 3; + + if (ap_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + ap_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + ap_rx_val < ap_op_val || ap_tx_val < ap_op_val) { + sdata_info(sdata, + "Invalid rates for %d Nss, rx %d, tx %d oper %d, disable HE\n", + nss, ap_rx_val, ap_rx_val, ap_op_val); + return false; + } + } + + return true; +} + +static bool +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_iftype_cap_vif(sband, &sdata->vif); + u16 ap_min_req_set; + int i; + + if (!sta_he_cap || !he_op) + return false; + + ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set); /* - * Ignore the DISABLED flag when we're already connected and only - * tracking the APs beacon for bandwidth changes - otherwise we - * might get disconnected here if we connect to an AP, update our - * regulatory information based on the AP's country IE and the - * information we have is wrong/outdated and disables the channel - * that we're actually using for the connection to the AP. + * Apparently iPhone 13 (at least iOS version 15.3.1) sets this to all + * zeroes, which is nonsense, and completely inconsistent with itself + * (it doesn't have 8 streams). Accept the settings in this case anyway. */ - while (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef, - tracking ? 0 : - IEEE80211_CHAN_DISABLED)) { - if (WARN_ON(chandef->width == NL80211_CHAN_WIDTH_20_NOHT)) { - ret = IEEE80211_CONN_DISABLE_HT | - IEEE80211_CONN_DISABLE_VHT | - IEEE80211_CONN_DISABLE_HE | - IEEE80211_CONN_DISABLE_EHT; - break; + if (!ap_min_req_set) + return true; + + /* Need to go over for 80MHz, 160MHz and for 80+80 */ + for (i = 0; i < 3; i++) { + const struct ieee80211_he_mcs_nss_supp *sta_mcs_nss_supp = + &sta_he_cap->he_mcs_nss_supp; + u16 sta_mcs_map_rx = + le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i]); + u16 sta_mcs_map_tx = + le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i + 1]); + u8 nss; + bool verified = true; + + /* + * For each band there is a maximum of 8 spatial streams + * possible. Each of the sta_mcs_map_* is a 16-bit struct built + * of 2 bits per NSS (1-8), with the values defined in enum + * ieee80211_he_mcs_support. Need to make sure STA TX and RX + * capabilities aren't less than the AP's minimum requirements + * for this HE BSS per SS. + * It is enough to find one such band that meets the reqs. + */ + for (nss = 8; nss > 0; nss--) { + u8 sta_rx_val = (sta_mcs_map_rx >> (2 * (nss - 1))) & 3; + u8 sta_tx_val = (sta_mcs_map_tx >> (2 * (nss - 1))) & 3; + u8 ap_val = (ap_min_req_set >> (2 * (nss - 1))) & 3; + + if (ap_val == IEEE80211_HE_MCS_NOT_SUPPORTED) + continue; + + /* + * Make sure the HE AP doesn't require MCSs that aren't + * supported by the client as required by spec + * + * P802.11-REVme/D0.3 + * 26.17.1 Basic HE BSS operation + * + * An HE STA shall not attempt to join * (MLME-JOIN.request primitive) + * a BSS, unless it supports (i.e., is able to both transmit and + * receive using) all of the <HE-MCS, NSS> tuples in the basic + * HE-MCS and NSS set. + */ + if (sta_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + sta_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || + (ap_val > sta_rx_val) || (ap_val > sta_tx_val)) { + verified = false; + break; + } } - ret |= ieee80211_chandef_downgrade(chandef); + if (verified) + return true; + } + + /* If here, STA doesn't meet AP's HE min requirements */ + return false; +} + +static u8 +ieee80211_get_eht_cap_mcs_nss(const struct ieee80211_sta_he_cap *sta_he_cap, + const struct ieee80211_sta_eht_cap *sta_eht_cap, + unsigned int idx, int bw) +{ + u8 he_phy_cap0 = sta_he_cap->he_cap_elem.phy_cap_info[0]; + u8 eht_phy_cap0 = sta_eht_cap->eht_cap_elem.phy_cap_info[0]; + + /* handle us being a 20 MHz-only EHT STA - with four values + * for MCS 0-7, 8-9, 10-11, 12-13. + */ + if (!(he_phy_cap0 & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) + return sta_eht_cap->eht_mcs_nss_supp.only_20mhz.rx_tx_max_nss[idx]; + + /* the others have MCS 0-9 together, rather than separately from 0-7 */ + if (idx > 0) + idx--; + + switch (bw) { + case 0: + return sta_eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_max_nss[idx]; + case 1: + if (!(he_phy_cap0 & + (IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G))) + return 0xff; /* pass check */ + return sta_eht_cap->eht_mcs_nss_supp.bw._160.rx_tx_max_nss[idx]; + case 2: + if (!(eht_phy_cap0 & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ)) + return 0xff; /* pass check */ + return sta_eht_cap->eht_mcs_nss_supp.bw._320.rx_tx_max_nss[idx]; } - if (!he_oper || !cfg80211_chandef_usable(sdata->wdev.wiphy, chandef, - IEEE80211_CHAN_NO_HE)) - ret |= IEEE80211_CONN_DISABLE_HE | IEEE80211_CONN_DISABLE_EHT; + WARN_ON(1); + return 0; +} - if (!eht_oper || !cfg80211_chandef_usable(sdata->wdev.wiphy, chandef, - IEEE80211_CHAN_NO_EHT)) - ret |= IEEE80211_CONN_DISABLE_EHT; +static bool +ieee80211_verify_sta_eht_mcs_support(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + const struct ieee80211_eht_operation *eht_op) +{ + const struct ieee80211_sta_he_cap *sta_he_cap = + ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); + const struct ieee80211_sta_eht_cap *sta_eht_cap = + ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif); + const struct ieee80211_eht_mcs_nss_supp_20mhz_only *req; + unsigned int i; - if (chandef->width != vht_chandef.width && !tracking) + if (!sta_he_cap || !sta_eht_cap || !eht_op) + return false; + + req = &eht_op->basic_mcs_nss; + + for (i = 0; i < ARRAY_SIZE(req->rx_tx_max_nss); i++) { + u8 req_rx_nss, req_tx_nss; + unsigned int bw; + + req_rx_nss = u8_get_bits(req->rx_tx_max_nss[i], + IEEE80211_EHT_MCS_NSS_RX); + req_tx_nss = u8_get_bits(req->rx_tx_max_nss[i], + IEEE80211_EHT_MCS_NSS_TX); + + for (bw = 0; bw < 3; bw++) { + u8 have, have_rx_nss, have_tx_nss; + + have = ieee80211_get_eht_cap_mcs_nss(sta_he_cap, + sta_eht_cap, + i, bw); + have_rx_nss = u8_get_bits(have, + IEEE80211_EHT_MCS_NSS_RX); + have_tx_nss = u8_get_bits(have, + IEEE80211_EHT_MCS_NSS_TX); + + if (req_rx_nss > have_rx_nss || + req_tx_nss > have_tx_nss) + return false; + } + } + + return true; +} + +static bool ieee80211_chandef_usable(struct ieee80211_sub_if_data *sdata, + const struct cfg80211_chan_def *chandef, + u32 prohibited_flags) +{ + if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, + chandef, prohibited_flags)) + return false; + + if (chandef->punctured && + ieee80211_hw_check(&sdata->local->hw, DISALLOW_PUNCTURING)) + return false; + + return true; +} + +static struct ieee802_11_elems * +ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, + struct ieee80211_conn_settings *conn, + struct cfg80211_bss *cbss, int link_id, + struct ieee80211_chan_req *chanreq) +{ + const struct cfg80211_bss_ies *ies = rcu_dereference(cbss->ies); + struct ieee80211_bss *bss = (void *)cbss->priv; + struct ieee80211_channel *channel = cbss->channel; + struct ieee80211_elems_parse_params parse_params = { + .link_id = -1, + .from_ap = true, + .start = ies->data, + .len = ies->len, + .mode = conn->mode, + }; + struct ieee802_11_elems *elems; + struct ieee80211_supported_band *sband; + struct cfg80211_chan_def ap_chandef; + enum ieee80211_conn_mode ap_mode; + int ret; + +again: + elems = ieee802_11_parse_elems_full(&parse_params); + if (!elems) + return ERR_PTR(-ENOMEM); + + ap_mode = ieee80211_determine_ap_chan(sdata, channel, bss->vht_cap_info, + elems, false, conn, &ap_chandef); + + mlme_link_id_dbg(sdata, link_id, "determined AP %pM to be %s\n", + cbss->bssid, ieee80211_conn_mode_str(ap_mode)); + + /* this should be impossible since parsing depends on our mode */ + if (WARN_ON(ap_mode > conn->mode)) { + ret = -EINVAL; + goto free; + } + + sband = sdata->local->hw.wiphy->bands[channel->band]; + + switch (channel->band) { + case NL80211_BAND_S1GHZ: + if (WARN_ON(ap_mode != IEEE80211_CONN_MODE_S1G)) { + ret = -EINVAL; + goto free; + } + return elems; + case NL80211_BAND_6GHZ: + if (ap_mode < IEEE80211_CONN_MODE_HE) { + sdata_info(sdata, + "Rejecting non-HE 6/7 GHz connection"); + ret = -EINVAL; + goto free; + } + break; + default: + if (WARN_ON(ap_mode == IEEE80211_CONN_MODE_S1G)) { + ret = -EINVAL; + goto free; + } + } + + switch (ap_mode) { + case IEEE80211_CONN_MODE_S1G: + WARN_ON(1); + ret = -EINVAL; + goto free; + case IEEE80211_CONN_MODE_LEGACY: + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_20; + break; + case IEEE80211_CONN_MODE_HT: + conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, + conn->bw_limit, + IEEE80211_CONN_BW_LIMIT_40); + break; + case IEEE80211_CONN_MODE_VHT: + case IEEE80211_CONN_MODE_HE: + conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, + conn->bw_limit, + IEEE80211_CONN_BW_LIMIT_160); + break; + case IEEE80211_CONN_MODE_EHT: + conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, + conn->bw_limit, + IEEE80211_CONN_BW_LIMIT_320); + break; + } + + conn->mode = ap_mode; + chanreq->oper = ap_chandef; + + /* wider-bandwidth OFDMA is only done in EHT */ + if (conn->mode >= IEEE80211_CONN_MODE_EHT && + !(sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW)) + chanreq->ap = ap_chandef; + else + chanreq->ap.chan = NULL; + + while (!ieee80211_chandef_usable(sdata, &chanreq->oper, + IEEE80211_CHAN_DISABLED)) { + if (WARN_ON(chanreq->oper.width == NL80211_CHAN_WIDTH_20_NOHT)) { + ret = -EINVAL; + goto free; + } + + ieee80211_chanreq_downgrade(chanreq, conn); + } + + if (conn->mode >= IEEE80211_CONN_MODE_HE && + !cfg80211_chandef_usable(sdata->wdev.wiphy, &chanreq->oper, + IEEE80211_CHAN_NO_HE)) { + conn->mode = IEEE80211_CONN_MODE_VHT; + conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, + conn->bw_limit, + IEEE80211_CONN_BW_LIMIT_160); + } + + if (conn->mode >= IEEE80211_CONN_MODE_EHT && + !cfg80211_chandef_usable(sdata->wdev.wiphy, &chanreq->oper, + IEEE80211_CHAN_NO_EHT)) { + conn->mode = IEEE80211_CONN_MODE_HE; + conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, + conn->bw_limit, + IEEE80211_CONN_BW_LIMIT_160); + } + + if (chanreq->oper.width != ap_chandef.width || ap_mode != conn->mode) sdata_info(sdata, - "capabilities/regulatory prevented using AP HT/VHT configuration, downgraded\n"); + "regulatory prevented using AP config, downgraded\n"); - WARN_ON_ONCE(!cfg80211_chandef_valid(chandef)); - return ret; + if (conn->mode >= IEEE80211_CONN_MODE_HE && + (!ieee80211_verify_peer_he_mcs_support(sdata, (void *)elems->he_cap, + elems->he_operation) || + !ieee80211_verify_sta_he_mcs_support(sdata, sband, + elems->he_operation))) { + conn->mode = IEEE80211_CONN_MODE_VHT; + sdata_info(sdata, "required MCSes not supported, disabling HE\n"); + } + + if (conn->mode >= IEEE80211_CONN_MODE_EHT && + !ieee80211_verify_sta_eht_mcs_support(sdata, sband, + elems->eht_operation)) { + conn->mode = IEEE80211_CONN_MODE_HE; + conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, + conn->bw_limit, + IEEE80211_CONN_BW_LIMIT_160); + sdata_info(sdata, "required MCSes not supported, disabling EHT\n"); + } + + /* the mode can only decrease, so this must terminate */ + if (ap_mode != conn->mode) + goto again; + + mlme_link_id_dbg(sdata, link_id, + "connecting with %s mode, max bandwidth %d MHz\n", + ieee80211_conn_mode_str(conn->mode), + 20 * (1 << conn->bw_limit)); + + if (WARN_ON_ONCE(!cfg80211_chandef_valid(&chanreq->oper))) { + ret = -EINVAL; + goto free; + } + + return elems; +free: + kfree(elems); + return ERR_PTR(ret); } static int ieee80211_config_bw(struct ieee80211_link_data *link, - const struct ieee80211_ht_cap *ht_cap, - const struct ieee80211_vht_cap *vht_cap, - const struct ieee80211_ht_operation *ht_oper, - const struct ieee80211_vht_operation *vht_oper, - const struct ieee80211_he_operation *he_oper, - const struct ieee80211_eht_operation *eht_oper, - const struct ieee80211_s1g_oper_ie *s1g_oper, - const u8 *bssid, u64 *changed) + struct ieee802_11_elems *elems, + bool update, u64 *changed) { + struct ieee80211_channel *channel = link->conf->chanreq.oper.chan; struct ieee80211_sub_if_data *sdata = link->sdata; - struct ieee80211_local *local = sdata->local; - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_channel *chan = link->conf->chandef.chan; - struct ieee80211_supported_band *sband = - local->hw.wiphy->bands[chan->band]; - struct cfg80211_chan_def chandef; - u16 ht_opmode; - ieee80211_conn_flags_t flags; + struct ieee80211_chan_req chanreq = {}; + enum ieee80211_conn_mode ap_mode; u32 vht_cap_info = 0; + u16 ht_opmode; int ret; - /* if HT was/is disabled, don't track any bandwidth changes */ - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HT || !ht_oper) + /* don't track any bandwidth changes in legacy/S1G modes */ + if (link->u.mgd.conn.mode == IEEE80211_CONN_MODE_LEGACY || + link->u.mgd.conn.mode == IEEE80211_CONN_MODE_S1G) return 0; - /* don't check VHT if we associated as non-VHT station */ - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT) - vht_oper = NULL; + if (elems->vht_cap_elem) + vht_cap_info = le32_to_cpu(elems->vht_cap_elem->vht_cap_info); - /* don't check HE if we associated as non-HE station */ - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE || - !ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif)) { - he_oper = NULL; - eht_oper = NULL; + ap_mode = ieee80211_determine_ap_chan(sdata, channel, vht_cap_info, + elems, true, &link->u.mgd.conn, + &chanreq.ap); + + if (ap_mode != link->u.mgd.conn.mode) { + link_info(link, + "AP appears to change mode (expected %s, found %s), disconnect\n", + ieee80211_conn_mode_str(link->u.mgd.conn.mode), + ieee80211_conn_mode_str(ap_mode)); + return -EINVAL; } - /* don't check EHT if we associated as non-EHT station */ - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_EHT || - !ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif)) - eht_oper = NULL; + chanreq.oper = chanreq.ap; + if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_EHT || + sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW) + chanreq.ap.chan = NULL; /* - * if bss configuration changed store the new one - + * if HT operation mode changed store the new one - * this may be applicable even if channel is identical */ - ht_opmode = le16_to_cpu(ht_oper->operation_mode); - if (link->conf->ht_operation_mode != ht_opmode) { - *changed |= BSS_CHANGED_HT; - link->conf->ht_operation_mode = ht_opmode; + if (elems->ht_operation) { + ht_opmode = le16_to_cpu(elems->ht_operation->operation_mode); + if (link->conf->ht_operation_mode != ht_opmode) { + *changed |= BSS_CHANGED_HT; + link->conf->ht_operation_mode = ht_opmode; + } } - if (vht_cap) - vht_cap_info = le32_to_cpu(vht_cap->vht_cap_info); - - /* calculate new channel (type) based on HT/VHT/HE operation IEs */ - flags = ieee80211_determine_chantype(sdata, link, - link->u.mgd.conn_flags, - sband, chan, vht_cap_info, - ht_oper, vht_oper, - he_oper, eht_oper, - s1g_oper, &chandef, true); - /* * Downgrade the new channel if we associated with restricted - * capabilities. For example, if we associated as a 20 MHz STA - * to a 40 MHz AP (due to regulatory, capabilities or config - * reasons) then switching to a 40 MHz channel now won't do us - * any good -- we couldn't use it with the AP. + * bandwidth capabilities. For example, if we associated as a + * 20 MHz STA to a 40 MHz AP (due to regulatory, capabilities + * or config reasons) then switching to a 40 MHz channel now + * won't do us any good -- we couldn't use it with the AP. */ - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_80P80MHZ && - chandef.width == NL80211_CHAN_WIDTH_80P80) - flags |= ieee80211_chandef_downgrade(&chandef); - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_160MHZ && - chandef.width == NL80211_CHAN_WIDTH_160) - flags |= ieee80211_chandef_downgrade(&chandef); - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_40MHZ && - chandef.width > NL80211_CHAN_WIDTH_20) - flags |= ieee80211_chandef_downgrade(&chandef); - - if (cfg80211_chandef_identical(&chandef, &link->conf->chandef)) + while (link->u.mgd.conn.bw_limit < + ieee80211_min_bw_limit_from_chandef(&chanreq.oper)) + ieee80211_chandef_downgrade(&chanreq.oper, NULL); + + if (ieee80211_chanreq_identical(&chanreq, &link->conf->chanreq)) return 0; link_info(link, - "AP %pM changed bandwidth, new config is %d.%03d MHz, width %d (%d.%03d/%d MHz)\n", - link->u.mgd.bssid, chandef.chan->center_freq, - chandef.chan->freq_offset, chandef.width, - chandef.center_freq1, chandef.freq1_offset, - chandef.center_freq2); - - if (flags != (link->u.mgd.conn_flags & - (IEEE80211_CONN_DISABLE_HT | - IEEE80211_CONN_DISABLE_VHT | - IEEE80211_CONN_DISABLE_HE | - IEEE80211_CONN_DISABLE_EHT | - IEEE80211_CONN_DISABLE_40MHZ | - IEEE80211_CONN_DISABLE_80P80MHZ | - IEEE80211_CONN_DISABLE_160MHZ | - IEEE80211_CONN_DISABLE_320MHZ)) || - !cfg80211_chandef_valid(&chandef)) { + "AP %pM changed bandwidth, new used config is %d.%03d MHz, width %d (%d.%03d/%d MHz)\n", + link->u.mgd.bssid, chanreq.oper.chan->center_freq, + chanreq.oper.chan->freq_offset, chanreq.oper.width, + chanreq.oper.center_freq1, chanreq.oper.freq1_offset, + chanreq.oper.center_freq2); + + if (!cfg80211_chandef_valid(&chanreq.oper)) { sdata_info(sdata, - "AP %pM changed caps/bw in a way we can't support (0x%x/0x%x) - disconnect\n", - link->u.mgd.bssid, flags, ifmgd->flags); + "AP %pM changed caps/bw in a way we can't support - disconnect\n", + link->u.mgd.bssid); return -EINVAL; } - ret = ieee80211_link_change_bandwidth(link, &chandef, changed); + if (!update) { + link->conf->chanreq = chanreq; + return 0; + } + /* + * We're tracking the current AP here, so don't do any further checks + * here. This keeps us from playing ping-pong with regulatory, without + * it the following can happen (for example): + * - connect to an AP with 80 MHz, world regdom allows 80 MHz + * - AP advertises regdom US + * - CRDA loads regdom US with 80 MHz prohibited (old database) + * - we detect an unsupported channel and disconnect + * - disconnect causes CRDA to reload world regdomain and the game + * starts anew. + * (see https://bugzilla.kernel.org/show_bug.cgi?id=70881) + * + * It seems possible that there are still scenarios with CSA or real + * bandwidth changes where a this could happen, but those cases are + * less common and wouldn't completely prevent using the AP. + */ + + ret = ieee80211_link_change_chanreq(link, &chanreq, changed); if (ret) { sdata_info(sdata, "AP %pM changed bandwidth to incompatible one - disconnect\n", @@ -612,7 +890,7 @@ static void ieee80211_add_ht_ie(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, struct ieee80211_channel *channel, enum ieee80211_smps_mode smps, - ieee80211_conn_flags_t conn_flags) + const struct ieee80211_conn_settings *conn) { u8 *pos; u32 flags = channel->flags; @@ -647,7 +925,7 @@ static void ieee80211_add_ht_ie(struct ieee80211_sub_if_data *sdata, * capable of 40 MHz -- some broken APs will never fall * back to trying to transmit in 20 MHz. */ - if (conn_flags & IEEE80211_CONN_DISABLE_40MHZ) { + if (conn->bw_limit <= IEEE80211_CONN_BW_LIMIT_20) { cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40; cap &= ~IEEE80211_HT_CAP_SGI_40; } @@ -686,7 +964,7 @@ static bool ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, struct ieee80211_supported_band *sband, struct ieee80211_vht_cap *ap_vht_cap, - ieee80211_conn_flags_t conn_flags) + const struct ieee80211_conn_settings *conn) { struct ieee80211_local *local = sdata->local; u8 *pos; @@ -703,16 +981,7 @@ static bool ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, /* determine capability flags */ cap = vht_cap.cap; - if (conn_flags & IEEE80211_CONN_DISABLE_80P80MHZ) { - u32 bw = cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; - - cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; - if (bw == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ || - bw == IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) - cap |= IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ; - } - - if (conn_flags & IEEE80211_CONN_DISABLE_160MHZ) { + if (conn->bw_limit <= IEEE80211_CONN_BW_LIMIT_80) { cap &= ~IEEE80211_VHT_CAP_SHORT_GI_160; cap &= ~IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; } @@ -769,79 +1038,12 @@ static bool ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, return mu_mimo_owner; } -/* This function determines HE capability flags for the association - * and builds the IE. - */ -static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, - struct ieee80211_supported_band *sband, - enum ieee80211_smps_mode smps_mode, - ieee80211_conn_flags_t conn_flags) -{ - u8 *pos, *pre_he_pos; - const struct ieee80211_sta_he_cap *he_cap; - u8 he_cap_size; - - he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); - if (WARN_ON(!he_cap)) - return; - - /* get a max size estimate */ - he_cap_size = - 2 + 1 + sizeof(he_cap->he_cap_elem) + - ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem) + - ieee80211_he_ppe_size(he_cap->ppe_thres[0], - he_cap->he_cap_elem.phy_cap_info); - pos = skb_put(skb, he_cap_size); - pre_he_pos = pos; - pos = ieee80211_ie_build_he_cap(conn_flags, - pos, he_cap, pos + he_cap_size); - /* trim excess if any */ - skb_trim(skb, skb->len - (pre_he_pos + he_cap_size - pos)); - - ieee80211_ie_build_he_6ghz_cap(sdata, smps_mode, skb); -} - -static void ieee80211_add_eht_ie(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, - struct ieee80211_supported_band *sband) -{ - u8 *pos; - const struct ieee80211_sta_he_cap *he_cap; - const struct ieee80211_sta_eht_cap *eht_cap; - u8 eht_cap_size; - - he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); - eht_cap = ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif); - - /* - * EHT capabilities element is only added if the HE capabilities element - * was added so assume that 'he_cap' is valid and don't check it. - */ - if (WARN_ON(!he_cap || !eht_cap)) - return; - - eht_cap_size = - 2 + 1 + sizeof(eht_cap->eht_cap_elem) + - ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem, - &eht_cap->eht_cap_elem, - false) + - ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], - eht_cap->eht_cap_elem.phy_cap_info); - pos = skb_put(skb, eht_cap_size); - ieee80211_ie_build_eht_cap(pos, he_cap, eht_cap, pos + eht_cap_size, - false); -} - static void ieee80211_assoc_add_rates(struct sk_buff *skb, enum nl80211_chan_width width, struct ieee80211_supported_band *sband, struct ieee80211_mgd_assoc_data *assoc_data) { - unsigned int rates_len, supp_rates_len; - u32 rates = 0; - int i, count; - u8 *pos; + u32 rates; if (assoc_data->supp_rates_len) { /* @@ -850,53 +1052,23 @@ static void ieee80211_assoc_add_rates(struct sk_buff *skb, * in the association request (e.g. D-Link DAP 1353 in * b-only mode)... */ - rates_len = ieee80211_parse_bitrates(width, sband, - assoc_data->supp_rates, - assoc_data->supp_rates_len, - &rates); + ieee80211_parse_bitrates(width, sband, + assoc_data->supp_rates, + assoc_data->supp_rates_len, + &rates); } else { /* * In case AP not provide any supported rates information * before association, we send information element(s) with * all rates that we support. */ - rates_len = sband->n_bitrates; - for (i = 0; i < sband->n_bitrates; i++) - rates |= BIT(i); - } - - supp_rates_len = rates_len; - if (supp_rates_len > 8) - supp_rates_len = 8; - - pos = skb_put(skb, supp_rates_len + 2); - *pos++ = WLAN_EID_SUPP_RATES; - *pos++ = supp_rates_len; - - count = 0; - for (i = 0; i < sband->n_bitrates; i++) { - if (BIT(i) & rates) { - int rate = DIV_ROUND_UP(sband->bitrates[i].bitrate, 5); - *pos++ = (u8)rate; - if (++count == 8) - break; - } + rates = ~0; } - if (rates_len > count) { - pos = skb_put(skb, rates_len - count + 2); - *pos++ = WLAN_EID_EXT_SUPP_RATES; - *pos++ = rates_len - count; - - for (i++; i < sband->n_bitrates; i++) { - if (BIT(i) & rates) { - int rate; - - rate = DIV_ROUND_UP(sband->bitrates[i].bitrate, 5); - *pos++ = (u8)rate; - } - } - } + ieee80211_put_srates_elem(skb, sband, 0, 0, ~rates, + WLAN_EID_SUPP_RATES); + ieee80211_put_srates_elem(skb, sband, 0, 0, ~rates, + WLAN_EID_EXT_SUPP_RATES); } static size_t ieee80211_add_before_ht_elems(struct sk_buff *skb, @@ -1133,11 +1305,11 @@ static size_t ieee80211_assoc_link_elems(struct ieee80211_sub_if_data *sdata, offset); if (sband->band != NL80211_BAND_6GHZ && - !(assoc_data->link[link_id].conn_flags & IEEE80211_CONN_DISABLE_HT)) { + assoc_data->link[link_id].conn.mode >= IEEE80211_CONN_MODE_HT) { ieee80211_add_ht_ie(sdata, skb, assoc_data->link[link_id].ap_ht_param, sband, chan, smps_mode, - assoc_data->link[link_id].conn_flags); + &assoc_data->link[link_id].conn); ADD_PRESENT_ELEM(WLAN_EID_HT_CAPABILITY); } @@ -1147,37 +1319,28 @@ static size_t ieee80211_assoc_link_elems(struct ieee80211_sub_if_data *sdata, offset); if (sband->band != NL80211_BAND_6GHZ && - !(assoc_data->link[link_id].conn_flags & IEEE80211_CONN_DISABLE_VHT)) { + assoc_data->link[link_id].conn.mode >= IEEE80211_CONN_MODE_VHT && + sband->vht_cap.vht_supported) { bool mu_mimo_owner = ieee80211_add_vht_ie(sdata, skb, sband, &assoc_data->link[link_id].ap_vht_cap, - assoc_data->link[link_id].conn_flags); + &assoc_data->link[link_id].conn); if (link) link->conf->mu_mimo_owner = mu_mimo_owner; ADD_PRESENT_ELEM(WLAN_EID_VHT_CAPABILITY); } - /* - * If AP doesn't support HT, mark HE and EHT as disabled. - * If on the 5GHz band, make sure it supports VHT. - */ - if (assoc_data->link[link_id].conn_flags & IEEE80211_CONN_DISABLE_HT || - (sband->band == NL80211_BAND_5GHZ && - assoc_data->link[link_id].conn_flags & IEEE80211_CONN_DISABLE_VHT)) - assoc_data->link[link_id].conn_flags |= - IEEE80211_CONN_DISABLE_HE | - IEEE80211_CONN_DISABLE_EHT; - /* if present, add any custom IEs that go before HE */ offset = ieee80211_add_before_he_elems(skb, extra_elems, extra_elems_len, offset); - if (!(assoc_data->link[link_id].conn_flags & IEEE80211_CONN_DISABLE_HE)) { - ieee80211_add_he_ie(sdata, skb, sband, smps_mode, - assoc_data->link[link_id].conn_flags); + if (assoc_data->link[link_id].conn.mode >= IEEE80211_CONN_MODE_HE) { + ieee80211_put_he_cap(skb, sdata, sband, + &assoc_data->link[link_id].conn); ADD_PRESENT_EXT_ELEM(WLAN_EID_EXT_HE_CAPABILITY); + ieee80211_put_he_6ghz_cap(skb, sdata, smps_mode); } /* @@ -1185,7 +1348,7 @@ static size_t ieee80211_assoc_link_elems(struct ieee80211_sub_if_data *sdata, * calling ieee80211_assoc_add_ml_elem(), so add this one if * we're going to put it after the ML element */ - if (!(assoc_data->link[link_id].conn_flags & IEEE80211_CONN_DISABLE_EHT)) + if (assoc_data->link[link_id].conn.mode >= IEEE80211_CONN_MODE_EHT) ADD_PRESENT_EXT_ELEM(WLAN_EID_EXT_EHT_CAPABILITY); if (link_id == assoc_data->assoc_link_id) @@ -1195,8 +1358,9 @@ static size_t ieee80211_assoc_link_elems(struct ieee80211_sub_if_data *sdata, /* crash if somebody gets it wrong */ present_elems = NULL; - if (!(assoc_data->link[link_id].conn_flags & IEEE80211_CONN_DISABLE_EHT)) - ieee80211_add_eht_ie(sdata, skb, sband); + if (assoc_data->link[link_id].conn.mode >= IEEE80211_CONN_MODE_EHT) + ieee80211_put_eht_cap(skb, sdata, sband, + &assoc_data->link[link_id].conn); if (sband->band == NL80211_BAND_S1GHZ) { ieee80211_add_aid_request_ie(sdata, skb); @@ -1206,9 +1370,6 @@ static size_t ieee80211_assoc_link_elems(struct ieee80211_sub_if_data *sdata, if (iftd && iftd->vendor_elems.data && iftd->vendor_elems.len) skb_put_data(skb, iftd->vendor_elems.data, iftd->vendor_elems.len); - if (link) - link->u.mgd.conn_flags = assoc_data->link[link_id].conn_flags; - return offset; } @@ -1318,8 +1479,6 @@ static void ieee80211_assoc_add_ml_elem(struct ieee80211_sub_if_data *sdata, cpu_to_le16(IEEE80211_MLC_BASIC_PRES_EML_CAPA); skb_put_data(skb, &eml_capa, sizeof(eml_capa)); } - /* need indication from userspace to support this */ - mld_capa_ops &= ~cpu_to_le16(IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP); skb_put_data(skb, &mld_capa_ops, sizeof(mld_capa_ops)); for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { @@ -1499,7 +1658,7 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) /* Set MBSSID support for HE AP if needed */ if (ieee80211_hw_check(&local->hw, SUPPORTS_ONLY_HE_MULTI_BSSID) && - !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE) && + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HE && ext_capa && ext_capa->datalen >= 3) ext_capa->data[2] |= WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT; @@ -1544,7 +1703,7 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) * for some reason check it and want it to be set, set the bit for all * pre-EHT connections as we used to do. */ - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_EHT) + if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_EHT) capab |= WLAN_CAPABILITY_ESS; /* add the elements for the assoc (main) link */ @@ -1741,8 +1900,8 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy, return; } - if (!cfg80211_chandef_identical(&link->conf->chandef, - &link->csa_chandef)) { + if (!ieee80211_chanreq_identical(&link->conf->chanreq, + &link->csa_chanreq)) { sdata_info(sdata, "failed to finalize channel switch, disconnecting\n"); wiphy_work_queue(sdata->local->hw.wiphy, @@ -1767,19 +1926,14 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_link_data *link) WARN_ON(!link->conf->csa_active); - if (link->csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - link->csa_block_tx = false; + sdata->csa_blocked_tx = false; } link->conf->csa_active = false; link->u.mgd.csa_waiting_bcn = false; - /* - * If the CSA IE is still present on the beacon after the switch, - * we need to consider it as a new CSA (possibly to self). - */ - link->u.mgd.beacon_crc_valid = false; ret = drv_post_channel_switch(link); if (ret) { @@ -1790,8 +1944,8 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_link_data *link) return; } - cfg80211_ch_switch_notify(sdata->dev, &link->reserved_chandef, - link->link_id, 0); + cfg80211_ch_switch_notify(sdata->dev, &link->reserved.oper, + link->link_id); } void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success, @@ -1838,14 +1992,15 @@ ieee80211_sta_abort_chanswitch(struct ieee80211_link_data *link) ieee80211_link_unreserve_chanctx(link); - if (link->csa_block_tx) + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_blocked_tx = false; + } - link->csa_block_tx = false; link->conf->csa_active = false; - drv_abort_channel_switch(sdata); + drv_abort_channel_switch(link); } static void @@ -1857,12 +2012,14 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct cfg80211_bss *cbss = link->u.mgd.bss; + struct cfg80211_bss *cbss = link->conf->bss; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *chanctx; enum nl80211_band current_band; struct ieee80211_csa_ie csa_ie; - struct ieee80211_channel_switch ch_switch; + struct ieee80211_channel_switch ch_switch = { + .link_id = link->link_id, + }; struct ieee80211_bss *bss; unsigned long timeout; int res; @@ -1876,14 +2033,14 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, bss = (void *)cbss->priv; res = ieee80211_parse_ch_switch_ie(sdata, elems, current_band, bss->vht_cap_info, - link->u.mgd.conn_flags, + &link->u.mgd.conn, link->u.mgd.bssid, &csa_ie); if (!res) { ch_switch.timestamp = timestamp; ch_switch.device_timestamp = device_timestamp; ch_switch.block_tx = csa_ie.mode; - ch_switch.chandef = csa_ie.chandef; + ch_switch.chandef = csa_ie.chanreq.oper; ch_switch.count = csa_ie.count; ch_switch.delay = csa_ie.max_switch_time; } @@ -1891,46 +2048,62 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, if (res < 0) goto drop_connection; - if (beacon && link->conf->csa_active && - !link->u.mgd.csa_waiting_bcn) { - if (res) + if (link->conf->csa_active) { + /* already processing - disregard action frames */ + if (!beacon) + return; + + if (link->u.mgd.csa_waiting_bcn) { + ieee80211_chswitch_post_beacon(link); + /* + * If the CSA IE is still present in the beacon after + * the switch, we need to consider it as a new CSA + * (possibly to self) - this happens by not returning + * here so we'll get to the check below. + */ + } else if (res) { ieee80211_sta_abort_chanswitch(link); - else + return; + } else { drv_channel_switch_rx_beacon(sdata, &ch_switch); - return; - } else if (link->conf->csa_active || res) { - /* disregard subsequent announcements if already processing */ - return; + return; + } } - if (link->conf->chandef.chan->band != - csa_ie.chandef.chan->band) { + /* nothing to do at all - no active CSA nor a new one */ + if (res) + return; + + if (link->conf->chanreq.oper.chan->band != + csa_ie.chanreq.oper.chan->band) { sdata_info(sdata, "AP %pM switches to different band (%d MHz, width:%d, CF1/2: %d/%d MHz), disconnecting\n", link->u.mgd.bssid, - csa_ie.chandef.chan->center_freq, - csa_ie.chandef.width, csa_ie.chandef.center_freq1, - csa_ie.chandef.center_freq2); + csa_ie.chanreq.oper.chan->center_freq, + csa_ie.chanreq.oper.width, + csa_ie.chanreq.oper.center_freq1, + csa_ie.chanreq.oper.center_freq2); goto drop_connection; } - if (!cfg80211_chandef_usable(local->hw.wiphy, &csa_ie.chandef, + if (!cfg80211_chandef_usable(local->hw.wiphy, &csa_ie.chanreq.oper, IEEE80211_CHAN_DISABLED)) { sdata_info(sdata, "AP %pM switches to unsupported channel " "(%d.%03d MHz, width:%d, CF1/2: %d.%03d/%d MHz), " "disconnecting\n", link->u.mgd.bssid, - csa_ie.chandef.chan->center_freq, - csa_ie.chandef.chan->freq_offset, - csa_ie.chandef.width, csa_ie.chandef.center_freq1, - csa_ie.chandef.freq1_offset, - csa_ie.chandef.center_freq2); + csa_ie.chanreq.oper.chan->center_freq, + csa_ie.chanreq.oper.chan->freq_offset, + csa_ie.chanreq.oper.width, + csa_ie.chanreq.oper.center_freq1, + csa_ie.chanreq.oper.freq1_offset, + csa_ie.chanreq.oper.center_freq2); goto drop_connection; } - if (cfg80211_chandef_identical(&csa_ie.chandef, - &link->conf->chandef) && + if (cfg80211_chandef_identical(&csa_ie.chanreq.oper, + &link->conf->chanreq.oper) && (!csa_ie.mode || !beacon)) { if (link->u.mgd.csa_ignored_same_chan) return; @@ -1942,12 +2115,13 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, } /* - * Drop all TDLS peers - either we disconnect or move to a different - * channel from this point on. There's no telling what our peer will do. + * Drop all TDLS peers on the affected link - either we disconnect or + * move to a different channel from this point on. There's no telling + * what our peer will do. * The TDLS WIDER_BW scenario is also problematic, as peers might now * have an incompatible wider chandef. */ - ieee80211_teardown_tdls_peers(sdata); + ieee80211_teardown_tdls_peers(link); conf = rcu_dereference_protected(link->conf->chanctx_conf, lockdep_is_held(&local->hw.wiphy->mtx)); @@ -1959,8 +2133,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, chanctx = container_of(conf, struct ieee80211_chanctx, conf); - if (local->use_chanctx && - !ieee80211_hw_check(&local->hw, CHANCTX_STA_CSA)) { + if (!ieee80211_hw_check(&local->hw, CHANCTX_STA_CSA)) { sdata_info(sdata, "driver doesn't support chan-switch with channel contexts\n"); goto drop_connection; @@ -1972,7 +2145,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, goto drop_connection; } - res = ieee80211_link_reserve_chanctx(link, &csa_ie.chandef, + res = ieee80211_link_reserve_chanctx(link, &csa_ie.chanreq, chanctx->mode, false); if (res) { sdata_info(sdata, @@ -1982,18 +2155,20 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, } link->conf->csa_active = true; - link->csa_chandef = csa_ie.chandef; - link->csa_block_tx = csa_ie.mode; + link->csa_chanreq = csa_ie.chanreq; link->u.mgd.csa_ignored_same_chan = false; link->u.mgd.beacon_crc_valid = false; - if (link->csa_block_tx) + if (csa_ie.mode && + !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) { ieee80211_stop_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_blocked_tx = true; + } - cfg80211_ch_switch_started_notify(sdata->dev, &csa_ie.chandef, + cfg80211_ch_switch_started_notify(sdata->dev, &csa_ie.chanreq.oper, link->link_id, csa_ie.count, - csa_ie.mode, 0); + csa_ie.mode); if (local->ops->channel_switch) { /* use driver's channel switch callback */ @@ -2017,7 +2192,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, * reset when the disconnection worker runs. */ link->conf->csa_active = true; - link->csa_block_tx = csa_ie.mode; + sdata->csa_blocked_tx = + csa_ie.mode && !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA); wiphy_work_queue(sdata->local->hw.wiphy, &ifmgd->csa_connection_drop_work); @@ -2414,7 +2590,7 @@ void ieee80211_dfs_cac_timer_work(struct wiphy *wiphy, struct wiphy_work *work) struct ieee80211_link_data *link = container_of(work, struct ieee80211_link_data, dfs_cac_timer_work.work); - struct cfg80211_chan_def chandef = link->conf->chandef; + struct cfg80211_chan_def chandef = link->conf->chanreq.oper; struct ieee80211_sub_if_data *sdata = link->sdata; lockdep_assert_wiphy(sdata->local->hw.wiphy); @@ -2769,7 +2945,7 @@ static u64 ieee80211_link_set_associated(struct ieee80211_link_data *link, ieee80211_check_rate_mask(link); - link->u.mgd.bss = cbss; + link->conf->bss = cbss; memcpy(link->u.mgd.bssid, cbss->bssid, ETH_ALEN); if (sdata->vif.p2p || @@ -2917,7 +3093,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ifmgd->associated = false; /* other links will be destroyed */ - sdata->deflink.u.mgd.bss = NULL; + sdata->deflink.conf->bss = NULL; sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; netif_carrier_off(sdata->dev); @@ -2992,7 +3168,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sdata->vif.cfg.ssid_len = 0; /* remove AP and TDLS peers */ - sta_info_flush(sdata); + sta_info_flush(sdata, -1); /* finally reset all BSS / config parameters */ if (!ieee80211_vif_is_mld(&sdata->vif)) @@ -3058,7 +3234,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sdata->deflink.u.mgd.disable_wmm_tracking = false; ifmgd->flags = 0; - sdata->deflink.u.mgd.conn_flags = 0; for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { struct ieee80211_link_data *link; @@ -3072,25 +3247,35 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.csa_active = false; sdata->deflink.u.mgd.csa_waiting_bcn = false; sdata->deflink.u.mgd.csa_ignored_same_chan = false; - if (sdata->deflink.csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->deflink.csa_block_tx = false; + sdata->csa_blocked_tx = false; } /* existing TX TSPEC sessions no longer exist */ memset(ifmgd->tx_tspec, 0, sizeof(ifmgd->tx_tspec)); wiphy_delayed_work_cancel(local->hw.wiphy, &ifmgd->tx_tspec_wk); + sdata->vif.bss_conf.power_type = IEEE80211_REG_UNSET_AP; sdata->vif.bss_conf.pwr_reduction = 0; sdata->vif.bss_conf.tx_pwr_env_num = 0; memset(sdata->vif.bss_conf.tx_pwr_env, 0, sizeof(sdata->vif.bss_conf.tx_pwr_env)); + sdata->vif.cfg.eml_cap = 0; + sdata->vif.cfg.eml_med_sync_delay = 0; + sdata->vif.cfg.mld_capa_op = 0; + memset(&sdata->u.mgd.ttlm_info, 0, sizeof(sdata->u.mgd.ttlm_info)); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); + + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &ifmgd->neg_ttlm_timeout_work); ieee80211_vif_set_links(sdata, 0, 0); + + ifmgd->mcast_seq_last = IEEE80211_SN_MODULO; } static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) @@ -3238,7 +3423,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) ieee80211_mlme_send_probe_req(sdata, sdata->vif.addr, dst, sdata->vif.cfg.ssid, sdata->vif.cfg.ssid_len, - sdata->deflink.u.mgd.bss->channel); + sdata->deflink.conf->bss->channel); } ifmgd->probe_timeout = jiffies + msecs_to_jiffies(probe_wait_ms); @@ -3321,7 +3506,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, return NULL; if (ifmgd->associated) - cbss = sdata->deflink.u.mgd.bss; + cbss = sdata->deflink.conf->bss; else if (ifmgd->auth_data) cbss = ifmgd->auth_data->bss; else if (ifmgd->assoc_data && ifmgd->assoc_data->link[0].bss) @@ -3378,9 +3563,12 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) if (!ifmgd->associated) return; - /* in MLO assume we have a link where we can TX the frame */ - tx = ieee80211_vif_is_mld(&sdata->vif) || - !sdata->deflink.csa_block_tx; + /* + * MLO drivers should have HANDLES_QUIET_CSA, so that csa_blocked_tx + * is always false; if they don't then this may try to transmit the + * frame but queues will be stopped. + */ + tx = !sdata->csa_blocked_tx; if (!ifmgd->driver_disconnect) { unsigned int link_id; @@ -3400,8 +3588,8 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) link = sdata_dereference(sdata->link[link_id], sdata); if (!link) continue; - cfg80211_unlink_bss(local->hw.wiphy, link->u.mgd.bss); - link->u.mgd.bss = NULL; + cfg80211_unlink_bss(local->hw.wiphy, link->conf->bss); + link->conf->bss = NULL; } } @@ -3413,10 +3601,10 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) /* the other links will be destroyed */ sdata->vif.bss_conf.csa_active = false; sdata->deflink.u.mgd.csa_waiting_bcn = false; - if (sdata->deflink.csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->deflink.csa_block_tx = false; + sdata->csa_blocked_tx = false; } ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), tx, @@ -3518,7 +3706,6 @@ static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata, sta_info_destroy_addr(sdata, auth_data->ap_addr); /* other links are destroyed */ - sdata->deflink.u.mgd.conn_flags = 0; eth_zero_addr(sdata->deflink.u.mgd.bssid); ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_BSSID); @@ -3556,7 +3743,6 @@ static void ieee80211_destroy_assoc_data(struct ieee80211_sub_if_data *sdata, del_timer_sync(&sdata->u.mgd.timer); sta_info_destroy_addr(sdata, assoc_data->ap_addr); - sdata->deflink.u.mgd.conn_flags = 0; eth_zero_addr(sdata->deflink.u.mgd.bssid); ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_BSSID); @@ -4006,11 +4192,13 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, struct ieee80211_local *local = sdata->local; unsigned int link_id = link->link_id; struct ieee80211_elems_parse_params parse_params = { + .mode = link->u.mgd.conn.mode, .start = elem_start, .len = elem_len, .link_id = link_id == assoc_data->assoc_link_id ? -1 : link_id, .from_ap = true, }; + bool is_5ghz = cbss->channel->band == NL80211_BAND_5GHZ; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; bool is_s1g = cbss->channel->band == NL80211_BAND_S1GHZ; const struct cfg80211_bss_ies *bss_ies = NULL; @@ -4034,15 +4222,17 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, */ assoc_data->link[link_id].status = WLAN_STATUS_SUCCESS; if (elems->ml_basic) { - if (!(elems->ml_basic->control & - cpu_to_le16(IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT))) { + int bss_param_ch_cnt = + ieee80211_mle_get_bss_param_ch_cnt((const void *)elems->ml_basic); + + if (bss_param_ch_cnt < 0) { ret = false; goto out; } - link->u.mgd.bss_param_ch_cnt = - ieee80211_mle_get_bss_param_ch_cnt(elems->ml_basic); + link->u.mgd.bss_param_ch_cnt = bss_param_ch_cnt; } - } else if (!elems->prof || + } else if (elems->parse_error & IEEE80211_PARSE_ERR_DUP_NEST_ML_BASIC || + !elems->prof || !(elems->prof->control & prof_bss_param_ch_present)) { ret = false; goto out; @@ -4086,9 +4276,9 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, */ if (!is_6ghz && ((assoc_data->wmm && !elems->wmm_param) || - (!(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HT) && + (link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT && (!elems->ht_cap_elem || !elems->ht_operation)) || - (!(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT) && + (link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT && (!elems->vht_cap_elem || !elems->vht_operation)))) { const struct cfg80211_bss_ies *ies; struct ieee802_11_elems *bss_elems; @@ -4125,25 +4315,25 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, * have to include the IEs in the (re)association response. */ if (!elems->ht_cap_elem && bss_elems->ht_cap_elem && - !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HT)) { + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT) { elems->ht_cap_elem = bss_elems->ht_cap_elem; sdata_info(sdata, "AP bug: HT capability missing from AssocResp\n"); } if (!elems->ht_operation && bss_elems->ht_operation && - !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HT)) { + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT) { elems->ht_operation = bss_elems->ht_operation; sdata_info(sdata, "AP bug: HT operation missing from AssocResp\n"); } if (!elems->vht_cap_elem && bss_elems->vht_cap_elem && - !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT)) { + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) { elems->vht_cap_elem = bss_elems->vht_cap_elem; sdata_info(sdata, "AP bug: VHT capa missing from AssocResp\n"); } if (!elems->vht_operation && bss_elems->vht_operation && - !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT)) { + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) { elems->vht_operation = bss_elems->vht_operation; sdata_info(sdata, "AP bug: VHT operation missing from AssocResp\n"); @@ -4155,8 +4345,10 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, /* * We previously checked these in the beacon/probe response, so * they should be present here. This is just a safety net. + * Note that the ieee80211_config_bw() below would also check + * for this (and more), but this has better error reporting. */ - if (!is_6ghz && !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HT) && + if (!is_6ghz && link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT && (!elems->wmm_param || !elems->ht_cap_elem || !elems->ht_operation)) { sdata_info(sdata, "HT AP is missing WMM params or HT capability/operation\n"); @@ -4164,7 +4356,7 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, goto out; } - if (!is_6ghz && !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT) && + if (is_5ghz && link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT && (!elems->vht_cap_elem || !elems->vht_operation)) { sdata_info(sdata, "VHT AP is missing VHT capability/operation\n"); @@ -4172,36 +4364,28 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, goto out; } - if (is_6ghz && !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE) && - !elems->he_6ghz_capa) { - sdata_info(sdata, - "HE 6 GHz AP is missing HE 6 GHz band capability\n"); - ret = false; - goto out; - } - - if (WARN_ON(!link->conf->chandef.chan)) { + /* check/update if AP changed anything in assoc response vs. scan */ + if (ieee80211_config_bw(link, elems, + link_id == assoc_data->assoc_link_id, + changed)) { ret = false; goto out; } - sband = local->hw.wiphy->bands[link->conf->chandef.chan->band]; - if (!(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE) && - (!elems->he_cap || !elems->he_operation)) { - sdata_info(sdata, - "HE AP is missing HE capability/operation\n"); + if (WARN_ON(!link->conf->chanreq.oper.chan)) { ret = false; goto out; } + sband = local->hw.wiphy->bands[link->conf->chanreq.oper.chan->band]; /* Set up internal HT/VHT capabilities */ - if (elems->ht_cap_elem && !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HT)) + if (elems->ht_cap_elem && link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT) ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, elems->ht_cap_elem, link_sta); if (elems->vht_cap_elem && - !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT)) { + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) { const struct ieee80211_vht_cap *bss_vht_cap = NULL; const struct cfg80211_bss_ies *ies; @@ -4228,14 +4412,41 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, rcu_read_unlock(); } - if (elems->he_operation && !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE) && + if (elems->he_operation && + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HE && elems->he_cap) { + const struct ieee80211_he_6ghz_oper *he_6ghz_oper; + ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, elems->he_cap, elems->he_cap_len, elems->he_6ghz_capa, link_sta); + he_6ghz_oper = ieee80211_he_6ghz_oper(elems->he_operation); + + if (is_6ghz && he_6ghz_oper) { + switch (u8_get_bits(he_6ghz_oper->control, + IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { + case IEEE80211_6GHZ_CTRL_REG_LPI_AP: + bss_conf->power_type = IEEE80211_REG_LPI_AP; + break; + case IEEE80211_6GHZ_CTRL_REG_SP_AP: + bss_conf->power_type = IEEE80211_REG_SP_AP; + break; + case IEEE80211_6GHZ_CTRL_REG_VLP_AP: + bss_conf->power_type = IEEE80211_REG_VLP_AP; + break; + default: + bss_conf->power_type = IEEE80211_REG_UNSET_AP; + break; + } + } else if (is_6ghz) { + link_info(link, + "HE 6 GHz operation missing (on %d MHz), expect issues\n", + bss_conf->chanreq.oper.chan->center_freq); + } + bss_conf->he_support = link_sta->pub->he_cap.has_he; if (elems->rsnx && elems->rsnx_len && (elems->rsnx[0] & WLAN_RSNX_CAPA_PROTECTED_TWT) && @@ -4249,7 +4460,7 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, link_sta, elems); if (elems->eht_operation && elems->eht_cap && - !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_EHT)) { + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_EHT) { ieee80211_eht_cap_ie_to_sta_eht_cap(sdata, sband, elems->he_cap, elems->he_cap_len, @@ -4258,7 +4469,6 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, link_sta); bss_conf->eht_support = link_sta->pub->eht_cap.has_eht; - *changed |= BSS_CHANGED_EHT_PUNCTURING; } else { bss_conf->eht_support = false; } @@ -4456,7 +4666,7 @@ static u8 ieee80211_max_rx_chains(struct ieee80211_link_data *link, bool support_160; u8 chains = 1; - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HT) + if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_HT) return chains; ht_cap_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_HT_CAPABILITY); @@ -4469,7 +4679,7 @@ static u8 ieee80211_max_rx_chains(struct ieee80211_link_data *link, */ } - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_VHT) + if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_VHT) return chains; vht_cap_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_VHT_CAPABILITY); @@ -4488,7 +4698,7 @@ static u8 ieee80211_max_rx_chains(struct ieee80211_link_data *link, chains = max(chains, nss); } - if (link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HE) + if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_HE) return chains; ies = rcu_dereference(cbss->ies); @@ -4539,533 +4749,331 @@ static u8 ieee80211_max_rx_chains(struct ieee80211_link_data *link, return chains; } -static bool -ieee80211_verify_peer_he_mcs_support(struct ieee80211_sub_if_data *sdata, - const struct cfg80211_bss_ies *ies, - const struct ieee80211_he_operation *he_op) +static void +ieee80211_determine_our_sta_mode(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + struct cfg80211_assoc_request *req, + bool wmm_used, int link_id, + struct ieee80211_conn_settings *conn) { - const struct element *he_cap_elem; - const struct ieee80211_he_cap_elem *he_cap; - struct ieee80211_he_mcs_nss_supp *he_mcs_nss_supp; - u16 mcs_80_map_tx, mcs_80_map_rx; - u16 ap_min_req_set; - int mcs_nss_size; - int nss; - - he_cap_elem = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_CAPABILITY, - ies->data, ies->len); - - if (!he_cap_elem) - return false; + struct ieee80211_sta_ht_cap sta_ht_cap = sband->ht_cap; + bool is_5ghz = sband->band == NL80211_BAND_5GHZ; + bool is_6ghz = sband->band == NL80211_BAND_6GHZ; + const struct ieee80211_sta_he_cap *he_cap; + const struct ieee80211_sta_eht_cap *eht_cap; + struct ieee80211_sta_vht_cap vht_cap; - /* invalid HE IE */ - if (he_cap_elem->datalen < 1 + sizeof(*he_cap)) { - sdata_info(sdata, - "Invalid HE elem, Disable HE\n"); - return false; + if (sband->band == NL80211_BAND_S1GHZ) { + conn->mode = IEEE80211_CONN_MODE_S1G; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_20; + mlme_dbg(sdata, "operating as S1G STA\n"); + return; } - /* skip one byte ext_tag_id */ - he_cap = (void *)(he_cap_elem->data + 1); - mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap); + conn->mode = IEEE80211_CONN_MODE_LEGACY; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_20; - /* invalid HE IE */ - if (he_cap_elem->datalen < 1 + sizeof(*he_cap) + mcs_nss_size) { - sdata_info(sdata, - "Invalid HE elem with nss size, Disable HE\n"); - return false; + ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap); + + if (req && req->flags & ASSOC_REQ_DISABLE_HT) { + mlme_link_id_dbg(sdata, link_id, + "HT disabled by flag, limiting to legacy\n"); + goto out; } - /* mcs_nss is right after he_cap info */ - he_mcs_nss_supp = (void *)(he_cap + 1); + if (!wmm_used) { + mlme_link_id_dbg(sdata, link_id, + "WMM/QoS not supported, limiting to legacy\n"); + goto out; + } - mcs_80_map_tx = le16_to_cpu(he_mcs_nss_supp->tx_mcs_80); - mcs_80_map_rx = le16_to_cpu(he_mcs_nss_supp->rx_mcs_80); + if (req) { + unsigned int i; - /* P802.11-REVme/D0.3 - * 27.1.1 Introduction to the HE PHY - * ... - * An HE STA shall support the following features: - * ... - * Single spatial stream HE-MCSs 0 to 7 (transmit and receive) in all - * supported channel widths for HE SU PPDUs - */ - if ((mcs_80_map_tx & 0x3) == IEEE80211_HE_MCS_NOT_SUPPORTED || - (mcs_80_map_rx & 0x3) == IEEE80211_HE_MCS_NOT_SUPPORTED) { - sdata_info(sdata, - "Missing mandatory rates for 1 Nss, rx 0x%x, tx 0x%x, disable HE\n", - mcs_80_map_tx, mcs_80_map_rx); - return false; + for (i = 0; i < req->crypto.n_ciphers_pairwise; i++) { + if (req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP40 || + req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_TKIP || + req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP104) { + netdev_info(sdata->dev, + "WEP/TKIP use, limiting to legacy\n"); + goto out; + } + } } - if (!he_op) - return true; + if (!sta_ht_cap.ht_supported && !is_6ghz) { + mlme_link_id_dbg(sdata, link_id, + "HT not supported (and not on 6 GHz), limiting to legacy\n"); + goto out; + } - ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set); + /* HT is fine */ + conn->mode = IEEE80211_CONN_MODE_HT; + conn->bw_limit = sta_ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? + IEEE80211_CONN_BW_LIMIT_40 : + IEEE80211_CONN_BW_LIMIT_20; - /* - * Apparently iPhone 13 (at least iOS version 15.3.1) sets this to all - * zeroes, which is nonsense, and completely inconsistent with itself - * (it doesn't have 8 streams). Accept the settings in this case anyway. - */ - if (!ap_min_req_set) - return true; - - /* make sure the AP is consistent with itself - * - * P802.11-REVme/D0.3 - * 26.17.1 Basic HE BSS operation - * - * A STA that is operating in an HE BSS shall be able to receive and - * transmit at each of the <HE-MCS, NSS> tuple values indicated by the - * Basic HE-MCS And NSS Set field of the HE Operation parameter of the - * MLME-START.request primitive and shall be able to receive at each of - * the <HE-MCS, NSS> tuple values indicated by the Supported HE-MCS and - * NSS Set field in the HE Capabilities parameter of the MLMESTART.request - * primitive - */ - for (nss = 8; nss > 0; nss--) { - u8 ap_op_val = (ap_min_req_set >> (2 * (nss - 1))) & 3; - u8 ap_rx_val; - u8 ap_tx_val; + memcpy(&vht_cap, &sband->vht_cap, sizeof(vht_cap)); + ieee80211_apply_vhtcap_overrides(sdata, &vht_cap); - if (ap_op_val == IEEE80211_HE_MCS_NOT_SUPPORTED) - continue; + if (req && req->flags & ASSOC_REQ_DISABLE_VHT) { + mlme_link_id_dbg(sdata, link_id, + "VHT disabled by flag, limiting to HT\n"); + goto out; + } - ap_rx_val = (mcs_80_map_rx >> (2 * (nss - 1))) & 3; - ap_tx_val = (mcs_80_map_tx >> (2 * (nss - 1))) & 3; + if (vht_cap.vht_supported && is_5ghz) { + bool have_80mhz = false; + unsigned int i; - if (ap_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || - ap_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || - ap_rx_val < ap_op_val || ap_tx_val < ap_op_val) { - sdata_info(sdata, - "Invalid rates for %d Nss, rx %d, tx %d oper %d, disable HE\n", - nss, ap_rx_val, ap_rx_val, ap_op_val); - return false; + if (conn->bw_limit == IEEE80211_CONN_BW_LIMIT_20) { + mlme_link_id_dbg(sdata, link_id, + "no 40 MHz support on 5 GHz, limiting to HT\n"); + goto out; } - } - return true; -} + /* Allow VHT if at least one channel on the sband supports 80 MHz */ + for (i = 0; i < sband->n_channels; i++) { + if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED | + IEEE80211_CHAN_NO_80MHZ)) + continue; -static bool -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_iftype_cap_vif(sband, &sdata->vif); - u16 ap_min_req_set; - int i; + have_80mhz = true; + break; + } - if (!sta_he_cap || !he_op) - return false; + if (!have_80mhz) { + mlme_link_id_dbg(sdata, link_id, + "no 80 MHz channel support on 5 GHz, limiting to HT\n"); + goto out; + } + } else if (is_5ghz) { /* !vht_supported but on 5 GHz */ + mlme_link_id_dbg(sdata, link_id, + "no VHT support on 5 GHz, limiting to HT\n"); + goto out; + } - ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set); + /* VHT - if we have - is fine, including 80 MHz, check 160 below again */ + if (sband->band != NL80211_BAND_2GHZ) { + conn->mode = IEEE80211_CONN_MODE_VHT; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_160; + } - /* - * Apparently iPhone 13 (at least iOS version 15.3.1) sets this to all - * zeroes, which is nonsense, and completely inconsistent with itself - * (it doesn't have 8 streams). Accept the settings in this case anyway. - */ - if (!ap_min_req_set) - return true; + if (is_5ghz && + !(vht_cap.cap & (IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ | + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ))) { + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_80; + mlme_link_id_dbg(sdata, link_id, + "no VHT 160 MHz capability on 5 GHz, limiting to 80 MHz"); + } - /* Need to go over for 80MHz, 160MHz and for 80+80 */ - for (i = 0; i < 3; i++) { - const struct ieee80211_he_mcs_nss_supp *sta_mcs_nss_supp = - &sta_he_cap->he_mcs_nss_supp; - u16 sta_mcs_map_rx = - le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i]); - u16 sta_mcs_map_tx = - le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i + 1]); - u8 nss; - bool verified = true; + if (req && req->flags & ASSOC_REQ_DISABLE_HE) { + mlme_link_id_dbg(sdata, link_id, + "HE disabled by flag, limiting to HT/VHT\n"); + goto out; + } - /* - * For each band there is a maximum of 8 spatial streams - * possible. Each of the sta_mcs_map_* is a 16-bit struct built - * of 2 bits per NSS (1-8), with the values defined in enum - * ieee80211_he_mcs_support. Need to make sure STA TX and RX - * capabilities aren't less than the AP's minimum requirements - * for this HE BSS per SS. - * It is enough to find one such band that meets the reqs. - */ - for (nss = 8; nss > 0; nss--) { - u8 sta_rx_val = (sta_mcs_map_rx >> (2 * (nss - 1))) & 3; - u8 sta_tx_val = (sta_mcs_map_tx >> (2 * (nss - 1))) & 3; - u8 ap_val = (ap_min_req_set >> (2 * (nss - 1))) & 3; + he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); + if (!he_cap) { + WARN_ON(is_6ghz); + mlme_link_id_dbg(sdata, link_id, + "no HE support, limiting to HT/VHT\n"); + goto out; + } - if (ap_val == IEEE80211_HE_MCS_NOT_SUPPORTED) - continue; + /* so we have HE */ + conn->mode = IEEE80211_CONN_MODE_HE; - /* - * Make sure the HE AP doesn't require MCSs that aren't - * supported by the client as required by spec - * - * P802.11-REVme/D0.3 - * 26.17.1 Basic HE BSS operation - * - * An HE STA shall not attempt to join * (MLME-JOIN.request primitive) - * a BSS, unless it supports (i.e., is able to both transmit and - * receive using) all of the <HE-MCS, NSS> tuples in the basic - * HE-MCS and NSS set. - */ - if (sta_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || - sta_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED || - (ap_val > sta_rx_val) || (ap_val > sta_tx_val)) { - verified = false; - break; - } + /* check bandwidth */ + switch (sband->band) { + default: + case NL80211_BAND_2GHZ: + if (he_cap->he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) + break; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_20; + mlme_link_id_dbg(sdata, link_id, + "no 40 MHz HE cap in 2.4 GHz, limiting to 20 MHz\n"); + break; + case NL80211_BAND_5GHZ: + if (!(he_cap->he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G)) { + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_20; + mlme_link_id_dbg(sdata, link_id, + "no 40/80 MHz HE cap in 5 GHz, limiting to 20 MHz\n"); + break; } - - if (verified) - return true; + if (!(he_cap->he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G)) { + conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, + conn->bw_limit, + IEEE80211_CONN_BW_LIMIT_80); + mlme_link_id_dbg(sdata, link_id, + "no 160 MHz HE cap in 5 GHz, limiting to 80 MHz\n"); + } + break; + case NL80211_BAND_6GHZ: + if (he_cap->he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + break; + conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, + conn->bw_limit, + IEEE80211_CONN_BW_LIMIT_80); + mlme_link_id_dbg(sdata, link_id, + "no 160 MHz HE cap in 6 GHz, limiting to 80 MHz\n"); + break; } - /* If here, STA doesn't meet AP's HE min requirements */ - return false; -} + if (req && req->flags & ASSOC_REQ_DISABLE_EHT) { + mlme_link_id_dbg(sdata, link_id, + "EHT disabled by flag, limiting to HE\n"); + goto out; + } -static u8 -ieee80211_get_eht_cap_mcs_nss(const struct ieee80211_sta_he_cap *sta_he_cap, - const struct ieee80211_sta_eht_cap *sta_eht_cap, - unsigned int idx, int bw) -{ - u8 he_phy_cap0 = sta_he_cap->he_cap_elem.phy_cap_info[0]; - u8 eht_phy_cap0 = sta_eht_cap->eht_cap_elem.phy_cap_info[0]; + eht_cap = ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif); + if (!eht_cap) { + mlme_link_id_dbg(sdata, link_id, + "no EHT support, limiting to HE\n"); + goto out; + } - /* handle us being a 20 MHz-only EHT STA - with four values - * for MCS 0-7, 8-9, 10-11, 12-13. - */ - if (!(he_phy_cap0 & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) - return sta_eht_cap->eht_mcs_nss_supp.only_20mhz.rx_tx_max_nss[idx]; + /* we have EHT */ - /* the others have MCS 0-9 together, rather than separately from 0-7 */ - if (idx > 0) - idx--; + conn->mode = IEEE80211_CONN_MODE_EHT; - switch (bw) { - case 0: - return sta_eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_max_nss[idx]; - case 1: - if (!(he_phy_cap0 & - (IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G))) - return 0xff; /* pass check */ - return sta_eht_cap->eht_mcs_nss_supp.bw._160.rx_tx_max_nss[idx]; - case 2: - if (!(eht_phy_cap0 & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ)) - return 0xff; /* pass check */ - return sta_eht_cap->eht_mcs_nss_supp.bw._320.rx_tx_max_nss[idx]; - } + /* check bandwidth */ + if (is_6ghz && + eht_cap->eht_cap_elem.phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_320; + else if (is_6ghz) + mlme_link_id_dbg(sdata, link_id, + "no EHT 320 MHz cap in 6 GHz, limiting to 160 MHz\n"); - WARN_ON(1); - return 0; +out: + mlme_link_id_dbg(sdata, link_id, + "determined local STA to be %s, BW limited to %d MHz\n", + ieee80211_conn_mode_str(conn->mode), + 20 * (1 << conn->bw_limit)); } -static bool -ieee80211_verify_sta_eht_mcs_support(struct ieee80211_sub_if_data *sdata, - struct ieee80211_supported_band *sband, - const struct ieee80211_eht_operation *eht_op) +static void +ieee80211_determine_our_sta_mode_auth(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + struct cfg80211_auth_request *req, + bool wmm_used, + struct ieee80211_conn_settings *conn) { - const struct ieee80211_sta_he_cap *sta_he_cap = - ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); - const struct ieee80211_sta_eht_cap *sta_eht_cap = - ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif); - const struct ieee80211_eht_mcs_nss_supp_20mhz_only *req; - unsigned int i; - - if (!sta_he_cap || !sta_eht_cap || !eht_op) - return false; - - req = &eht_op->basic_mcs_nss; - - for (i = 0; i < ARRAY_SIZE(req->rx_tx_max_nss); i++) { - u8 req_rx_nss, req_tx_nss; - unsigned int bw; - - req_rx_nss = u8_get_bits(req->rx_tx_max_nss[i], - IEEE80211_EHT_MCS_NSS_RX); - req_tx_nss = u8_get_bits(req->rx_tx_max_nss[i], - IEEE80211_EHT_MCS_NSS_TX); + ieee80211_determine_our_sta_mode(sdata, sband, NULL, wmm_used, + req->link_id > 0 ? req->link_id : 0, + conn); +} - for (bw = 0; bw < 3; bw++) { - u8 have, have_rx_nss, have_tx_nss; +static void +ieee80211_determine_our_sta_mode_assoc(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, + struct cfg80211_assoc_request *req, + bool wmm_used, int link_id, + struct ieee80211_conn_settings *conn) +{ + struct ieee80211_conn_settings tmp; - have = ieee80211_get_eht_cap_mcs_nss(sta_he_cap, - sta_eht_cap, - i, bw); - have_rx_nss = u8_get_bits(have, - IEEE80211_EHT_MCS_NSS_RX); - have_tx_nss = u8_get_bits(have, - IEEE80211_EHT_MCS_NSS_TX); + WARN_ON(!req); - if (req_rx_nss > have_rx_nss || - req_tx_nss > have_tx_nss) - return false; - } - } + ieee80211_determine_our_sta_mode(sdata, sband, req, wmm_used, link_id, + &tmp); - return true; + conn->mode = min_t(enum ieee80211_conn_mode, + conn->mode, tmp.mode); + conn->bw_limit = min_t(enum ieee80211_conn_bw_limit, + conn->bw_limit, tmp.bw_limit); } static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, - struct cfg80211_bss *cbss, - bool mlo, - ieee80211_conn_flags_t *conn_flags) + int link_id, + struct cfg80211_bss *cbss, bool mlo, + struct ieee80211_conn_settings *conn) { struct ieee80211_local *local = sdata->local; - const struct ieee80211_ht_cap *ht_cap = NULL; - const struct ieee80211_ht_operation *ht_oper = NULL; - const struct ieee80211_vht_operation *vht_oper = NULL; - const struct ieee80211_he_operation *he_oper = NULL; - const struct ieee80211_eht_operation *eht_oper = NULL; - const struct ieee80211_s1g_oper_ie *s1g_oper = NULL; - struct ieee80211_supported_band *sband; - struct cfg80211_chan_def chandef; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; - bool is_5ghz = cbss->channel->band == NL80211_BAND_5GHZ; - bool supports_mlo = false; - struct ieee80211_bss *bss = (void *)cbss->priv; - struct ieee80211_elems_parse_params parse_params = { - .link_id = -1, - .from_ap = true, - }; + struct ieee80211_chan_req chanreq = {}; struct ieee802_11_elems *elems; - const struct cfg80211_bss_ies *ies; int ret; u32 i; - bool have_80mhz; lockdep_assert_wiphy(local->hw.wiphy); rcu_read_lock(); + elems = ieee80211_determine_chan_mode(sdata, conn, cbss, link_id, + &chanreq); - ies = rcu_dereference(cbss->ies); - parse_params.start = ies->data; - parse_params.len = ies->len; - elems = ieee802_11_parse_elems_full(&parse_params); - if (!elems) { + if (IS_ERR(elems)) { rcu_read_unlock(); - return -ENOMEM; - } - - sband = local->hw.wiphy->bands[cbss->channel->band]; - - *conn_flags &= ~(IEEE80211_CONN_DISABLE_40MHZ | - IEEE80211_CONN_DISABLE_80P80MHZ | - IEEE80211_CONN_DISABLE_160MHZ); - - /* disable HT/VHT/HE if we don't support them */ - if (!sband->ht_cap.ht_supported && !is_6ghz) { - mlme_dbg(sdata, "HT not supported, disabling HT/VHT/HE/EHT\n"); - *conn_flags |= IEEE80211_CONN_DISABLE_HT; - *conn_flags |= IEEE80211_CONN_DISABLE_VHT; - *conn_flags |= IEEE80211_CONN_DISABLE_HE; - *conn_flags |= IEEE80211_CONN_DISABLE_EHT; + return PTR_ERR(elems); } - if (!sband->vht_cap.vht_supported && is_5ghz) { - mlme_dbg(sdata, "VHT not supported, disabling VHT/HE/EHT\n"); - *conn_flags |= IEEE80211_CONN_DISABLE_VHT; - *conn_flags |= IEEE80211_CONN_DISABLE_HE; - *conn_flags |= IEEE80211_CONN_DISABLE_EHT; - } - - if (!ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif)) { - mlme_dbg(sdata, "HE not supported, disabling HE and EHT\n"); - *conn_flags |= IEEE80211_CONN_DISABLE_HE; - *conn_flags |= IEEE80211_CONN_DISABLE_EHT; - } - - if (!ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif)) { - mlme_dbg(sdata, "EHT not supported, disabling EHT\n"); - *conn_flags |= IEEE80211_CONN_DISABLE_EHT; - } - - if (!(*conn_flags & IEEE80211_CONN_DISABLE_HT) && !is_6ghz) { - ht_oper = elems->ht_operation; - ht_cap = elems->ht_cap_elem; - - if (!ht_cap) { - *conn_flags |= IEEE80211_CONN_DISABLE_HT; - ht_oper = NULL; - } - } - - if (!(*conn_flags & IEEE80211_CONN_DISABLE_VHT) && !is_6ghz) { - vht_oper = elems->vht_operation; - if (vht_oper && !ht_oper) { - vht_oper = NULL; - sdata_info(sdata, - "AP advertised VHT without HT, disabling HT/VHT/HE\n"); - *conn_flags |= IEEE80211_CONN_DISABLE_HT; - *conn_flags |= IEEE80211_CONN_DISABLE_VHT; - *conn_flags |= IEEE80211_CONN_DISABLE_HE; - *conn_flags |= IEEE80211_CONN_DISABLE_EHT; - } - - if (!elems->vht_cap_elem) { - *conn_flags |= IEEE80211_CONN_DISABLE_VHT; - vht_oper = NULL; - } + if (mlo && !elems->ml_basic) { + sdata_info(sdata, "Rejecting MLO as it is not supported by AP\n"); + rcu_read_unlock(); + kfree(elems); + return -EINVAL; } - if (!(*conn_flags & IEEE80211_CONN_DISABLE_HE)) { - he_oper = elems->he_operation; - - if (link && is_6ghz) { - struct ieee80211_bss_conf *bss_conf; - u8 j = 0; + if (link && is_6ghz && conn->mode >= IEEE80211_CONN_MODE_HE) { + struct ieee80211_bss_conf *bss_conf; + u8 j = 0; - bss_conf = link->conf; + bss_conf = link->conf; - if (elems->pwr_constr_elem) - bss_conf->pwr_reduction = *elems->pwr_constr_elem; + if (elems->pwr_constr_elem) + bss_conf->pwr_reduction = *elems->pwr_constr_elem; - BUILD_BUG_ON(ARRAY_SIZE(bss_conf->tx_pwr_env) != - ARRAY_SIZE(elems->tx_pwr_env)); - - for (i = 0; i < elems->tx_pwr_env_num; i++) { - if (elems->tx_pwr_env_len[i] > - sizeof(bss_conf->tx_pwr_env[j])) - continue; + BUILD_BUG_ON(ARRAY_SIZE(bss_conf->tx_pwr_env) != + ARRAY_SIZE(elems->tx_pwr_env)); - bss_conf->tx_pwr_env_num++; - memcpy(&bss_conf->tx_pwr_env[j], elems->tx_pwr_env[i], - elems->tx_pwr_env_len[i]); - j++; - } - } - - if (!ieee80211_verify_peer_he_mcs_support(sdata, ies, he_oper) || - !ieee80211_verify_sta_he_mcs_support(sdata, sband, he_oper)) - *conn_flags |= IEEE80211_CONN_DISABLE_HE | - IEEE80211_CONN_DISABLE_EHT; - } - - /* - * EHT requires HE to be supported as well. Specifically for 6 GHz - * channels, the operation channel information can only be deduced from - * both the 6 GHz operation information (from the HE operation IE) and - * EHT operation. - */ - if (!(*conn_flags & - (IEEE80211_CONN_DISABLE_HE | - IEEE80211_CONN_DISABLE_EHT)) && - he_oper) { - const struct cfg80211_bss_ies *cbss_ies; - const struct element *eht_ml_elem; - const u8 *eht_oper_ie; - - cbss_ies = rcu_dereference(cbss->ies); - eht_oper_ie = cfg80211_find_ext_ie(WLAN_EID_EXT_EHT_OPERATION, - cbss_ies->data, cbss_ies->len); - if (eht_oper_ie && eht_oper_ie[1] >= - 1 + sizeof(struct ieee80211_eht_operation)) - eht_oper = (void *)(eht_oper_ie + 3); - else - eht_oper = NULL; - - if (!ieee80211_verify_sta_eht_mcs_support(sdata, sband, eht_oper)) - *conn_flags |= IEEE80211_CONN_DISABLE_EHT; - - eht_ml_elem = cfg80211_find_ext_elem(WLAN_EID_EXT_EHT_MULTI_LINK, - cbss_ies->data, cbss_ies->len); - - /* data + 1 / datalen - 1 since it's an extended element */ - if (!(*conn_flags & IEEE80211_CONN_DISABLE_EHT) && - eht_ml_elem && - ieee80211_mle_type_ok(eht_ml_elem->data + 1, - IEEE80211_ML_CONTROL_TYPE_BASIC, - eht_ml_elem->datalen - 1)) { - supports_mlo = true; + for (i = 0; i < elems->tx_pwr_env_num; i++) { + if (elems->tx_pwr_env_len[i] > sizeof(bss_conf->tx_pwr_env[j])) + continue; - sdata->vif.cfg.eml_cap = - ieee80211_mle_get_eml_cap(eht_ml_elem->data + 1); - sdata->vif.cfg.eml_med_sync_delay = - ieee80211_mle_get_eml_med_sync_delay(eht_ml_elem->data + 1); + bss_conf->tx_pwr_env_num++; + memcpy(&bss_conf->tx_pwr_env[j], elems->tx_pwr_env[i], + elems->tx_pwr_env_len[i]); + j++; } } - - /* Allow VHT if at least one channel on the sband supports 80 MHz */ - have_80mhz = false; - for (i = 0; i < sband->n_channels; i++) { - if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED | - IEEE80211_CHAN_NO_80MHZ)) - continue; - - have_80mhz = true; - break; - } - - if (!have_80mhz) { - sdata_info(sdata, "80 MHz not supported, disabling VHT\n"); - *conn_flags |= IEEE80211_CONN_DISABLE_VHT; - } - - if (sband->band == NL80211_BAND_S1GHZ) { - s1g_oper = elems->s1g_oper; - if (!s1g_oper) - sdata_info(sdata, - "AP missing S1G operation element?\n"); - } - - *conn_flags |= - ieee80211_determine_chantype(sdata, link, *conn_flags, - sband, - cbss->channel, - bss->vht_cap_info, - ht_oper, vht_oper, - he_oper, eht_oper, - s1g_oper, - &chandef, false); - - if (link) - link->needed_rx_chains = - min(ieee80211_max_rx_chains(link, cbss), - local->rx_chains); - rcu_read_unlock(); /* the element data was RCU protected so no longer valid anyway */ kfree(elems); elems = NULL; - if (*conn_flags & IEEE80211_CONN_DISABLE_HE && is_6ghz) { - sdata_info(sdata, "Rejecting non-HE 6/7 GHz connection"); - return -EINVAL; - } - - if (mlo && !supports_mlo) { - sdata_info(sdata, "Rejecting MLO as it is not supported by AP\n"); - return -EINVAL; - } - if (!link) return 0; + rcu_read_lock(); + link->needed_rx_chains = min(ieee80211_max_rx_chains(link, cbss), + local->rx_chains); + rcu_read_unlock(); + /* * If this fails (possibly due to channel context sharing * on incompatible channels, e.g. 80+80 and 160 sharing the * same control channel) try to use a smaller bandwidth. */ - ret = ieee80211_link_use_channel(link, &chandef, + ret = ieee80211_link_use_channel(link, &chanreq, IEEE80211_CHANCTX_SHARED); /* don't downgrade for 5 and 10 MHz channels, though. */ - if (chandef.width == NL80211_CHAN_WIDTH_5 || - chandef.width == NL80211_CHAN_WIDTH_10) - goto out; + if (chanreq.oper.width == NL80211_CHAN_WIDTH_5 || + chanreq.oper.width == NL80211_CHAN_WIDTH_10) + return ret; + + while (ret && chanreq.oper.width != NL80211_CHAN_WIDTH_20_NOHT) { + ieee80211_chanreq_downgrade(&chanreq, conn); - while (ret && chandef.width != NL80211_CHAN_WIDTH_20_NOHT) { - *conn_flags |= - ieee80211_chandef_downgrade(&chandef); - ret = ieee80211_link_use_channel(link, &chandef, + ret = ieee80211_link_use_channel(link, &chanreq, IEEE80211_CHANCTX_SHARED); } - out: + return ret; } @@ -5126,6 +5134,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, if (WARN_ON(!sta)) goto out_err; + sta->sta.spp_amsdu = assoc_data->spp_amsdu; + if (ieee80211_vif_is_mld(&sdata->vif)) { for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { if (!assoc_data->link[link_id].bss) @@ -5189,8 +5199,10 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, link->conf->dtim_period = link->u.mgd.dtim_period ?: 1; if (link_id != assoc_data->assoc_link_id) { - err = ieee80211_prep_channel(sdata, link, cbss, true, - &link->u.mgd.conn_flags); + link->u.mgd.conn = assoc_data->link[link_id].conn; + + err = ieee80211_prep_channel(sdata, link, link_id, cbss, + true, &link->u.mgd.conn); if (err) { link_info(link, "prep_channel failed\n"); goto out_err; @@ -5308,6 +5320,9 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, if (!assoc_data) return; + parse_params.mode = + assoc_data->link[assoc_data->assoc_link_id].conn.mode; + if (!ether_addr_equal(assoc_data->ap_addr, mgmt->bssid) || !ether_addr_equal(assoc_data->ap_addr, mgmt->sa)) return; @@ -5424,6 +5439,13 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, assoc_data->ap_addr); goto abandon_assoc; } + + sdata->vif.cfg.eml_cap = + ieee80211_mle_get_eml_cap((const void *)elems->ml_basic); + sdata->vif.cfg.eml_med_sync_delay = + ieee80211_mle_get_eml_med_sync_delay((const void *)elems->ml_basic); + sdata->vif.cfg.mld_capa_op = + ieee80211_mle_get_mld_capa_op((const void *)elems->ml_basic); } sdata->vif.cfg.aid = aid; @@ -5686,49 +5708,6 @@ static bool ieee80211_rx_our_beacon(const u8 *tx_bssid, return ether_addr_equal(tx_bssid, bss->transmitted_bss->bssid); } -static bool ieee80211_config_puncturing(struct ieee80211_link_data *link, - const struct ieee80211_eht_operation *eht_oper, - u64 *changed) -{ - struct ieee80211_local *local = link->sdata->local; - u16 bitmap = 0, extracted; - - if ((eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT) && - (eht_oper->params & - IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)) { - const struct ieee80211_eht_operation_info *info = - (void *)eht_oper->optional; - const u8 *disable_subchannel_bitmap = info->optional; - - bitmap = get_unaligned_le16(disable_subchannel_bitmap); - } - - extracted = ieee80211_extract_dis_subch_bmap(eht_oper, - &link->conf->chandef, - bitmap); - - /* accept if there are no changes */ - if (!(*changed & BSS_CHANGED_BANDWIDTH) && - extracted == link->conf->eht_puncturing) - return true; - - if (!cfg80211_valid_disable_subchannel_bitmap(&bitmap, - &link->conf->chandef)) { - link_info(link, - "Got an invalid disable subchannel bitmap from AP %pM: bitmap = 0x%x, bw = 0x%x. disconnect\n", - link->u.mgd.bssid, - bitmap, - link->conf->chandef.width); - return false; - } - - if (bitmap && ieee80211_hw_check(&local->hw, DISALLOW_PUNCTURING)) - return false; - - ieee80211_handle_puncturing_bitmap(link, eht_oper, bitmap, changed); - return true; -} - static void ieee80211_ml_reconf_work(struct wiphy *wiphy, struct wiphy_work *work) { @@ -5792,9 +5771,7 @@ out: static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems) { - const struct ieee80211_multi_link_elem *ml; const struct element *sub; - ssize_t ml_len; unsigned long removed_links = 0; u16 link_removal_timeout[IEEE80211_MLD_MAX_NUM_LINKS] = {}; u8 link_id; @@ -5803,24 +5780,11 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, if (!ieee80211_vif_is_mld(&sdata->vif) || !elems->ml_reconf) return; - ml_len = cfg80211_defragment_element(elems->ml_reconf_elem, - elems->ie_start, - elems->total_len, - elems->scratch_pos, - elems->scratch + elems->scratch_len - - elems->scratch_pos, - WLAN_EID_FRAGMENT); - if (ml_len < 0) - return; - - elems->ml_reconf = (const void *)elems->scratch_pos; - elems->ml_reconf_len = ml_len; - ml = elems->ml_reconf; - /* Directly parse the sub elements as the common information doesn't * hold any useful information. */ - for_each_mle_subelement(sub, (u8 *)ml, ml_len) { + for_each_mle_subelement(sub, (const u8 *)elems->ml_reconf, + elems->ml_reconf_len) { struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data; u8 *pos = prof->variable; u16 control; @@ -5888,6 +5852,56 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, TU_TO_JIFFIES(delay)); } +static int ieee80211_ttlm_set_links(struct ieee80211_sub_if_data *sdata, + u16 active_links, u16 dormant_links, + u16 suspended_links) +{ + u64 changed = 0; + int ret; + + if (!active_links) { + ret = -EINVAL; + goto out; + } + + /* If there is an active negotiated TTLM, it should be discarded by + * the new negotiated/advertised TTLM. + */ + if (sdata->vif.neg_ttlm.valid) { + memset(&sdata->vif.neg_ttlm, 0, sizeof(sdata->vif.neg_ttlm)); + sdata->vif.suspended_links = 0; + changed = BSS_CHANGED_MLD_TTLM; + } + + if (sdata->vif.active_links != active_links) { + ret = ieee80211_set_active_links(&sdata->vif, active_links); + if (ret) { + sdata_info(sdata, "Failed to set TTLM active links\n"); + goto out; + } + } + + ret = ieee80211_vif_set_links(sdata, sdata->vif.valid_links, + dormant_links); + if (ret) { + sdata_info(sdata, "Failed to set TTLM dormant links\n"); + goto out; + } + + changed |= BSS_CHANGED_MLD_VALID_LINKS; + sdata->vif.suspended_links = suspended_links; + if (sdata->vif.suspended_links) + changed |= BSS_CHANGED_MLD_TTLM; + + ieee80211_vif_cfg_change_notify(sdata, changed); + +out: + if (ret) + ieee80211_disconnect(&sdata->vif, false); + + return ret; +} + static void ieee80211_tid_to_link_map_work(struct wiphy *wiphy, struct wiphy_work *work) { @@ -5895,30 +5909,19 @@ static void ieee80211_tid_to_link_map_work(struct wiphy *wiphy, struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, u.mgd.ttlm_work.work); - int ret; new_active_links = sdata->u.mgd.ttlm_info.map & sdata->vif.valid_links; new_dormant_links = ~sdata->u.mgd.ttlm_info.map & sdata->vif.valid_links; - if (!new_active_links) { - ieee80211_disconnect(&sdata->vif, false); - return; - } ieee80211_vif_set_links(sdata, sdata->vif.valid_links, 0); - new_active_links = BIT(ffs(new_active_links) - 1); - ieee80211_set_active_links(&sdata->vif, new_active_links); - - ret = ieee80211_vif_set_links(sdata, sdata->vif.valid_links, - new_dormant_links); + if (ieee80211_ttlm_set_links(sdata, new_active_links, new_dormant_links, + 0)) + return; sdata->u.mgd.ttlm_info.active = true; sdata->u.mgd.ttlm_info.switch_time = 0; - - if (!ret) - ieee80211_vif_cfg_change_notify(sdata, - BSS_CHANGED_MLD_VALID_LINKS); } static u16 ieee80211_get_ttlm(u8 bm_size, u8 *data) @@ -6128,6 +6131,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, u8 *bssid, *variable = mgmt->u.beacon.variable; u8 deauth_buf[IEEE80211_DEAUTH_FRAME_LEN]; struct ieee80211_elems_parse_params parse_params = { + .mode = link->u.mgd.conn.mode, .link_id = -1, .from_ap = true, }; @@ -6210,7 +6214,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, } if (!ifmgd->associated || - !ieee80211_rx_our_beacon(bssid, link->u.mgd.bss)) + !ieee80211_rx_our_beacon(bssid, link->conf->bss)) return; bssid = link->u.mgd.bssid; @@ -6237,7 +6241,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, */ if (!ieee80211_is_s1g_beacon(hdr->frame_control)) ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4); - parse_params.bss = link->u.mgd.bss; + parse_params.bss = link->conf->bss; parse_params.filter = care_about_ies; parse_params.crc = ncrc; elems = ieee802_11_parse_elems_full(&parse_params); @@ -6299,9 +6303,6 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, } } - if (link->u.mgd.csa_waiting_bcn) - ieee80211_chswitch_post_beacon(link); - /* * Update beacon timing and dtim count on every beacon appearance. This * will allow the driver to use the most updated values. Do it before @@ -6375,21 +6376,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, goto free; } - if (WARN_ON(!link->conf->chandef.chan)) + if (WARN_ON(!link->conf->chanreq.oper.chan)) goto free; - sband = local->hw.wiphy->bands[link->conf->chandef.chan->band]; + sband = local->hw.wiphy->bands[link->conf->chanreq.oper.chan->band]; changed |= ieee80211_recalc_twt_req(sdata, sband, link, link_sta, elems); - if (ieee80211_config_bw(link, elems->ht_cap_elem, - elems->vht_cap_elem, elems->ht_operation, - elems->vht_operation, elems->he_operation, - elems->eht_operation, - elems->s1g_oper, bssid, &changed)) { - sdata_info(sdata, - "failed to follow AP %pM bandwidth change, disconnect\n", - bssid); + if (ieee80211_config_bw(link, elems, true, &changed)) { ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DEAUTH_LEAVING, true, deauth_buf); @@ -6411,21 +6405,6 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, elems->pwr_constr_elem, elems->cisco_dtpc_elem); - if (elems->eht_operation && - !(link->u.mgd.conn_flags & IEEE80211_CONN_DISABLE_EHT)) { - if (!ieee80211_config_puncturing(link, elems->eht_operation, - &changed)) { - ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, - WLAN_REASON_DEAUTH_LEAVING, - true, deauth_buf); - ieee80211_report_disconnect(sdata, deauth_buf, - sizeof(deauth_buf), true, - WLAN_REASON_DEAUTH_LEAVING, - false); - goto free; - } - } - ieee80211_ml_reconfiguration(sdata, elems); ieee80211_process_adv_ttlm(sdata, elems, le64_to_cpu(mgmt->u.beacon.timestamp)); @@ -6435,6 +6414,376 @@ free: kfree(elems); } +static void ieee80211_apply_neg_ttlm(struct ieee80211_sub_if_data *sdata, + struct ieee80211_neg_ttlm neg_ttlm) +{ + u16 new_active_links, new_dormant_links, new_suspended_links, map = 0; + u8 i; + + for (i = 0; i < IEEE80211_TTLM_NUM_TIDS; i++) + map |= neg_ttlm.downlink[i] | neg_ttlm.uplink[i]; + + /* If there is an active TTLM, unset previously suspended links */ + if (sdata->vif.neg_ttlm.valid) + sdata->vif.dormant_links &= ~sdata->vif.suspended_links; + + /* exclude links that are already disabled by advertised TTLM */ + new_active_links = + map & sdata->vif.valid_links & ~sdata->vif.dormant_links; + new_suspended_links = + (~map & sdata->vif.valid_links) & ~sdata->vif.dormant_links; + new_dormant_links = sdata->vif.dormant_links | new_suspended_links; + if (ieee80211_ttlm_set_links(sdata, new_active_links, + new_dormant_links, new_suspended_links)) + return; + + sdata->vif.neg_ttlm = neg_ttlm; + sdata->vif.neg_ttlm.valid = true; +} + +static void ieee80211_neg_ttlm_timeout_work(struct wiphy *wiphy, + struct wiphy_work *work) +{ + struct ieee80211_sub_if_data *sdata = + container_of(work, struct ieee80211_sub_if_data, + u.mgd.neg_ttlm_timeout_work.work); + + sdata_info(sdata, + "No negotiated TTLM response from AP, disconnecting.\n"); + + __ieee80211_disconnect(sdata); +} + +static void +ieee80211_neg_ttlm_add_suggested_map(struct sk_buff *skb, + struct ieee80211_neg_ttlm *neg_ttlm) +{ + u8 i, direction[IEEE80211_TTLM_MAX_CNT]; + + if (memcmp(neg_ttlm->downlink, neg_ttlm->uplink, + sizeof(neg_ttlm->downlink))) { + direction[0] = IEEE80211_TTLM_DIRECTION_DOWN; + direction[1] = IEEE80211_TTLM_DIRECTION_UP; + } else { + direction[0] = IEEE80211_TTLM_DIRECTION_BOTH; + } + + for (i = 0; i < ARRAY_SIZE(direction); i++) { + u8 tid, len, map_ind = 0, *len_pos, *map_ind_pos, *pos; + __le16 map; + + len = sizeof(struct ieee80211_ttlm_elem) + 1 + 1; + + pos = skb_put(skb, len + 2); + *pos++ = WLAN_EID_EXTENSION; + len_pos = pos++; + *pos++ = WLAN_EID_EXT_TID_TO_LINK_MAPPING; + *pos++ = direction[i]; + map_ind_pos = pos++; + for (tid = 0; tid < IEEE80211_TTLM_NUM_TIDS; tid++) { + map = direction[i] == IEEE80211_TTLM_DIRECTION_UP ? + cpu_to_le16(neg_ttlm->uplink[tid]) : + cpu_to_le16(neg_ttlm->downlink[tid]); + if (!map) + continue; + + len += 2; + map_ind |= BIT(tid); + skb_put_data(skb, &map, sizeof(map)); + } + + *map_ind_pos = map_ind; + *len_pos = len; + + if (direction[i] == IEEE80211_TTLM_DIRECTION_BOTH) + break; + } +} + +static void +ieee80211_send_neg_ttlm_req(struct ieee80211_sub_if_data *sdata, + struct ieee80211_neg_ttlm *neg_ttlm, + u8 dialog_token) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_mgmt *mgmt; + struct sk_buff *skb; + int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.ttlm_req); + int ttlm_max_len = 2 + 1 + sizeof(struct ieee80211_ttlm_elem) + 1 + + 2 * 2 * IEEE80211_TTLM_NUM_TIDS; + + skb = dev_alloc_skb(local->tx_headroom + hdr_len + ttlm_max_len); + if (!skb) + return; + + skb_reserve(skb, local->tx_headroom); + mgmt = skb_put_zero(skb, hdr_len); + mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION); + memcpy(mgmt->da, sdata->vif.cfg.ap_addr, ETH_ALEN); + memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); + memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN); + + mgmt->u.action.category = WLAN_CATEGORY_PROTECTED_EHT; + mgmt->u.action.u.ttlm_req.action_code = + WLAN_PROTECTED_EHT_ACTION_TTLM_REQ; + mgmt->u.action.u.ttlm_req.dialog_token = dialog_token; + ieee80211_neg_ttlm_add_suggested_map(skb, neg_ttlm); + ieee80211_tx_skb(sdata, skb); +} + +int ieee80211_req_neg_ttlm(struct ieee80211_sub_if_data *sdata, + struct cfg80211_ttlm_params *params) +{ + struct ieee80211_neg_ttlm neg_ttlm = {}; + u8 i; + + if (!ieee80211_vif_is_mld(&sdata->vif) || + !(sdata->vif.cfg.mld_capa_op & + IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP)) + return -EINVAL; + + for (i = 0; i < IEEE80211_TTLM_NUM_TIDS; i++) { + if ((params->dlink[i] & ~sdata->vif.valid_links) || + (params->ulink[i] & ~sdata->vif.valid_links)) + return -EINVAL; + + neg_ttlm.downlink[i] = params->dlink[i]; + neg_ttlm.uplink[i] = params->ulink[i]; + } + + if (drv_can_neg_ttlm(sdata->local, sdata, &neg_ttlm) != + NEG_TTLM_RES_ACCEPT) + return -EINVAL; + + ieee80211_apply_neg_ttlm(sdata, neg_ttlm); + sdata->u.mgd.dialog_token_alloc++; + ieee80211_send_neg_ttlm_req(sdata, &sdata->vif.neg_ttlm, + sdata->u.mgd.dialog_token_alloc); + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &sdata->u.mgd.neg_ttlm_timeout_work); + wiphy_delayed_work_queue(sdata->local->hw.wiphy, + &sdata->u.mgd.neg_ttlm_timeout_work, + IEEE80211_NEG_TTLM_REQ_TIMEOUT); + return 0; +} + +static void +ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, + enum ieee80211_neg_ttlm_res ttlm_res, + u8 dialog_token, + struct ieee80211_neg_ttlm *neg_ttlm) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_mgmt *mgmt; + struct sk_buff *skb; + int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.ttlm_res); + int ttlm_max_len = 2 + 1 + sizeof(struct ieee80211_ttlm_elem) + 1 + + 2 * 2 * IEEE80211_TTLM_NUM_TIDS; + + skb = dev_alloc_skb(local->tx_headroom + hdr_len + ttlm_max_len); + if (!skb) + return; + + skb_reserve(skb, local->tx_headroom); + mgmt = skb_put_zero(skb, hdr_len); + mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION); + memcpy(mgmt->da, sdata->vif.cfg.ap_addr, ETH_ALEN); + memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); + memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN); + + mgmt->u.action.category = WLAN_CATEGORY_PROTECTED_EHT; + mgmt->u.action.u.ttlm_res.action_code = + WLAN_PROTECTED_EHT_ACTION_TTLM_RES; + mgmt->u.action.u.ttlm_res.dialog_token = dialog_token; + switch (ttlm_res) { + default: + WARN_ON(1); + fallthrough; + case NEG_TTLM_RES_REJECT: + mgmt->u.action.u.ttlm_res.status_code = + WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING; + break; + case NEG_TTLM_RES_ACCEPT: + mgmt->u.action.u.ttlm_res.status_code = WLAN_STATUS_SUCCESS; + break; + case NEG_TTLM_RES_SUGGEST_PREFERRED: + mgmt->u.action.u.ttlm_res.status_code = + WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED; + ieee80211_neg_ttlm_add_suggested_map(skb, neg_ttlm); + break; + } + + ieee80211_tx_skb(sdata, skb); +} + +static int +ieee80211_parse_neg_ttlm(struct ieee80211_sub_if_data *sdata, + const struct ieee80211_ttlm_elem *ttlm, + struct ieee80211_neg_ttlm *neg_ttlm, + u8 *direction) +{ + u8 control, link_map_presence, map_size, tid; + u8 *pos; + + /* The element size was already validated in + * ieee80211_tid_to_link_map_size_ok() + */ + pos = (void *)ttlm->optional; + + control = ttlm->control; + + /* mapping switch time and expected duration fields are not expected + * in case of negotiated TTLM + */ + if (control & (IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT | + IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT)) { + mlme_dbg(sdata, + "Invalid TTLM element in negotiated TTLM request\n"); + return -EINVAL; + } + + if (control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP) { + for (tid = 0; tid < IEEE80211_TTLM_NUM_TIDS; tid++) { + neg_ttlm->downlink[tid] = sdata->vif.valid_links; + neg_ttlm->uplink[tid] = sdata->vif.valid_links; + } + *direction = IEEE80211_TTLM_DIRECTION_BOTH; + return 0; + } + + *direction = u8_get_bits(control, IEEE80211_TTLM_CONTROL_DIRECTION); + if (*direction != IEEE80211_TTLM_DIRECTION_DOWN && + *direction != IEEE80211_TTLM_DIRECTION_UP && + *direction != IEEE80211_TTLM_DIRECTION_BOTH) + return -EINVAL; + + link_map_presence = *pos; + pos++; + + if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) + map_size = 1; + else + map_size = 2; + + for (tid = 0; tid < IEEE80211_TTLM_NUM_TIDS; tid++) { + u16 map; + + if (link_map_presence & BIT(tid)) { + map = ieee80211_get_ttlm(map_size, pos); + if (!map) { + mlme_dbg(sdata, + "No active links for TID %d", tid); + return -EINVAL; + } + } else { + map = 0; + } + + switch (*direction) { + case IEEE80211_TTLM_DIRECTION_BOTH: + neg_ttlm->downlink[tid] = map; + neg_ttlm->uplink[tid] = map; + break; + case IEEE80211_TTLM_DIRECTION_DOWN: + neg_ttlm->downlink[tid] = map; + break; + case IEEE80211_TTLM_DIRECTION_UP: + neg_ttlm->uplink[tid] = map; + break; + default: + return -EINVAL; + } + pos += map_size; + } + return 0; +} + +void ieee80211_process_neg_ttlm_req(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len) +{ + u8 dialog_token, direction[IEEE80211_TTLM_MAX_CNT] = {}, i; + size_t ies_len; + enum ieee80211_neg_ttlm_res ttlm_res = NEG_TTLM_RES_ACCEPT; + struct ieee802_11_elems *elems = NULL; + struct ieee80211_neg_ttlm neg_ttlm = {}; + + BUILD_BUG_ON(ARRAY_SIZE(direction) != ARRAY_SIZE(elems->ttlm)); + + if (!ieee80211_vif_is_mld(&sdata->vif)) + return; + + dialog_token = mgmt->u.action.u.ttlm_req.dialog_token; + ies_len = len - offsetof(struct ieee80211_mgmt, + u.action.u.ttlm_req.variable); + elems = ieee802_11_parse_elems(mgmt->u.action.u.ttlm_req.variable, + ies_len, true, NULL); + if (!elems) { + ttlm_res = NEG_TTLM_RES_REJECT; + goto out; + } + + for (i = 0; i < elems->ttlm_num; i++) { + if (ieee80211_parse_neg_ttlm(sdata, elems->ttlm[i], + &neg_ttlm, &direction[i]) || + (direction[i] == IEEE80211_TTLM_DIRECTION_BOTH && + elems->ttlm_num != 1)) { + ttlm_res = NEG_TTLM_RES_REJECT; + goto out; + } + } + + if (!elems->ttlm_num || + (elems->ttlm_num == 2 && direction[0] == direction[1])) { + ttlm_res = NEG_TTLM_RES_REJECT; + goto out; + } + + for (i = 0; i < IEEE80211_TTLM_NUM_TIDS; i++) { + if ((neg_ttlm.downlink[i] && + (neg_ttlm.downlink[i] & ~sdata->vif.valid_links)) || + (neg_ttlm.uplink[i] && + (neg_ttlm.uplink[i] & ~sdata->vif.valid_links))) { + ttlm_res = NEG_TTLM_RES_REJECT; + goto out; + } + } + + ttlm_res = drv_can_neg_ttlm(sdata->local, sdata, &neg_ttlm); + + if (ttlm_res != NEG_TTLM_RES_ACCEPT) + goto out; + + ieee80211_apply_neg_ttlm(sdata, neg_ttlm); +out: + kfree(elems); + ieee80211_send_neg_ttlm_res(sdata, ttlm_res, dialog_token, &neg_ttlm); +} + +void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgmt *mgmt, size_t len) +{ + if (!ieee80211_vif_is_mld(&sdata->vif) || + mgmt->u.action.u.ttlm_req.dialog_token != + sdata->u.mgd.dialog_token_alloc) + return; + + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &sdata->u.mgd.neg_ttlm_timeout_work); + + /* MLD station sends a TID to link mapping request, mainly to handle + * BTM (BSS transition management) request, in which case it needs to + * restrict the active links set. + * In this case it's not expected that the MLD AP will reject the + * negotiated TTLM request. + * This can be better implemented in the future, to handle request + * rejections. + */ + if (mgmt->u.action.u.ttlm_res.status_code != WLAN_STATUS_SUCCESS) + __ieee80211_disconnect(sdata); +} + void ieee80211_sta_rx_queued_ext(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { @@ -7064,6 +7413,8 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) ieee80211_sta_handle_tspec_ac_params_wk); wiphy_delayed_work_init(&ifmgd->ttlm_work, ieee80211_tid_to_link_map_work); + wiphy_delayed_work_init(&ifmgd->neg_ttlm_timeout_work, + ieee80211_neg_ttlm_timeout_work); ifmgd->flags = 0; ifmgd->powersave = sdata->wdev.ps; @@ -7073,6 +7424,7 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) spin_lock_init(&ifmgd->teardown_lock); ifmgd->teardown_skb = NULL; ifmgd->orig_teardown_skb = NULL; + ifmgd->mcast_seq_last = IEEE80211_SN_MODULO; } static void ieee80211_recalc_smps_work(struct wiphy *wiphy, @@ -7092,7 +7444,6 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link) unsigned int link_id = link->link_id; link->u.mgd.p2p_noa_index = -1; - link->u.mgd.conn_flags = 0; link->conf->bssid = link->u.mgd.bssid; link->smps_mode = IEEE80211_SMPS_OFF; @@ -7132,6 +7483,7 @@ void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local) static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, struct cfg80211_bss *cbss, s8 link_id, const u8 *ap_mld_addr, bool assoc, + struct ieee80211_conn_settings *conn, bool override) { struct ieee80211_local *local = sdata->local; @@ -7263,13 +7615,22 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, } if (new_sta || override) { - err = ieee80211_prep_channel(sdata, link, cbss, mlo, - &link->u.mgd.conn_flags); + /* + * Only set this if we're also going to calculate the AP + * settings etc., otherwise this was set before in a + * previous call. Note override is set to %true in assoc + * if the settings were changed. + */ + link->u.mgd.conn = *conn; + err = ieee80211_prep_channel(sdata, link, link->link_id, cbss, + mlo, &link->u.mgd.conn); if (err) { if (new_sta) sta_info_free(local, new_sta); goto out_err; } + /* pass out for use in assoc */ + *conn = link->u.mgd.conn; } if (new_sta) { @@ -7384,10 +7745,13 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_mgd_auth_data *auth_data; + struct ieee80211_conn_settings conn; struct ieee80211_link_data *link; + struct ieee80211_supported_band *sband; + struct ieee80211_bss *bss; u16 auth_alg; int err; - bool cont_auth; + bool cont_auth, wmm_used; lockdep_assert_wiphy(sdata->local->hw.wiphy); @@ -7518,15 +7882,24 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, /* needed for transmitting the auth frame(s) properly */ memcpy(sdata->vif.cfg.ap_addr, auth_data->ap_addr, ETH_ALEN); + bss = (void *)req->bss->priv; + wmm_used = bss->wmm_used && (local->hw.queues >= IEEE80211_NUM_ACS); + + sband = local->hw.wiphy->bands[req->bss->channel->band]; + + ieee80211_determine_our_sta_mode_auth(sdata, sband, req, wmm_used, + &conn); + err = ieee80211_prep_connection(sdata, req->bss, req->link_id, - req->ap_mld_addr, cont_auth, false); + req->ap_mld_addr, cont_auth, + &conn, false); if (err) goto err_clear; - if (req->link_id > 0) + if (req->link_id >= 0) link = sdata_dereference(sdata->link[req->link_id], sdata); else - link = sdata_dereference(sdata->link[0], sdata); + link = &sdata->deflink; if (WARN_ON(!link)) { err = -ENOLINK; @@ -7558,38 +7931,33 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, return err; } -static ieee80211_conn_flags_t +static void ieee80211_setup_assoc_link(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgd_assoc_data *assoc_data, struct cfg80211_assoc_request *req, - ieee80211_conn_flags_t conn_flags, + struct ieee80211_conn_settings *conn, unsigned int link_id) { struct ieee80211_local *local = sdata->local; const struct cfg80211_bss_ies *bss_ies; struct ieee80211_supported_band *sband; - const struct element *ht_elem, *vht_elem; struct ieee80211_link_data *link; struct cfg80211_bss *cbss; struct ieee80211_bss *bss; - bool is_5ghz, is_6ghz; cbss = assoc_data->link[link_id].bss; if (WARN_ON(!cbss)) - return 0; + return; bss = (void *)cbss->priv; sband = local->hw.wiphy->bands[cbss->channel->band]; if (WARN_ON(!sband)) - return 0; + return; link = sdata_dereference(sdata->link[link_id], sdata); if (WARN_ON(!link)) - return 0; - - is_5ghz = cbss->channel->band == NL80211_BAND_5GHZ; - is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; + return; /* for MLO connections assume advertising all rates is OK */ if (!req->ap_mld_addr) { @@ -7606,40 +7974,18 @@ ieee80211_setup_assoc_link(struct ieee80211_sub_if_data *sdata, assoc_data->ie_pos += req->links[link_id].elems_len; } - rcu_read_lock(); - ht_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_HT_OPERATION); - if (ht_elem && ht_elem->datalen >= sizeof(struct ieee80211_ht_operation)) - assoc_data->link[link_id].ap_ht_param = - ((struct ieee80211_ht_operation *)(ht_elem->data))->ht_param; - else if (!is_6ghz) - conn_flags |= IEEE80211_CONN_DISABLE_HT; - vht_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_VHT_CAPABILITY); - if (vht_elem && vht_elem->datalen >= sizeof(struct ieee80211_vht_cap)) { - memcpy(&assoc_data->link[link_id].ap_vht_cap, vht_elem->data, - sizeof(struct ieee80211_vht_cap)); - } else if (is_5ghz) { - link_info(link, - "VHT capa missing/short, disabling VHT/HE/EHT\n"); - conn_flags |= IEEE80211_CONN_DISABLE_VHT | - IEEE80211_CONN_DISABLE_HE | - IEEE80211_CONN_DISABLE_EHT; - } - rcu_read_unlock(); - link->u.mgd.beacon_crc_valid = false; link->u.mgd.dtim_period = 0; link->u.mgd.have_beacon = false; - /* override HT/VHT configuration only if the AP and we support it */ - if (!(conn_flags & IEEE80211_CONN_DISABLE_HT)) { + /* override HT configuration only if the AP and we support it */ + if (conn->mode >= IEEE80211_CONN_MODE_HT) { struct ieee80211_sta_ht_cap sta_ht_cap; memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap)); ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap); } - link->conf->eht_puncturing = 0; - rcu_read_lock(); bss_ies = rcu_dereference(cbss->beacon_ies); if (bss_ies) { @@ -7660,7 +8006,6 @@ ieee80211_setup_assoc_link(struct ieee80211_sub_if_data *sdata, } if (bss_ies) { - const struct ieee80211_eht_operation *eht_oper; const struct element *elem; elem = cfg80211_find_ext_elem(WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION, @@ -7677,32 +8022,6 @@ ieee80211_setup_assoc_link(struct ieee80211_sub_if_data *sdata, link->conf->ema_ap = true; else link->conf->ema_ap = false; - - elem = cfg80211_find_ext_elem(WLAN_EID_EXT_EHT_OPERATION, - bss_ies->data, bss_ies->len); - eht_oper = (const void *)(elem->data + 1); - - if (elem && - ieee80211_eht_oper_size_ok((const void *)(elem->data + 1), - elem->datalen - 1) && - (eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT) && - (eht_oper->params & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)) { - const struct ieee80211_eht_operation_info *info = - (void *)eht_oper->optional; - const u8 *disable_subchannel_bitmap = info->optional; - u16 bitmap; - - bitmap = get_unaligned_le16(disable_subchannel_bitmap); - if (cfg80211_valid_disable_subchannel_bitmap(&bitmap, - &link->conf->chandef) && - !(bitmap && ieee80211_hw_check(&local->hw, DISALLOW_PUNCTURING))) - ieee80211_handle_puncturing_bitmap(link, - eht_oper, - bitmap, - NULL); - else - conn_flags |= IEEE80211_CONN_DISABLE_EHT; - } } rcu_read_unlock(); @@ -7729,8 +8048,67 @@ ieee80211_setup_assoc_link(struct ieee80211_sub_if_data *sdata, } else { link->smps_mode = link->u.mgd.req_smps; } +} + +static int +ieee80211_mgd_get_ap_ht_vht_capa(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_assoc_data *assoc_data, + int link_id) +{ + struct cfg80211_bss *cbss = assoc_data->link[link_id].bss; + enum nl80211_band band = cbss->channel->band; + struct ieee80211_supported_band *sband; + const struct element *elem; + int err; + + /* neither HT nor VHT elements used on 6 GHz */ + if (band == NL80211_BAND_6GHZ) + return 0; + + if (assoc_data->link[link_id].conn.mode < IEEE80211_CONN_MODE_HT) + return 0; - return conn_flags; + rcu_read_lock(); + elem = ieee80211_bss_get_elem(cbss, WLAN_EID_HT_OPERATION); + if (!elem || elem->datalen < sizeof(struct ieee80211_ht_operation)) { + mlme_link_id_dbg(sdata, link_id, "no HT operation on BSS %pM\n", + cbss->bssid); + err = -EINVAL; + goto out_rcu; + } + assoc_data->link[link_id].ap_ht_param = + ((struct ieee80211_ht_operation *)(elem->data))->ht_param; + rcu_read_unlock(); + + if (assoc_data->link[link_id].conn.mode < IEEE80211_CONN_MODE_VHT) + return 0; + + /* some drivers want to support VHT on 2.4 GHz even */ + sband = sdata->local->hw.wiphy->bands[band]; + if (!sband->vht_cap.vht_supported) + return 0; + + rcu_read_lock(); + elem = ieee80211_bss_get_elem(cbss, WLAN_EID_VHT_CAPABILITY); + /* but even then accept it not being present on the AP */ + if (!elem && band == NL80211_BAND_2GHZ) { + err = 0; + goto out_rcu; + } + if (!elem || elem->datalen < sizeof(struct ieee80211_vht_cap)) { + mlme_link_id_dbg(sdata, link_id, "no VHT capa on BSS %pM\n", + cbss->bssid); + err = -EINVAL; + goto out_rcu; + } + memcpy(&assoc_data->link[link_id].ap_vht_cap, elem->data, + sizeof(struct ieee80211_vht_cap)); + rcu_read_unlock(); + + return 0; +out_rcu: + rcu_read_unlock(); + return err; } int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, @@ -7742,11 +8120,10 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgd_assoc_data *assoc_data; const struct element *ssid_elem; struct ieee80211_vif_cfg *vif_cfg = &sdata->vif.cfg; - ieee80211_conn_flags_t conn_flags = 0; struct ieee80211_link_data *link; struct cfg80211_bss *cbss; - struct ieee80211_bss *bss; - bool override; + bool override, uapsd_supported; + bool match_auth; int i, err; size_t size = sizeof(*assoc_data) + req->ie_len; @@ -7765,44 +8142,26 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (ieee80211_mgd_csa_in_process(sdata, cbss)) { sdata_info(sdata, "AP is in CSA process, reject assoc\n"); - kfree(assoc_data); - return -EINVAL; + err = -EINVAL; + goto err_free; } rcu_read_lock(); ssid_elem = ieee80211_bss_get_elem(cbss, WLAN_EID_SSID); if (!ssid_elem || ssid_elem->datalen > sizeof(assoc_data->ssid)) { rcu_read_unlock(); - kfree(assoc_data); - return -EINVAL; + err = -EINVAL; + goto err_free; } memcpy(assoc_data->ssid, ssid_elem->data, ssid_elem->datalen); assoc_data->ssid_len = ssid_elem->datalen; - memcpy(vif_cfg->ssid, assoc_data->ssid, assoc_data->ssid_len); - vif_cfg->ssid_len = assoc_data->ssid_len; rcu_read_unlock(); - if (req->ap_mld_addr) { - for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) { - if (!req->links[i].bss) - continue; - link = sdata_dereference(sdata->link[i], sdata); - if (link) - ether_addr_copy(assoc_data->link[i].addr, - link->conf->addr); - else - eth_random_addr(assoc_data->link[i].addr); - } - } else { - memcpy(assoc_data->link[0].addr, sdata->vif.addr, ETH_ALEN); - } - - assoc_data->s1g = cbss->channel->band == NL80211_BAND_S1GHZ; - - memcpy(assoc_data->ap_addr, - req->ap_mld_addr ?: req->bss->bssid, - ETH_ALEN); + if (req->ap_mld_addr) + memcpy(assoc_data->ap_addr, req->ap_mld_addr, ETH_ALEN); + else + memcpy(assoc_data->ap_addr, cbss->bssid, ETH_ALEN); if (ifmgd->associated) { u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; @@ -7820,98 +8179,146 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, false); } - if (ifmgd->auth_data && !ifmgd->auth_data->done) { - err = -EBUSY; - goto err_free; - } + memcpy(&ifmgd->ht_capa, &req->ht_capa, sizeof(ifmgd->ht_capa)); + memcpy(&ifmgd->ht_capa_mask, &req->ht_capa_mask, + sizeof(ifmgd->ht_capa_mask)); - if (ifmgd->assoc_data) { - err = -EBUSY; - goto err_free; - } + memcpy(&ifmgd->vht_capa, &req->vht_capa, sizeof(ifmgd->vht_capa)); + memcpy(&ifmgd->vht_capa_mask, &req->vht_capa_mask, + sizeof(ifmgd->vht_capa_mask)); - if (ifmgd->auth_data) { - bool match; + memcpy(&ifmgd->s1g_capa, &req->s1g_capa, sizeof(ifmgd->s1g_capa)); + memcpy(&ifmgd->s1g_capa_mask, &req->s1g_capa_mask, + sizeof(ifmgd->s1g_capa_mask)); - /* keep sta info, bssid if matching */ - match = ether_addr_equal(ifmgd->auth_data->ap_addr, - assoc_data->ap_addr) && - ifmgd->auth_data->link_id == req->link_id; + /* keep some setup (AP STA, channel, ...) if matching */ + match_auth = ifmgd->auth_data && + ether_addr_equal(ifmgd->auth_data->ap_addr, + assoc_data->ap_addr) && + ifmgd->auth_data->link_id == req->link_id; - /* Cleanup is delayed if auth_data matches */ - if (!match) - ieee80211_destroy_auth_data(sdata, false); - } + if (req->ap_mld_addr) { + uapsd_supported = true; - /* prepare assoc data */ + for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) { + struct ieee80211_supported_band *sband; + struct cfg80211_bss *link_cbss = req->links[i].bss; + struct ieee80211_bss *bss; - bss = (void *)cbss->priv; - assoc_data->wmm = bss->wmm_used && - (local->hw.queues >= IEEE80211_NUM_ACS); + if (!link_cbss) + continue; - /* - * IEEE802.11n does not allow TKIP/WEP as pairwise ciphers in HT mode. - * We still associate in non-HT mode (11a/b/g) if any one of these - * ciphers is configured as pairwise. - * We can set this to true for non-11n hardware, that'll be checked - * separately along with the peer capabilities. - */ - for (i = 0; i < req->crypto.n_ciphers_pairwise; i++) { - if (req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP40 || - req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_TKIP || - req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP104) { - conn_flags |= IEEE80211_CONN_DISABLE_HT; - conn_flags |= IEEE80211_CONN_DISABLE_VHT; - conn_flags |= IEEE80211_CONN_DISABLE_HE; - conn_flags |= IEEE80211_CONN_DISABLE_EHT; - netdev_info(sdata->dev, - "disabling HT/VHT/HE due to WEP/TKIP use\n"); + bss = (void *)link_cbss->priv; + + if (!bss->wmm_used) { + err = -EINVAL; + goto err_free; + } + + if (req->flags & (ASSOC_REQ_DISABLE_HT | + ASSOC_REQ_DISABLE_VHT | + ASSOC_REQ_DISABLE_HE | + ASSOC_REQ_DISABLE_EHT)) { + err = -EINVAL; + goto err_free; + } + + if (link_cbss->channel->band == NL80211_BAND_S1GHZ) { + err = -EINVAL; + goto err_free; + } + + link = sdata_dereference(sdata->link[i], sdata); + if (link) + ether_addr_copy(assoc_data->link[i].addr, + link->conf->addr); + else + eth_random_addr(assoc_data->link[i].addr); + sband = local->hw.wiphy->bands[link_cbss->channel->band]; + + if (match_auth && i == assoc_link_id && link) + assoc_data->link[i].conn = link->u.mgd.conn; + else + assoc_data->link[i].conn = + ieee80211_conn_settings_unlimited; + ieee80211_determine_our_sta_mode_assoc(sdata, sband, + req, true, i, + &assoc_data->link[i].conn); + assoc_data->link[i].bss = link_cbss; + assoc_data->link[i].disabled = req->links[i].disabled; + + if (!bss->uapsd_supported) + uapsd_supported = false; + + if (assoc_data->link[i].conn.mode < IEEE80211_CONN_MODE_EHT) { + err = -EINVAL; + req->links[i].error = err; + goto err_free; + } + + err = ieee80211_mgd_get_ap_ht_vht_capa(sdata, + assoc_data, i); + if (err) { + err = -EINVAL; + req->links[i].error = err; + goto err_free; + } } - } - /* also disable HT/VHT/HE/EHT if the AP doesn't use WMM */ - if (!bss->wmm_used) { - conn_flags |= IEEE80211_CONN_DISABLE_HT; - conn_flags |= IEEE80211_CONN_DISABLE_VHT; - conn_flags |= IEEE80211_CONN_DISABLE_HE; - conn_flags |= IEEE80211_CONN_DISABLE_EHT; - netdev_info(sdata->dev, - "disabling HT/VHT/HE as WMM/QoS is not supported by the AP\n"); - } + assoc_data->wmm = true; + } else { + struct ieee80211_supported_band *sband; + struct ieee80211_bss *bss = (void *)cbss->priv; - if (req->flags & ASSOC_REQ_DISABLE_HT) { - mlme_dbg(sdata, "HT disabled by flag, disabling HT/VHT/HE\n"); - conn_flags |= IEEE80211_CONN_DISABLE_HT; - conn_flags |= IEEE80211_CONN_DISABLE_VHT; - conn_flags |= IEEE80211_CONN_DISABLE_HE; - conn_flags |= IEEE80211_CONN_DISABLE_EHT; - } + memcpy(assoc_data->link[0].addr, sdata->vif.addr, ETH_ALEN); + assoc_data->s1g = cbss->channel->band == NL80211_BAND_S1GHZ; - if (req->flags & ASSOC_REQ_DISABLE_VHT) { - mlme_dbg(sdata, "VHT disabled by flag, disabling VHT\n"); - conn_flags |= IEEE80211_CONN_DISABLE_VHT; - } + assoc_data->wmm = bss->wmm_used && + (local->hw.queues >= IEEE80211_NUM_ACS); - if (req->flags & ASSOC_REQ_DISABLE_HE) { - mlme_dbg(sdata, "HE disabled by flag, disabling HE/EHT\n"); - conn_flags |= IEEE80211_CONN_DISABLE_HE; - conn_flags |= IEEE80211_CONN_DISABLE_EHT; + if (cbss->channel->band == NL80211_BAND_6GHZ && + req->flags & (ASSOC_REQ_DISABLE_HT | + ASSOC_REQ_DISABLE_VHT | + ASSOC_REQ_DISABLE_HE)) { + err = -EINVAL; + goto err_free; + } + + sband = local->hw.wiphy->bands[cbss->channel->band]; + + assoc_data->link[0].bss = cbss; + + if (match_auth) + assoc_data->link[0].conn = sdata->deflink.u.mgd.conn; + else + assoc_data->link[0].conn = + ieee80211_conn_settings_unlimited; + ieee80211_determine_our_sta_mode_assoc(sdata, sband, req, + assoc_data->wmm, 0, + &assoc_data->link[0].conn); + + uapsd_supported = bss->uapsd_supported; + + err = ieee80211_mgd_get_ap_ht_vht_capa(sdata, assoc_data, 0); + if (err) + goto err_free; } - if (req->flags & ASSOC_REQ_DISABLE_EHT) - conn_flags |= IEEE80211_CONN_DISABLE_EHT; + assoc_data->spp_amsdu = req->flags & ASSOC_REQ_SPP_AMSDU; - memcpy(&ifmgd->ht_capa, &req->ht_capa, sizeof(ifmgd->ht_capa)); - memcpy(&ifmgd->ht_capa_mask, &req->ht_capa_mask, - sizeof(ifmgd->ht_capa_mask)); + if (ifmgd->auth_data && !ifmgd->auth_data->done) { + err = -EBUSY; + goto err_free; + } - memcpy(&ifmgd->vht_capa, &req->vht_capa, sizeof(ifmgd->vht_capa)); - memcpy(&ifmgd->vht_capa_mask, &req->vht_capa_mask, - sizeof(ifmgd->vht_capa_mask)); + if (ifmgd->assoc_data) { + err = -EBUSY; + goto err_free; + } - memcpy(&ifmgd->s1g_capa, &req->s1g_capa, sizeof(ifmgd->s1g_capa)); - memcpy(&ifmgd->s1g_capa_mask, &req->s1g_capa_mask, - sizeof(ifmgd->s1g_capa_mask)); + /* Cleanup is delayed if auth_data matches */ + if (ifmgd->auth_data && !match_auth) + ieee80211_destroy_auth_data(sdata, false); if (req->ie && req->ie_len) { memcpy(assoc_data->ie, req->ie, req->ie_len); @@ -7943,19 +8350,10 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, assoc_data->assoc_link_id = assoc_link_id; if (req->ap_mld_addr) { - for (i = 0; i < ARRAY_SIZE(assoc_data->link); i++) { - assoc_data->link[i].conn_flags = conn_flags; - assoc_data->link[i].bss = req->links[i].bss; - assoc_data->link[i].disabled = req->links[i].disabled; - } - /* if there was no authentication, set up the link */ err = ieee80211_vif_set_links(sdata, BIT(assoc_link_id), 0); if (err) goto err_clear; - } else { - assoc_data->link[0].conn_flags = conn_flags; - assoc_data->link[0].bss = cbss; } link = sdata_dereference(sdata->link[assoc_link_id], sdata); @@ -7964,19 +8362,21 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, goto err_clear; } - /* keep old conn_flags from ieee80211_prep_channel() from auth */ - conn_flags |= link->u.mgd.conn_flags; - conn_flags |= ieee80211_setup_assoc_link(sdata, assoc_data, req, - conn_flags, assoc_link_id); - override = link->u.mgd.conn_flags != conn_flags; - link->u.mgd.conn_flags |= conn_flags; + override = link->u.mgd.conn.mode != + assoc_data->link[assoc_link_id].conn.mode || + link->u.mgd.conn.bw_limit != + assoc_data->link[assoc_link_id].conn.bw_limit; + link->u.mgd.conn = assoc_data->link[assoc_link_id].conn; + + ieee80211_setup_assoc_link(sdata, assoc_data, req, &link->u.mgd.conn, + assoc_link_id); if (WARN((sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_UAPSD) && ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK), "U-APSD not supported with HW_PS_NULLFUNC_STACK\n")) sdata->vif.driver_flags &= ~IEEE80211_VIF_SUPPORTS_UAPSD; - if (bss->wmm_used && bss->uapsd_supported && + if (assoc_data->wmm && uapsd_supported && (sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_UAPSD)) { assoc_data->uapsd = true; ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED; @@ -8020,27 +8420,29 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, continue; if (i == assoc_data->assoc_link_id) continue; - /* only calculate the flags, hence link == NULL */ - err = ieee80211_prep_channel(sdata, NULL, + /* only calculate the mode, hence link == NULL */ + err = ieee80211_prep_channel(sdata, NULL, i, assoc_data->link[i].bss, true, - &assoc_data->link[i].conn_flags); + &assoc_data->link[i].conn); if (err) { req->links[i].error = err; goto err_clear; } } + memcpy(vif_cfg->ssid, assoc_data->ssid, assoc_data->ssid_len); + vif_cfg->ssid_len = assoc_data->ssid_len; + /* needed for transmitting the assoc frames properly */ memcpy(sdata->vif.cfg.ap_addr, assoc_data->ap_addr, ETH_ALEN); err = ieee80211_prep_connection(sdata, cbss, req->link_id, - req->ap_mld_addr, true, override); + req->ap_mld_addr, true, + &assoc_data->link[assoc_link_id].conn, + override); if (err) goto err_clear; - assoc_data->link[assoc_data->assoc_link_id].conn_flags = - link->u.mgd.conn_flags; - if (ieee80211_hw_check(&sdata->local->hw, NEED_DTIM_BEFORE_ASSOC)) { const struct cfg80211_bss_ies *beacon_ies; @@ -8204,6 +8606,8 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata) wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ml_reconf_work); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &ifmgd->neg_ttlm_timeout_work); if (ifmgd->assoc_data) ieee80211_destroy_assoc_data(sdata, ASSOC_TIMEOUT); diff --git a/net/mac80211/ocb.c b/net/mac80211/ocb.c index 449af4e1cca4..9ef14e475c90 100644 --- a/net/mac80211/ocb.c +++ b/net/mac80211/ocb.c @@ -168,6 +168,7 @@ void ieee80211_ocb_setup_sdata(struct ieee80211_sub_if_data *sdata) int ieee80211_ocb_join(struct ieee80211_sub_if_data *sdata, struct ocb_setup *setup) { + struct ieee80211_chan_req chanreq = { .oper = setup->chandef }; struct ieee80211_local *local = sdata->local; struct ieee80211_if_ocb *ifocb = &sdata->u.ocb; u64 changed = BSS_CHANGED_OCB | BSS_CHANGED_BSSID; @@ -182,7 +183,7 @@ int ieee80211_ocb_join(struct ieee80211_sub_if_data *sdata, sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; sdata->deflink.needed_rx_chains = sdata->local->rx_chains; - err = ieee80211_link_use_channel(&sdata->deflink, &setup->chandef, + err = ieee80211_link_use_channel(&sdata->deflink, &chanreq, IEEE80211_CHANCTX_SHARED); if (err) return err; @@ -207,7 +208,7 @@ int ieee80211_ocb_leave(struct ieee80211_sub_if_data *sdata) lockdep_assert_wiphy(sdata->local->hw.wiphy); ifocb->joined = false; - sta_info_flush(sdata); + sta_info_flush(sdata, -1); spin_lock_bh(&ifocb->incomplete_lock); while (!list_empty(&ifocb->incomplete_stations)) { diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 6c4080202573..221695d841fd 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -86,7 +86,7 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local) lockdep_assert_wiphy(local->hw.wiphy); - if (WARN_ON(local->use_chanctx)) + if (WARN_ON(!local->emulate_chanctx)) return; /* @@ -136,7 +136,7 @@ void ieee80211_offchannel_return(struct ieee80211_local *local) lockdep_assert_wiphy(local->hw.wiphy); - if (WARN_ON(local->use_chanctx)) + if (WARN_ON(!local->emulate_chanctx)) return; list_for_each_entry(sdata, &local->interfaces, list) { @@ -351,10 +351,13 @@ static void _ieee80211_start_next_roc(struct ieee80211_local *local) * 20 MHz channel width) don't stop all the operations but still * treat it as though the ROC operation started properly, so * other ROC operations won't interfere with this one. + * + * Note: scan can't run, tmp_channel is what we use, so this + * must be the currently active channel. */ - roc->on_channel = roc->chan == local->_oper_chandef.chan && - local->_oper_chandef.width != NL80211_CHAN_WIDTH_5 && - local->_oper_chandef.width != NL80211_CHAN_WIDTH_10; + roc->on_channel = roc->chan == local->hw.conf.chandef.chan && + local->hw.conf.chandef.width != NL80211_CHAN_WIDTH_5 && + local->hw.conf.chandef.width != NL80211_CHAN_WIDTH_10; /* start this ROC */ ieee80211_recalc_idle(local); @@ -363,7 +366,7 @@ static void _ieee80211_start_next_roc(struct ieee80211_local *local) ieee80211_offchannel_stop_vifs(local); local->tmp_channel = roc->chan; - ieee80211_hw_config(local, 0); + ieee80211_hw_conf_chan(local); } wiphy_delayed_work_queue(local->hw.wiphy, &local->roc_work, @@ -426,7 +429,7 @@ static void __ieee80211_roc_work(struct ieee80211_local *local) return; if (!roc->started) { - WARN_ON(local->use_chanctx); + WARN_ON(!local->emulate_chanctx); _ieee80211_start_next_roc(local); } else { on_channel = roc->on_channel; @@ -439,7 +442,7 @@ static void __ieee80211_roc_work(struct ieee80211_local *local) ieee80211_flush_queues(local, NULL, false); local->tmp_channel = NULL; - ieee80211_hw_config(local, 0); + ieee80211_hw_conf_chan(local); ieee80211_offchannel_return(local); } @@ -539,7 +542,7 @@ static int ieee80211_start_roc_work(struct ieee80211_local *local, /* this may work, but is untested */ return -EOPNOTSUPP; - if (local->use_chanctx && !local->ops->remain_on_channel) + if (!local->emulate_chanctx && !local->ops->remain_on_channel) return -EOPNOTSUPP; roc = kzalloc(sizeof(*roc), GFP_KERNEL); diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c new file mode 100644 index 000000000000..55e5497f8978 --- /dev/null +++ b/net/mac80211/parse.c @@ -0,0 +1,971 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2002-2005, Instant802 Networks, Inc. + * Copyright 2005-2006, Devicescape Software, Inc. + * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> + * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> + * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright (C) 2015-2017 Intel Deutschland GmbH + * Copyright (C) 2018-2024 Intel Corporation + * + * element parsing for mac80211 + */ + +#include <net/mac80211.h> +#include <linux/netdevice.h> +#include <linux/export.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/skbuff.h> +#include <linux/etherdevice.h> +#include <linux/if_arp.h> +#include <linux/bitmap.h> +#include <linux/crc32.h> +#include <net/net_namespace.h> +#include <net/cfg80211.h> +#include <net/rtnetlink.h> +#include <kunit/visibility.h> + +#include "ieee80211_i.h" +#include "driver-ops.h" +#include "rate.h" +#include "mesh.h" +#include "wme.h" +#include "led.h" +#include "wep.h" + +struct ieee80211_elems_parse { + /* must be first for kfree to work */ + struct ieee802_11_elems elems; + + /* The basic Multi-Link element in the original elements */ + const struct element *ml_basic_elem; + + /* The reconfiguration Multi-Link element in the original elements */ + const struct element *ml_reconf_elem; + + /* + * scratch buffer that can be used for various element parsing related + * tasks, e.g., element de-fragmentation etc. + */ + size_t scratch_len; + u8 *scratch_pos; + u8 scratch[] __counted_by(scratch_len); +}; + +static void +ieee80211_parse_extension_element(u32 *crc, + const struct element *elem, + struct ieee80211_elems_parse *elems_parse, + struct ieee80211_elems_parse_params *params) +{ + struct ieee802_11_elems *elems = &elems_parse->elems; + const void *data = elem->data + 1; + bool calc_crc = false; + u8 len; + + if (!elem->datalen) + return; + + len = elem->datalen - 1; + + switch (elem->data[0]) { + case WLAN_EID_EXT_HE_MU_EDCA: + if (params->mode < IEEE80211_CONN_MODE_HE) + break; + calc_crc = true; + if (len >= sizeof(*elems->mu_edca_param_set)) + elems->mu_edca_param_set = data; + break; + case WLAN_EID_EXT_HE_CAPABILITY: + if (params->mode < IEEE80211_CONN_MODE_HE) + break; + if (ieee80211_he_capa_size_ok(data, len)) { + elems->he_cap = data; + elems->he_cap_len = len; + } + break; + case WLAN_EID_EXT_HE_OPERATION: + if (params->mode < IEEE80211_CONN_MODE_HE) + break; + calc_crc = true; + if (len >= sizeof(*elems->he_operation) && + len >= ieee80211_he_oper_size(data) - 1) + elems->he_operation = data; + break; + case WLAN_EID_EXT_UORA: + if (params->mode < IEEE80211_CONN_MODE_HE) + break; + if (len >= 1) + elems->uora_element = data; + break; + case WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME: + if (len == 3) + elems->max_channel_switch_time = data; + break; + case WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION: + if (len >= sizeof(*elems->mbssid_config_ie)) + elems->mbssid_config_ie = data; + break; + case WLAN_EID_EXT_HE_SPR: + if (params->mode < IEEE80211_CONN_MODE_HE) + break; + if (len >= sizeof(*elems->he_spr) && + len >= ieee80211_he_spr_size(data)) + elems->he_spr = data; + break; + case WLAN_EID_EXT_HE_6GHZ_CAPA: + if (params->mode < IEEE80211_CONN_MODE_HE) + break; + if (len >= sizeof(*elems->he_6ghz_capa)) + elems->he_6ghz_capa = data; + break; + case WLAN_EID_EXT_EHT_CAPABILITY: + if (params->mode < IEEE80211_CONN_MODE_EHT) + break; + if (ieee80211_eht_capa_size_ok(elems->he_cap, + data, len, + params->from_ap)) { + elems->eht_cap = data; + elems->eht_cap_len = len; + } + break; + case WLAN_EID_EXT_EHT_OPERATION: + if (params->mode < IEEE80211_CONN_MODE_EHT) + break; + if (ieee80211_eht_oper_size_ok(data, len)) + elems->eht_operation = data; + calc_crc = true; + break; + case WLAN_EID_EXT_EHT_MULTI_LINK: + if (params->mode < IEEE80211_CONN_MODE_EHT) + break; + calc_crc = true; + + if (ieee80211_mle_size_ok(data, len)) { + const struct ieee80211_multi_link_elem *mle = + (void *)data; + + switch (le16_get_bits(mle->control, + IEEE80211_ML_CONTROL_TYPE)) { + case IEEE80211_ML_CONTROL_TYPE_BASIC: + if (elems_parse->ml_basic_elem) { + elems->parse_error |= + IEEE80211_PARSE_ERR_DUP_NEST_ML_BASIC; + break; + } + elems_parse->ml_basic_elem = elem; + break; + case IEEE80211_ML_CONTROL_TYPE_RECONF: + elems_parse->ml_reconf_elem = elem; + break; + default: + break; + } + } + break; + case WLAN_EID_EXT_BANDWIDTH_INDICATION: + if (params->mode < IEEE80211_CONN_MODE_EHT) + break; + if (ieee80211_bandwidth_indication_size_ok(data, len)) + elems->bandwidth_indication = data; + calc_crc = true; + break; + case WLAN_EID_EXT_TID_TO_LINK_MAPPING: + if (params->mode < IEEE80211_CONN_MODE_EHT) + break; + calc_crc = true; + if (ieee80211_tid_to_link_map_size_ok(data, len) && + elems->ttlm_num < ARRAY_SIZE(elems->ttlm)) { + elems->ttlm[elems->ttlm_num] = (void *)data; + elems->ttlm_num++; + } + break; + } + + if (crc && calc_crc) + *crc = crc32_be(*crc, (void *)elem, elem->datalen + 2); +} + +static u32 +_ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, + struct ieee80211_elems_parse *elems_parse, + const struct element *check_inherit) +{ + struct ieee802_11_elems *elems = &elems_parse->elems; + const struct element *elem; + bool calc_crc = params->filter != 0; + DECLARE_BITMAP(seen_elems, 256); + u32 crc = params->crc; + + bitmap_zero(seen_elems, 256); + + for_each_element(elem, params->start, params->len) { + const struct element *subelem; + u8 elem_parse_failed; + u8 id = elem->id; + u8 elen = elem->datalen; + const u8 *pos = elem->data; + + if (check_inherit && + !cfg80211_is_element_inherited(elem, + check_inherit)) + continue; + + switch (id) { + case WLAN_EID_SSID: + case WLAN_EID_SUPP_RATES: + case WLAN_EID_FH_PARAMS: + case WLAN_EID_DS_PARAMS: + case WLAN_EID_CF_PARAMS: + case WLAN_EID_TIM: + case WLAN_EID_IBSS_PARAMS: + case WLAN_EID_CHALLENGE: + case WLAN_EID_RSN: + case WLAN_EID_ERP_INFO: + case WLAN_EID_EXT_SUPP_RATES: + case WLAN_EID_HT_CAPABILITY: + case WLAN_EID_HT_OPERATION: + case WLAN_EID_VHT_CAPABILITY: + case WLAN_EID_VHT_OPERATION: + case WLAN_EID_MESH_ID: + case WLAN_EID_MESH_CONFIG: + case WLAN_EID_PEER_MGMT: + case WLAN_EID_PREQ: + case WLAN_EID_PREP: + case WLAN_EID_PERR: + case WLAN_EID_RANN: + case WLAN_EID_CHANNEL_SWITCH: + case WLAN_EID_EXT_CHANSWITCH_ANN: + case WLAN_EID_COUNTRY: + case WLAN_EID_PWR_CONSTRAINT: + case WLAN_EID_TIMEOUT_INTERVAL: + case WLAN_EID_SECONDARY_CHANNEL_OFFSET: + case WLAN_EID_WIDE_BW_CHANNEL_SWITCH: + case WLAN_EID_CHAN_SWITCH_PARAM: + case WLAN_EID_EXT_CAPABILITY: + case WLAN_EID_CHAN_SWITCH_TIMING: + case WLAN_EID_LINK_ID: + case WLAN_EID_BSS_MAX_IDLE_PERIOD: + case WLAN_EID_RSNX: + case WLAN_EID_S1G_BCN_COMPAT: + case WLAN_EID_S1G_CAPABILITIES: + case WLAN_EID_S1G_OPERATION: + case WLAN_EID_AID_RESPONSE: + case WLAN_EID_S1G_SHORT_BCN_INTERVAL: + /* + * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible + * that if the content gets bigger it might be needed more than once + */ + if (test_bit(id, seen_elems)) { + elems->parse_error |= + IEEE80211_PARSE_ERR_DUP_ELEM; + continue; + } + break; + } + + if (calc_crc && id < 64 && (params->filter & (1ULL << id))) + crc = crc32_be(crc, pos - 2, elen + 2); + + elem_parse_failed = 0; + + switch (id) { + case WLAN_EID_LINK_ID: + if (elen + 2 < sizeof(struct ieee80211_tdls_lnkie)) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + elems->lnk_id = (void *)(pos - 2); + break; + case WLAN_EID_CHAN_SWITCH_TIMING: + if (elen < sizeof(struct ieee80211_ch_switch_timing)) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + elems->ch_sw_timing = (void *)pos; + break; + case WLAN_EID_EXT_CAPABILITY: + elems->ext_capab = pos; + elems->ext_capab_len = elen; + break; + case WLAN_EID_SSID: + elems->ssid = pos; + elems->ssid_len = elen; + break; + case WLAN_EID_SUPP_RATES: + elems->supp_rates = pos; + elems->supp_rates_len = elen; + break; + case WLAN_EID_DS_PARAMS: + if (elen >= 1) + elems->ds_params = pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_TIM: + if (elen >= sizeof(struct ieee80211_tim_ie)) { + elems->tim = (void *)pos; + elems->tim_len = elen; + } else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_VENDOR_SPECIFIC: + if (elen >= 4 && pos[0] == 0x00 && pos[1] == 0x50 && + pos[2] == 0xf2) { + /* Microsoft OUI (00:50:F2) */ + + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + + if (elen >= 5 && pos[3] == 2) { + /* OUI Type 2 - WMM IE */ + if (pos[4] == 0) { + elems->wmm_info = pos; + elems->wmm_info_len = elen; + } else if (pos[4] == 1) { + elems->wmm_param = pos; + elems->wmm_param_len = elen; + } + } + } + break; + case WLAN_EID_RSN: + elems->rsn = pos; + elems->rsn_len = elen; + break; + case WLAN_EID_ERP_INFO: + if (elen >= 1) + elems->erp_info = pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_EXT_SUPP_RATES: + elems->ext_supp_rates = pos; + elems->ext_supp_rates_len = elen; + break; + case WLAN_EID_HT_CAPABILITY: + if (params->mode < IEEE80211_CONN_MODE_HT) + break; + if (elen >= sizeof(struct ieee80211_ht_cap)) + elems->ht_cap_elem = (void *)pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_HT_OPERATION: + if (params->mode < IEEE80211_CONN_MODE_HT) + break; + if (elen >= sizeof(struct ieee80211_ht_operation)) + elems->ht_operation = (void *)pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_VHT_CAPABILITY: + if (params->mode < IEEE80211_CONN_MODE_VHT) + break; + if (elen >= sizeof(struct ieee80211_vht_cap)) + elems->vht_cap_elem = (void *)pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_VHT_OPERATION: + if (params->mode < IEEE80211_CONN_MODE_VHT) + break; + if (elen >= sizeof(struct ieee80211_vht_operation)) { + elems->vht_operation = (void *)pos; + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + break; + } + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_OPMODE_NOTIF: + if (params->mode < IEEE80211_CONN_MODE_VHT) + break; + if (elen > 0) { + elems->opmode_notif = pos; + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + break; + } + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_MESH_ID: + elems->mesh_id = pos; + elems->mesh_id_len = elen; + break; + case WLAN_EID_MESH_CONFIG: + if (elen >= sizeof(struct ieee80211_meshconf_ie)) + elems->mesh_config = (void *)pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_PEER_MGMT: + elems->peering = pos; + elems->peering_len = elen; + break; + case WLAN_EID_MESH_AWAKE_WINDOW: + if (elen >= 2) + elems->awake_window = (void *)pos; + break; + case WLAN_EID_PREQ: + elems->preq = pos; + elems->preq_len = elen; + break; + case WLAN_EID_PREP: + elems->prep = pos; + elems->prep_len = elen; + break; + case WLAN_EID_PERR: + elems->perr = pos; + elems->perr_len = elen; + break; + case WLAN_EID_RANN: + if (elen >= sizeof(struct ieee80211_rann_ie)) + elems->rann = (void *)pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_CHANNEL_SWITCH: + if (elen != sizeof(struct ieee80211_channel_sw_ie)) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + elems->ch_switch_ie = (void *)pos; + break; + case WLAN_EID_EXT_CHANSWITCH_ANN: + if (elen != sizeof(struct ieee80211_ext_chansw_ie)) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + elems->ext_chansw_ie = (void *)pos; + break; + case WLAN_EID_SECONDARY_CHANNEL_OFFSET: + if (params->mode < IEEE80211_CONN_MODE_HT) + break; + if (elen != sizeof(struct ieee80211_sec_chan_offs_ie)) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + elems->sec_chan_offs = (void *)pos; + break; + case WLAN_EID_CHAN_SWITCH_PARAM: + if (elen < + sizeof(*elems->mesh_chansw_params_ie)) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + elems->mesh_chansw_params_ie = (void *)pos; + break; + case WLAN_EID_WIDE_BW_CHANNEL_SWITCH: + if (params->mode < IEEE80211_CONN_MODE_VHT) + break; + + if (!params->action) { + elem_parse_failed = + IEEE80211_PARSE_ERR_UNEXPECTED_ELEM; + break; + } + + if (elen < sizeof(*elems->wide_bw_chansw_ie)) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + elems->wide_bw_chansw_ie = (void *)pos; + break; + case WLAN_EID_CHANNEL_SWITCH_WRAPPER: + if (params->mode < IEEE80211_CONN_MODE_VHT) + break; + if (params->action) { + elem_parse_failed = + IEEE80211_PARSE_ERR_UNEXPECTED_ELEM; + break; + } + /* + * This is a bit tricky, but as we only care about + * a few elements, parse them out manually. + */ + subelem = cfg80211_find_elem(WLAN_EID_WIDE_BW_CHANNEL_SWITCH, + pos, elen); + if (subelem) { + if (subelem->datalen >= sizeof(*elems->wide_bw_chansw_ie)) + elems->wide_bw_chansw_ie = + (void *)subelem->data; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + } + + if (params->mode < IEEE80211_CONN_MODE_EHT) + break; + + subelem = cfg80211_find_ext_elem(WLAN_EID_EXT_BANDWIDTH_INDICATION, + pos, elen); + if (subelem) { + const void *edata = subelem->data + 1; + u8 edatalen = subelem->datalen - 1; + + if (ieee80211_bandwidth_indication_size_ok(edata, + edatalen)) + elems->bandwidth_indication = edata; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + } + break; + case WLAN_EID_COUNTRY: + elems->country_elem = pos; + elems->country_elem_len = elen; + break; + case WLAN_EID_PWR_CONSTRAINT: + if (elen != 1) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + elems->pwr_constr_elem = pos; + break; + case WLAN_EID_CISCO_VENDOR_SPECIFIC: + /* Lots of different options exist, but we only care + * about the Dynamic Transmit Power Control element. + * First check for the Cisco OUI, then for the DTPC + * tag (0x00). + */ + if (elen < 4) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + + if (pos[0] != 0x00 || pos[1] != 0x40 || + pos[2] != 0x96 || pos[3] != 0x00) + break; + + if (elen != 6) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + + elems->cisco_dtpc_elem = pos; + break; + case WLAN_EID_ADDBA_EXT: + if (elen < sizeof(struct ieee80211_addba_ext_ie)) { + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + } + elems->addba_ext_ie = (void *)pos; + break; + case WLAN_EID_TIMEOUT_INTERVAL: + if (elen >= sizeof(struct ieee80211_timeout_interval_ie)) + elems->timeout_int = (void *)pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_BSS_MAX_IDLE_PERIOD: + if (elen >= sizeof(*elems->max_idle_period_ie)) + elems->max_idle_period_ie = (void *)pos; + break; + case WLAN_EID_RSNX: + elems->rsnx = pos; + elems->rsnx_len = elen; + break; + case WLAN_EID_TX_POWER_ENVELOPE: + if (elen < 1 || + elen > sizeof(struct ieee80211_tx_pwr_env)) + break; + + if (elems->tx_pwr_env_num >= ARRAY_SIZE(elems->tx_pwr_env)) + break; + + elems->tx_pwr_env[elems->tx_pwr_env_num] = (void *)pos; + elems->tx_pwr_env_len[elems->tx_pwr_env_num] = elen; + elems->tx_pwr_env_num++; + break; + case WLAN_EID_EXTENSION: + ieee80211_parse_extension_element(calc_crc ? + &crc : NULL, + elem, elems_parse, + params); + break; + case WLAN_EID_S1G_CAPABILITIES: + if (params->mode != IEEE80211_CONN_MODE_S1G) + break; + if (elen >= sizeof(*elems->s1g_capab)) + elems->s1g_capab = (void *)pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_S1G_OPERATION: + if (params->mode != IEEE80211_CONN_MODE_S1G) + break; + if (elen == sizeof(*elems->s1g_oper)) + elems->s1g_oper = (void *)pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_S1G_BCN_COMPAT: + if (params->mode != IEEE80211_CONN_MODE_S1G) + break; + if (elen == sizeof(*elems->s1g_bcn_compat)) + elems->s1g_bcn_compat = (void *)pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + case WLAN_EID_AID_RESPONSE: + if (params->mode != IEEE80211_CONN_MODE_S1G) + break; + if (elen == sizeof(struct ieee80211_aid_response_ie)) + elems->aid_resp = (void *)pos; + else + elem_parse_failed = + IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; + break; + default: + break; + } + + if (elem_parse_failed) + elems->parse_error |= elem_parse_failed; + else + __set_bit(id, seen_elems); + } + + if (!for_each_element_completed(elem, params->start, params->len)) + elems->parse_error |= IEEE80211_PARSE_ERR_INVALID_END; + + return crc; +} + +static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len, + struct ieee802_11_elems *elems, + struct cfg80211_bss *bss, + u8 *nontransmitted_profile) +{ + const struct element *elem, *sub; + size_t profile_len = 0; + bool found = false; + + if (!bss || !bss->transmitted_bss) + return profile_len; + + for_each_element_id(elem, WLAN_EID_MULTIPLE_BSSID, start, len) { + if (elem->datalen < 2) + continue; + if (elem->data[0] < 1 || elem->data[0] > 8) + continue; + + for_each_element(sub, elem->data + 1, elem->datalen - 1) { + u8 new_bssid[ETH_ALEN]; + const u8 *index; + + if (sub->id != 0 || sub->datalen < 4) { + /* not a valid BSS profile */ + continue; + } + + if (sub->data[0] != WLAN_EID_NON_TX_BSSID_CAP || + sub->data[1] != 2) { + /* The first element of the + * Nontransmitted BSSID Profile is not + * the Nontransmitted BSSID Capability + * element. + */ + continue; + } + + memset(nontransmitted_profile, 0, len); + profile_len = cfg80211_merge_profile(start, len, + elem, + sub, + nontransmitted_profile, + len); + + /* found a Nontransmitted BSSID Profile */ + index = cfg80211_find_ie(WLAN_EID_MULTI_BSSID_IDX, + nontransmitted_profile, + profile_len); + if (!index || index[1] < 1 || index[2] == 0) { + /* Invalid MBSSID Index element */ + continue; + } + + cfg80211_gen_new_bssid(bss->transmitted_bss->bssid, + elem->data[0], + index[2], + new_bssid); + if (ether_addr_equal(new_bssid, bss->bssid)) { + found = true; + elems->bssid_index_len = index[1]; + elems->bssid_index = (void *)&index[2]; + break; + } + } + } + + return found ? profile_len : 0; +} + +static void +ieee80211_mle_get_sta_prof(struct ieee80211_elems_parse *elems_parse, + u8 link_id) +{ + struct ieee802_11_elems *elems = &elems_parse->elems; + const struct ieee80211_multi_link_elem *ml = elems->ml_basic; + ssize_t ml_len = elems->ml_basic_len; + const struct element *sub; + + for_each_mle_subelement(sub, (u8 *)ml, ml_len) { + struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data; + ssize_t sta_prof_len; + u16 control; + + if (sub->id != IEEE80211_MLE_SUBELEM_PER_STA_PROFILE) + continue; + + if (!ieee80211_mle_basic_sta_prof_size_ok(sub->data, + sub->datalen)) + return; + + control = le16_to_cpu(prof->control); + + if (link_id != u16_get_bits(control, + IEEE80211_MLE_STA_CONTROL_LINK_ID)) + continue; + + if (!(control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE)) + return; + + /* the sub element can be fragmented */ + sta_prof_len = + cfg80211_defragment_element(sub, + (u8 *)ml, ml_len, + elems_parse->scratch_pos, + elems_parse->scratch + + elems_parse->scratch_len - + elems_parse->scratch_pos, + IEEE80211_MLE_SUBELEM_FRAGMENT); + + if (sta_prof_len < 0) + return; + + elems->prof = (void *)elems_parse->scratch_pos; + elems->sta_prof_len = sta_prof_len; + elems_parse->scratch_pos += sta_prof_len; + + return; + } +} + +static void ieee80211_mle_parse_link(struct ieee80211_elems_parse *elems_parse, + struct ieee80211_elems_parse_params *params) +{ + struct ieee802_11_elems *elems = &elems_parse->elems; + struct ieee80211_mle_per_sta_profile *prof; + struct ieee80211_elems_parse_params sub = { + .mode = params->mode, + .action = params->action, + .from_ap = params->from_ap, + .link_id = -1, + }; + ssize_t ml_len = elems->ml_basic_len; + const struct element *non_inherit = NULL; + const u8 *end; + + ml_len = cfg80211_defragment_element(elems_parse->ml_basic_elem, + elems->ie_start, + elems->total_len, + elems_parse->scratch_pos, + elems_parse->scratch + + elems_parse->scratch_len - + elems_parse->scratch_pos, + WLAN_EID_FRAGMENT); + + if (ml_len < 0) + return; + + elems->ml_basic = (const void *)elems_parse->scratch_pos; + elems->ml_basic_len = ml_len; + elems_parse->scratch_pos += ml_len; + + if (params->link_id == -1) + return; + + ieee80211_mle_get_sta_prof(elems_parse, params->link_id); + prof = elems->prof; + + if (!prof) + return; + + /* check if we have the 4 bytes for the fixed part in assoc response */ + if (elems->sta_prof_len < sizeof(*prof) + prof->sta_info_len - 1 + 4) { + elems->prof = NULL; + elems->sta_prof_len = 0; + return; + } + + /* + * Skip the capability information and the status code that are expected + * as part of the station profile in association response frames. Note + * the -1 is because the 'sta_info_len' is accounted to as part of the + * per-STA profile, but not part of the 'u8 variable[]' portion. + */ + sub.start = prof->variable + prof->sta_info_len - 1 + 4; + end = (const u8 *)prof + elems->sta_prof_len; + sub.len = end - sub.start; + + non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, + sub.start, sub.len); + _ieee802_11_parse_elems_full(&sub, elems_parse, non_inherit); +} + +static void +ieee80211_mle_defrag_reconf(struct ieee80211_elems_parse *elems_parse) +{ + struct ieee802_11_elems *elems = &elems_parse->elems; + ssize_t ml_len; + + ml_len = cfg80211_defragment_element(elems_parse->ml_reconf_elem, + elems->ie_start, + elems->total_len, + elems_parse->scratch_pos, + elems_parse->scratch + + elems_parse->scratch_len - + elems_parse->scratch_pos, + WLAN_EID_FRAGMENT); + if (ml_len < 0) + return; + elems->ml_reconf = (void *)elems_parse->scratch_pos; + elems->ml_reconf_len = ml_len; + elems_parse->scratch_pos += ml_len; +} + +struct ieee802_11_elems * +ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) +{ + struct ieee80211_elems_parse *elems_parse; + struct ieee802_11_elems *elems; + const struct element *non_inherit = NULL; + u8 *nontransmitted_profile; + int nontransmitted_profile_len = 0; + size_t scratch_len = 3 * params->len; + + BUILD_BUG_ON(offsetof(typeof(*elems_parse), elems) != 0); + + elems_parse = kzalloc(struct_size(elems_parse, scratch, scratch_len), + GFP_ATOMIC); + if (!elems_parse) + return NULL; + + elems_parse->scratch_len = scratch_len; + elems_parse->scratch_pos = elems_parse->scratch; + + elems = &elems_parse->elems; + elems->ie_start = params->start; + elems->total_len = params->len; + + nontransmitted_profile = elems_parse->scratch_pos; + nontransmitted_profile_len = + ieee802_11_find_bssid_profile(params->start, params->len, + elems, params->bss, + nontransmitted_profile); + elems_parse->scratch_pos += nontransmitted_profile_len; + non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, + nontransmitted_profile, + nontransmitted_profile_len); + + elems->crc = _ieee802_11_parse_elems_full(params, elems_parse, + non_inherit); + + /* Override with nontransmitted profile, if found */ + if (nontransmitted_profile_len) { + struct ieee80211_elems_parse_params sub = { + .mode = params->mode, + .start = nontransmitted_profile, + .len = nontransmitted_profile_len, + .action = params->action, + .link_id = params->link_id, + }; + + _ieee802_11_parse_elems_full(&sub, elems_parse, NULL); + } + + ieee80211_mle_parse_link(elems_parse, params); + + ieee80211_mle_defrag_reconf(elems_parse); + + if (elems->tim && !elems->parse_error) { + const struct ieee80211_tim_ie *tim_ie = elems->tim; + + elems->dtim_period = tim_ie->dtim_period; + elems->dtim_count = tim_ie->dtim_count; + } + + /* Override DTIM period and count if needed */ + if (elems->bssid_index && + elems->bssid_index_len >= + offsetofend(struct ieee80211_bssid_index, dtim_period)) + elems->dtim_period = elems->bssid_index->dtim_period; + + if (elems->bssid_index && + elems->bssid_index_len >= + offsetofend(struct ieee80211_bssid_index, dtim_count)) + elems->dtim_count = elems->bssid_index->dtim_count; + + return elems; +} +EXPORT_SYMBOL_IF_KUNIT(ieee802_11_parse_elems_full); + +int ieee80211_parse_bitrates(enum nl80211_chan_width width, + const struct ieee80211_supported_band *sband, + const u8 *srates, int srates_len, u32 *rates) +{ + u32 rate_flags = ieee80211_chanwidth_rate_flags(width); + struct ieee80211_rate *br; + int brate, rate, i, j, count = 0; + + *rates = 0; + + for (i = 0; i < srates_len; i++) { + rate = srates[i] & 0x7f; + + for (j = 0; j < sband->n_bitrates; j++) { + br = &sband->bitrates[j]; + if ((rate_flags & br->flags) != rate_flags) + continue; + + brate = DIV_ROUND_UP(br->bitrate, 5); + if (brate == rate) { + *rates |= BIT(j); + count++; + break; + } + } + } + return count; +} diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 9d33fd2377c8..23404b275457 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -4,7 +4,7 @@ * Copyright 2005-2006, Devicescape Software, Inc. * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2022 Intel Corporation + * Copyright (C) 2019, 2022-2024 Intel Corporation */ #include <linux/kernel.h> @@ -37,7 +37,7 @@ void rate_control_rate_init(struct sta_info *sta) struct ieee80211_supported_band *sband; struct ieee80211_chanctx_conf *chanctx_conf; - ieee80211_sta_set_rx_nss(&sta->deflink); + ieee80211_sta_init_nss(&sta->deflink); if (!ref) return; @@ -279,10 +279,10 @@ void ieee80211_check_rate_mask(struct ieee80211_link_data *link) u32 user_mask, basic_rates = link->conf->basic_rates; enum nl80211_band band; - if (WARN_ON(!link->conf->chandef.chan)) + if (WARN_ON(!link->conf->chanreq.oper.chan)) return; - band = link->conf->chandef.chan->band; + band = link->conf->chanreq.oper.chan->band; if (band == NL80211_BAND_S1GHZ) { /* TODO */ return; @@ -762,7 +762,7 @@ static bool rate_control_cap_mask(struct ieee80211_sub_if_data *sdata, u32 i, flags; *mask = sdata->rc_rateidx_mask[sband->band]; - flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chandef); + flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chanreq.oper); for (i = 0; i < sband->n_bitrates; i++) { if ((flags & sband->bitrates[i].flags) != flags) *mask &= ~BIT(i); @@ -818,7 +818,7 @@ rate_control_apply_mask_ratetbl(struct sta_info *sta, mcs_mask, vht_mask)) return; - chan_width = sta->sdata->vif.bss_conf.chandef.width; + chan_width = sta->sdata->vif.bss_conf.chanreq.oper.width; for (i = 0; i < IEEE80211_TX_RATE_TABLE_SIZE; i++) { if (rates->rate[i].idx < 0) break; @@ -855,7 +855,7 @@ static void rate_control_apply_mask(struct ieee80211_sub_if_data *sdata, * included in the configured mask and change the rate indexes * if needed. */ - chan_width = sdata->vif.bss_conf.chandef.width; + chan_width = sdata->vif.bss_conf.chanreq.oper.width; for (i = 0; i < max_rates; i++) { /* Skip invalid rates */ if (rates[i].idx < 0) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0bf72928ccfc..c1f850138405 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -6,7 +6,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include <linux/jiffies.h> @@ -1251,8 +1251,7 @@ static bool ieee80211_sta_manage_reorder_buf(struct ieee80211_sub_if_data *sdata { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - u16 sc = le16_to_cpu(hdr->seq_ctrl); - u16 mpdu_seq_num = (sc & IEEE80211_SCTL_SEQ) >> 4; + u16 mpdu_seq_num = ieee80211_get_sn(hdr); u16 head_seq_num, buf_size; int index; bool ret = true; @@ -1435,13 +1434,31 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx) return RX_CONTINUE; if (ieee80211_is_ctl(hdr->frame_control) || - ieee80211_is_any_nullfunc(hdr->frame_control) || - is_multicast_ether_addr(hdr->addr1)) + ieee80211_is_any_nullfunc(hdr->frame_control)) return RX_CONTINUE; if (!rx->sta) return RX_CONTINUE; + if (unlikely(is_multicast_ether_addr(hdr->addr1))) { + struct ieee80211_sub_if_data *sdata = rx->sdata; + u16 sn = ieee80211_get_sn(hdr); + + if (!ieee80211_is_data_present(hdr->frame_control)) + return RX_CONTINUE; + + if (!ieee80211_vif_is_mld(&sdata->vif) || + sdata->vif.type != NL80211_IFTYPE_STATION) + return RX_CONTINUE; + + if (sdata->u.mgd.mcast_seq_last != IEEE80211_SN_MODULO && + ieee80211_sn_less_eq(sn, sdata->u.mgd.mcast_seq_last)) + return RX_DROP_U_DUP; + + sdata->u.mgd.mcast_seq_last = sn; + return RX_CONTINUE; + } + if (unlikely(ieee80211_has_retry(hdr->frame_control) && rx->sta->last_seq_ctrl[rx->seqno_idx] == hdr->seq_ctrl)) { I802_DEBUG_INC(rx->local->dot11FrameDuplicateCount); @@ -3369,8 +3386,7 @@ ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx) IEEE80211_HE_OPERATION_BSS_COLOR_MASK); if (color == bss_conf->he_bss_color.color) ieee80211_obss_color_collision_notify(&rx->sdata->vif, - BIT_ULL(color), - GFP_ATOMIC); + BIT_ULL(color)); } } @@ -3763,6 +3779,28 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) break; } break; + case WLAN_CATEGORY_PROTECTED_EHT: + switch (mgmt->u.action.u.ttlm_req.action_code) { + case WLAN_PROTECTED_EHT_ACTION_TTLM_REQ: + if (sdata->vif.type != NL80211_IFTYPE_STATION) + break; + + if (len < offsetofend(typeof(*mgmt), + u.action.u.ttlm_req)) + goto invalid; + goto queue; + case WLAN_PROTECTED_EHT_ACTION_TTLM_RES: + if (sdata->vif.type != NL80211_IFTYPE_STATION) + break; + + if (len < offsetofend(typeof(*mgmt), + u.action.u.ttlm_res)) + goto invalid; + goto queue; + default: + break; + } + break; } return RX_CONTINUE; @@ -5192,7 +5230,6 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, */ if (!status->link_valid && pubsta->mlo) { - struct ieee80211_hdr *hdr = (void *)skb->data; struct link_sta_info *link_sta; link_sta = link_sta_info_get_bss(rx.sdata, diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index f9d5842601fa..0429e59ba387 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -257,7 +257,6 @@ static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata, void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); - struct ieee80211_sub_if_data *sdata1, *sdata2; struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_bss *bss; struct ieee80211_channel *channel; @@ -281,12 +280,6 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) if (skb->len < min_hdr_len) return; - sdata1 = rcu_dereference(local->scan_sdata); - sdata2 = rcu_dereference(local->sched_scan_sdata); - - if (likely(!sdata1 && !sdata2)) - return; - if (test_and_clear_bit(SCAN_BEACON_WAIT, &local->scanning)) { /* * we were passive scanning because of radar/no-IR, but @@ -304,10 +297,17 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) return; if (ieee80211_is_probe_resp(mgmt->frame_control)) { + struct ieee80211_sub_if_data *sdata1, *sdata2; struct cfg80211_scan_request *scan_req; struct cfg80211_sched_scan_request *sched_scan_req; u32 scan_req_flags = 0, sched_scan_req_flags = 0; + sdata1 = rcu_dereference(local->scan_sdata); + sdata2 = rcu_dereference(local->sched_scan_sdata); + + if (likely(!sdata1 && !sdata2)) + return; + scan_req = rcu_dereference(local->scan_req); sched_scan_req = rcu_dereference(local->sched_scan_req); @@ -327,8 +327,16 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) sched_scan_req_flags, mgmt->da)) return; + } else { + /* Beacons are expected only with broadcast address */ + if (!is_broadcast_ether_addr(mgmt->da)) + return; } + /* Do not update the BSS table in case of only monitor interfaces */ + if (local->open_count == local->monitors) + return; + bss = ieee80211_bss_info_update(local, rx_status, mgmt, skb->len, channel); @@ -400,6 +408,8 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) req->ie, req->ie_len, bands_used, req->rates, &chandef, flags); + if (ielen < 0) + return false; local->hw_scan_req->req.ie_len = ielen; local->hw_scan_req->req.no_cck = req->no_cck; ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr); @@ -476,7 +486,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) } /* Set power back to normal operating levels. */ - ieee80211_hw_config(local, 0); + ieee80211_hw_conf_chan(local); if (!hw_scan && was_scanning) { ieee80211_configure_filter(local); @@ -523,7 +533,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { /* Software scan is not supported in multi-channel cases */ - if (local->use_chanctx) + if (!local->emulate_chanctx) return -EOPNOTSUPP; /* @@ -553,7 +563,7 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local, ieee80211_configure_filter(local); /* We need to set power level at maximum rate for scanning. */ - ieee80211_hw_config(local, 0); + ieee80211_hw_conf_chan(local); wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0); @@ -677,7 +687,10 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, * After sending probe requests, wait for probe responses * on the channel. */ - *next_delay = IEEE80211_CHANNEL_TIME; + *next_delay = msecs_to_jiffies(scan_req->duration) > + IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME ? + msecs_to_jiffies(scan_req->duration) - IEEE80211_PROBE_DELAY : + IEEE80211_CHANNEL_TIME; local->next_scan_state = SCAN_DECISION; } @@ -787,7 +800,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, if (hw_scan) { __set_bit(SCAN_HW_SCANNING, &local->scanning); } else if ((req->n_channels == 1) && - (req->channels[0] == local->_oper_chandef.chan)) { + (req->channels[0] == local->hw.conf.chandef.chan)) { /* * If we are scanning only on the operating channel * then we do not need to stop normal activities @@ -805,7 +818,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, ieee80211_configure_filter(local); /* accept probe-responses */ /* We need to ensure power level is at max for scanning. */ - ieee80211_hw_config(local, 0); + ieee80211_hw_conf_chan(local); if ((req->channels[0]->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) || @@ -970,13 +983,13 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, /* If scanning on oper channel, use whatever channel-type * is currently in use. */ - if (chan == local->_oper_chandef.chan) - local->scan_chandef = local->_oper_chandef; + if (chan == local->hw.conf.chandef.chan) + local->scan_chandef = local->hw.conf.chandef; else local->scan_chandef.width = NL80211_CHAN_WIDTH_20_NOHT; set_channel: - if (ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL)) + if (ieee80211_hw_conf_chan(local)) skip = 1; /* advance state machine to next channel/band */ @@ -1000,7 +1013,10 @@ set_channel: */ if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) || !scan_req->n_ssids) { - *next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; + *next_delay = msecs_to_jiffies(scan_req->duration) > + IEEE80211_PASSIVE_CHANNEL_TIME ? + msecs_to_jiffies(scan_req->duration) : + IEEE80211_PASSIVE_CHANNEL_TIME; local->next_scan_state = SCAN_DECISION; if (scan_req->n_ssids) set_bit(SCAN_BEACON_WAIT, &local->scanning); @@ -1017,7 +1033,7 @@ static void ieee80211_scan_state_suspend(struct ieee80211_local *local, { /* switch back to the operating channel */ local->scan_chandef.chan = NULL; - ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + ieee80211_hw_conf_chan(local); /* disable PS */ ieee80211_offchannel_return(local); @@ -1316,10 +1332,12 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, ieee80211_prepare_scan_chandef(&chandef); - ieee80211_build_preq_ies(sdata, ie, num_bands * iebufsz, - &sched_scan_ies, req->ie, - req->ie_len, bands_used, rate_masks, &chandef, - flags); + ret = ieee80211_build_preq_ies(sdata, ie, num_bands * iebufsz, + &sched_scan_ies, req->ie, + req->ie_len, bands_used, rate_masks, + &chandef, flags); + if (ret < 0) + goto error; ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies); if (ret == 0) { @@ -1327,8 +1345,8 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, rcu_assign_pointer(local->sched_scan_req, req); } +error: kfree(ie); - out: if (ret) { /* Clean in case of failure after HW restart or upon resume. */ diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 55959b0b24c5..327c74e296e2 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -19,21 +19,222 @@ #include "sta_info.h" #include "wme.h" +static bool +wbcs_elem_to_chandef(const struct ieee80211_wide_bw_chansw_ie *wbcs_elem, + struct cfg80211_chan_def *chandef) +{ + u8 ccfs0 = wbcs_elem->new_center_freq_seg0; + u8 ccfs1 = wbcs_elem->new_center_freq_seg1; + u32 cf0 = ieee80211_channel_to_frequency(ccfs0, chandef->chan->band); + u32 cf1 = ieee80211_channel_to_frequency(ccfs1, chandef->chan->band); + + switch (wbcs_elem->new_channel_width) { + case IEEE80211_VHT_CHANWIDTH_160MHZ: + /* deprecated encoding */ + chandef->width = NL80211_CHAN_WIDTH_160; + chandef->center_freq1 = cf0; + break; + case IEEE80211_VHT_CHANWIDTH_80P80MHZ: + /* deprecated encoding */ + chandef->width = NL80211_CHAN_WIDTH_80P80; + chandef->center_freq1 = cf0; + chandef->center_freq2 = cf1; + break; + case IEEE80211_VHT_CHANWIDTH_80MHZ: + chandef->width = NL80211_CHAN_WIDTH_80; + chandef->center_freq1 = cf0; + + if (ccfs1) { + u8 diff = abs(ccfs0 - ccfs1); + + if (diff == 8) { + chandef->width = NL80211_CHAN_WIDTH_160; + chandef->center_freq1 = cf1; + } else if (diff > 8) { + chandef->width = NL80211_CHAN_WIDTH_80P80; + chandef->center_freq2 = cf1; + } + } + break; + case IEEE80211_VHT_CHANWIDTH_USE_HT: + default: + /* If the WBCS Element is present, new channel bandwidth is + * at least 40 MHz. + */ + chandef->width = NL80211_CHAN_WIDTH_40; + chandef->center_freq1 = cf0; + break; + } + + return cfg80211_chandef_valid(chandef); +} + +static void +validate_chandef_by_ht_vht_oper(struct ieee80211_sub_if_data *sdata, + struct ieee80211_conn_settings *conn, + u32 vht_cap_info, + struct cfg80211_chan_def *chandef) +{ + u32 control_freq, center_freq1, center_freq2; + enum nl80211_chan_width chan_width; + struct ieee80211_ht_operation ht_oper; + struct ieee80211_vht_operation vht_oper; + + if (conn->mode < IEEE80211_CONN_MODE_HT || + conn->bw_limit < IEEE80211_CONN_BW_LIMIT_40) { + chandef->chan = NULL; + return; + } + + control_freq = chandef->chan->center_freq; + center_freq1 = chandef->center_freq1; + center_freq2 = chandef->center_freq2; + chan_width = chandef->width; + + ht_oper.primary_chan = ieee80211_frequency_to_channel(control_freq); + if (control_freq != center_freq1) + ht_oper.ht_param = control_freq > center_freq1 ? + IEEE80211_HT_PARAM_CHA_SEC_BELOW : + IEEE80211_HT_PARAM_CHA_SEC_ABOVE; + else + ht_oper.ht_param = IEEE80211_HT_PARAM_CHA_SEC_NONE; + + ieee80211_chandef_ht_oper(&ht_oper, chandef); + + if (conn->mode < IEEE80211_CONN_MODE_VHT) + return; + + vht_oper.center_freq_seg0_idx = + ieee80211_frequency_to_channel(center_freq1); + vht_oper.center_freq_seg1_idx = center_freq2 ? + ieee80211_frequency_to_channel(center_freq2) : 0; + + switch (chan_width) { + case NL80211_CHAN_WIDTH_320: + WARN_ON(1); + break; + case NL80211_CHAN_WIDTH_160: + vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; + vht_oper.center_freq_seg1_idx = vht_oper.center_freq_seg0_idx; + vht_oper.center_freq_seg0_idx += + control_freq < center_freq1 ? -8 : 8; + break; + case NL80211_CHAN_WIDTH_80P80: + vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; + break; + case NL80211_CHAN_WIDTH_80: + vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_80MHZ; + break; + default: + vht_oper.chan_width = IEEE80211_VHT_CHANWIDTH_USE_HT; + break; + } + + ht_oper.operation_mode = + le16_encode_bits(vht_oper.center_freq_seg1_idx, + IEEE80211_HT_OP_MODE_CCFS2_MASK); + + if (!ieee80211_chandef_vht_oper(&sdata->local->hw, vht_cap_info, + &vht_oper, &ht_oper, chandef)) + chandef->chan = NULL; +} + +static void +validate_chandef_by_6ghz_he_eht_oper(struct ieee80211_sub_if_data *sdata, + struct ieee80211_conn_settings *conn, + struct cfg80211_chan_def *chandef) +{ + struct ieee80211_local *local = sdata->local; + u32 control_freq, center_freq1, center_freq2; + enum nl80211_chan_width chan_width; + struct { + struct ieee80211_he_operation _oper; + struct ieee80211_he_6ghz_oper _6ghz_oper; + } __packed he; + struct { + struct ieee80211_eht_operation _oper; + struct ieee80211_eht_operation_info _oper_info; + } __packed eht; + + if (conn->mode < IEEE80211_CONN_MODE_HE) { + chandef->chan = NULL; + return; + } + + control_freq = chandef->chan->center_freq; + center_freq1 = chandef->center_freq1; + center_freq2 = chandef->center_freq2; + chan_width = chandef->width; + + he._oper.he_oper_params = + le32_encode_bits(1, IEEE80211_HE_OPERATION_6GHZ_OP_INFO); + he._6ghz_oper.primary = + ieee80211_frequency_to_channel(control_freq); + he._6ghz_oper.ccfs0 = ieee80211_frequency_to_channel(center_freq1); + he._6ghz_oper.ccfs1 = center_freq2 ? + ieee80211_frequency_to_channel(center_freq2) : 0; + + switch (chan_width) { + case NL80211_CHAN_WIDTH_320: + he._6ghz_oper.ccfs1 = he._6ghz_oper.ccfs0; + he._6ghz_oper.ccfs0 += control_freq < center_freq1 ? -16 : 16; + he._6ghz_oper.control = IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ; + break; + case NL80211_CHAN_WIDTH_160: + he._6ghz_oper.ccfs1 = he._6ghz_oper.ccfs0; + he._6ghz_oper.ccfs0 += control_freq < center_freq1 ? -8 : 8; + fallthrough; + case NL80211_CHAN_WIDTH_80P80: + he._6ghz_oper.control = + IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ; + break; + case NL80211_CHAN_WIDTH_80: + he._6ghz_oper.control = + IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ; + break; + case NL80211_CHAN_WIDTH_40: + he._6ghz_oper.control = + IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ; + break; + default: + he._6ghz_oper.control = + IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ; + break; + } + + if (conn->mode < IEEE80211_CONN_MODE_EHT) { + if (!ieee80211_chandef_he_6ghz_oper(local, &he._oper, + NULL, chandef)) + chandef->chan = NULL; + } else { + eht._oper.params = IEEE80211_EHT_OPER_INFO_PRESENT; + eht._oper_info.control = he._6ghz_oper.control; + eht._oper_info.ccfs0 = he._6ghz_oper.ccfs0; + eht._oper_info.ccfs1 = he._6ghz_oper.ccfs1; + + if (!ieee80211_chandef_he_6ghz_oper(local, &he._oper, + &eht._oper, chandef)) + chandef->chan = NULL; + } +} + int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems, enum nl80211_band current_band, u32 vht_cap_info, - ieee80211_conn_flags_t conn_flags, u8 *bssid, + struct ieee80211_conn_settings *conn, + u8 *bssid, struct ieee80211_csa_ie *csa_ie) { enum nl80211_band new_band = current_band; int new_freq; - u8 new_chan_no; + u8 new_chan_no = 0, new_op_class = 0; struct ieee80211_channel *new_chan; - struct cfg80211_chan_def new_vht_chandef = {}; + struct cfg80211_chan_def new_chandef = {}; const struct ieee80211_sec_chan_offs_ie *sec_chan_offs; const struct ieee80211_wide_bw_chansw_ie *wide_bw_chansw_ie; const struct ieee80211_bandwidth_indication *bwi; + const struct ieee80211_ext_chansw_ie *ext_chansw_elem; int secondary_channel_offset = -1; memset(csa_ie, 0, sizeof(*csa_ie)); @@ -41,36 +242,41 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, sec_chan_offs = elems->sec_chan_offs; wide_bw_chansw_ie = elems->wide_bw_chansw_ie; bwi = elems->bandwidth_indication; + ext_chansw_elem = elems->ext_chansw_ie; - if (conn_flags & (IEEE80211_CONN_DISABLE_HT | - IEEE80211_CONN_DISABLE_40MHZ)) { + if (conn->mode < IEEE80211_CONN_MODE_HT || + conn->bw_limit < IEEE80211_CONN_BW_LIMIT_40) { sec_chan_offs = NULL; wide_bw_chansw_ie = NULL; } - if (conn_flags & IEEE80211_CONN_DISABLE_VHT) + if (conn->mode < IEEE80211_CONN_MODE_VHT) wide_bw_chansw_ie = NULL; - if (elems->ext_chansw_ie) { - if (!ieee80211_operating_class_to_band( - elems->ext_chansw_ie->new_operating_class, - &new_band)) { - sdata_info(sdata, - "cannot understand ECSA IE operating class, %d, ignoring\n", - elems->ext_chansw_ie->new_operating_class); + if (ext_chansw_elem) { + new_op_class = ext_chansw_elem->new_operating_class; + + if (!ieee80211_operating_class_to_band(new_op_class, &new_band)) { + new_op_class = 0; + sdata_info(sdata, "cannot understand ECSA IE operating class, %d, ignoring\n", + ext_chansw_elem->new_operating_class); + } else { + new_chan_no = ext_chansw_elem->new_ch_num; + csa_ie->count = ext_chansw_elem->count; + csa_ie->mode = ext_chansw_elem->mode; } - new_chan_no = elems->ext_chansw_ie->new_ch_num; - csa_ie->count = elems->ext_chansw_ie->count; - csa_ie->mode = elems->ext_chansw_ie->mode; - } else if (elems->ch_switch_ie) { + } + + if (!new_op_class && elems->ch_switch_ie) { new_chan_no = elems->ch_switch_ie->new_ch_num; csa_ie->count = elems->ch_switch_ie->count; csa_ie->mode = elems->ch_switch_ie->mode; - } else { - /* nothing here we understand */ - return 1; } + /* nothing here we understand */ + if (!new_chan_no) + return 1; + /* Mesh Channel Switch Parameters Element */ if (elems->mesh_chansw_params_ie) { csa_ie->ttl = elems->mesh_chansw_params_ie->mesh_ttl; @@ -95,7 +301,7 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, if (sec_chan_offs) { secondary_channel_offset = sec_chan_offs->sec_chan_offs; - } else if (!(conn_flags & IEEE80211_CONN_DISABLE_HT)) { + } else if (conn->mode >= IEEE80211_CONN_MODE_HT) { /* If the secondary channel offset IE is not present, * we can't know what's the post-CSA offset, so the * best we can do is use 20MHz. @@ -107,26 +313,26 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, default: /* secondary_channel_offset was present but is invalid */ case IEEE80211_HT_PARAM_CHA_SEC_NONE: - cfg80211_chandef_create(&csa_ie->chandef, new_chan, + cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_HT20); break; case IEEE80211_HT_PARAM_CHA_SEC_ABOVE: - cfg80211_chandef_create(&csa_ie->chandef, new_chan, + cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_HT40PLUS); break; case IEEE80211_HT_PARAM_CHA_SEC_BELOW: - cfg80211_chandef_create(&csa_ie->chandef, new_chan, + cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_HT40MINUS); break; case -1: - cfg80211_chandef_create(&csa_ie->chandef, new_chan, + cfg80211_chandef_create(&csa_ie->chanreq.oper, new_chan, NL80211_CHAN_NO_HT); /* keep width for 5/10 MHz channels */ - switch (sdata->vif.bss_conf.chandef.width) { + switch (sdata->vif.bss_conf.chanreq.oper.width) { case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: - csa_ie->chandef.width = - sdata->vif.bss_conf.chandef.width; + csa_ie->chanreq.oper.width = + sdata->vif.bss_conf.chanreq.oper.width; break; default: break; @@ -134,59 +340,48 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, break; } + /* parse one of the Elements to build a new chandef */ + memset(&new_chandef, 0, sizeof(new_chandef)); + new_chandef.chan = new_chan; if (bwi) { /* start with the CSA one */ - new_vht_chandef = csa_ie->chandef; + new_chandef = csa_ie->chanreq.oper; /* and update the width accordingly */ - /* FIXME: support 160/320 */ - ieee80211_chandef_eht_oper(&bwi->info, true, true, - &new_vht_chandef); - } else if (wide_bw_chansw_ie) { - u8 new_seg1 = wide_bw_chansw_ie->new_center_freq_seg1; - struct ieee80211_vht_operation vht_oper = { - .chan_width = - wide_bw_chansw_ie->new_channel_width, - .center_freq_seg0_idx = - wide_bw_chansw_ie->new_center_freq_seg0, - .center_freq_seg1_idx = new_seg1, - /* .basic_mcs_set doesn't matter */ - }; - struct ieee80211_ht_operation ht_oper = { - .operation_mode = - cpu_to_le16(new_seg1 << - IEEE80211_HT_OP_MODE_CCFS2_SHIFT), - }; - - /* default, for the case of IEEE80211_VHT_CHANWIDTH_USE_HT, - * to the previously parsed chandef - */ - new_vht_chandef = csa_ie->chandef; - - /* ignore if parsing fails */ - if (!ieee80211_chandef_vht_oper(&sdata->local->hw, - vht_cap_info, - &vht_oper, &ht_oper, - &new_vht_chandef)) - new_vht_chandef.chan = NULL; - - if (conn_flags & IEEE80211_CONN_DISABLE_80P80MHZ && - new_vht_chandef.width == NL80211_CHAN_WIDTH_80P80) - ieee80211_chandef_downgrade(&new_vht_chandef); - if (conn_flags & IEEE80211_CONN_DISABLE_160MHZ && - new_vht_chandef.width == NL80211_CHAN_WIDTH_160) - ieee80211_chandef_downgrade(&new_vht_chandef); + ieee80211_chandef_eht_oper(&bwi->info, &new_chandef); + } else if (!wide_bw_chansw_ie || !wbcs_elem_to_chandef(wide_bw_chansw_ie, + &new_chandef)) { + if (!ieee80211_operating_class_to_chandef(new_op_class, new_chan, + &new_chandef)) + new_chandef = csa_ie->chanreq.oper; } - /* if VHT data is there validate & use it */ - if (new_vht_chandef.chan) { - if (!cfg80211_chandef_compatible(&new_vht_chandef, - &csa_ie->chandef)) { + /* check if the new chandef fits the capabilities */ + if (new_band == NL80211_BAND_6GHZ) + validate_chandef_by_6ghz_he_eht_oper(sdata, conn, &new_chandef); + else + validate_chandef_by_ht_vht_oper(sdata, conn, vht_cap_info, + &new_chandef); + + /* if data is there validate the bandwidth & use it */ + if (new_chandef.chan) { + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_320 && + new_chandef.width == NL80211_CHAN_WIDTH_320) + ieee80211_chandef_downgrade(&new_chandef, NULL); + + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_160 && + (new_chandef.width == NL80211_CHAN_WIDTH_80P80 || + new_chandef.width == NL80211_CHAN_WIDTH_160)) + ieee80211_chandef_downgrade(&new_chandef, NULL); + + if (!cfg80211_chandef_compatible(&new_chandef, + &csa_ie->chanreq.oper)) { sdata_info(sdata, "BSS %pM: CSA has inconsistent channel data, disconnecting\n", bssid); return -EINVAL; } - csa_ie->chandef = new_vht_chandef; + + csa_ie->chanreq.oper = new_chandef; } if (elems->max_channel_switch_time) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 4391d8dd634b..da5fdd6f5c85 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1566,7 +1566,8 @@ void sta_info_stop(struct ieee80211_local *local) } -int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans) +int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans, + int link_id) { struct ieee80211_local *local = sdata->local; struct sta_info *sta, *tmp; @@ -1580,12 +1581,18 @@ int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans) WARN_ON(vlans && !sdata->bss); list_for_each_entry_safe(sta, tmp, &local->sta_list, list) { - if (sdata == sta->sdata || - (vlans && sdata->bss == sta->sdata->bss)) { - if (!WARN_ON(__sta_info_destroy_part1(sta))) - list_add(&sta->free_list, &free_list); - ret++; - } + if (sdata != sta->sdata && + (!vlans || sdata->bss != sta->sdata->bss)) + continue; + + if (link_id >= 0 && sta->sta.valid_links && + !(sta->sta.valid_links & BIT(link_id))) + continue; + + if (!WARN_ON(__sta_info_destroy_part1(sta))) + list_add(&sta->free_list, &free_list); + + ret++; } if (!list_empty(&free_list)) { diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 5ef1554f991f..a52fb76386d0 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -3,7 +3,7 @@ * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright(c) 2020-2023 Intel Corporation + * Copyright(c) 2020-2024 Intel Corporation */ #ifndef STA_INFO_H @@ -482,6 +482,8 @@ struct ieee80211_fragment_cache { * same for non-MLD STA. This is used as key for searching link STA * @link_id: Link ID uniquely identifying the link STA. This is 0 for non-MLD * and set to the corresponding vif LinkId for MLD STA + * @op_mode_nss: NSS limit as set by operating mode notification, or 0 + * @capa_nss: NSS limit as determined by local and peer capabilities * @link_hash_node: hash node for rhashtable * @sta: Points to the STA info * @gtk: group keys negotiated with this station, if any @@ -518,6 +520,8 @@ struct link_sta_info { u8 addr[ETH_ALEN]; u8 link_id; + u8 op_mode_nss, capa_nss; + struct rhlist_head link_hash_node; struct sta_info *sta; @@ -886,8 +890,12 @@ void sta_info_stop(struct ieee80211_local *local); * * @sdata: sdata to remove all stations from * @vlans: if the given interface is an AP interface, also flush VLANs + * @link_id: if given (>=0), all those STA entries using @link_id only + * will be removed. If -1 is passed, all STA entries will be + * removed. */ -int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans); +int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans, + int link_id); /** * sta_info_flush - flush matching STA entries from the STA table @@ -895,10 +903,14 @@ int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans); * Returns the number of removed STA entries. * * @sdata: sdata to remove all stations from + * @link_id: if given (>=0), all those STA entries using @link_id only + * will be removed. If -1 is passed, all STA entries will be + * removed. */ -static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata) +static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata, + int link_id) { - return __sta_info_flush(sdata, false); + return __sta_info_flush(sdata, false, link_id); } void sta_set_rate_info_tx(struct sta_info *sta, diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 49730b424141..f07b40916485 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -6,7 +6,7 @@ * Copyright 2014, Intel Corporation * Copyright 2014 Intel Mobile Communications GmbH * Copyright 2015 - 2016 Intel Deutschland GmbH - * Copyright (C) 2019, 2021-2023 Intel Corporation + * Copyright (C) 2019, 2021-2024 Intel Corporation */ #include <linux/ieee80211.h> @@ -159,7 +159,7 @@ static void ieee80211_tdls_add_oper_classes(struct ieee80211_link_data *link, u8 *pos; u8 op_class; - if (!ieee80211_chandef_to_operating_class(&link->conf->chandef, + if (!ieee80211_chandef_to_operating_class(&link->conf->chanreq.oper, &op_class)) return; @@ -347,7 +347,7 @@ ieee80211_tdls_chandef_vht_upgrade(struct ieee80211_sub_if_data *sdata, (uc.width > sta->tdls_chandef.width && !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc, sdata->wdev.iftype))) - ieee80211_chandef_downgrade(&uc); + ieee80211_chandef_downgrade(&uc, NULL); if (!cfg80211_chandef_identical(&uc, &sta->tdls_chandef)) { tdls_dbg(sdata, "TDLS ch width upgraded %d -> %d\n", @@ -382,8 +382,8 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_link_data *link, if (WARN_ON_ONCE(!sband)) return; - ieee80211_add_srates_ie(sdata, skb, false, sband->band); - ieee80211_add_ext_srates_ie(sdata, skb, false, sband->band); + ieee80211_put_srates_elem(skb, sband, 0, 0, 0, WLAN_EID_SUPP_RATES); + ieee80211_put_srates_elem(skb, sband, 0, 0, 0, WLAN_EID_EXT_SUPP_RATES); ieee80211_tdls_add_supp_channels(sdata, skb); /* add any custom IEs that go before Extended Capabilities */ @@ -438,7 +438,7 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_link_data *link, if (WARN_ON_ONCE(!sta)) return; - sta->tdls_chandef = link->conf->chandef; + sta->tdls_chandef = link->conf->chanreq.oper; } ieee80211_tdls_add_oper_classes(link, skb); @@ -548,30 +548,14 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_link_data *link, } /* build the HE-cap from sband */ - if (he_cap && - (action_code == WLAN_TDLS_SETUP_REQUEST || - action_code == WLAN_TDLS_SETUP_RESPONSE || - action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES)) { - __le16 he_6ghz_capa; - u8 cap_size; - - cap_size = - 2 + 1 + sizeof(he_cap->he_cap_elem) + - ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem) + - ieee80211_he_ppe_size(he_cap->ppe_thres[0], - he_cap->he_cap_elem.phy_cap_info); - pos = skb_put(skb, cap_size); - pos = ieee80211_ie_build_he_cap(0, pos, he_cap, pos + cap_size); + if (action_code == WLAN_TDLS_SETUP_REQUEST || + action_code == WLAN_TDLS_SETUP_RESPONSE || + action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) { + ieee80211_put_he_cap(skb, sdata, sband, NULL); /* Build HE 6Ghz capa IE from sband */ - if (sband->band == NL80211_BAND_6GHZ) { - cap_size = 2 + 1 + sizeof(struct ieee80211_he_6ghz_capa); - pos = skb_put(skb, cap_size); - he_6ghz_capa = - ieee80211_get_he_6ghz_capa_vif(sband, &sdata->vif); - pos = ieee80211_write_he_6ghz_cap(pos, he_6ghz_capa, - pos + cap_size); - } + if (sband->band == NL80211_BAND_6GHZ) + ieee80211_put_he_6ghz_cap(skb, sdata, link->smps_mode); } /* add any custom IEs that go before EHT capabilities */ @@ -591,21 +575,10 @@ ieee80211_tdls_add_setup_start_ies(struct ieee80211_link_data *link, } /* build the EHT-cap from sband */ - if (he_cap && eht_cap && - (action_code == WLAN_TDLS_SETUP_REQUEST || - action_code == WLAN_TDLS_SETUP_RESPONSE || - action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES)) { - u8 cap_size; - - cap_size = - 2 + 1 + sizeof(eht_cap->eht_cap_elem) + - ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem, - &eht_cap->eht_cap_elem, false) + - ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], - eht_cap->eht_cap_elem.phy_cap_info); - pos = skb_put(skb, cap_size); - ieee80211_ie_build_eht_cap(pos, he_cap, eht_cap, pos + cap_size, false); - } + if (action_code == WLAN_TDLS_SETUP_REQUEST || + action_code == WLAN_TDLS_SETUP_RESPONSE || + action_code == WLAN_PUB_ACTION_TDLS_DISCOVER_RES) + ieee80211_put_eht_cap(skb, sdata, sband, NULL); /* add any remaining IEs */ if (extra_ies_len) { @@ -638,7 +611,7 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_link_data *link, if (WARN_ON_ONCE(!sta || !ap_sta)) return; - sta->tdls_chandef = link->conf->chandef; + sta->tdls_chandef = link->conf->chanreq.oper; /* add any custom IEs that go before the QoS IE */ if (extra_ies_len) { @@ -684,7 +657,7 @@ ieee80211_tdls_add_setup_cfm_ies(struct ieee80211_link_data *link, pos = skb_put(skb, 2 + sizeof(struct ieee80211_ht_operation)); ieee80211_ie_build_ht_oper(pos, &sta->sta.deflink.ht_cap, - &link->conf->chandef, prot, + &link->conf->chanreq.oper, prot, true); } @@ -1413,8 +1386,8 @@ iee80211_tdls_recalc_ht_protection(struct ieee80211_sub_if_data *sdata, IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT; u16 opmode; - /* Nothing to do if the BSS connection uses HT */ - if (!(sdata->deflink.u.mgd.conn_flags & IEEE80211_CONN_DISABLE_HT)) + /* Nothing to do if the BSS connection uses (at least) HT */ + if (sdata->deflink.u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT) return; tdls_ht = (sta && sta->sta.deflink.ht_cap.ht_supported) || @@ -2055,8 +2028,9 @@ ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, } } -void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata) +void ieee80211_teardown_tdls_peers(struct ieee80211_link_data *link) { + struct ieee80211_sub_if_data *sdata = link->sdata; struct sta_info *sta; u16 reason = WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED; @@ -2066,6 +2040,9 @@ void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata) !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) continue; + if (sta->deflink.link_id != link->link_id) + continue; + ieee80211_tdls_oper_request(&sdata->vif, sta->sta.addr, NL80211_TDLS_TEARDOWN, reason, GFP_ATOMIC); diff --git a/net/mac80211/tests/elems.c b/net/mac80211/tests/elems.c index 997d0cd27b2d..a413ba29f759 100644 --- a/net/mac80211/tests/elems.c +++ b/net/mac80211/tests/elems.c @@ -2,7 +2,7 @@ /* * KUnit tests for element parsing * - * Copyright (C) 2023 Intel Corporation + * Copyright (C) 2023-2024 Intel Corporation */ #include <kunit/test.h> #include "../ieee80211_i.h" @@ -14,6 +14,7 @@ static void mle_defrag(struct kunit *test) struct ieee80211_elems_parse_params parse_params = { .link_id = 12, .from_ap = true, + .mode = IEEE80211_CONN_MODE_EHT, }; struct ieee802_11_elems *parsed; struct sk_buff *skb; @@ -68,7 +69,7 @@ static void mle_defrag(struct kunit *test) if (IS_ERR_OR_NULL(parsed)) goto free_skb; - KUNIT_EXPECT_NOT_NULL(test, parsed->ml_basic_elem); + KUNIT_EXPECT_NOT_NULL(test, parsed->ml_basic); KUNIT_EXPECT_EQ(test, parsed->ml_basic_len, 2 /* control */ + diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 06835ed4c44f..8e758b5074bd 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 - 2023 Intel Corporation + * Copyright (C) 2018 - 2024 Intel Corporation */ #if !defined(__MAC80211_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) @@ -50,7 +50,7 @@ __entry->center_freq1 = (c) ? (c)->center_freq1 : 0; \ __entry->freq1_offset = (c) ? (c)->freq1_offset : 0; \ __entry->center_freq2 = (c) ? (c)->center_freq2 : 0; -#define CHANDEF_PR_FMT " control:%d.%03d MHz width:%d center: %d.%03d/%d MHz" +#define CHANDEF_PR_FMT " chandef(%d.%03d MHz,width:%d,center: %d.%03d/%d MHz)" #define CHANDEF_PR_ARG __entry->control_freq, __entry->freq_offset, __entry->chan_width, \ __entry->center_freq1, __entry->freq1_offset, __entry->center_freq2 @@ -69,22 +69,45 @@ __entry->min_center_freq1 = (c)->center_freq1; \ __entry->min_freq1_offset = (c)->freq1_offset; \ __entry->min_center_freq2 = (c)->center_freq2; -#define MIN_CHANDEF_PR_FMT " min_control:%d.%03d MHz min_width:%d min_center: %d.%03d/%d MHz" +#define MIN_CHANDEF_PR_FMT " mindef(%d.%03d MHz,width:%d,center: %d.%03d/%d MHz)" #define MIN_CHANDEF_PR_ARG __entry->min_control_freq, __entry->min_freq_offset, \ __entry->min_chan_width, \ __entry->min_center_freq1, __entry->min_freq1_offset, \ __entry->min_center_freq2 +#define AP_CHANDEF_ENTRY \ + __field(u32, ap_control_freq) \ + __field(u32, ap_freq_offset) \ + __field(u32, ap_chan_width) \ + __field(u32, ap_center_freq1) \ + __field(u32, ap_freq1_offset) \ + __field(u32, ap_center_freq2) + +#define AP_CHANDEF_ASSIGN(c) \ + __entry->ap_control_freq = (c)->chan ? (c)->chan->center_freq : 0;\ + __entry->ap_freq_offset = (c)->chan ? (c)->chan->freq_offset : 0;\ + __entry->ap_chan_width = (c)->chan ? (c)->width : 0; \ + __entry->ap_center_freq1 = (c)->chan ? (c)->center_freq1 : 0; \ + __entry->ap_freq1_offset = (c)->chan ? (c)->freq1_offset : 0; \ + __entry->ap_center_freq2 = (c)->chan ? (c)->center_freq2 : 0; +#define AP_CHANDEF_PR_FMT " ap(%d.%03d MHz,width:%d,center: %d.%03d/%d MHz)" +#define AP_CHANDEF_PR_ARG __entry->ap_control_freq, __entry->ap_freq_offset, \ + __entry->ap_chan_width, \ + __entry->ap_center_freq1, __entry->ap_freq1_offset, \ + __entry->ap_center_freq2 + #define CHANCTX_ENTRY CHANDEF_ENTRY \ MIN_CHANDEF_ENTRY \ + AP_CHANDEF_ENTRY \ __field(u8, rx_chains_static) \ __field(u8, rx_chains_dynamic) #define CHANCTX_ASSIGN CHANDEF_ASSIGN(&ctx->conf.def) \ MIN_CHANDEF_ASSIGN(&ctx->conf.min_def) \ + AP_CHANDEF_ASSIGN(&ctx->conf.ap) \ __entry->rx_chains_static = ctx->conf.rx_chains_static; \ __entry->rx_chains_dynamic = ctx->conf.rx_chains_dynamic -#define CHANCTX_PR_FMT CHANDEF_PR_FMT MIN_CHANDEF_PR_FMT " chains:%d/%d" -#define CHANCTX_PR_ARG CHANDEF_PR_ARG, MIN_CHANDEF_PR_ARG, \ +#define CHANCTX_PR_FMT CHANDEF_PR_FMT MIN_CHANDEF_PR_FMT AP_CHANDEF_PR_FMT " chains:%d/%d" +#define CHANCTX_PR_ARG CHANDEF_PR_ARG, MIN_CHANDEF_PR_ARG, AP_CHANDEF_PR_ARG, \ __entry->rx_chains_static, __entry->rx_chains_dynamic #define KEY_ENTRY __field(u32, cipher) \ @@ -503,9 +526,9 @@ TRACE_EVENT(drv_link_info_changed, __entry->ht_operation_mode = link_conf->ht_operation_mode; __entry->cqm_rssi_thold = link_conf->cqm_rssi_thold; __entry->cqm_rssi_hyst = link_conf->cqm_rssi_hyst; - __entry->channel_width = link_conf->chandef.width; - __entry->channel_cfreq1 = link_conf->chandef.center_freq1; - __entry->channel_cfreq1_offset = link_conf->chandef.freq1_offset; + __entry->channel_width = link_conf->chanreq.oper.width; + __entry->channel_cfreq1 = link_conf->chanreq.oper.center_freq1; + __entry->channel_cfreq1_offset = link_conf->chanreq.oper.freq1_offset; __entry->qos = link_conf->qos; __entry->hidden_ssid = link_conf->hidden_ssid; __entry->txpower = link_conf->txpower; @@ -1186,7 +1209,7 @@ DEFINE_EVENT(sta_event, drv_flush_sta, TP_ARGS(local, sdata, sta) ); -TRACE_EVENT(drv_channel_switch, +DECLARE_EVENT_CLASS(chanswitch_evt, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_channel_switch *ch_switch), @@ -1201,6 +1224,7 @@ TRACE_EVENT(drv_channel_switch, __field(u32, device_timestamp) __field(bool, block_tx) __field(u8, count) + __field(u8, link_id) ), TP_fast_assign( @@ -1211,14 +1235,24 @@ TRACE_EVENT(drv_channel_switch, __entry->device_timestamp = ch_switch->device_timestamp; __entry->block_tx = ch_switch->block_tx; __entry->count = ch_switch->count; + __entry->link_id = ch_switch->link_id; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT " new " CHANDEF_PR_FMT " count:%d", - LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count + LOCAL_PR_FMT VIF_PR_FMT CHANDEF_PR_FMT " count:%d block_tx:%d timestamp:%llu device_ts:%u link_id:%d", + LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count, + __entry->block_tx, __entry->timestamp, + __entry->device_timestamp, __entry->link_id ) ); +DEFINE_EVENT(chanswitch_evt, drv_channel_switch, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_channel_switch *ch_switch), + TP_ARGS(local, sdata, ch_switch) +); + TRACE_EVENT(drv_set_antenna, TP_PROTO(struct ieee80211_local *local, u32 tx_ant, u32 rx_ant, int ret), @@ -2098,39 +2132,11 @@ TRACE_EVENT(drv_channel_switch_beacon, ) ); -TRACE_EVENT(drv_pre_channel_switch, +DEFINE_EVENT(chanswitch_evt, drv_pre_channel_switch, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_channel_switch *ch_switch), - - TP_ARGS(local, sdata, ch_switch), - - TP_STRUCT__entry( - LOCAL_ENTRY - VIF_ENTRY - CHANDEF_ENTRY - __field(u64, timestamp) - __field(u32, device_timestamp) - __field(bool, block_tx) - __field(u8, count) - ), - - TP_fast_assign( - LOCAL_ASSIGN; - VIF_ASSIGN; - CHANDEF_ASSIGN(&ch_switch->chandef) - __entry->timestamp = ch_switch->timestamp; - __entry->device_timestamp = ch_switch->device_timestamp; - __entry->block_tx = ch_switch->block_tx; - __entry->count = ch_switch->count; - ), - - TP_printk( - LOCAL_PR_FMT VIF_PR_FMT " prepare channel switch to " - CHANDEF_PR_FMT " count:%d block_tx:%d timestamp:%llu", - LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count, - __entry->block_tx, __entry->timestamp - ) + TP_ARGS(local, sdata, ch_switch) ); DEFINE_EVENT(local_sdata_evt, drv_post_channel_switch, @@ -2145,40 +2151,11 @@ DEFINE_EVENT(local_sdata_evt, drv_abort_channel_switch, TP_ARGS(local, sdata) ); -TRACE_EVENT(drv_channel_switch_rx_beacon, +DEFINE_EVENT(chanswitch_evt, drv_channel_switch_rx_beacon, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_channel_switch *ch_switch), - - TP_ARGS(local, sdata, ch_switch), - - TP_STRUCT__entry( - LOCAL_ENTRY - VIF_ENTRY - CHANDEF_ENTRY - __field(u64, timestamp) - __field(u32, device_timestamp) - __field(bool, block_tx) - __field(u8, count) - ), - - TP_fast_assign( - LOCAL_ASSIGN; - VIF_ASSIGN; - CHANDEF_ASSIGN(&ch_switch->chandef) - __entry->timestamp = ch_switch->timestamp; - __entry->device_timestamp = ch_switch->device_timestamp; - __entry->block_tx = ch_switch->block_tx; - __entry->count = ch_switch->count; - ), - - TP_printk( - LOCAL_PR_FMT VIF_PR_FMT - " received a channel switch beacon to " - CHANDEF_PR_FMT " count:%d block_tx:%d timestamp:%llu", - LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count, - __entry->block_tx, __entry->timestamp - ) + TP_ARGS(local, sdata, ch_switch) ); TRACE_EVENT(drv_get_txpower, @@ -3035,6 +3012,34 @@ TRACE_EVENT(api_radar_detected, ) ); +TRACE_EVENT(api_request_smps, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_link_data *link, + enum ieee80211_smps_mode smps_mode), + + TP_ARGS(local, sdata, link, smps_mode), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + __field(int, link_id) + __field(u32, smps_mode) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + __entry->link_id = link->link_id, + __entry->smps_mode = smps_mode; + ), + + TP_printk( + LOCAL_PR_FMT " " VIF_PR_FMT " link:%d, smps_mode:%d", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->link_id, __entry->smps_mode + ) +); + /* * Tracing for internal functions * (which may also be called in response to driver calls) @@ -3088,6 +3093,58 @@ TRACE_EVENT(stop_queue, ) ); +TRACE_EVENT(drv_can_neg_ttlm, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_neg_ttlm *neg_ttlm), + + TP_ARGS(local, sdata, neg_ttlm), + + TP_STRUCT__entry(LOCAL_ENTRY + VIF_ENTRY + __array(u16, downlink, sizeof(u16) * 8) + __array(u16, uplink, sizeof(u16) * 8) + ), + + TP_fast_assign(LOCAL_ASSIGN; + VIF_ASSIGN; + memcpy(__entry->downlink, neg_ttlm->downlink, + sizeof(neg_ttlm->downlink)); + memcpy(__entry->uplink, neg_ttlm->uplink, + sizeof(neg_ttlm->uplink)); + ), + + TP_printk(LOCAL_PR_FMT ", " VIF_PR_FMT, LOCAL_PR_ARG, VIF_PR_ARG) +); + +TRACE_EVENT(drv_neg_ttlm_res, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum ieee80211_neg_ttlm_res res, + struct ieee80211_neg_ttlm *neg_ttlm), + + TP_ARGS(local, sdata, res, neg_ttlm), + + TP_STRUCT__entry(LOCAL_ENTRY + VIF_ENTRY + __field(u32, res) + __array(u16, downlink, sizeof(u16) * 8) + __array(u16, uplink, sizeof(u16) * 8) + ), + + TP_fast_assign(LOCAL_ASSIGN; + VIF_ASSIGN; + __entry->res = res; + memcpy(__entry->downlink, neg_ttlm->downlink, + sizeof(neg_ttlm->downlink)); + memcpy(__entry->uplink, neg_ttlm->uplink, + sizeof(neg_ttlm->uplink)); + ), + + TP_printk(LOCAL_PR_FMT VIF_PR_FMT " response: %d\n ", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->res + ) +); #endif /* !__MAC80211_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/mac80211/trace_msg.h b/net/mac80211/trace_msg.h index c9dbe9aab7bd..aea4ce55c5ac 100644 --- a/net/mac80211/trace_msg.h +++ b/net/mac80211/trace_msg.h @@ -16,8 +16,6 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM mac80211_msg -#define MAX_MSG_LEN 120 - DECLARE_EVENT_CLASS(mac80211_msg_event, TP_PROTO(struct va_format *vaf), diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 6fbb15b65902..6bf223e6cd1a 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -133,6 +133,7 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, mrate = sband->bitrates[0].bitrate; for (i = 0; i < sband->n_bitrates; i++) { struct ieee80211_rate *r = &sband->bitrates[i]; + u32 flag; if (r->bitrate > txrate->bitrate) break; @@ -145,28 +146,24 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, switch (sband->band) { case NL80211_BAND_2GHZ: - case NL80211_BAND_LC: { - u32 flag; + case NL80211_BAND_LC: if (tx->sdata->deflink.operating_11g_mode) flag = IEEE80211_RATE_MANDATORY_G; else flag = IEEE80211_RATE_MANDATORY_B; - if (r->flags & flag) - mrate = r->bitrate; break; - } case NL80211_BAND_5GHZ: case NL80211_BAND_6GHZ: - if (r->flags & IEEE80211_RATE_MANDATORY_A) - mrate = r->bitrate; + flag = IEEE80211_RATE_MANDATORY_A; break; - case NL80211_BAND_S1GHZ: - case NL80211_BAND_60GHZ: - /* TODO, for now fall through */ - case NUM_NL80211_BANDS: + default: + flag = 0; WARN_ON(1); break; } + + if (r->flags & flag) + mrate = r->bitrate; } if (rate == -1) { /* No matching basic rate found; use highest suitable mandatory @@ -2393,12 +2390,18 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, if (chanctx_conf) chandef = &chanctx_conf->def; - else if (!local->use_chanctx) - chandef = &local->_oper_chandef; else goto fail_rcu; /* + * If driver/HW supports IEEE80211_CHAN_CAN_MONITOR we still + * shouldn't transmit on disabled channels. + */ + if (!cfg80211_chandef_usable(local->hw.wiphy, chandef, + IEEE80211_CHAN_DISABLED)) + goto fail_rcu; + + /* * Frame injection is not allowed if beaconing is not allowed * or if we need radar detection. Beaconing is usually not allowed when * the mode or operation (Adhoc, AP, Mesh) does not support DFS. @@ -3959,7 +3962,8 @@ begin: ieee80211_free_txskb(&local->hw, skb); goto begin; } else { - vif = NULL; + info->control.vif = NULL; + return skb; } break; case NL80211_IFTYPE_AP_VLAN: @@ -5032,16 +5036,24 @@ static u8 __ieee80211_beacon_update_cntdwn(struct beacon_data *beacon) return beacon->cntdwn_current_counter; } -u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif) +u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_link_data *link; struct beacon_data *beacon = NULL; u8 count = 0; + if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) + return 0; + rcu_read_lock(); + link = rcu_dereference(sdata->link[link_id]); + if (!link) + goto unlock; + if (sdata->vif.type == NL80211_IFTYPE_AP) - beacon = rcu_dereference(sdata->deflink.u.ap.beacon); + beacon = rcu_dereference(link->u.ap.beacon); else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) beacon = rcu_dereference(sdata->u.ibss.presp); else if (ieee80211_vif_is_mesh(&sdata->vif)) @@ -5083,9 +5095,11 @@ unlock: } EXPORT_SYMBOL(ieee80211_beacon_set_cntdwn); -bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif) +bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif, + unsigned int link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_link_data *link; struct beacon_data *beacon = NULL; u8 *beacon_data; size_t beacon_data_len; @@ -5094,9 +5108,17 @@ bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif) if (!ieee80211_sdata_running(sdata)) return false; + if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) + return 0; + rcu_read_lock(); + + link = rcu_dereference(sdata->link[link_id]); + if (!link) + goto out; + if (vif->type == NL80211_IFTYPE_AP) { - beacon = rcu_dereference(sdata->deflink.u.ap.beacon); + beacon = rcu_dereference(link->u.ap.beacon); if (WARN_ON(!beacon || !beacon->tail)) goto out; beacon_data = beacon->tail; @@ -5282,7 +5304,7 @@ ieee80211_beacon_get_ap(struct ieee80211_hw *hw, if (beacon->cntdwn_counter_offsets[0]) { if (!is_template) - ieee80211_beacon_update_cntdwn(vif); + ieee80211_beacon_update_cntdwn(vif, link->link_id); ieee80211_set_beacon_cntdwn(sdata, beacon, link); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 643c54855be6..a237cbcf7b49 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) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation * * utilities for mac80211 */ @@ -46,6 +46,11 @@ struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy) } EXPORT_SYMBOL(wiphy_to_ieee80211_hw); +const struct ieee80211_conn_settings ieee80211_conn_settings_unlimited = { + .mode = IEEE80211_CONN_MODE_EHT, + .bw_limit = IEEE80211_CONN_BW_LIMIT_320, +}; + u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, enum nl80211_iftype type) { @@ -912,776 +917,6 @@ void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_queue_delayed_work); -static void -ieee80211_parse_extension_element(u32 *crc, - const struct element *elem, - struct ieee802_11_elems *elems, - struct ieee80211_elems_parse_params *params) -{ - const void *data = elem->data + 1; - bool calc_crc = false; - u8 len; - - if (!elem->datalen) - return; - - len = elem->datalen - 1; - - switch (elem->data[0]) { - case WLAN_EID_EXT_HE_MU_EDCA: - calc_crc = true; - if (len >= sizeof(*elems->mu_edca_param_set)) - elems->mu_edca_param_set = data; - break; - case WLAN_EID_EXT_HE_CAPABILITY: - if (ieee80211_he_capa_size_ok(data, len)) { - elems->he_cap = data; - elems->he_cap_len = len; - } - break; - case WLAN_EID_EXT_HE_OPERATION: - calc_crc = true; - if (len >= sizeof(*elems->he_operation) && - len >= ieee80211_he_oper_size(data) - 1) - elems->he_operation = data; - break; - case WLAN_EID_EXT_UORA: - if (len >= 1) - elems->uora_element = data; - break; - case WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME: - if (len == 3) - elems->max_channel_switch_time = data; - break; - case WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION: - if (len >= sizeof(*elems->mbssid_config_ie)) - elems->mbssid_config_ie = data; - break; - case WLAN_EID_EXT_HE_SPR: - if (len >= sizeof(*elems->he_spr) && - len >= ieee80211_he_spr_size(data)) - elems->he_spr = data; - break; - case WLAN_EID_EXT_HE_6GHZ_CAPA: - if (len >= sizeof(*elems->he_6ghz_capa)) - elems->he_6ghz_capa = data; - break; - case WLAN_EID_EXT_EHT_CAPABILITY: - if (ieee80211_eht_capa_size_ok(elems->he_cap, - data, len, - params->from_ap)) { - elems->eht_cap = data; - elems->eht_cap_len = len; - } - break; - case WLAN_EID_EXT_EHT_OPERATION: - if (ieee80211_eht_oper_size_ok(data, len)) - elems->eht_operation = data; - calc_crc = true; - break; - case WLAN_EID_EXT_EHT_MULTI_LINK: - calc_crc = true; - - if (ieee80211_mle_size_ok(data, len)) { - const struct ieee80211_multi_link_elem *mle = - (void *)data; - - switch (le16_get_bits(mle->control, - IEEE80211_ML_CONTROL_TYPE)) { - case IEEE80211_ML_CONTROL_TYPE_BASIC: - elems->ml_basic_elem = (void *)elem; - elems->ml_basic = data; - elems->ml_basic_len = len; - break; - case IEEE80211_ML_CONTROL_TYPE_RECONF: - elems->ml_reconf_elem = (void *)elem; - elems->ml_reconf = data; - elems->ml_reconf_len = len; - break; - default: - break; - } - } - break; - case WLAN_EID_EXT_BANDWIDTH_INDICATION: - if (ieee80211_bandwidth_indication_size_ok(data, len)) - elems->bandwidth_indication = data; - calc_crc = true; - break; - case WLAN_EID_EXT_TID_TO_LINK_MAPPING: - calc_crc = true; - if (ieee80211_tid_to_link_map_size_ok(data, len) && - elems->ttlm_num < ARRAY_SIZE(elems->ttlm)) { - elems->ttlm[elems->ttlm_num] = (void *)data; - elems->ttlm_num++; - } - break; - } - - if (crc && calc_crc) - *crc = crc32_be(*crc, (void *)elem, elem->datalen + 2); -} - -static u32 -_ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, - struct ieee802_11_elems *elems, - const struct element *check_inherit) -{ - const struct element *elem; - bool calc_crc = params->filter != 0; - DECLARE_BITMAP(seen_elems, 256); - u32 crc = params->crc; - - bitmap_zero(seen_elems, 256); - - for_each_element(elem, params->start, params->len) { - const struct element *subelem; - bool elem_parse_failed; - u8 id = elem->id; - u8 elen = elem->datalen; - const u8 *pos = elem->data; - - if (check_inherit && - !cfg80211_is_element_inherited(elem, - check_inherit)) - continue; - - switch (id) { - case WLAN_EID_SSID: - case WLAN_EID_SUPP_RATES: - case WLAN_EID_FH_PARAMS: - case WLAN_EID_DS_PARAMS: - case WLAN_EID_CF_PARAMS: - case WLAN_EID_TIM: - case WLAN_EID_IBSS_PARAMS: - case WLAN_EID_CHALLENGE: - case WLAN_EID_RSN: - case WLAN_EID_ERP_INFO: - case WLAN_EID_EXT_SUPP_RATES: - case WLAN_EID_HT_CAPABILITY: - case WLAN_EID_HT_OPERATION: - case WLAN_EID_VHT_CAPABILITY: - case WLAN_EID_VHT_OPERATION: - case WLAN_EID_MESH_ID: - case WLAN_EID_MESH_CONFIG: - case WLAN_EID_PEER_MGMT: - case WLAN_EID_PREQ: - case WLAN_EID_PREP: - case WLAN_EID_PERR: - case WLAN_EID_RANN: - case WLAN_EID_CHANNEL_SWITCH: - case WLAN_EID_EXT_CHANSWITCH_ANN: - case WLAN_EID_COUNTRY: - case WLAN_EID_PWR_CONSTRAINT: - case WLAN_EID_TIMEOUT_INTERVAL: - case WLAN_EID_SECONDARY_CHANNEL_OFFSET: - case WLAN_EID_WIDE_BW_CHANNEL_SWITCH: - case WLAN_EID_CHAN_SWITCH_PARAM: - case WLAN_EID_EXT_CAPABILITY: - case WLAN_EID_CHAN_SWITCH_TIMING: - case WLAN_EID_LINK_ID: - case WLAN_EID_BSS_MAX_IDLE_PERIOD: - case WLAN_EID_RSNX: - case WLAN_EID_S1G_BCN_COMPAT: - case WLAN_EID_S1G_CAPABILITIES: - case WLAN_EID_S1G_OPERATION: - case WLAN_EID_AID_RESPONSE: - case WLAN_EID_S1G_SHORT_BCN_INTERVAL: - /* - * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible - * that if the content gets bigger it might be needed more than once - */ - if (test_bit(id, seen_elems)) { - elems->parse_error = true; - continue; - } - break; - } - - if (calc_crc && id < 64 && (params->filter & (1ULL << id))) - crc = crc32_be(crc, pos - 2, elen + 2); - - elem_parse_failed = false; - - switch (id) { - case WLAN_EID_LINK_ID: - if (elen + 2 < sizeof(struct ieee80211_tdls_lnkie)) { - elem_parse_failed = true; - break; - } - elems->lnk_id = (void *)(pos - 2); - break; - case WLAN_EID_CHAN_SWITCH_TIMING: - if (elen < sizeof(struct ieee80211_ch_switch_timing)) { - elem_parse_failed = true; - break; - } - elems->ch_sw_timing = (void *)pos; - break; - case WLAN_EID_EXT_CAPABILITY: - elems->ext_capab = pos; - elems->ext_capab_len = elen; - break; - case WLAN_EID_SSID: - elems->ssid = pos; - elems->ssid_len = elen; - break; - case WLAN_EID_SUPP_RATES: - elems->supp_rates = pos; - elems->supp_rates_len = elen; - break; - case WLAN_EID_DS_PARAMS: - if (elen >= 1) - elems->ds_params = pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_TIM: - if (elen >= sizeof(struct ieee80211_tim_ie)) { - elems->tim = (void *)pos; - elems->tim_len = elen; - } else - elem_parse_failed = true; - break; - case WLAN_EID_VENDOR_SPECIFIC: - if (elen >= 4 && pos[0] == 0x00 && pos[1] == 0x50 && - pos[2] == 0xf2) { - /* Microsoft OUI (00:50:F2) */ - - if (calc_crc) - crc = crc32_be(crc, pos - 2, elen + 2); - - if (elen >= 5 && pos[3] == 2) { - /* OUI Type 2 - WMM IE */ - if (pos[4] == 0) { - elems->wmm_info = pos; - elems->wmm_info_len = elen; - } else if (pos[4] == 1) { - elems->wmm_param = pos; - elems->wmm_param_len = elen; - } - } - } - break; - case WLAN_EID_RSN: - elems->rsn = pos; - elems->rsn_len = elen; - break; - case WLAN_EID_ERP_INFO: - if (elen >= 1) - elems->erp_info = pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_EXT_SUPP_RATES: - elems->ext_supp_rates = pos; - elems->ext_supp_rates_len = elen; - break; - case WLAN_EID_HT_CAPABILITY: - if (elen >= sizeof(struct ieee80211_ht_cap)) - elems->ht_cap_elem = (void *)pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_HT_OPERATION: - if (elen >= sizeof(struct ieee80211_ht_operation)) - elems->ht_operation = (void *)pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_VHT_CAPABILITY: - if (elen >= sizeof(struct ieee80211_vht_cap)) - elems->vht_cap_elem = (void *)pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_VHT_OPERATION: - if (elen >= sizeof(struct ieee80211_vht_operation)) { - elems->vht_operation = (void *)pos; - if (calc_crc) - crc = crc32_be(crc, pos - 2, elen + 2); - break; - } - elem_parse_failed = true; - break; - case WLAN_EID_OPMODE_NOTIF: - if (elen > 0) { - elems->opmode_notif = pos; - if (calc_crc) - crc = crc32_be(crc, pos - 2, elen + 2); - break; - } - elem_parse_failed = true; - break; - case WLAN_EID_MESH_ID: - elems->mesh_id = pos; - elems->mesh_id_len = elen; - break; - case WLAN_EID_MESH_CONFIG: - if (elen >= sizeof(struct ieee80211_meshconf_ie)) - elems->mesh_config = (void *)pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_PEER_MGMT: - elems->peering = pos; - elems->peering_len = elen; - break; - case WLAN_EID_MESH_AWAKE_WINDOW: - if (elen >= 2) - elems->awake_window = (void *)pos; - break; - case WLAN_EID_PREQ: - elems->preq = pos; - elems->preq_len = elen; - break; - case WLAN_EID_PREP: - elems->prep = pos; - elems->prep_len = elen; - break; - case WLAN_EID_PERR: - elems->perr = pos; - elems->perr_len = elen; - break; - case WLAN_EID_RANN: - if (elen >= sizeof(struct ieee80211_rann_ie)) - elems->rann = (void *)pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_CHANNEL_SWITCH: - if (elen != sizeof(struct ieee80211_channel_sw_ie)) { - elem_parse_failed = true; - break; - } - elems->ch_switch_ie = (void *)pos; - break; - case WLAN_EID_EXT_CHANSWITCH_ANN: - if (elen != sizeof(struct ieee80211_ext_chansw_ie)) { - elem_parse_failed = true; - break; - } - elems->ext_chansw_ie = (void *)pos; - break; - case WLAN_EID_SECONDARY_CHANNEL_OFFSET: - if (elen != sizeof(struct ieee80211_sec_chan_offs_ie)) { - elem_parse_failed = true; - break; - } - elems->sec_chan_offs = (void *)pos; - break; - case WLAN_EID_CHAN_SWITCH_PARAM: - if (elen < - sizeof(*elems->mesh_chansw_params_ie)) { - elem_parse_failed = true; - break; - } - elems->mesh_chansw_params_ie = (void *)pos; - break; - case WLAN_EID_WIDE_BW_CHANNEL_SWITCH: - if (!params->action || - elen < sizeof(*elems->wide_bw_chansw_ie)) { - elem_parse_failed = true; - break; - } - elems->wide_bw_chansw_ie = (void *)pos; - break; - case WLAN_EID_CHANNEL_SWITCH_WRAPPER: - if (params->action) { - elem_parse_failed = true; - break; - } - /* - * This is a bit tricky, but as we only care about - * a few elements, parse them out manually. - */ - subelem = cfg80211_find_elem(WLAN_EID_WIDE_BW_CHANNEL_SWITCH, - pos, elen); - if (subelem) { - if (subelem->datalen >= sizeof(*elems->wide_bw_chansw_ie)) - elems->wide_bw_chansw_ie = - (void *)subelem->data; - else - elem_parse_failed = true; - } - - subelem = cfg80211_find_ext_elem(WLAN_EID_EXT_BANDWIDTH_INDICATION, - pos, elen); - if (subelem) { - const void *edata = subelem->data + 1; - u8 edatalen = subelem->datalen - 1; - - if (ieee80211_bandwidth_indication_size_ok(edata, - edatalen)) - elems->bandwidth_indication = edata; - else - elem_parse_failed = true; - } - break; - case WLAN_EID_COUNTRY: - elems->country_elem = pos; - elems->country_elem_len = elen; - break; - case WLAN_EID_PWR_CONSTRAINT: - if (elen != 1) { - elem_parse_failed = true; - break; - } - elems->pwr_constr_elem = pos; - break; - case WLAN_EID_CISCO_VENDOR_SPECIFIC: - /* Lots of different options exist, but we only care - * about the Dynamic Transmit Power Control element. - * First check for the Cisco OUI, then for the DTPC - * tag (0x00). - */ - if (elen < 4) { - elem_parse_failed = true; - break; - } - - if (pos[0] != 0x00 || pos[1] != 0x40 || - pos[2] != 0x96 || pos[3] != 0x00) - break; - - if (elen != 6) { - elem_parse_failed = true; - break; - } - - if (calc_crc) - crc = crc32_be(crc, pos - 2, elen + 2); - - elems->cisco_dtpc_elem = pos; - break; - case WLAN_EID_ADDBA_EXT: - if (elen < sizeof(struct ieee80211_addba_ext_ie)) { - elem_parse_failed = true; - break; - } - elems->addba_ext_ie = (void *)pos; - break; - case WLAN_EID_TIMEOUT_INTERVAL: - if (elen >= sizeof(struct ieee80211_timeout_interval_ie)) - elems->timeout_int = (void *)pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_BSS_MAX_IDLE_PERIOD: - if (elen >= sizeof(*elems->max_idle_period_ie)) - elems->max_idle_period_ie = (void *)pos; - break; - case WLAN_EID_RSNX: - elems->rsnx = pos; - elems->rsnx_len = elen; - break; - case WLAN_EID_TX_POWER_ENVELOPE: - if (elen < 1 || - elen > sizeof(struct ieee80211_tx_pwr_env)) - break; - - if (elems->tx_pwr_env_num >= ARRAY_SIZE(elems->tx_pwr_env)) - break; - - elems->tx_pwr_env[elems->tx_pwr_env_num] = (void *)pos; - elems->tx_pwr_env_len[elems->tx_pwr_env_num] = elen; - elems->tx_pwr_env_num++; - break; - case WLAN_EID_EXTENSION: - ieee80211_parse_extension_element(calc_crc ? - &crc : NULL, - elem, elems, params); - break; - case WLAN_EID_S1G_CAPABILITIES: - if (elen >= sizeof(*elems->s1g_capab)) - elems->s1g_capab = (void *)pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_S1G_OPERATION: - if (elen == sizeof(*elems->s1g_oper)) - elems->s1g_oper = (void *)pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_S1G_BCN_COMPAT: - if (elen == sizeof(*elems->s1g_bcn_compat)) - elems->s1g_bcn_compat = (void *)pos; - else - elem_parse_failed = true; - break; - case WLAN_EID_AID_RESPONSE: - if (elen == sizeof(struct ieee80211_aid_response_ie)) - elems->aid_resp = (void *)pos; - else - elem_parse_failed = true; - break; - default: - break; - } - - if (elem_parse_failed) - elems->parse_error = true; - else - __set_bit(id, seen_elems); - } - - if (!for_each_element_completed(elem, params->start, params->len)) - elems->parse_error = true; - - return crc; -} - -static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len, - struct ieee802_11_elems *elems, - struct cfg80211_bss *bss, - u8 *nontransmitted_profile) -{ - const struct element *elem, *sub; - size_t profile_len = 0; - bool found = false; - - if (!bss || !bss->transmitted_bss) - return profile_len; - - for_each_element_id(elem, WLAN_EID_MULTIPLE_BSSID, start, len) { - if (elem->datalen < 2) - continue; - if (elem->data[0] < 1 || elem->data[0] > 8) - continue; - - for_each_element(sub, elem->data + 1, elem->datalen - 1) { - u8 new_bssid[ETH_ALEN]; - const u8 *index; - - if (sub->id != 0 || sub->datalen < 4) { - /* not a valid BSS profile */ - continue; - } - - if (sub->data[0] != WLAN_EID_NON_TX_BSSID_CAP || - sub->data[1] != 2) { - /* The first element of the - * Nontransmitted BSSID Profile is not - * the Nontransmitted BSSID Capability - * element. - */ - continue; - } - - memset(nontransmitted_profile, 0, len); - profile_len = cfg80211_merge_profile(start, len, - elem, - sub, - nontransmitted_profile, - len); - - /* found a Nontransmitted BSSID Profile */ - index = cfg80211_find_ie(WLAN_EID_MULTI_BSSID_IDX, - nontransmitted_profile, - profile_len); - if (!index || index[1] < 1 || index[2] == 0) { - /* Invalid MBSSID Index element */ - continue; - } - - cfg80211_gen_new_bssid(bss->transmitted_bss->bssid, - elem->data[0], - index[2], - new_bssid); - if (ether_addr_equal(new_bssid, bss->bssid)) { - found = true; - elems->bssid_index_len = index[1]; - elems->bssid_index = (void *)&index[2]; - break; - } - } - } - - return found ? profile_len : 0; -} - -static void ieee80211_mle_get_sta_prof(struct ieee802_11_elems *elems, - u8 link_id) -{ - const struct ieee80211_multi_link_elem *ml = elems->ml_basic; - ssize_t ml_len = elems->ml_basic_len; - const struct element *sub; - - if (!ml || !ml_len) - return; - - if (le16_get_bits(ml->control, IEEE80211_ML_CONTROL_TYPE) != - IEEE80211_ML_CONTROL_TYPE_BASIC) - return; - - for_each_mle_subelement(sub, (u8 *)ml, ml_len) { - struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data; - ssize_t sta_prof_len; - u16 control; - - if (sub->id != IEEE80211_MLE_SUBELEM_PER_STA_PROFILE) - continue; - - if (!ieee80211_mle_basic_sta_prof_size_ok(sub->data, - sub->datalen)) - return; - - control = le16_to_cpu(prof->control); - - if (link_id != u16_get_bits(control, - IEEE80211_MLE_STA_CONTROL_LINK_ID)) - continue; - - if (!(control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE)) - return; - - /* the sub element can be fragmented */ - sta_prof_len = - cfg80211_defragment_element(sub, - (u8 *)ml, ml_len, - elems->scratch_pos, - elems->scratch + - elems->scratch_len - - elems->scratch_pos, - IEEE80211_MLE_SUBELEM_FRAGMENT); - - if (sta_prof_len < 0) - return; - - elems->prof = (void *)elems->scratch_pos; - elems->sta_prof_len = sta_prof_len; - elems->scratch_pos += sta_prof_len; - - return; - } -} - -static void ieee80211_mle_parse_link(struct ieee802_11_elems *elems, - struct ieee80211_elems_parse_params *params) -{ - struct ieee80211_mle_per_sta_profile *prof; - struct ieee80211_elems_parse_params sub = { - .action = params->action, - .from_ap = params->from_ap, - .link_id = -1, - }; - ssize_t ml_len = elems->ml_basic_len; - const struct element *non_inherit = NULL; - const u8 *end; - - if (params->link_id == -1) - return; - - ml_len = cfg80211_defragment_element(elems->ml_basic_elem, - elems->ie_start, - elems->total_len, - elems->scratch_pos, - elems->scratch + - elems->scratch_len - - elems->scratch_pos, - WLAN_EID_FRAGMENT); - - if (ml_len < 0) - return; - - elems->ml_basic = (const void *)elems->scratch_pos; - elems->ml_basic_len = ml_len; - - ieee80211_mle_get_sta_prof(elems, params->link_id); - prof = elems->prof; - - if (!prof) - return; - - /* check if we have the 4 bytes for the fixed part in assoc response */ - if (elems->sta_prof_len < sizeof(*prof) + prof->sta_info_len - 1 + 4) { - elems->prof = NULL; - elems->sta_prof_len = 0; - return; - } - - /* - * Skip the capability information and the status code that are expected - * as part of the station profile in association response frames. Note - * the -1 is because the 'sta_info_len' is accounted to as part of the - * per-STA profile, but not part of the 'u8 variable[]' portion. - */ - sub.start = prof->variable + prof->sta_info_len - 1 + 4; - end = (const u8 *)prof + elems->sta_prof_len; - sub.len = end - sub.start; - - non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, - sub.start, sub.len); - _ieee802_11_parse_elems_full(&sub, elems, non_inherit); -} - -struct ieee802_11_elems * -ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) -{ - struct ieee802_11_elems *elems; - const struct element *non_inherit = NULL; - u8 *nontransmitted_profile; - int nontransmitted_profile_len = 0; - size_t scratch_len = 3 * params->len; - - elems = kzalloc(struct_size(elems, scratch, scratch_len), GFP_ATOMIC); - if (!elems) - return NULL; - elems->ie_start = params->start; - elems->total_len = params->len; - elems->scratch_len = scratch_len; - elems->scratch_pos = elems->scratch; - - nontransmitted_profile = elems->scratch_pos; - nontransmitted_profile_len = - ieee802_11_find_bssid_profile(params->start, params->len, - elems, params->bss, - nontransmitted_profile); - elems->scratch_pos += nontransmitted_profile_len; - elems->scratch_len -= nontransmitted_profile_len; - non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, - nontransmitted_profile, - nontransmitted_profile_len); - - elems->crc = _ieee802_11_parse_elems_full(params, elems, non_inherit); - - /* Override with nontransmitted profile, if found */ - if (nontransmitted_profile_len) { - struct ieee80211_elems_parse_params sub = { - .start = nontransmitted_profile, - .len = nontransmitted_profile_len, - .action = params->action, - .link_id = params->link_id, - }; - - _ieee802_11_parse_elems_full(&sub, elems, NULL); - } - - ieee80211_mle_parse_link(elems, params); - - if (elems->tim && !elems->parse_error) { - const struct ieee80211_tim_ie *tim_ie = elems->tim; - - elems->dtim_period = tim_ie->dtim_period; - elems->dtim_count = tim_ie->dtim_count; - } - - /* Override DTIM period and count if needed */ - if (elems->bssid_index && - elems->bssid_index_len >= - offsetofend(struct ieee80211_bssid_index, dtim_period)) - elems->dtim_period = elems->bssid_index->dtim_period; - - if (elems->bssid_index && - elems->bssid_index_len >= - offsetofend(struct ieee80211_bssid_index, dtim_count)) - elems->dtim_count = elems->bssid_index->dtim_count; - - return elems; -} -EXPORT_SYMBOL_IF_KUNIT(ieee802_11_parse_elems_full); - void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, struct ieee80211_tx_queue_params *qparam, int ac) @@ -1938,37 +1173,34 @@ void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, } } -u8 *ieee80211_write_he_6ghz_cap(u8 *pos, __le16 cap, u8 *end) +static int ieee80211_put_s1g_cap(struct sk_buff *skb, + struct ieee80211_sta_s1g_cap *s1g_cap) { - if ((end - pos) < 5) - return pos; + if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_s1g_cap)) + return -ENOBUFS; - *pos++ = WLAN_EID_EXTENSION; - *pos++ = 1 + sizeof(cap); - *pos++ = WLAN_EID_EXT_HE_6GHZ_CAPA; - memcpy(pos, &cap, sizeof(cap)); + skb_put_u8(skb, WLAN_EID_S1G_CAPABILITIES); + skb_put_u8(skb, sizeof(struct ieee80211_s1g_cap)); - return pos + 2; + skb_put_data(skb, &s1g_cap->cap, sizeof(s1g_cap->cap)); + skb_put_data(skb, &s1g_cap->nss_mcs, sizeof(s1g_cap->nss_mcs)); + + return 0; } -static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, - u8 *buffer, size_t buffer_len, - const u8 *ie, size_t ie_len, - enum nl80211_band band, - u32 rate_mask, - struct cfg80211_chan_def *chandef, - size_t *offset, u32 flags) +static int ieee80211_put_preq_ies_band(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata, + const u8 *ie, size_t ie_len, + size_t *offset, + enum nl80211_band band, + u32 rate_mask, + struct cfg80211_chan_def *chandef, + u32 flags) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; - const struct ieee80211_sta_he_cap *he_cap; - const struct ieee80211_sta_eht_cap *eht_cap; - u8 *pos = buffer, *end = buffer + buffer_len; + int i, err; size_t noffset; - int supp_rates_len, i; - u8 rates[32]; - int num_rates; - int ext_rates_len; u32 rate_flags; bool have_80mhz = false; @@ -1981,32 +1213,13 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, rate_flags = ieee80211_chandef_rate_flags(chandef); /* For direct scan add S1G IE and consider its override bits */ - if (band == NL80211_BAND_S1GHZ) { - if (end - pos < 2 + sizeof(struct ieee80211_s1g_cap)) - goto out_err; - pos = ieee80211_ie_build_s1g_cap(pos, &sband->s1g_cap); - goto done; - } + if (band == NL80211_BAND_S1GHZ) + return ieee80211_put_s1g_cap(skb, &sband->s1g_cap); - num_rates = 0; - for (i = 0; i < sband->n_bitrates; i++) { - if ((BIT(i) & rate_mask) == 0) - continue; /* skip rate */ - if ((rate_flags & sband->bitrates[i].flags) != rate_flags) - continue; - - rates[num_rates++] = - (u8) DIV_ROUND_UP(sband->bitrates[i].bitrate, 5); - } - - supp_rates_len = min_t(int, num_rates, 8); - - if (end - pos < 2 + supp_rates_len) - goto out_err; - *pos++ = WLAN_EID_SUPP_RATES; - *pos++ = supp_rates_len; - memcpy(pos, rates, supp_rates_len); - pos += supp_rates_len; + err = ieee80211_put_srates_elem(skb, sband, 0, rate_flags, + ~rate_mask, WLAN_EID_SUPP_RATES); + if (err) + return err; /* insert "request information" if in custom IEs */ if (ie && ie_len) { @@ -2019,34 +1232,28 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, before_extrates, ARRAY_SIZE(before_extrates), *offset); - if (end - pos < noffset - *offset) - goto out_err; - memcpy(pos, ie + *offset, noffset - *offset); - pos += noffset - *offset; + if (skb_tailroom(skb) < noffset - *offset) + return -ENOBUFS; + skb_put_data(skb, ie + *offset, noffset - *offset); *offset = noffset; } - ext_rates_len = num_rates - supp_rates_len; - if (ext_rates_len > 0) { - if (end - pos < 2 + ext_rates_len) - goto out_err; - *pos++ = WLAN_EID_EXT_SUPP_RATES; - *pos++ = ext_rates_len; - memcpy(pos, rates + supp_rates_len, ext_rates_len); - pos += ext_rates_len; - } + err = ieee80211_put_srates_elem(skb, sband, 0, rate_flags, + ~rate_mask, WLAN_EID_EXT_SUPP_RATES); + if (err) + return err; if (chandef->chan && sband->band == NL80211_BAND_2GHZ) { - if (end - pos < 3) - goto out_err; - *pos++ = WLAN_EID_DS_PARAMS; - *pos++ = 1; - *pos++ = ieee80211_frequency_to_channel( - chandef->chan->center_freq); + if (skb_tailroom(skb) < 3) + return -ENOBUFS; + skb_put_u8(skb, WLAN_EID_DS_PARAMS); + skb_put_u8(skb, 1); + skb_put_u8(skb, + ieee80211_frequency_to_channel(chandef->chan->center_freq)); } if (flags & IEEE80211_PROBE_FLAG_MIN_CONTENT) - goto done; + return 0; /* insert custom IEs that go before HT */ if (ie && ie_len) { @@ -2061,18 +1268,21 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, noffset = ieee80211_ie_split(ie, ie_len, before_ht, ARRAY_SIZE(before_ht), *offset); - if (end - pos < noffset - *offset) - goto out_err; - memcpy(pos, ie + *offset, noffset - *offset); - pos += noffset - *offset; + if (skb_tailroom(skb) < noffset - *offset) + return -ENOBUFS; + skb_put_data(skb, ie + *offset, noffset - *offset); *offset = noffset; } if (sband->ht_cap.ht_supported) { - if (end - pos < 2 + sizeof(struct ieee80211_ht_cap)) - goto out_err; - pos = ieee80211_ie_build_ht_cap(pos, &sband->ht_cap, - sband->ht_cap.cap); + u8 *pos; + + if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_ht_cap)) + return -ENOBUFS; + + pos = skb_put(skb, 2 + sizeof(struct ieee80211_ht_cap)); + ieee80211_ie_build_ht_cap(pos, &sband->ht_cap, + sband->ht_cap.cap); } /* insert custom IEs that go before VHT */ @@ -2093,10 +1303,9 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, noffset = ieee80211_ie_split(ie, ie_len, before_vht, ARRAY_SIZE(before_vht), *offset); - if (end - pos < noffset - *offset) - goto out_err; - memcpy(pos, ie + *offset, noffset - *offset); - pos += noffset - *offset; + if (skb_tailroom(skb) < noffset - *offset) + return -ENOBUFS; + skb_put_data(skb, ie + *offset, noffset - *offset); *offset = noffset; } @@ -2111,10 +1320,14 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, } if (sband->vht_cap.vht_supported && have_80mhz) { - if (end - pos < 2 + sizeof(struct ieee80211_vht_cap)) - goto out_err; - pos = ieee80211_ie_build_vht_cap(pos, &sband->vht_cap, - sband->vht_cap.cap); + u8 *pos; + + if (skb_tailroom(skb) < 2 + sizeof(struct ieee80211_vht_cap)) + return -ENOBUFS; + + pos = skb_put(skb, 2 + sizeof(struct ieee80211_vht_cap)); + ieee80211_ie_build_vht_cap(pos, &sband->vht_cap, + sband->vht_cap.cap); } /* insert custom IEs that go before HE */ @@ -2131,107 +1344,128 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, noffset = ieee80211_ie_split(ie, ie_len, before_he, ARRAY_SIZE(before_he), *offset); - if (end - pos < noffset - *offset) - goto out_err; - memcpy(pos, ie + *offset, noffset - *offset); - pos += noffset - *offset; + if (skb_tailroom(skb) < noffset - *offset) + return -ENOBUFS; + skb_put_data(skb, ie + *offset, noffset - *offset); *offset = noffset; } - he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); - if (he_cap && - cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band), + if (cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band), IEEE80211_CHAN_NO_HE)) { - pos = ieee80211_ie_build_he_cap(0, pos, he_cap, end); - if (!pos) - goto out_err; + err = ieee80211_put_he_cap(skb, sdata, sband, NULL); + if (err) + return err; } - eht_cap = ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif); - - if (eht_cap && - cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band), + if (cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band), IEEE80211_CHAN_NO_HE | IEEE80211_CHAN_NO_EHT)) { - pos = ieee80211_ie_build_eht_cap(pos, he_cap, eht_cap, end, - sdata->vif.type == NL80211_IFTYPE_AP); - if (!pos) - goto out_err; + err = ieee80211_put_eht_cap(skb, sdata, sband, NULL); + if (err) + return err; } - if (cfg80211_any_usable_channels(local->hw.wiphy, - BIT(NL80211_BAND_6GHZ), - IEEE80211_CHAN_NO_HE)) { - struct ieee80211_supported_band *sband6; - - sband6 = local->hw.wiphy->bands[NL80211_BAND_6GHZ]; - he_cap = ieee80211_get_he_iftype_cap_vif(sband6, &sdata->vif); - - if (he_cap) { - enum nl80211_iftype iftype = - ieee80211_vif_type_p2p(&sdata->vif); - __le16 cap = ieee80211_get_he_6ghz_capa(sband6, iftype); - - pos = ieee80211_write_he_6ghz_cap(pos, cap, end); - } - } + err = ieee80211_put_he_6ghz_cap(skb, sdata, IEEE80211_SMPS_OFF); + if (err) + return err; /* * If adding more here, adjust code in main.c * that calculates local->scan_ies_len. */ - return pos - buffer; - out_err: - WARN_ONCE(1, "not enough space for preq IEs\n"); - done: - return pos - buffer; + return 0; } -int ieee80211_build_preq_ies(struct ieee80211_sub_if_data *sdata, u8 *buffer, - size_t buffer_len, - struct ieee80211_scan_ies *ie_desc, - const u8 *ie, size_t ie_len, - u8 bands_used, u32 *rate_masks, - struct cfg80211_chan_def *chandef, - u32 flags) +static int ieee80211_put_preq_ies(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_scan_ies *ie_desc, + const u8 *ie, size_t ie_len, + u8 bands_used, u32 *rate_masks, + struct cfg80211_chan_def *chandef, + u32 flags) { - size_t pos = 0, old_pos = 0, custom_ie_offset = 0; - int i; + size_t custom_ie_offset = 0; + int i, err; memset(ie_desc, 0, sizeof(*ie_desc)); for (i = 0; i < NUM_NL80211_BANDS; i++) { if (bands_used & BIT(i)) { - pos += ieee80211_build_preq_ies_band(sdata, - buffer + pos, - buffer_len - pos, - ie, ie_len, i, - rate_masks[i], - chandef, - &custom_ie_offset, - flags); - ie_desc->ies[i] = buffer + old_pos; - ie_desc->len[i] = pos - old_pos; - old_pos = pos; + ie_desc->ies[i] = skb_tail_pointer(skb); + err = ieee80211_put_preq_ies_band(skb, sdata, + ie, ie_len, + &custom_ie_offset, + i, rate_masks[i], + chandef, flags); + if (err) + return err; + ie_desc->len[i] = skb_tail_pointer(skb) - + ie_desc->ies[i]; } } /* add any remaining custom IEs */ if (ie && ie_len) { - if (WARN_ONCE(buffer_len - pos < ie_len - custom_ie_offset, + if (WARN_ONCE(skb_tailroom(skb) < ie_len - custom_ie_offset, "not enough space for preq custom IEs\n")) - return pos; - memcpy(buffer + pos, ie + custom_ie_offset, - ie_len - custom_ie_offset); - ie_desc->common_ies = buffer + pos; - ie_desc->common_ie_len = ie_len - custom_ie_offset; - pos += ie_len - custom_ie_offset; + return -ENOBUFS; + ie_desc->common_ies = skb_tail_pointer(skb); + skb_put_data(skb, ie + custom_ie_offset, + ie_len - custom_ie_offset); + ie_desc->common_ie_len = skb_tail_pointer(skb) - + ie_desc->common_ies; } - return pos; + return 0; }; +int ieee80211_build_preq_ies(struct ieee80211_sub_if_data *sdata, u8 *buffer, + size_t buffer_len, + struct ieee80211_scan_ies *ie_desc, + const u8 *ie, size_t ie_len, + u8 bands_used, u32 *rate_masks, + struct cfg80211_chan_def *chandef, + u32 flags) +{ + struct sk_buff *skb = alloc_skb(buffer_len, GFP_KERNEL); + uintptr_t offs; + int ret, i; + u8 *start; + + if (!skb) + return -ENOMEM; + + start = skb_tail_pointer(skb); + memset(start, 0, skb_tailroom(skb)); + ret = ieee80211_put_preq_ies(skb, sdata, ie_desc, ie, ie_len, + bands_used, rate_masks, chandef, + flags); + if (ret < 0) { + goto out; + } + + if (skb->len > buffer_len) { + ret = -ENOBUFS; + goto out; + } + + memcpy(buffer, start, skb->len); + + /* adjust ie_desc for copy */ + for (i = 0; i < NUM_NL80211_BANDS; i++) { + offs = ie_desc->ies[i] - start; + ie_desc->ies[i] = buffer + offs; + } + offs = ie_desc->common_ies - start; + ie_desc->common_ies = buffer + offs; + + ret = skb->len; +out: + consume_skb(skb); + return ret; +} + struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, const u8 *src, const u8 *dst, u32 ratemask, @@ -2244,7 +1478,6 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, struct cfg80211_chan_def chandef; struct sk_buff *skb; struct ieee80211_mgmt *mgmt; - int ies_len; u32 rate_masks[NUM_NL80211_BANDS] = {}; struct ieee80211_scan_ies dummy_ie_desc; @@ -2253,7 +1486,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, * in order to maximize the chance that we get a response. Some * badly-behaved APs don't respond when this parameter is included. */ - chandef.width = sdata->vif.bss_conf.chandef.width; + chandef.width = sdata->vif.bss_conf.chanreq.oper.width; if (flags & IEEE80211_PROBE_FLAG_DIRECTED) chandef.chan = NULL; else @@ -2265,11 +1498,9 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, return NULL; rate_masks[chan->band] = ratemask; - ies_len = ieee80211_build_preq_ies(sdata, skb_tail_pointer(skb), - skb_tailroom(skb), &dummy_ie_desc, - ie, ie_len, BIT(chan->band), - rate_masks, &chandef, flags); - skb_put(skb, ies_len); + ieee80211_put_preq_ies(skb, sdata, &dummy_ie_desc, + ie, ie_len, BIT(chan->band), + rate_masks, &chandef, flags); if (dst) { mgmt = (struct ieee80211_mgmt *) skb->data; @@ -2295,7 +1526,8 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, if (WARN_ON(!sband)) return 1; - rate_flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chandef); + rate_flags = + ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chanreq.oper); num_rates = sband->n_bitrates; supp_rates = 0; @@ -2416,9 +1648,6 @@ static void ieee80211_assign_chanctx(struct ieee80211_local *local, lockdep_assert_wiphy(local->hw.wiphy); - if (!local->use_chanctx) - return; - conf = rcu_dereference_protected(link->conf->chanctx_conf, lockdep_is_held(&local->hw.wiphy->mtx)); if (conf) { @@ -2648,20 +1877,20 @@ int ieee80211_reconfig(struct ieee80211_local *local) } /* add channel contexts */ - if (local->use_chanctx) { - list_for_each_entry(ctx, &local->chanctx_list, list) - if (ctx->replace_state != - IEEE80211_CHANCTX_REPLACES_OTHER) - WARN_ON(drv_add_chanctx(local, ctx)); - - sdata = wiphy_dereference(local->hw.wiphy, - local->monitor_sdata); - if (sdata && ieee80211_sdata_running(sdata)) - ieee80211_assign_chanctx(local, sdata, &sdata->deflink); - } + list_for_each_entry(ctx, &local->chanctx_list, list) + if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) + WARN_ON(drv_add_chanctx(local, ctx)); + + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); + if (sdata && ieee80211_sdata_running(sdata)) + ieee80211_assign_chanctx(local, sdata, &sdata->deflink); /* reconfigure hardware */ - ieee80211_hw_config(local, ~0); + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_LISTEN_INTERVAL | + IEEE80211_CONF_CHANGE_MONITOR | + IEEE80211_CONF_CHANGE_PS | + IEEE80211_CONF_CHANGE_RETRY_LIMITS | + IEEE80211_CONF_CHANGE_IDLE); ieee80211_configure_filter(local); @@ -2706,8 +1935,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) for (link_id = 0; link_id < ARRAY_SIZE(sdata->vif.link_conf); link_id++) { - if (ieee80211_vif_is_mld(&sdata->vif) && - !(sdata->vif.active_links & BIT(link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link_id)) continue; link = sdata_dereference(sdata->link[link_id], sdata); @@ -2756,9 +1984,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) sdata->vif.bss_conf.protected_keep_alive) changed |= BSS_CHANGED_KEEP_ALIVE; - if (sdata->vif.bss_conf.eht_puncturing) - changed |= BSS_CHANGED_EHT_PUNCTURING; - ieee80211_bss_info_change_notify(sdata, changed); } else if (!WARN_ON(!link)) { @@ -3109,21 +2334,6 @@ size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset) return pos; } -u8 *ieee80211_ie_build_s1g_cap(u8 *pos, struct ieee80211_sta_s1g_cap *s1g_cap) -{ - *pos++ = WLAN_EID_S1G_CAPABILITIES; - *pos++ = sizeof(struct ieee80211_s1g_cap); - memset(pos, 0, sizeof(struct ieee80211_s1g_cap)); - - memcpy(pos, &s1g_cap->cap, sizeof(s1g_cap->cap)); - pos += sizeof(s1g_cap->cap); - - memcpy(pos, &s1g_cap->nss_mcs, sizeof(s1g_cap->nss_mcs)); - pos += sizeof(s1g_cap->nss_mcs); - - return pos; -} - u8 *ieee80211_ie_build_ht_cap(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, u16 cap) { @@ -3180,7 +2390,8 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap, return pos; } -u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) +/* this may return more than ieee80211_put_he_6ghz_cap() will need */ +u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata) { const struct ieee80211_sta_he_cap *he_cap; struct ieee80211_supported_band *sband; @@ -3190,7 +2401,7 @@ u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) if (!sband) return 0; - he_cap = ieee80211_get_he_iftype_cap(sband, iftype); + he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); if (!he_cap) return 0; @@ -3201,38 +2412,75 @@ u8 ieee80211_ie_len_he_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) he_cap->he_cap_elem.phy_cap_info); } -u8 *ieee80211_ie_build_he_cap(ieee80211_conn_flags_t disable_flags, u8 *pos, +static void +ieee80211_get_adjusted_he_cap(const struct ieee80211_conn_settings *conn, const struct ieee80211_sta_he_cap *he_cap, - u8 *end) + struct ieee80211_he_cap_elem *elem) { - struct ieee80211_he_cap_elem elem; - u8 n; - u8 ie_len; - u8 *orig_pos = pos; + u8 ru_limit, max_ru; - /* Make sure we have place for the IE */ - /* - * TODO: the 1 added is because this temporarily is under the EXTENSION - * IE. Get rid of it when it moves. - */ - if (!he_cap) - return orig_pos; + *elem = he_cap->he_cap_elem; - /* modify on stack first to calculate 'n' and 'ie_len' correctly */ - elem = he_cap->he_cap_elem; + switch (conn->bw_limit) { + case IEEE80211_CONN_BW_LIMIT_20: + ru_limit = IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242; + break; + case IEEE80211_CONN_BW_LIMIT_40: + ru_limit = IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_484; + break; + case IEEE80211_CONN_BW_LIMIT_80: + ru_limit = IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_996; + break; + default: + ru_limit = IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996; + break; + } + + max_ru = elem->phy_cap_info[8] & IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK; + max_ru = min(max_ru, ru_limit); + elem->phy_cap_info[8] &= ~IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK; + elem->phy_cap_info[8] |= max_ru; - if (disable_flags & IEEE80211_CONN_DISABLE_40MHZ) - elem.phy_cap_info[0] &= + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_40) { + elem->phy_cap_info[0] &= ~(IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G); + elem->phy_cap_info[9] &= + ~IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM; + } + + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_160) { + elem->phy_cap_info[0] &= + ~(IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G); + elem->phy_cap_info[5] &= + ~IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK; + elem->phy_cap_info[7] &= + ~(IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ | + IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ); + } +} - if (disable_flags & IEEE80211_CONN_DISABLE_160MHZ) - elem.phy_cap_info[0] &= - ~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; +int ieee80211_put_he_cap(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata, + const struct ieee80211_supported_band *sband, + const struct ieee80211_conn_settings *conn) +{ + const struct ieee80211_sta_he_cap *he_cap; + struct ieee80211_he_cap_elem elem; + u8 *len; + u8 n; + u8 ie_len; - if (disable_flags & IEEE80211_CONN_DISABLE_80P80MHZ) - elem.phy_cap_info[0] &= - ~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G; + if (!conn) + conn = &ieee80211_conn_settings_unlimited; + + he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); + if (!he_cap) + return 0; + + /* modify on stack first to calculate 'n' and 'ie_len' correctly */ + ieee80211_get_adjusted_he_cap(conn, he_cap, &elem); n = ieee80211_he_mcs_nss_size(&elem); ie_len = 2 + 1 + @@ -3240,19 +2488,17 @@ u8 *ieee80211_ie_build_he_cap(ieee80211_conn_flags_t disable_flags, u8 *pos, ieee80211_he_ppe_size(he_cap->ppe_thres[0], he_cap->he_cap_elem.phy_cap_info); - if ((end - pos) < ie_len) - return orig_pos; + if (skb_tailroom(skb) < ie_len) + return -ENOBUFS; - *pos++ = WLAN_EID_EXTENSION; - pos++; /* We'll set the size later below */ - *pos++ = WLAN_EID_EXT_HE_CAPABILITY; + skb_put_u8(skb, WLAN_EID_EXTENSION); + len = skb_put(skb, 1); /* We'll set the size later below */ + skb_put_u8(skb, WLAN_EID_EXT_HE_CAPABILITY); /* Fixed data */ - memcpy(pos, &elem, sizeof(elem)); - pos += sizeof(elem); + skb_put_data(skb, &elem, sizeof(elem)); - memcpy(pos, &he_cap->he_mcs_nss_supp, n); - pos += n; + skb_put_data(skb, &he_cap->he_mcs_nss_supp, n); /* Check if PPE Threshold should be present */ if ((he_cap->he_cap_elem.phy_cap_info[6] & @@ -3276,41 +2522,39 @@ u8 *ieee80211_ie_build_he_cap(ieee80211_conn_flags_t disable_flags, u8 *pos, n = DIV_ROUND_UP(n, 8); /* Copy PPE Thresholds */ - memcpy(pos, &he_cap->ppe_thres, n); - pos += n; + skb_put_data(skb, &he_cap->ppe_thres, n); end: - orig_pos[1] = (pos - orig_pos) - 2; - return pos; + *len = skb_tail_pointer(skb) - len - 1; + return 0; } -void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, - enum ieee80211_smps_mode smps_mode, - struct sk_buff *skb) +int ieee80211_put_he_6ghz_cap(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata, + enum ieee80211_smps_mode smps_mode) { struct ieee80211_supported_band *sband; const struct ieee80211_sband_iftype_data *iftd; enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); - u8 *pos; - u16 cap; + __le16 cap; if (!cfg80211_any_usable_channels(sdata->local->hw.wiphy, BIT(NL80211_BAND_6GHZ), IEEE80211_CHAN_NO_HE)) - return; + return 0; sband = sdata->local->hw.wiphy->bands[NL80211_BAND_6GHZ]; iftd = ieee80211_get_sband_iftype_data(sband, iftype); if (!iftd) - return; + return 0; /* Check for device HE 6 GHz capability before adding element */ if (!iftd->he_6ghz_capa.capa) - return; + return 0; - cap = le16_to_cpu(iftd->he_6ghz_capa.capa); - cap &= ~IEEE80211_HE_6GHZ_CAP_SM_PS; + cap = iftd->he_6ghz_capa.capa; + cap &= cpu_to_le16(~IEEE80211_HE_6GHZ_CAP_SM_PS); switch (smps_mode) { case IEEE80211_SMPS_AUTOMATIC: @@ -3318,22 +2562,27 @@ void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, WARN_ON(1); fallthrough; case IEEE80211_SMPS_OFF: - cap |= u16_encode_bits(WLAN_HT_CAP_SM_PS_DISABLED, - IEEE80211_HE_6GHZ_CAP_SM_PS); + cap |= le16_encode_bits(WLAN_HT_CAP_SM_PS_DISABLED, + IEEE80211_HE_6GHZ_CAP_SM_PS); break; case IEEE80211_SMPS_STATIC: - cap |= u16_encode_bits(WLAN_HT_CAP_SM_PS_STATIC, - IEEE80211_HE_6GHZ_CAP_SM_PS); + cap |= le16_encode_bits(WLAN_HT_CAP_SM_PS_STATIC, + IEEE80211_HE_6GHZ_CAP_SM_PS); break; case IEEE80211_SMPS_DYNAMIC: - cap |= u16_encode_bits(WLAN_HT_CAP_SM_PS_DYNAMIC, - IEEE80211_HE_6GHZ_CAP_SM_PS); + cap |= le16_encode_bits(WLAN_HT_CAP_SM_PS_DYNAMIC, + IEEE80211_HE_6GHZ_CAP_SM_PS); break; } - pos = skb_put(skb, 2 + 1 + sizeof(cap)); - ieee80211_write_he_6ghz_cap(pos, cpu_to_le16(cap), - pos + 2 + 1 + sizeof(cap)); + if (skb_tailroom(skb) < 2 + 1 + sizeof(cap)) + return -ENOBUFS; + + skb_put_u8(skb, WLAN_EID_EXTENSION); + skb_put_u8(skb, 1 + sizeof(cap)); + skb_put_u8(skb, WLAN_EID_EXT_HE_6GHZ_CAPA); + skb_put_data(skb, &cap, sizeof(cap)); + return 0; } u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap, @@ -3785,7 +3034,6 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, u32 vht_cap_info, } void ieee80211_chandef_eht_oper(const struct ieee80211_eht_operation_info *info, - bool support_160, bool support_320, struct cfg80211_chan_def *chandef) { chandef->center_freq1 = @@ -3804,90 +3052,38 @@ void ieee80211_chandef_eht_oper(const struct ieee80211_eht_operation_info *info, chandef->width = NL80211_CHAN_WIDTH_80; break; case IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ: - if (support_160) { - chandef->width = NL80211_CHAN_WIDTH_160; - chandef->center_freq1 = - ieee80211_channel_to_frequency(info->ccfs1, - chandef->chan->band); - } else { - chandef->width = NL80211_CHAN_WIDTH_80; - } + chandef->width = NL80211_CHAN_WIDTH_160; + chandef->center_freq1 = + ieee80211_channel_to_frequency(info->ccfs1, + chandef->chan->band); break; case IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ: - if (support_320) { - chandef->width = NL80211_CHAN_WIDTH_320; - chandef->center_freq1 = - ieee80211_channel_to_frequency(info->ccfs1, - chandef->chan->band); - } else if (support_160) { - chandef->width = NL80211_CHAN_WIDTH_160; - } else { - chandef->width = NL80211_CHAN_WIDTH_80; - - if (chandef->center_freq1 > chandef->chan->center_freq) - chandef->center_freq1 -= 40; - else - chandef->center_freq1 += 40; - } + chandef->width = NL80211_CHAN_WIDTH_320; + chandef->center_freq1 = + ieee80211_channel_to_frequency(info->ccfs1, + chandef->chan->band); break; } } -bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, +bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_local *local, const struct ieee80211_he_operation *he_oper, const struct ieee80211_eht_operation *eht_oper, struct cfg80211_chan_def *chandef) { - struct ieee80211_local *local = sdata->local; - struct ieee80211_supported_band *sband; - enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); - const struct ieee80211_sta_he_cap *he_cap; - const struct ieee80211_sta_eht_cap *eht_cap; struct cfg80211_chan_def he_chandef = *chandef; const struct ieee80211_he_6ghz_oper *he_6ghz_oper; - struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; - bool support_80_80, support_160, support_320; - u8 he_phy_cap, eht_phy_cap; u32 freq; if (chandef->chan->band != NL80211_BAND_6GHZ) return true; - sband = local->hw.wiphy->bands[NL80211_BAND_6GHZ]; - - he_cap = ieee80211_get_he_iftype_cap(sband, iftype); - if (!he_cap) { - sdata_info(sdata, "Missing iftype sband data/HE cap"); - return false; - } - - he_phy_cap = he_cap->he_cap_elem.phy_cap_info[0]; - support_160 = - he_phy_cap & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; - support_80_80 = - he_phy_cap & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G; - - if (!he_oper) { - sdata_info(sdata, - "HE is not advertised on (on %d MHz), expect issues\n", - chandef->chan->center_freq); + if (!he_oper) return false; - } - - eht_cap = ieee80211_get_eht_iftype_cap(sband, iftype); - if (!eht_cap) - eht_oper = NULL; he_6ghz_oper = ieee80211_he_6ghz_oper(he_oper); - - if (!he_6ghz_oper) { - sdata_info(sdata, - "HE 6GHz operation missing (on %d MHz), expect issues\n", - chandef->chan->center_freq); + if (!he_6ghz_oper) return false; - } /* * The EHT operation IE does not contain the primary channel so the @@ -3896,20 +3092,10 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, */ freq = ieee80211_channel_to_frequency(he_6ghz_oper->primary, NL80211_BAND_6GHZ); - he_chandef.chan = ieee80211_get_channel(sdata->local->hw.wiphy, freq); + he_chandef.chan = ieee80211_get_channel(local->hw.wiphy, freq); - switch (u8_get_bits(he_6ghz_oper->control, - IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { - case IEEE80211_6GHZ_CTRL_REG_LPI_AP: - bss_conf->power_type = IEEE80211_REG_LPI_AP; - break; - case IEEE80211_6GHZ_CTRL_REG_SP_AP: - bss_conf->power_type = IEEE80211_REG_SP_AP; - break; - default: - bss_conf->power_type = IEEE80211_REG_UNSET_AP; - break; - } + if (!he_chandef.chan) + return false; if (!eht_oper || !(eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT)) { @@ -3928,13 +3114,10 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, he_chandef.width = NL80211_CHAN_WIDTH_80; if (!he_6ghz_oper->ccfs1) break; - if (abs(he_6ghz_oper->ccfs1 - he_6ghz_oper->ccfs0) == 8) { - if (support_160) - he_chandef.width = NL80211_CHAN_WIDTH_160; - } else { - if (support_80_80) - he_chandef.width = NL80211_CHAN_WIDTH_80P80; - } + if (abs(he_6ghz_oper->ccfs1 - he_6ghz_oper->ccfs0) == 8) + he_chandef.width = NL80211_CHAN_WIDTH_160; + else + he_chandef.width = NL80211_CHAN_WIDTH_80P80; break; } @@ -3946,30 +3129,17 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, he_chandef.center_freq1 = ieee80211_channel_to_frequency(he_6ghz_oper->ccfs0, NL80211_BAND_6GHZ); - if (support_80_80 || support_160) - he_chandef.center_freq2 = - ieee80211_channel_to_frequency(he_6ghz_oper->ccfs1, - NL80211_BAND_6GHZ); + he_chandef.center_freq2 = + ieee80211_channel_to_frequency(he_6ghz_oper->ccfs1, + NL80211_BAND_6GHZ); } } else { - eht_phy_cap = eht_cap->eht_cap_elem.phy_cap_info[0]; - support_320 = - eht_phy_cap & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ; - ieee80211_chandef_eht_oper((const void *)eht_oper->optional, - support_160, support_320, &he_chandef); } - if (!cfg80211_chandef_valid(&he_chandef)) { - sdata_info(sdata, - "HE 6GHz operation resulted in invalid chandef: %d MHz/%d/%d MHz/%d MHz\n", - he_chandef.chan ? he_chandef.chan->center_freq : 0, - he_chandef.width, - he_chandef.center_freq1, - he_chandef.center_freq2); + if (!cfg80211_chandef_valid(&he_chandef)) return false; - } *chandef = he_chandef; @@ -4012,121 +3182,62 @@ bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper, return true; } -int ieee80211_parse_bitrates(enum nl80211_chan_width width, - const struct ieee80211_supported_band *sband, - const u8 *srates, int srates_len, u32 *rates) -{ - u32 rate_flags = ieee80211_chanwidth_rate_flags(width); - struct ieee80211_rate *br; - int brate, rate, i, j, count = 0; - - *rates = 0; - - for (i = 0; i < srates_len; i++) { - rate = srates[i] & 0x7f; - - for (j = 0; j < sband->n_bitrates; j++) { - br = &sband->bitrates[j]; - if ((rate_flags & br->flags) != rate_flags) - continue; - - brate = DIV_ROUND_UP(br->bitrate, 5); - if (brate == rate) { - *rates |= BIT(j); - count++; - break; - } - } - } - return count; -} - -int ieee80211_add_srates_ie(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, bool need_basic, - enum nl80211_band band) +int ieee80211_put_srates_elem(struct sk_buff *skb, + const struct ieee80211_supported_band *sband, + u32 basic_rates, u32 rate_flags, u32 masked_rates, + u8 element_id) { - struct ieee80211_local *local = sdata->local; - struct ieee80211_supported_band *sband; - int rate; - u8 i, rates, *pos; - u32 basic_rates = sdata->vif.bss_conf.basic_rates; - u32 rate_flags; + u8 i, rates, skip; - rate_flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chandef); - sband = local->hw.wiphy->bands[band]; rates = 0; for (i = 0; i < sband->n_bitrates; i++) { if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; + if (masked_rates & BIT(i)) + continue; rates++; } - if (rates > 8) - rates = 8; - - if (skb_tailroom(skb) < rates + 2) - return -ENOMEM; - - pos = skb_put(skb, rates + 2); - *pos++ = WLAN_EID_SUPP_RATES; - *pos++ = rates; - for (i = 0; i < rates; i++) { - u8 basic = 0; - if ((rate_flags & sband->bitrates[i].flags) != rate_flags) - continue; - if (need_basic && basic_rates & BIT(i)) - basic = 0x80; - rate = DIV_ROUND_UP(sband->bitrates[i].bitrate, 5); - *pos++ = basic | (u8) rate; + if (element_id == WLAN_EID_SUPP_RATES) { + rates = min_t(u8, rates, 8); + skip = 0; + } else { + skip = 8; + if (rates <= skip) + return 0; + rates -= skip; } - return 0; -} + if (skb_tailroom(skb) < rates + 2) + return -ENOBUFS; -int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, bool need_basic, - enum nl80211_band band) -{ - struct ieee80211_local *local = sdata->local; - struct ieee80211_supported_band *sband; - int rate; - u8 i, exrates, *pos; - u32 basic_rates = sdata->vif.bss_conf.basic_rates; - u32 rate_flags; + skb_put_u8(skb, element_id); + skb_put_u8(skb, rates); - rate_flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chandef); + for (i = 0; i < sband->n_bitrates && rates; i++) { + int rate; + u8 basic; - sband = local->hw.wiphy->bands[band]; - exrates = 0; - for (i = 0; i < sband->n_bitrates; i++) { if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; - exrates++; - } + if (masked_rates & BIT(i)) + continue; - if (exrates > 8) - exrates -= 8; - else - exrates = 0; + if (skip > 0) { + skip--; + continue; + } - if (skb_tailroom(skb) < exrates + 2) - return -ENOMEM; + basic = basic_rates & BIT(i) ? 0x80 : 0; - if (exrates) { - pos = skb_put(skb, exrates + 2); - *pos++ = WLAN_EID_EXT_SUPP_RATES; - *pos++ = exrates; - for (i = 8; i < sband->n_bitrates; i++) { - u8 basic = 0; - if ((rate_flags & sband->bitrates[i].flags) - != rate_flags) - continue; - if (need_basic && basic_rates & BIT(i)) - basic = 0x80; - rate = DIV_ROUND_UP(sband->bitrates[i].bitrate, 5); - *pos++ = basic | (u8) rate; - } + rate = DIV_ROUND_UP(sband->bitrates[i].bitrate, 5); + skb_put_u8(skb, basic | (u8)rate); + rates--; } + + WARN(rates > 0, "rates confused: rates:%d, element:%d\n", + rates, element_id); + return 0; } @@ -4338,7 +3449,7 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local) &sdata->deflink.dfs_cac_timer_work); if (sdata->wdev.cac_started) { - chandef = sdata->vif.bss_conf.chandef; + chandef = sdata->vif.bss_conf.chanreq.oper; ieee80211_link_release_channel(&sdata->deflink); cfg80211_cac_event(sdata->dev, &chandef, @@ -4386,78 +3497,92 @@ void ieee80211_radar_detected(struct ieee80211_hw *hw) } EXPORT_SYMBOL(ieee80211_radar_detected); -ieee80211_conn_flags_t ieee80211_chandef_downgrade(struct cfg80211_chan_def *c) +void ieee80211_chandef_downgrade(struct cfg80211_chan_def *c, + struct ieee80211_conn_settings *conn) { - ieee80211_conn_flags_t ret; - int tmp; + enum nl80211_chan_width new_primary_width; + struct ieee80211_conn_settings _ignored = {}; + + /* allow passing NULL if caller doesn't care */ + if (!conn) + conn = &_ignored; + +again: + /* no-HT indicates nothing to do */ + new_primary_width = NL80211_CHAN_WIDTH_20_NOHT; switch (c->width) { + default: + case NL80211_CHAN_WIDTH_20_NOHT: + WARN_ON_ONCE(1); + fallthrough; case NL80211_CHAN_WIDTH_20: c->width = NL80211_CHAN_WIDTH_20_NOHT; - ret = IEEE80211_CONN_DISABLE_HT | IEEE80211_CONN_DISABLE_VHT; + conn->mode = IEEE80211_CONN_MODE_LEGACY; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_20; + c->punctured = 0; break; case NL80211_CHAN_WIDTH_40: c->width = NL80211_CHAN_WIDTH_20; c->center_freq1 = c->chan->center_freq; - ret = IEEE80211_CONN_DISABLE_40MHZ | - IEEE80211_CONN_DISABLE_VHT; + if (conn->mode == IEEE80211_CONN_MODE_VHT) + conn->mode = IEEE80211_CONN_MODE_HT; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_20; + c->punctured = 0; break; case NL80211_CHAN_WIDTH_80: - tmp = (30 + c->chan->center_freq - c->center_freq1)/20; - /* n_P40 */ - tmp /= 2; - /* freq_P40 */ - c->center_freq1 = c->center_freq1 - 20 + 40 * tmp; - c->width = NL80211_CHAN_WIDTH_40; - ret = IEEE80211_CONN_DISABLE_VHT; + new_primary_width = NL80211_CHAN_WIDTH_40; + if (conn->mode == IEEE80211_CONN_MODE_VHT) + conn->mode = IEEE80211_CONN_MODE_HT; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_40; break; case NL80211_CHAN_WIDTH_80P80: c->center_freq2 = 0; c->width = NL80211_CHAN_WIDTH_80; - ret = IEEE80211_CONN_DISABLE_80P80MHZ | - IEEE80211_CONN_DISABLE_160MHZ; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_80; break; case NL80211_CHAN_WIDTH_160: - /* n_P20 */ - tmp = (70 + c->chan->center_freq - c->center_freq1)/20; - /* n_P80 */ - tmp /= 4; - c->center_freq1 = c->center_freq1 - 40 + 80 * tmp; - c->width = NL80211_CHAN_WIDTH_80; - ret = IEEE80211_CONN_DISABLE_80P80MHZ | - IEEE80211_CONN_DISABLE_160MHZ; + new_primary_width = NL80211_CHAN_WIDTH_80; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_80; break; case NL80211_CHAN_WIDTH_320: - /* n_P20 */ - tmp = (150 + c->chan->center_freq - c->center_freq1) / 20; - /* n_P160 */ - tmp /= 8; - c->center_freq1 = c->center_freq1 - 80 + 160 * tmp; - c->width = NL80211_CHAN_WIDTH_160; - ret = IEEE80211_CONN_DISABLE_320MHZ; - break; - default: - case NL80211_CHAN_WIDTH_20_NOHT: - WARN_ON_ONCE(1); - c->width = NL80211_CHAN_WIDTH_20_NOHT; - ret = IEEE80211_CONN_DISABLE_HT | IEEE80211_CONN_DISABLE_VHT; + new_primary_width = NL80211_CHAN_WIDTH_160; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_160; break; case NL80211_CHAN_WIDTH_1: case NL80211_CHAN_WIDTH_2: case NL80211_CHAN_WIDTH_4: case NL80211_CHAN_WIDTH_8: case NL80211_CHAN_WIDTH_16: + WARN_ON_ONCE(1); + /* keep c->width */ + conn->mode = IEEE80211_CONN_MODE_S1G; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_20; + break; case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: WARN_ON_ONCE(1); /* keep c->width */ - ret = IEEE80211_CONN_DISABLE_HT | IEEE80211_CONN_DISABLE_VHT; + conn->mode = IEEE80211_CONN_MODE_LEGACY; + conn->bw_limit = IEEE80211_CONN_BW_LIMIT_20; break; } - WARN_ON_ONCE(!cfg80211_chandef_valid(c)); + if (new_primary_width != NL80211_CHAN_WIDTH_20_NOHT) { + c->center_freq1 = cfg80211_chandef_primary(c, new_primary_width, + &c->punctured); + c->width = new_primary_width; + } - return ret; + /* + * With an 80 MHz channel, we might have the puncturing in the primary + * 40 Mhz channel, but that's not valid when downgraded to 40 MHz width. + * In that case, downgrade again. + */ + if (!cfg80211_chandef_valid(c) && c->punctured) + goto again; + + WARN_ON_ONCE(!cfg80211_chandef_valid(c)); } /* @@ -4773,7 +3898,7 @@ static u8 ieee80211_chanctx_radar_detect(struct ieee80211_local *local, list_for_each_entry(link, &ctx->reserved_links, reserved_chanctx_list) if (link->reserved_radar_required) - radar_detect |= BIT(link->reserved_chandef.width); + radar_detect |= BIT(link->reserved.oper.width); /* * An in-place reservation context should not have any assigned vifs @@ -4787,7 +3912,7 @@ static u8 ieee80211_chanctx_radar_detect(struct ieee80211_local *local, continue; radar_detect |= - BIT(link->conf->chandef.width); + BIT(link->conf->chanreq.oper.width); } return radar_detect; @@ -5037,7 +4162,8 @@ u16 ieee80211_encode_usf(int listen_interval) return (u16) listen_interval; } -u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) +/* this may return more than ieee80211_put_eht_cap() will need */ +u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata) { const struct ieee80211_sta_he_cap *he_cap; const struct ieee80211_sta_eht_cap *eht_cap; @@ -5049,13 +4175,12 @@ u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) if (!sband) return 0; - he_cap = ieee80211_get_he_iftype_cap(sband, iftype); - eht_cap = ieee80211_get_eht_iftype_cap(sband, iftype); + he_cap = ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); + eht_cap = ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif); if (!he_cap || !eht_cap) return 0; - is_ap = iftype == NL80211_IFTYPE_AP || - iftype == NL80211_IFTYPE_P2P_GO; + is_ap = sdata->vif.type == NL80211_IFTYPE_AP; n = ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem, &eht_cap->eht_cap_elem, @@ -5067,45 +4192,134 @@ u8 ieee80211_ie_len_eht_cap(struct ieee80211_sub_if_data *sdata, u8 iftype) return 0; } -u8 *ieee80211_ie_build_eht_cap(u8 *pos, - const struct ieee80211_sta_he_cap *he_cap, - const struct ieee80211_sta_eht_cap *eht_cap, - u8 *end, - bool for_ap) +int ieee80211_put_eht_cap(struct sk_buff *skb, + struct ieee80211_sub_if_data *sdata, + const struct ieee80211_supported_band *sband, + const struct ieee80211_conn_settings *conn) { + const struct ieee80211_sta_he_cap *he_cap = + ieee80211_get_he_iftype_cap_vif(sband, &sdata->vif); + const struct ieee80211_sta_eht_cap *eht_cap = + ieee80211_get_eht_iftype_cap_vif(sband, &sdata->vif); + bool for_ap = sdata->vif.type == NL80211_IFTYPE_AP; + struct ieee80211_eht_cap_elem_fixed fixed; + struct ieee80211_he_cap_elem he; u8 mcs_nss_len, ppet_len; + u8 orig_mcs_nss_len; u8 ie_len; - u8 *orig_pos = pos; + + if (!conn) + conn = &ieee80211_conn_settings_unlimited; /* Make sure we have place for the IE */ if (!he_cap || !eht_cap) - return orig_pos; + return 0; + + orig_mcs_nss_len = ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem, + &eht_cap->eht_cap_elem, + for_ap); - mcs_nss_len = ieee80211_eht_mcs_nss_size(&he_cap->he_cap_elem, - &eht_cap->eht_cap_elem, - for_ap); + ieee80211_get_adjusted_he_cap(conn, he_cap, &he); + + fixed = eht_cap->eht_cap_elem; + + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_80) + fixed.phy_cap_info[6] &= + ~IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_80MHZ; + + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_160) { + fixed.phy_cap_info[1] &= + ~IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK; + fixed.phy_cap_info[2] &= + ~IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK; + fixed.phy_cap_info[6] &= + ~IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_160MHZ; + } + + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_320) { + fixed.phy_cap_info[0] &= + ~IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ; + fixed.phy_cap_info[1] &= + ~IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK; + fixed.phy_cap_info[2] &= + ~IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK; + fixed.phy_cap_info[6] &= + ~IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_320MHZ; + } + + if (conn->bw_limit == IEEE80211_CONN_BW_LIMIT_20) + fixed.phy_cap_info[0] &= + ~IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ; + + mcs_nss_len = ieee80211_eht_mcs_nss_size(&he, &fixed, for_ap); ppet_len = ieee80211_eht_ppe_size(eht_cap->eht_ppe_thres[0], - eht_cap->eht_cap_elem.phy_cap_info); + fixed.phy_cap_info); ie_len = 2 + 1 + sizeof(eht_cap->eht_cap_elem) + mcs_nss_len + ppet_len; - if ((end - pos) < ie_len) - return orig_pos; + if (skb_tailroom(skb) < ie_len) + return -ENOBUFS; - *pos++ = WLAN_EID_EXTENSION; - *pos++ = ie_len - 2; - *pos++ = WLAN_EID_EXT_EHT_CAPABILITY; + skb_put_u8(skb, WLAN_EID_EXTENSION); + skb_put_u8(skb, ie_len - 2); + skb_put_u8(skb, WLAN_EID_EXT_EHT_CAPABILITY); + skb_put_data(skb, &fixed, sizeof(fixed)); - /* Fixed data */ - memcpy(pos, &eht_cap->eht_cap_elem, sizeof(eht_cap->eht_cap_elem)); - pos += sizeof(eht_cap->eht_cap_elem); + if (mcs_nss_len == 4 && orig_mcs_nss_len != 4) { + /* + * If the (non-AP) STA became 20 MHz only, then convert from + * <=80 to 20-MHz-only format, where MCSes are indicated in + * the groups 0-7, 8-9, 10-11, 12-13 rather than just 0-9, + * 10-11, 12-13. Thus, use 0-9 for 0-7 and 8-9. + */ + skb_put_u8(skb, eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_mcs9_max_nss); + skb_put_u8(skb, eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_mcs9_max_nss); + skb_put_u8(skb, eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_mcs11_max_nss); + skb_put_u8(skb, eht_cap->eht_mcs_nss_supp.bw._80.rx_tx_mcs13_max_nss); + } else { + skb_put_data(skb, &eht_cap->eht_mcs_nss_supp, mcs_nss_len); + } - memcpy(pos, &eht_cap->eht_mcs_nss_supp, mcs_nss_len); - pos += mcs_nss_len; + if (ppet_len) + skb_put_data(skb, &eht_cap->eht_ppe_thres, ppet_len); - if (ppet_len) { - memcpy(pos, &eht_cap->eht_ppe_thres, ppet_len); - pos += ppet_len; - } + return 0; +} - return pos; +const char *ieee80211_conn_mode_str(enum ieee80211_conn_mode mode) +{ + static const char * const modes[] = { + [IEEE80211_CONN_MODE_S1G] = "S1G", + [IEEE80211_CONN_MODE_LEGACY] = "legacy", + [IEEE80211_CONN_MODE_HT] = "HT", + [IEEE80211_CONN_MODE_VHT] = "VHT", + [IEEE80211_CONN_MODE_HE] = "HE", + [IEEE80211_CONN_MODE_EHT] = "EHT", + }; + + if (WARN_ON(mode >= ARRAY_SIZE(modes))) + return "<out of range>"; + + return modes[mode] ?: "<missing string>"; +} + +enum ieee80211_conn_bw_limit +ieee80211_min_bw_limit_from_chandef(struct cfg80211_chan_def *chandef) +{ + switch (chandef->width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + return IEEE80211_CONN_BW_LIMIT_20; + case NL80211_CHAN_WIDTH_40: + return IEEE80211_CONN_BW_LIMIT_40; + case NL80211_CHAN_WIDTH_80: + return IEEE80211_CONN_BW_LIMIT_80; + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + return IEEE80211_CONN_BW_LIMIT_160; + case NL80211_CHAN_WIDTH_320: + return IEEE80211_CONN_BW_LIMIT_320; + default: + WARN(1, "unhandled chandef width %d\n", chandef->width); + return IEEE80211_CONN_BW_LIMIT_20; + } } diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index b3a5c3e96a72..642891cafbaf 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -4,7 +4,7 @@ * * Portions of this file * Copyright(c) 2015 - 2016 Intel Deutschland GmbH - * Copyright (C) 2018 - 2023 Intel Corporation + * Copyright (C) 2018 - 2024 Intel Corporation */ #include <linux/ieee80211.h> @@ -369,7 +369,7 @@ ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta) link_conf = rcu_dereference(sdata->vif.link_conf[link_id]); if (eht_cap->has_eht && - link_conf->chandef.chan->band == NL80211_BAND_6GHZ) { + link_conf->chanreq.oper.chan->band == NL80211_BAND_6GHZ) { info = eht_cap->eht_cap_elem.phy_cap_info[0]; if (info & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) { @@ -380,7 +380,7 @@ ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta) info = he_cap->he_cap_elem.phy_cap_info[0]; - if (link_conf->chandef.chan->band == NL80211_BAND_2GHZ) { + if (link_conf->chanreq.oper.chan->band == NL80211_BAND_2GHZ) { if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) ret = IEEE80211_STA_RX_BW_40; else @@ -515,7 +515,7 @@ ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta) if (WARN_ON(!link_conf)) bss_width = NL80211_CHAN_WIDTH_20_NOHT; else - bss_width = link_conf->chandef.width; + bss_width = link_conf->chanreq.oper.width; rcu_read_unlock(); bw = ieee80211_sta_cap_rx_bw(link_sta); @@ -541,15 +541,11 @@ ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta) return bw; } -void ieee80211_sta_set_rx_nss(struct link_sta_info *link_sta) +void ieee80211_sta_init_nss(struct link_sta_info *link_sta) { u8 ht_rx_nss = 0, vht_rx_nss = 0, he_rx_nss = 0, eht_rx_nss = 0, rx_nss; bool support_160; - /* if we received a notification already don't overwrite it */ - if (link_sta->pub->rx_nss) - return; - if (link_sta->pub->eht_cap.has_eht) { int i; const u8 *rx_nss_mcs = (void *)&link_sta->pub->eht_cap.eht_mcs_nss_supp; @@ -627,7 +623,15 @@ void ieee80211_sta_set_rx_nss(struct link_sta_info *link_sta) rx_nss = max(vht_rx_nss, ht_rx_nss); rx_nss = max(he_rx_nss, rx_nss); rx_nss = max(eht_rx_nss, rx_nss); - link_sta->pub->rx_nss = max_t(u8, 1, rx_nss); + rx_nss = max_t(u8, 1, rx_nss); + link_sta->capa_nss = rx_nss; + + /* that shouldn't be set yet, but we can handle it anyway */ + if (link_sta->op_mode_nss) + link_sta->pub->rx_nss = + min_t(u8, rx_nss, link_sta->op_mode_nss); + else + link_sta->pub->rx_nss = rx_nss; } u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, @@ -637,7 +641,7 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, enum ieee80211_sta_rx_bandwidth new_bw; struct sta_opmode_info sta_opmode = {}; u32 changed = 0; - u8 nss, cur_nss; + u8 nss; /* ignore - no support for BF yet */ if (opmode & IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF) @@ -647,23 +651,17 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, nss >>= IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT; nss += 1; - if (link_sta->pub->rx_nss != nss) { - cur_nss = link_sta->pub->rx_nss; - /* Reset rx_nss and call ieee80211_sta_set_rx_nss() which - * will set the same to max nss value calculated based on capability. - */ - link_sta->pub->rx_nss = 0; - ieee80211_sta_set_rx_nss(link_sta); - /* Do not allow an nss change to rx_nss greater than max_nss - * negotiated and capped to APs capability during association. - */ - if (nss <= link_sta->pub->rx_nss) { - link_sta->pub->rx_nss = nss; - sta_opmode.rx_nss = nss; - changed |= IEEE80211_RC_NSS_CHANGED; - sta_opmode.changed |= STA_OPMODE_N_SS_CHANGED; + if (link_sta->op_mode_nss != nss) { + if (nss <= link_sta->capa_nss) { + link_sta->op_mode_nss = nss; + + if (nss != link_sta->pub->rx_nss) { + link_sta->pub->rx_nss = nss; + changed |= IEEE80211_RC_NSS_CHANGED; + sta_opmode.rx_nss = link_sta->pub->rx_nss; + sta_opmode.changed |= STA_OPMODE_N_SS_CHANGED; + } } else { - link_sta->pub->rx_nss = cur_nss; pr_warn_ratelimited("Ignoring NSS change in VHT Operating Mode Notification from %pM with invalid nss %d", link_sta->pub->addr, nss); } diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 94dae7cb6dbd..e40529b8c5c9 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -315,7 +315,7 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) * Calculate AAD for CCMP/GCMP, returning qos_tid since we * need that in CCMP also for b_0. */ -static u8 ccmp_gcmp_aad(struct sk_buff *skb, u8 *aad) +static u8 ccmp_gcmp_aad(struct sk_buff *skb, u8 *aad, bool spp_amsdu) { struct ieee80211_hdr *hdr = (void *)skb->data; __le16 mask_fc; @@ -340,7 +340,14 @@ static u8 ccmp_gcmp_aad(struct sk_buff *skb, u8 *aad) len_a += 6; if (ieee80211_is_data_qos(hdr->frame_control)) { - qos_tid = ieee80211_get_tid(hdr); + qos_tid = *ieee80211_get_qos_ctl(hdr); + + if (spp_amsdu) + qos_tid &= IEEE80211_QOS_CTL_TID_MASK | + IEEE80211_QOS_CTL_A_MSDU_PRESENT; + else + qos_tid &= IEEE80211_QOS_CTL_TID_MASK; + mask_fc &= ~cpu_to_le16(IEEE80211_FCTL_ORDER); len_a += 2; } else { @@ -369,10 +376,11 @@ static u8 ccmp_gcmp_aad(struct sk_buff *skb, u8 *aad) return qos_tid; } -static void ccmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *b_0, u8 *aad) +static void ccmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *b_0, u8 *aad, + bool spp_amsdu) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - u8 qos_tid = ccmp_gcmp_aad(skb, aad); + u8 qos_tid = ccmp_gcmp_aad(skb, aad, spp_amsdu); /* In CCM, the initial vectors (IV) used for CTR mode encryption and CBC * mode authentication are not allowed to collide, yet both are derived @@ -479,7 +487,8 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb, return 0; pos += IEEE80211_CCMP_HDR_LEN; - ccmp_special_blocks(skb, pn, b_0, aad); + ccmp_special_blocks(skb, pn, b_0, aad, + key->conf.flags & IEEE80211_KEY_FLAG_SPP_AMSDU); return ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len, skb_put(skb, mic_len)); } @@ -557,7 +566,8 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, u8 aad[2 * AES_BLOCK_SIZE]; u8 b_0[AES_BLOCK_SIZE]; /* hardware didn't decrypt/verify MIC */ - ccmp_special_blocks(skb, pn, b_0, aad); + ccmp_special_blocks(skb, pn, b_0, aad, + key->conf.flags & IEEE80211_KEY_FLAG_SPP_AMSDU); if (ieee80211_aes_ccm_decrypt( key->u.ccmp.tfm, b_0, aad, @@ -581,7 +591,8 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, return RX_CONTINUE; } -static void gcmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *j_0, u8 *aad) +static void gcmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *j_0, u8 *aad, + bool spp_amsdu) { struct ieee80211_hdr *hdr = (void *)skb->data; @@ -591,7 +602,7 @@ static void gcmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *j_0, u8 *aad) j_0[14] = 0; j_0[AES_BLOCK_SIZE - 1] = 0x01; - ccmp_gcmp_aad(skb, aad); + ccmp_gcmp_aad(skb, aad, spp_amsdu); } static inline void gcmp_pn2hdr(u8 *hdr, const u8 *pn, int key_id) @@ -680,7 +691,8 @@ static int gcmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) return 0; pos += IEEE80211_GCMP_HDR_LEN; - gcmp_special_blocks(skb, pn, j_0, aad); + gcmp_special_blocks(skb, pn, j_0, aad, + key->conf.flags & IEEE80211_KEY_FLAG_SPP_AMSDU); return ieee80211_aes_gcm_encrypt(key->u.gcmp.tfm, j_0, aad, pos, len, skb_put(skb, IEEE80211_GCMP_MIC_LEN)); } @@ -753,7 +765,8 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) u8 aad[2 * AES_BLOCK_SIZE]; u8 j_0[AES_BLOCK_SIZE]; /* hardware didn't decrypt/verify MIC */ - gcmp_special_blocks(skb, pn, j_0, aad); + gcmp_special_blocks(skb, pn, j_0, aad, + key->conf.flags & IEEE80211_KEY_FLAG_SPP_AMSDU); if (ieee80211_aes_gcm_decrypt( key->u.gcmp.tfm, j_0, aad, diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 8d2eabc71bbe..f13b07ebfb98 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -265,19 +265,27 @@ fail: return -ENOMEM; } +static void mac802154_llsec_key_del_rcu(struct rcu_head *rcu) +{ + struct ieee802154_llsec_key_entry *pos; + struct mac802154_llsec_key *mkey; + + pos = container_of(rcu, struct ieee802154_llsec_key_entry, rcu); + mkey = container_of(pos->key, struct mac802154_llsec_key, key); + + llsec_key_put(mkey); + kfree_sensitive(pos); +} + int mac802154_llsec_key_del(struct mac802154_llsec *sec, const struct ieee802154_llsec_key_id *key) { struct ieee802154_llsec_key_entry *pos; list_for_each_entry(pos, &sec->table.keys, list) { - struct mac802154_llsec_key *mkey; - - mkey = container_of(pos->key, struct mac802154_llsec_key, key); - if (llsec_key_id_equal(&pos->id, key)) { list_del_rcu(&pos->list); - llsec_key_put(mkey); + call_rcu(&pos->rcu, mac802154_llsec_key_del_rcu); return 0; } } diff --git a/net/mctp/Kconfig b/net/mctp/Kconfig index 3a5c0e70da77..d8d3413a37f7 100644 --- a/net/mctp/Kconfig +++ b/net/mctp/Kconfig @@ -14,6 +14,7 @@ menuconfig MCTP config MCTP_TEST bool "MCTP core tests" if !KUNIT_ALL_TESTS + select MCTP_FLOWS depends on MCTP=y && KUNIT=y default KUNIT_ALL_TESTS diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index f6be58b68c6f..de52a9191da0 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -350,30 +350,102 @@ static int mctp_getsockopt(struct socket *sock, int level, int optname, return -EINVAL; } -static int mctp_ioctl_alloctag(struct mctp_sock *msk, unsigned long arg) +/* helpers for reading/writing the tag ioc, handling compatibility across the + * two versions, and some basic API error checking + */ +static int mctp_ioctl_tag_copy_from_user(unsigned long arg, + struct mctp_ioc_tag_ctl2 *ctl, + bool tagv2) +{ + struct mctp_ioc_tag_ctl ctl_compat; + unsigned long size; + void *ptr; + int rc; + + if (tagv2) { + size = sizeof(*ctl); + ptr = ctl; + } else { + size = sizeof(ctl_compat); + ptr = &ctl_compat; + } + + rc = copy_from_user(ptr, (void __user *)arg, size); + if (rc) + return -EFAULT; + + if (!tagv2) { + /* compat, using defaults for new fields */ + ctl->net = MCTP_INITIAL_DEFAULT_NET; + ctl->peer_addr = ctl_compat.peer_addr; + ctl->local_addr = MCTP_ADDR_ANY; + ctl->flags = ctl_compat.flags; + ctl->tag = ctl_compat.tag; + } + + if (ctl->flags) + return -EINVAL; + + if (ctl->local_addr != MCTP_ADDR_ANY && + ctl->local_addr != MCTP_ADDR_NULL) + return -EINVAL; + + return 0; +} + +static int mctp_ioctl_tag_copy_to_user(unsigned long arg, + struct mctp_ioc_tag_ctl2 *ctl, + bool tagv2) +{ + struct mctp_ioc_tag_ctl ctl_compat; + unsigned long size; + void *ptr; + int rc; + + if (tagv2) { + ptr = ctl; + size = sizeof(*ctl); + } else { + ctl_compat.peer_addr = ctl->peer_addr; + ctl_compat.tag = ctl->tag; + ctl_compat.flags = ctl->flags; + + ptr = &ctl_compat; + size = sizeof(ctl_compat); + } + + rc = copy_to_user((void __user *)arg, ptr, size); + if (rc) + return -EFAULT; + + return 0; +} + +static int mctp_ioctl_alloctag(struct mctp_sock *msk, bool tagv2, + unsigned long arg) { struct net *net = sock_net(&msk->sk); struct mctp_sk_key *key = NULL; - struct mctp_ioc_tag_ctl ctl; + struct mctp_ioc_tag_ctl2 ctl; unsigned long flags; u8 tag; + int rc; - if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl))) - return -EFAULT; + rc = mctp_ioctl_tag_copy_from_user(arg, &ctl, tagv2); + if (rc) + return rc; if (ctl.tag) return -EINVAL; - if (ctl.flags) - return -EINVAL; - - key = mctp_alloc_local_tag(msk, ctl.peer_addr, MCTP_ADDR_ANY, - true, &tag); + key = mctp_alloc_local_tag(msk, ctl.net, MCTP_ADDR_ANY, + ctl.peer_addr, true, &tag); if (IS_ERR(key)) return PTR_ERR(key); ctl.tag = tag | MCTP_TAG_OWNER | MCTP_TAG_PREALLOC; - if (copy_to_user((void __user *)arg, &ctl, sizeof(ctl))) { + rc = mctp_ioctl_tag_copy_to_user(arg, &ctl, tagv2); + if (rc) { unsigned long fl2; /* Unwind our key allocation: the keys list lock needs to be * taken before the individual key locks, and we need a valid @@ -385,28 +457,27 @@ static int mctp_ioctl_alloctag(struct mctp_sock *msk, unsigned long arg) __mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_DROPPED); mctp_key_unref(key); spin_unlock_irqrestore(&net->mctp.keys_lock, flags); - return -EFAULT; + return rc; } mctp_key_unref(key); return 0; } -static int mctp_ioctl_droptag(struct mctp_sock *msk, unsigned long arg) +static int mctp_ioctl_droptag(struct mctp_sock *msk, bool tagv2, + unsigned long arg) { struct net *net = sock_net(&msk->sk); - struct mctp_ioc_tag_ctl ctl; + struct mctp_ioc_tag_ctl2 ctl; unsigned long flags, fl2; struct mctp_sk_key *key; struct hlist_node *tmp; int rc; u8 tag; - if (copy_from_user(&ctl, (void __user *)arg, sizeof(ctl))) - return -EFAULT; - - if (ctl.flags) - return -EINVAL; + rc = mctp_ioctl_tag_copy_from_user(arg, &ctl, tagv2); + if (rc) + return rc; /* Must be a local tag, TO set, preallocated */ if ((ctl.tag & ~MCTP_TAG_MASK) != (MCTP_TAG_OWNER | MCTP_TAG_PREALLOC)) @@ -422,6 +493,7 @@ static int mctp_ioctl_droptag(struct mctp_sock *msk, unsigned long arg) */ spin_lock_irqsave(&key->lock, fl2); if (key->manual_alloc && + ctl.net == key->net && ctl.peer_addr == key->peer_addr && tag == key->tag) { __mctp_key_remove(key, net, fl2, @@ -439,12 +511,17 @@ static int mctp_ioctl_droptag(struct mctp_sock *msk, unsigned long arg) static int mctp_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); + bool tagv2 = false; switch (cmd) { + case SIOCMCTPALLOCTAG2: case SIOCMCTPALLOCTAG: - return mctp_ioctl_alloctag(msk, arg); + tagv2 = cmd == SIOCMCTPALLOCTAG2; + return mctp_ioctl_alloctag(msk, tagv2, arg); case SIOCMCTPDROPTAG: - return mctp_ioctl_droptag(msk, arg); + case SIOCMCTPDROPTAG2: + tagv2 = cmd == SIOCMCTPDROPTAG2; + return mctp_ioctl_droptag(msk, tagv2, arg); } return -EINVAL; diff --git a/net/mctp/route.c b/net/mctp/route.c index ceee44ea09d9..eefd7834d9a0 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -73,13 +73,50 @@ static struct mctp_sock *mctp_lookup_bind(struct net *net, struct sk_buff *skb) return NULL; } -static bool mctp_key_match(struct mctp_sk_key *key, mctp_eid_t local, - mctp_eid_t peer, u8 tag) +/* A note on the key allocations. + * + * struct net->mctp.keys contains our set of currently-allocated keys for + * MCTP tag management. The lookup tuple for these is the peer EID, + * local EID and MCTP tag. + * + * In some cases, the peer EID may be MCTP_EID_ANY: for example, when a + * broadcast message is sent, we may receive responses from any peer EID. + * Because the broadcast dest address is equivalent to ANY, we create + * a key with (local = local-eid, peer = ANY). This allows a match on the + * incoming broadcast responses from any peer. + * + * We perform lookups when packets are received, and when tags are allocated + * in two scenarios: + * + * - when a packet is sent, with a locally-owned tag: we need to find an + * unused tag value for the (local, peer) EID pair. + * + * - when a tag is manually allocated: we need to find an unused tag value + * for the peer EID, but don't have a specific local EID at that stage. + * + * in the latter case, on successful allocation, we end up with a tag with + * (local = ANY, peer = peer-eid). + * + * So, the key set allows both a local EID of ANY, as well as a peer EID of + * ANY in the lookup tuple. Both may be ANY if we prealloc for a broadcast. + * The matching (in mctp_key_match()) during lookup allows the match value to + * be ANY in either the dest or source addresses. + * + * When allocating (+ inserting) a tag, we need to check for conflicts amongst + * the existing tag set. This requires macthing either exactly on the local + * and peer addresses, or either being ANY. + */ + +static bool mctp_key_match(struct mctp_sk_key *key, unsigned int net, + mctp_eid_t local, mctp_eid_t peer, u8 tag) { + if (key->net != net) + return false; + if (!mctp_address_matches(key->local_addr, local)) return false; - if (key->peer_addr != peer) + if (!mctp_address_matches(key->peer_addr, peer)) return false; if (key->tag != tag) @@ -92,7 +129,7 @@ static bool mctp_key_match(struct mctp_sk_key *key, mctp_eid_t local, * key exists. */ static struct mctp_sk_key *mctp_lookup_key(struct net *net, struct sk_buff *skb, - mctp_eid_t peer, + unsigned int netid, mctp_eid_t peer, unsigned long *irqflags) __acquires(&key->lock) { @@ -108,7 +145,7 @@ static struct mctp_sk_key *mctp_lookup_key(struct net *net, struct sk_buff *skb, spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry(key, &net->mctp.keys, hlist) { - if (!mctp_key_match(key, mh->dest, peer, tag)) + if (!mctp_key_match(key, netid, mh->dest, peer, tag)) continue; spin_lock(&key->lock); @@ -131,6 +168,7 @@ static struct mctp_sk_key *mctp_lookup_key(struct net *net, struct sk_buff *skb, } static struct mctp_sk_key *mctp_key_alloc(struct mctp_sock *msk, + unsigned int net, mctp_eid_t local, mctp_eid_t peer, u8 tag, gfp_t gfp) { @@ -140,6 +178,7 @@ static struct mctp_sk_key *mctp_key_alloc(struct mctp_sock *msk, if (!key) return NULL; + key->net = net; key->peer_addr = peer; key->local_addr = local; key->tag = tag; @@ -185,8 +224,8 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk) } hlist_for_each_entry(tmp, &net->mctp.keys, hlist) { - if (mctp_key_match(tmp, key->local_addr, key->peer_addr, - key->tag)) { + if (mctp_key_match(tmp, key->net, key->local_addr, + key->peer_addr, key->tag)) { spin_lock(&tmp->lock); if (tmp->valid) rc = -EEXIST; @@ -327,6 +366,7 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) struct net *net = dev_net(skb->dev); struct mctp_sock *msk; struct mctp_hdr *mh; + unsigned int netid; unsigned long f; u8 tag, flags; int rc; @@ -345,6 +385,7 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) /* grab header, advance data ptr */ mh = mctp_hdr(skb); + netid = mctp_cb(skb)->net; skb_pull(skb, sizeof(struct mctp_hdr)); if (mh->ver != 1) @@ -358,7 +399,7 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) /* lookup socket / reasm context, exactly matching (src,dest,tag). * we hold a ref on the key, and key->lock held. */ - key = mctp_lookup_key(net, skb, mh->src, &f); + key = mctp_lookup_key(net, skb, netid, mh->src, &f); if (flags & MCTP_HDR_FLAG_SOM) { if (key) { @@ -368,8 +409,12 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * key lookup to find the socket, but don't use this * key for reassembly - we'll create a more specific * one for future packets if required (ie, !EOM). + * + * this lookup requires key->peer to be MCTP_ADDR_ANY, + * it doesn't match just any key->peer. */ - any_key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY, &f); + any_key = mctp_lookup_key(net, skb, netid, + MCTP_ADDR_ANY, &f); if (any_key) { msk = container_of(any_key->sk, struct mctp_sock, sk); @@ -406,7 +451,7 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * packets for this message */ if (!key) { - key = mctp_key_alloc(msk, mh->dest, mh->src, + key = mctp_key_alloc(msk, netid, mh->dest, mh->src, tag, GFP_ATOMIC); if (!key) { rc = -ENOMEM; @@ -596,11 +641,12 @@ static void mctp_reserve_tag(struct net *net, struct mctp_sk_key *key, refcount_inc(&key->refs); } -/* Allocate a locally-owned tag value for (saddr, daddr), and reserve +/* Allocate a locally-owned tag value for (local, peer), and reserve * it for the socket msk */ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, - mctp_eid_t daddr, mctp_eid_t saddr, + unsigned int netid, + mctp_eid_t local, mctp_eid_t peer, bool manual, u8 *tagp) { struct net *net = sock_net(&msk->sk); @@ -610,11 +656,11 @@ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, u8 tagbits; /* for NULL destination EIDs, we may get a response from any peer */ - if (daddr == MCTP_ADDR_NULL) - daddr = MCTP_ADDR_ANY; + if (peer == MCTP_ADDR_NULL) + peer = MCTP_ADDR_ANY; /* be optimistic, alloc now */ - key = mctp_key_alloc(msk, saddr, daddr, 0, GFP_KERNEL); + key = mctp_key_alloc(msk, netid, local, peer, 0, GFP_KERNEL); if (!key) return ERR_PTR(-ENOMEM); @@ -631,12 +677,24 @@ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, * lock held, they don't change over the lifetime of the key. */ + /* tags are net-specific */ + if (tmp->net != netid) + continue; + /* if we don't own the tag, it can't conflict */ if (tmp->tag & MCTP_HDR_FLAG_TO) continue; - if (!(mctp_address_matches(tmp->peer_addr, daddr) && - mctp_address_matches(tmp->local_addr, saddr))) + /* Since we're avoiding conflicting entries, match peer and + * local addresses, including with a wildcard on ANY. See + * 'A note on key allocations' for background. + */ + if (peer != MCTP_ADDR_ANY && + !mctp_address_matches(tmp->peer_addr, peer)) + continue; + + if (local != MCTP_ADDR_ANY && + !mctp_address_matches(tmp->local_addr, local)) continue; spin_lock(&tmp->lock); @@ -671,6 +729,7 @@ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, } static struct mctp_sk_key *mctp_lookup_prealloc_tag(struct mctp_sock *msk, + unsigned int netid, mctp_eid_t daddr, u8 req_tag, u8 *tagp) { @@ -685,6 +744,9 @@ static struct mctp_sk_key *mctp_lookup_prealloc_tag(struct mctp_sock *msk, spin_lock_irqsave(&mns->keys_lock, flags); hlist_for_each_entry(tmp, &mns->keys, hlist) { + if (tmp->net != netid) + continue; + if (tmp->tag != req_tag) continue; @@ -843,6 +905,9 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, /* copy message payload */ skb_copy_bits(skb, pos, skb_transport_header(skb2), size); + /* we need to copy the extensions, for MCTP flow data */ + skb_ext_copy(skb2, skb); + /* do route */ rc = rt->output(rt, skb2); if (rc) @@ -865,6 +930,7 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct mctp_sk_key *key; struct mctp_hdr *hdr; unsigned long flags; + unsigned int netid; unsigned int mtu; mctp_eid_t saddr; bool ext_rt; @@ -916,16 +982,17 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, rc = 0; } spin_unlock_irqrestore(&rt->dev->addrs_lock, flags); + netid = READ_ONCE(rt->dev->net); if (rc) goto out_release; if (req_tag & MCTP_TAG_OWNER) { if (req_tag & MCTP_TAG_PREALLOC) - key = mctp_lookup_prealloc_tag(msk, daddr, + key = mctp_lookup_prealloc_tag(msk, netid, daddr, req_tag, &tag); else - key = mctp_alloc_local_tag(msk, daddr, saddr, + key = mctp_alloc_local_tag(msk, netid, saddr, daddr, false, &tag); if (IS_ERR(key)) { diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 92ea4158f7fc..77e5dd422258 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -79,6 +79,16 @@ static void mctp_test_route_destroy(struct kunit *test, kfree_rcu(&rt->rt, rcu); } +static void mctp_test_skb_set_dev(struct sk_buff *skb, + struct mctp_test_dev *dev) +{ + struct mctp_skb_cb *cb; + + cb = mctp_cb(skb); + cb->net = READ_ONCE(dev->mdev->net); + skb->dev = dev->ndev; +} + static struct sk_buff *mctp_test_create_skb(const struct mctp_hdr *hdr, unsigned int data_len) { @@ -91,6 +101,7 @@ static struct sk_buff *mctp_test_create_skb(const struct mctp_hdr *hdr, if (!skb) return NULL; + __mctp_cb(skb); memcpy(skb_put(skb, hdr_len), hdr, hdr_len); buf = skb_put(skb, data_len); @@ -111,6 +122,7 @@ static struct sk_buff *__mctp_test_create_skb_data(const struct mctp_hdr *hdr, if (!skb) return NULL; + __mctp_cb(skb); memcpy(skb_put(skb, hdr_len), hdr, hdr_len); memcpy(skb_put(skb, data_len), data, data_len); @@ -249,8 +261,6 @@ static void mctp_test_rx_input(struct kunit *test) skb = mctp_test_create_skb(¶ms->hdr, 1); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb); - __mctp_cb(skb); - mctp_pkttype_receive(skb, dev->ndev, &mctp_packet_type, NULL); KUNIT_EXPECT_EQ(test, !!rt->pkts.qlen, params->input); @@ -283,7 +293,8 @@ KUNIT_ARRAY_PARAM(mctp_rx_input, mctp_rx_input_tests, static void __mctp_route_test_init(struct kunit *test, struct mctp_test_dev **devp, struct mctp_test_route **rtp, - struct socket **sockp) + struct socket **sockp, + unsigned int netid) { struct sockaddr_mctp addr = {0}; struct mctp_test_route *rt; @@ -293,6 +304,8 @@ static void __mctp_route_test_init(struct kunit *test, dev = mctp_test_create_dev(); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + if (netid != MCTP_NET_ANY) + WRITE_ONCE(dev->mdev->net, netid); rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt); @@ -301,7 +314,7 @@ static void __mctp_route_test_init(struct kunit *test, KUNIT_ASSERT_EQ(test, rc, 0); addr.smctp_family = AF_MCTP; - addr.smctp_network = MCTP_NET_ANY; + addr.smctp_network = netid; addr.smctp_addr.s_addr = 8; addr.smctp_type = 0; rc = kernel_bind(sock, (struct sockaddr *)&addr, sizeof(addr)); @@ -339,13 +352,12 @@ static void mctp_test_route_input_sk(struct kunit *test) params = test->param_value; - __mctp_route_test_init(test, &dev, &rt, &sock); + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); skb = mctp_test_create_skb_data(¶ms->hdr, ¶ms->type); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb); - skb->dev = dev->ndev; - __mctp_cb(skb); + mctp_test_skb_set_dev(skb, dev); rc = mctp_route_input(&rt->rt, skb); @@ -410,15 +422,14 @@ static void mctp_test_route_input_sk_reasm(struct kunit *test) params = test->param_value; - __mctp_route_test_init(test, &dev, &rt, &sock); + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); for (i = 0; i < params->n_hdrs; i++) { c = i; skb = mctp_test_create_skb_data(¶ms->hdrs[i], &c); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb); - skb->dev = dev->ndev; - __mctp_cb(skb); + mctp_test_skb_set_dev(skb, dev); rc = mctp_route_input(&rt->rt, skb); } @@ -544,6 +555,7 @@ static void mctp_test_route_input_sk_keys(struct kunit *test) struct mctp_sock *msk; struct socket *sock; unsigned long flags; + unsigned int net; int rc; u8 c; @@ -551,6 +563,7 @@ static void mctp_test_route_input_sk_keys(struct kunit *test) dev = mctp_test_create_dev(); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + net = READ_ONCE(dev->mdev->net); rt = mctp_test_create_route(&init_net, dev->mdev, 8, 68); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt); @@ -562,8 +575,9 @@ static void mctp_test_route_input_sk_keys(struct kunit *test) mns = &sock_net(sock->sk)->mctp; /* set the incoming tag according to test params */ - key = mctp_key_alloc(msk, params->key_local_addr, params->key_peer_addr, - params->key_tag, GFP_KERNEL); + key = mctp_key_alloc(msk, net, params->key_local_addr, + params->key_peer_addr, params->key_tag, + GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, key); @@ -576,8 +590,7 @@ static void mctp_test_route_input_sk_keys(struct kunit *test) skb = mctp_test_create_skb_data(¶ms->hdr, &c); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb); - skb->dev = dev->ndev; - __mctp_cb(skb); + mctp_test_skb_set_dev(skb, dev); rc = mctp_route_input(&rt->rt, skb); @@ -665,6 +678,373 @@ static void mctp_route_input_sk_keys_to_desc( KUNIT_ARRAY_PARAM(mctp_route_input_sk_keys, mctp_route_input_sk_keys_tests, mctp_route_input_sk_keys_to_desc); +struct test_net { + unsigned int netid; + struct mctp_test_dev *dev; + struct mctp_test_route *rt; + struct socket *sock; + struct sk_buff *skb; + struct mctp_sk_key *key; + struct { + u8 type; + unsigned int data; + } msg; +}; + +static void +mctp_test_route_input_multiple_nets_bind_init(struct kunit *test, + struct test_net *t) +{ + struct mctp_hdr hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1) | FL_TO); + + t->msg.data = t->netid; + + __mctp_route_test_init(test, &t->dev, &t->rt, &t->sock, t->netid); + + t->skb = mctp_test_create_skb_data(&hdr, &t->msg); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, t->skb); + mctp_test_skb_set_dev(t->skb, t->dev); +} + +static void +mctp_test_route_input_multiple_nets_bind_fini(struct kunit *test, + struct test_net *t) +{ + __mctp_route_test_fini(test, t->dev, t->rt, t->sock); +} + +/* Test that skbs from different nets (otherwise identical) get routed to their + * corresponding socket via the sockets' bind() + */ +static void mctp_test_route_input_multiple_nets_bind(struct kunit *test) +{ + struct sk_buff *rx_skb1, *rx_skb2; + struct test_net t1, t2; + int rc; + + t1.netid = 1; + t2.netid = 2; + + t1.msg.type = 0; + t2.msg.type = 0; + + mctp_test_route_input_multiple_nets_bind_init(test, &t1); + mctp_test_route_input_multiple_nets_bind_init(test, &t2); + + rc = mctp_route_input(&t1.rt->rt, t1.skb); + KUNIT_ASSERT_EQ(test, rc, 0); + rc = mctp_route_input(&t2.rt->rt, t2.skb); + KUNIT_ASSERT_EQ(test, rc, 0); + + rx_skb1 = skb_recv_datagram(t1.sock->sk, MSG_DONTWAIT, &rc); + KUNIT_EXPECT_NOT_ERR_OR_NULL(test, rx_skb1); + KUNIT_EXPECT_EQ(test, rx_skb1->len, sizeof(t1.msg)); + KUNIT_EXPECT_EQ(test, + *(unsigned int *)skb_pull(rx_skb1, sizeof(t1.msg.data)), + t1.netid); + kfree_skb(rx_skb1); + + rx_skb2 = skb_recv_datagram(t2.sock->sk, MSG_DONTWAIT, &rc); + KUNIT_EXPECT_NOT_ERR_OR_NULL(test, rx_skb2); + KUNIT_EXPECT_EQ(test, rx_skb2->len, sizeof(t2.msg)); + KUNIT_EXPECT_EQ(test, + *(unsigned int *)skb_pull(rx_skb2, sizeof(t2.msg.data)), + t2.netid); + kfree_skb(rx_skb2); + + mctp_test_route_input_multiple_nets_bind_fini(test, &t1); + mctp_test_route_input_multiple_nets_bind_fini(test, &t2); +} + +static void +mctp_test_route_input_multiple_nets_key_init(struct kunit *test, + struct test_net *t) +{ + struct mctp_hdr hdr = RX_HDR(1, 9, 8, FL_S | FL_E | FL_T(1)); + struct mctp_sock *msk; + struct netns_mctp *mns; + unsigned long flags; + + t->msg.data = t->netid; + + __mctp_route_test_init(test, &t->dev, &t->rt, &t->sock, t->netid); + + msk = container_of(t->sock->sk, struct mctp_sock, sk); + + t->key = mctp_key_alloc(msk, t->netid, hdr.dest, hdr.src, 1, GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, t->key); + + mns = &sock_net(t->sock->sk)->mctp; + spin_lock_irqsave(&mns->keys_lock, flags); + mctp_reserve_tag(&init_net, t->key, msk); + spin_unlock_irqrestore(&mns->keys_lock, flags); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, t->key); + t->skb = mctp_test_create_skb_data(&hdr, &t->msg); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, t->skb); + mctp_test_skb_set_dev(t->skb, t->dev); +} + +static void +mctp_test_route_input_multiple_nets_key_fini(struct kunit *test, + struct test_net *t) +{ + mctp_key_unref(t->key); + __mctp_route_test_fini(test, t->dev, t->rt, t->sock); +} + +/* test that skbs from different nets (otherwise identical) get routed to their + * corresponding socket via the sk_key + */ +static void mctp_test_route_input_multiple_nets_key(struct kunit *test) +{ + struct sk_buff *rx_skb1, *rx_skb2; + struct test_net t1, t2; + int rc; + + t1.netid = 1; + t2.netid = 2; + + /* use type 1 which is not bound */ + t1.msg.type = 1; + t2.msg.type = 1; + + mctp_test_route_input_multiple_nets_key_init(test, &t1); + mctp_test_route_input_multiple_nets_key_init(test, &t2); + + rc = mctp_route_input(&t1.rt->rt, t1.skb); + KUNIT_ASSERT_EQ(test, rc, 0); + rc = mctp_route_input(&t2.rt->rt, t2.skb); + KUNIT_ASSERT_EQ(test, rc, 0); + + rx_skb1 = skb_recv_datagram(t1.sock->sk, MSG_DONTWAIT, &rc); + KUNIT_EXPECT_NOT_ERR_OR_NULL(test, rx_skb1); + KUNIT_EXPECT_EQ(test, rx_skb1->len, sizeof(t1.msg)); + KUNIT_EXPECT_EQ(test, + *(unsigned int *)skb_pull(rx_skb1, sizeof(t1.msg.data)), + t1.netid); + kfree_skb(rx_skb1); + + rx_skb2 = skb_recv_datagram(t2.sock->sk, MSG_DONTWAIT, &rc); + KUNIT_EXPECT_NOT_ERR_OR_NULL(test, rx_skb2); + KUNIT_EXPECT_EQ(test, rx_skb2->len, sizeof(t2.msg)); + KUNIT_EXPECT_EQ(test, + *(unsigned int *)skb_pull(rx_skb2, sizeof(t2.msg.data)), + t2.netid); + kfree_skb(rx_skb2); + + mctp_test_route_input_multiple_nets_key_fini(test, &t1); + mctp_test_route_input_multiple_nets_key_fini(test, &t2); +} + +#if IS_ENABLED(CONFIG_MCTP_FLOWS) + +static void mctp_test_flow_init(struct kunit *test, + struct mctp_test_dev **devp, + struct mctp_test_route **rtp, + struct socket **sock, + struct sk_buff **skbp, + unsigned int len) +{ + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct sk_buff *skb; + + /* we have a slightly odd routing setup here; the test route + * is for EID 8, which is our local EID. We don't do a routing + * lookup, so that's fine - all we require is a path through + * mctp_local_output, which will call rt->output on whatever + * route we provide + */ + __mctp_route_test_init(test, &dev, &rt, sock, MCTP_NET_ANY); + + /* Assign a single EID. ->addrs is freed on mctp netdev release */ + dev->mdev->addrs = kmalloc(sizeof(u8), GFP_KERNEL); + dev->mdev->num_addrs = 1; + dev->mdev->addrs[0] = 8; + + skb = alloc_skb(len + sizeof(struct mctp_hdr) + 1, GFP_KERNEL); + KUNIT_ASSERT_TRUE(test, skb); + __mctp_cb(skb); + skb_reserve(skb, sizeof(struct mctp_hdr) + 1); + memset(skb_put(skb, len), 0, len); + + /* take a ref for the route, we'll decrement in local output */ + refcount_inc(&rt->rt.refs); + + *devp = dev; + *rtp = rt; + *skbp = skb; +} + +static void mctp_test_flow_fini(struct kunit *test, + struct mctp_test_dev *dev, + struct mctp_test_route *rt, + struct socket *sock) +{ + __mctp_route_test_fini(test, dev, rt, sock); +} + +/* test that an outgoing skb has the correct MCTP extension data set */ +static void mctp_test_packet_flow(struct kunit *test) +{ + struct sk_buff *skb, *skb2; + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct mctp_flow *flow; + struct socket *sock; + u8 dst = 8; + int n, rc; + + mctp_test_flow_init(test, &dev, &rt, &sock, &skb, 30); + + rc = mctp_local_output(sock->sk, &rt->rt, skb, dst, MCTP_TAG_OWNER); + KUNIT_ASSERT_EQ(test, rc, 0); + + n = rt->pkts.qlen; + KUNIT_ASSERT_EQ(test, n, 1); + + skb2 = skb_dequeue(&rt->pkts); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb2); + + flow = skb_ext_find(skb2, SKB_EXT_MCTP); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, flow); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, flow->key); + KUNIT_ASSERT_PTR_EQ(test, flow->key->sk, sock->sk); + + kfree_skb(skb2); + mctp_test_flow_fini(test, dev, rt, sock); +} + +/* test that outgoing skbs, after fragmentation, all have the correct MCTP + * extension data set. + */ +static void mctp_test_fragment_flow(struct kunit *test) +{ + struct mctp_flow *flows[2]; + struct sk_buff *tx_skbs[2]; + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct sk_buff *skb; + struct socket *sock; + u8 dst = 8; + int n, rc; + + mctp_test_flow_init(test, &dev, &rt, &sock, &skb, 100); + + rc = mctp_local_output(sock->sk, &rt->rt, skb, dst, MCTP_TAG_OWNER); + KUNIT_ASSERT_EQ(test, rc, 0); + + n = rt->pkts.qlen; + KUNIT_ASSERT_EQ(test, n, 2); + + /* both resulting packets should have the same flow data */ + tx_skbs[0] = skb_dequeue(&rt->pkts); + tx_skbs[1] = skb_dequeue(&rt->pkts); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, tx_skbs[0]); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, tx_skbs[1]); + + flows[0] = skb_ext_find(tx_skbs[0], SKB_EXT_MCTP); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, flows[0]); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, flows[0]->key); + KUNIT_ASSERT_PTR_EQ(test, flows[0]->key->sk, sock->sk); + + flows[1] = skb_ext_find(tx_skbs[1], SKB_EXT_MCTP); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, flows[1]); + KUNIT_ASSERT_PTR_EQ(test, flows[1]->key, flows[0]->key); + + kfree_skb(tx_skbs[0]); + kfree_skb(tx_skbs[1]); + mctp_test_flow_fini(test, dev, rt, sock); +} + +#else +static void mctp_test_packet_flow(struct kunit *test) +{ + kunit_skip(test, "Requires CONFIG_MCTP_FLOWS=y"); +} + +static void mctp_test_fragment_flow(struct kunit *test) +{ + kunit_skip(test, "Requires CONFIG_MCTP_FLOWS=y"); +} +#endif + +/* Test that outgoing skbs cause a suitable tag to be created */ +static void mctp_test_route_output_key_create(struct kunit *test) +{ + const unsigned int netid = 50; + const u8 dst = 26, src = 15; + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct mctp_sk_key *key; + struct netns_mctp *mns; + unsigned long flags; + struct socket *sock; + struct sk_buff *skb; + bool empty, single; + const int len = 2; + int rc; + + dev = mctp_test_create_dev(); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev); + WRITE_ONCE(dev->mdev->net, netid); + + rt = mctp_test_create_route(&init_net, dev->mdev, dst, 68); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, rt); + + rc = sock_create_kern(&init_net, AF_MCTP, SOCK_DGRAM, 0, &sock); + KUNIT_ASSERT_EQ(test, rc, 0); + + dev->mdev->addrs = kmalloc(sizeof(u8), GFP_KERNEL); + dev->mdev->num_addrs = 1; + dev->mdev->addrs[0] = src; + + skb = alloc_skb(sizeof(struct mctp_hdr) + 1 + len, GFP_KERNEL); + KUNIT_ASSERT_TRUE(test, skb); + __mctp_cb(skb); + skb_reserve(skb, sizeof(struct mctp_hdr) + 1 + len); + memset(skb_put(skb, len), 0, len); + + refcount_inc(&rt->rt.refs); + + mns = &sock_net(sock->sk)->mctp; + + /* We assume we're starting from an empty keys list, which requires + * preceding tests to clean up correctly! + */ + spin_lock_irqsave(&mns->keys_lock, flags); + empty = hlist_empty(&mns->keys); + spin_unlock_irqrestore(&mns->keys_lock, flags); + KUNIT_ASSERT_TRUE(test, empty); + + rc = mctp_local_output(sock->sk, &rt->rt, skb, dst, MCTP_TAG_OWNER); + KUNIT_ASSERT_EQ(test, rc, 0); + + key = NULL; + single = false; + spin_lock_irqsave(&mns->keys_lock, flags); + if (!hlist_empty(&mns->keys)) { + key = hlist_entry(mns->keys.first, struct mctp_sk_key, hlist); + single = hlist_is_singular_node(&key->hlist, &mns->keys); + } + spin_unlock_irqrestore(&mns->keys_lock, flags); + + KUNIT_ASSERT_NOT_NULL(test, key); + KUNIT_ASSERT_TRUE(test, single); + + KUNIT_EXPECT_EQ(test, key->net, netid); + KUNIT_EXPECT_EQ(test, key->local_addr, src); + KUNIT_EXPECT_EQ(test, key->peer_addr, dst); + /* key has incoming tag, so inverse of what we sent */ + KUNIT_EXPECT_FALSE(test, key->tag & MCTP_TAG_OWNER); + + sock_release(sock); + mctp_test_route_destroy(test, rt); + mctp_test_destroy_dev(dev); +} + static struct kunit_case mctp_test_cases[] = { KUNIT_CASE_PARAM(mctp_test_fragment, mctp_frag_gen_params), KUNIT_CASE_PARAM(mctp_test_rx_input, mctp_rx_input_gen_params), @@ -673,6 +1053,11 @@ static struct kunit_case mctp_test_cases[] = { mctp_route_input_sk_reasm_gen_params), KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys, mctp_route_input_sk_keys_gen_params), + KUNIT_CASE(mctp_test_route_input_multiple_nets_bind), + KUNIT_CASE(mctp_test_route_input_multiple_nets_key), + KUNIT_CASE(mctp_test_packet_flow), + KUNIT_CASE(mctp_test_fragment_flow), + KUNIT_CASE(mctp_test_route_output_key_create), {} }; diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c index e03ba66bbe18..565763eb0211 100644 --- a/net/mctp/test/utils.c +++ b/net/mctp/test/utils.c @@ -4,6 +4,7 @@ #include <linux/mctp.h> #include <linux/if_arp.h> +#include <net/mctp.h> #include <net/mctpdevice.h> #include <net/pkt_sched.h> @@ -54,6 +55,7 @@ struct mctp_test_dev *mctp_test_create_dev(void) rcu_read_lock(); dev->mdev = __mctp_dev_get(ndev); + dev->mdev->net = mctp_default_net(dev_net(ndev)); rcu_read_unlock(); return dev; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 1af29af65388..6dab883a08dd 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -2179,7 +2179,9 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct mpls_route __rcu **platform_label; - struct fib_dump_filter filter = {}; + struct fib_dump_filter filter = { + .rtnl_held = true, + }; unsigned int flags = NLM_F_MULTI; size_t platform_labels; unsigned int index; diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index 533d082f0701..45d1e6a157fc 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -27,6 +27,9 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, __be16 mpls_protocol; unsigned int mpls_hlen; + if (!skb_inner_network_header_was_set(skb)) + goto out; + skb_reset_network_header(skb); mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb); if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN)) diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index ef59e25dc482..8fc790f2a01b 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -55,8 +55,6 @@ static int mpls_xmit(struct sk_buff *skb) out_dev = dst->dev; net = dev_net(out_dev); - skb_orphan(skb); - if (!mpls_output_possible(out_dev) || !dst->lwtstate || skb_warn_if_lro(skb)) goto drop; diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 7017dd60659d..3ae46b545d2c 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -10,7 +10,6 @@ #include <linux/net.h> #include <linux/inet_diag.h> #include <net/netlink.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" static int subflow_get_info(struct sock *sk, struct sk_buff *skb) diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index 5409c2ea3f57..0566dd793810 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -10,7 +10,6 @@ #include <linux/net.h> #include <linux/inet_diag.h> #include <net/netlink.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, @@ -225,6 +224,7 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } static const struct inet_diag_handler mptcp_diag_handler = { + .owner = THIS_MODULE, .dump = mptcp_diag_dump, .dump_one = mptcp_diag_dump_one, .idiag_get_info = mptcp_diag_get_info, diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c index 670da7822e6c..c30a2a90a192 100644 --- a/net/mptcp/mptcp_pm_gen.c +++ b/net/mptcp/mptcp_pm_gen.c @@ -32,8 +32,9 @@ const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] }; /* MPTCP_PM_CMD_GET_ADDR - do */ -const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { - [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ATTR_TOKEN + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, }; /* MPTCP_PM_CMD_FLUSH_ADDRS - do */ @@ -110,7 +111,7 @@ const struct genl_ops mptcp_pm_nl_ops[11] = { .doit = mptcp_pm_nl_get_addr_doit, .dumpit = mptcp_pm_nl_get_addr_dumpit, .policy = mptcp_pm_get_addr_nl_policy, - .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .maxattr = MPTCP_PM_ATTR_TOKEN, .flags = GENL_UNS_ADMIN_PERM, }, { diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h index ac9fc7225b6a..e24258f6f819 100644 --- a/net/mptcp/mptcp_pm_gen.h +++ b/net/mptcp/mptcp_pm_gen.h @@ -18,7 +18,7 @@ extern const struct nla_policy mptcp_pm_add_addr_nl_policy[MPTCP_PM_ENDPOINT_ADD extern const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; -extern const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; +extern const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ATTR_TOKEN + 1]; extern const struct nla_policy mptcp_pm_flush_addrs_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 63fc0758c22d..27ca42c77b02 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -689,8 +689,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * opts->suboptions |= OPTION_MPTCP_ADD_ADDR; if (!echo) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX); - opts->ahmac = add_addr_generate_hmac(msk->local_key, - msk->remote_key, + opts->ahmac = add_addr_generate_hmac(READ_ONCE(msk->local_key), + READ_ONCE(msk->remote_key), &opts->addr); } else { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX); @@ -792,7 +792,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk, *size = TCPOLEN_MPTCP_FASTCLOSE; opts->suboptions |= OPTION_MPTCP_FASTCLOSE; - opts->rcvr_key = msk->remote_key; + opts->rcvr_key = READ_ONCE(msk->remote_key); pr_debug("FASTCLOSE key=%llu", opts->rcvr_key); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX); @@ -1031,7 +1031,7 @@ u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq) static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una) { msk->bytes_acked += new_snd_una - msk->snd_una; - msk->snd_una = new_snd_una; + WRITE_ONCE(msk->snd_una, new_snd_una); } static void ack_update_msk(struct mptcp_sock *msk, @@ -1058,10 +1058,10 @@ static void ack_update_msk(struct mptcp_sock *msk, new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd; if (after64(new_wnd_end, msk->wnd_end)) - msk->wnd_end = new_wnd_end; + WRITE_ONCE(msk->wnd_end, new_wnd_end); /* this assumes mptcp_incoming_options() is invoked after tcp_ack() */ - if (after64(msk->wnd_end, READ_ONCE(msk->snd_nxt))) + if (after64(msk->wnd_end, snd_nxt)) __mptcp_check_push(sk, ssk); if (after64(new_snd_una, old_snd_una)) { @@ -1072,7 +1072,7 @@ static void ack_update_msk(struct mptcp_sock *msk, trace_ack_update_msk(mp_opt->data_ack, old_snd_una, new_snd_una, - new_wnd_end, msk->wnd_end); + new_wnd_end, READ_ONCE(msk->wnd_end)); } bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit) @@ -1100,8 +1100,8 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, if (mp_opt->echo) return true; - hmac = add_addr_generate_hmac(msk->remote_key, - msk->local_key, + hmac = add_addr_generate_hmac(READ_ONCE(msk->remote_key), + READ_ONCE(msk->local_key), &mp_opt->addr); pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n", @@ -1148,7 +1148,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) if (unlikely(mp_opt.suboptions != OPTION_MPTCP_DSS)) { if ((mp_opt.suboptions & OPTION_MPTCP_FASTCLOSE) && - msk->local_key == mp_opt.rcvr_key) { + READ_ONCE(msk->local_key) == mp_opt.rcvr_key) { WRITE_ONCE(msk->rcv_fastclose, true); mptcp_schedule_work((struct sock *)msk); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSERX); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 4ae19113b8eb..55406720c607 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -6,7 +6,6 @@ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/kernel.h> -#include <net/tcp.h> #include <net/mptcp.h> #include "protocol.h" @@ -77,7 +76,7 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int { struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p, token=%u side=%d", msk, msk->token, server_side); + pr_debug("msk=%p, token=%u side=%d", msk, READ_ONCE(msk->token), server_side); WRITE_ONCE(pm->server_side, server_side); mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC); @@ -441,13 +440,27 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); } -int mptcp_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup) +int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info) { - if (token) - return mptcp_userspace_pm_set_flags(net, token, loc, rem, bkup); - return mptcp_pm_nl_set_flags(net, loc, bkup); + if (info->attrs[MPTCP_PM_ATTR_TOKEN]) + return mptcp_userspace_pm_get_addr(skb, info); + return mptcp_pm_nl_get_addr(skb, info); +} + +int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb) +{ + const struct genl_info *info = genl_info_dump(cb); + + if (info->attrs[MPTCP_PM_ATTR_TOKEN]) + return mptcp_userspace_pm_dump_addr(msg, cb); + return mptcp_pm_nl_dump_addr(msg, cb); +} + +int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info) +{ + if (info->attrs[MPTCP_PM_ATTR_TOKEN]) + return mptcp_userspace_pm_set_flags(skb, info); + return mptcp_pm_nl_set_flags(skb, info); } void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 58d17d9604e7..5c17d39146ea 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -8,19 +8,13 @@ #include <linux/inet.h> #include <linux/kernel.h> -#include <net/tcp.h> #include <net/inet_common.h> #include <net/netns/generic.h> #include <net/mptcp.h> -#include <net/genetlink.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" #include "mib.h" -/* forward declaration */ -static struct genl_family mptcp_genl_family; - static int pm_nl_pernet_id; struct mptcp_pm_add_entry { @@ -505,15 +499,12 @@ __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id) } static struct mptcp_pm_addr_entry * -__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info, - bool lookup_by_id) +__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) { struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, &pernet->local_addr_list, list) { - if ((!lookup_by_id && - mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) || - (lookup_by_id && entry->addr.id == info->id)) + if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) return entry; } return NULL; @@ -543,7 +534,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) mptcp_local_address((struct sock_common *)msk->first, &mpc_addr); rcu_read_lock(); - entry = __lookup_addr(pernet, &mpc_addr, false); + entry = __lookup_addr(pernet, &mpc_addr); if (entry) { __clear_bit(entry->addr.id, msk->pm.id_avail_bitmap); msk->mpc_endpoint_id = entry->addr.id; @@ -1550,8 +1541,8 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) } } -void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, - struct list_head *rm_list) +static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, + struct list_head *rm_list) { struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 }; struct mptcp_pm_addr_entry *entry; @@ -1636,8 +1627,8 @@ int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info) return 0; } -static int mptcp_nl_fill_addr(struct sk_buff *skb, - struct mptcp_pm_addr_entry *entry) +int mptcp_nl_fill_addr(struct sk_buff *skb, + struct mptcp_pm_addr_entry *entry) { struct mptcp_addr_info *addr = &entry->addr; struct nlattr *attr; @@ -1675,7 +1666,7 @@ nla_put_failure: return -EMSGSIZE; } -int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); @@ -1725,8 +1716,13 @@ fail: return ret; } -int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info) +{ + return mptcp_pm_get_addr(skb, info); +} + +int mptcp_pm_nl_dump_addr(struct sk_buff *msg, + struct netlink_callback *cb) { struct net *net = sock_net(msg->sk); struct mptcp_pm_addr_entry *entry; @@ -1768,6 +1764,12 @@ int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, return msg->len; } +int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + return mptcp_pm_dump_addr(msg, cb); +} + static int parse_limit(struct genl_info *info, int id, unsigned int *limit) { struct nlattr *attr = info->attrs[id]; @@ -1882,66 +1884,63 @@ next: return ret; } -int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup) +int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info) { - struct pm_nl_pernet *pernet = pm_nl_get_pernet(net); + struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; + struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | MPTCP_PM_ADDR_FLAG_FULLMESH; + struct net *net = sock_net(skb->sk); struct mptcp_pm_addr_entry *entry; + struct pm_nl_pernet *pernet; u8 lookup_by_id = 0; + u8 bkup = 0; + int ret; + + pernet = pm_nl_get_pernet(net); + + ret = mptcp_pm_parse_entry(attr, info, false, &addr); + if (ret < 0) + return ret; - if (addr->addr.family == AF_UNSPEC) { + if (addr.addr.family == AF_UNSPEC) { lookup_by_id = 1; - if (!addr->addr.id) + if (!addr.addr.id) { + GENL_SET_ERR_MSG(info, "missing required inputs"); return -EOPNOTSUPP; + } } + if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) + bkup = 1; + spin_lock_bh(&pernet->lock); - entry = __lookup_addr(pernet, &addr->addr, lookup_by_id); + entry = lookup_by_id ? __lookup_addr_by_id(pernet, addr.addr.id) : + __lookup_addr(pernet, &addr.addr); if (!entry) { spin_unlock_bh(&pernet->lock); + GENL_SET_ERR_MSG(info, "address not found"); return -EINVAL; } - if ((addr->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && + if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { spin_unlock_bh(&pernet->lock); + GENL_SET_ERR_MSG(info, "invalid addr flags"); return -EINVAL; } - changed = (addr->flags ^ entry->flags) & mask; - entry->flags = (entry->flags & ~mask) | (addr->flags & mask); - *addr = *entry; + changed = (addr.flags ^ entry->flags) & mask; + entry->flags = (entry->flags & ~mask) | (addr.flags & mask); + addr = *entry; spin_unlock_bh(&pernet->lock); - mptcp_nl_set_flags(net, &addr->addr, bkup, changed); + mptcp_nl_set_flags(net, &addr.addr, bkup, changed); return 0; } int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info) { - struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, }; - struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; - struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; - struct net *net = sock_net(skb->sk); - u8 bkup = 0; - int ret; - - ret = mptcp_pm_parse_entry(attr, info, false, &addr); - if (ret < 0) - return ret; - - if (attr_rem) { - ret = mptcp_pm_parse_entry(attr_rem, info, false, &remote); - if (ret < 0) - return ret; - } - - if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) - bkup = 1; - - return mptcp_pm_set_flags(net, token, &addr, &remote, bkup); + return mptcp_pm_set_flags(skb, info); } static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp) @@ -2014,7 +2013,7 @@ static int mptcp_event_put_token_and_ssk(struct sk_buff *skb, const struct mptcp_subflow_context *sf; u8 sk_err; - if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token)) + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) return -EMSGSIZE; if (mptcp_event_add_subflow(skb, ssk)) @@ -2072,7 +2071,7 @@ static int mptcp_event_created(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { - int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token); + int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)); if (err) return err; @@ -2100,7 +2099,7 @@ void mptcp_event_addr_removed(const struct mptcp_sock *msk, uint8_t id) if (!nlh) goto nla_put_failure; - if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token)) + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, id)) @@ -2135,7 +2134,7 @@ void mptcp_event_addr_announced(const struct sock *ssk, if (!nlh) goto nla_put_failure; - if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token)) + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, info->id)) @@ -2251,7 +2250,7 @@ void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, goto nla_put_failure; break; case MPTCP_EVENT_CLOSED: - if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, msk->token) < 0) + if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)) < 0) goto nla_put_failure; break; case MPTCP_EVENT_ANNOUNCED: @@ -2281,7 +2280,7 @@ nla_put_failure: nlmsg_free(skb); } -static struct genl_family mptcp_genl_family __ro_after_init = { +struct genl_family mptcp_genl_family __ro_after_init = { .name = MPTCP_PM_NAME, .version = MPTCP_PM_VER, .netnsok = true, diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index bc97cc30f013..9f5d422d5ef6 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -106,19 +106,26 @@ static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk, return -EINVAL; } +static struct mptcp_pm_addr_entry * +mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id) +{ + struct mptcp_pm_addr_entry *entry; + + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (entry->addr.id == id) + return entry; + } + return NULL; +} + int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex) { - struct mptcp_pm_addr_entry *entry, *match = NULL; + struct mptcp_pm_addr_entry *match; spin_lock_bh(&msk->pm.lock); - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { - if (id == entry->addr.id) { - match = entry; - break; - } - } + match = mptcp_userspace_pm_lookup_addr_by_id(msk, id); spin_unlock_bh(&msk->pm.lock); if (match) { *flags = match->flags; @@ -261,7 +268,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *id = info->attrs[MPTCP_PM_ATTR_LOC_ID]; - struct mptcp_pm_addr_entry *match = NULL; + struct mptcp_pm_addr_entry *match; struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; LIST_HEAD(free_list); @@ -298,13 +305,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) lock_sock(sk); - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { - if (entry->addr.id == id_val) { - match = entry; - break; - } - } - + match = mptcp_userspace_pm_lookup_addr_by_id(msk, id_val); if (!match) { GENL_SET_ERR_MSG(info, "address with specified id not found"); release_sock(sk); @@ -334,7 +335,6 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct mptcp_pm_addr_entry local = { 0 }; struct mptcp_addr_info addr_r; - struct mptcp_addr_info addr_l; struct mptcp_sock *msk; int err = -EINVAL; struct sock *sk; @@ -360,25 +360,31 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) goto create_err; } - err = mptcp_pm_parse_addr(laddr, info, &addr_l); + err = mptcp_pm_parse_entry(laddr, info, true, &local); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr"); goto create_err; } + if (local.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { + GENL_SET_ERR_MSG(info, "invalid addr flags"); + err = -EINVAL; + goto create_err; + } + local.flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW; + err = mptcp_pm_parse_addr(raddr, info, &addr_r); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr"); goto create_err; } - if (!mptcp_pm_addr_families_match(sk, &addr_l, &addr_r)) { + if (!mptcp_pm_addr_families_match(sk, &local.addr, &addr_r)) { GENL_SET_ERR_MSG(info, "families mismatch"); err = -EINVAL; goto create_err; } - local.addr = addr_l; err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); @@ -387,7 +393,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) lock_sock(sk); - err = __mptcp_subflow_connect(sk, &addr_l, &addr_r); + err = __mptcp_subflow_connect(sk, &local.addr, &addr_r); release_sock(sk); @@ -540,35 +546,194 @@ destroy_err: return err; } -int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup) +int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info) { + struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, }; + struct mptcp_pm_addr_entry rem = { .addr = { .family = AF_UNSPEC }, }; + struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; + struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; + struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct net *net = sock_net(skb->sk); struct mptcp_sock *msk; int ret = -EINVAL; struct sock *sk; u32 token_val; + u8 bkup = 0; token_val = nla_get_u32(token); msk = mptcp_token_get_sock(net, token_val); - if (!msk) + if (!msk) { + NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); return ret; + } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) + if (!mptcp_pm_is_userspace(msk)) { + GENL_SET_ERR_MSG(info, "userspace PM not selected"); goto set_flags_err; + } + + ret = mptcp_pm_parse_entry(attr, info, false, &loc); + if (ret < 0) + goto set_flags_err; + + if (attr_rem) { + ret = mptcp_pm_parse_entry(attr_rem, info, false, &rem); + if (ret < 0) + goto set_flags_err; + } - if (loc->addr.family == AF_UNSPEC || - rem->addr.family == AF_UNSPEC) + if (loc.addr.family == AF_UNSPEC || + rem.addr.family == AF_UNSPEC) { + GENL_SET_ERR_MSG(info, "invalid address families"); + ret = -EINVAL; goto set_flags_err; + } + + if (loc.flags & MPTCP_PM_ADDR_FLAG_BACKUP) + bkup = 1; lock_sock(sk); - ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc->addr, &rem->addr, bkup); + ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc.addr, &rem.addr, bkup); release_sock(sk); set_flags_err: sock_put(sk); return ret; } + +int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct id_bitmap { + DECLARE_BITMAP(map, MPTCP_PM_MAX_ADDR_ID + 1); + } *bitmap; + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(msg->sk); + struct mptcp_pm_addr_entry *entry; + struct mptcp_sock *msk; + struct nlattr *token; + int ret = -EINVAL; + struct sock *sk; + void *hdr; + + bitmap = (struct id_bitmap *)cb->ctx; + token = info->attrs[MPTCP_PM_ATTR_TOKEN]; + + msk = mptcp_token_get_sock(net, nla_get_u32(token)); + if (!msk) { + NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + return ret; + } + + sk = (struct sock *)msk; + + if (!mptcp_pm_is_userspace(msk)) { + GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); + goto out; + } + + lock_sock(sk); + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (test_bit(entry->addr.id, bitmap->map)) + continue; + + hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &mptcp_genl_family, + NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); + if (!hdr) + break; + + if (mptcp_nl_fill_addr(msg, entry) < 0) { + genlmsg_cancel(msg, hdr); + break; + } + + __set_bit(entry->addr.id, bitmap->map); + genlmsg_end(msg, hdr); + } + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); + ret = msg->len; + +out: + sock_put(sk); + return ret; +} + +int mptcp_userspace_pm_get_addr(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; + struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; + struct mptcp_pm_addr_entry addr, *entry; + struct net *net = sock_net(skb->sk); + struct mptcp_sock *msk; + struct sk_buff *msg; + int ret = -EINVAL; + struct sock *sk; + void *reply; + + msk = mptcp_token_get_sock(net, nla_get_u32(token)); + if (!msk) { + NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + return ret; + } + + sk = (struct sock *)msk; + + if (!mptcp_pm_is_userspace(msk)) { + GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); + goto out; + } + + ret = mptcp_pm_parse_entry(attr, info, false, &addr); + if (ret < 0) + goto out; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; + goto out; + } + + reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0, + info->genlhdr->cmd); + if (!reply) { + GENL_SET_ERR_MSG(info, "not enough space in Netlink message"); + ret = -EMSGSIZE; + goto fail; + } + + lock_sock(sk); + spin_lock_bh(&msk->pm.lock); + entry = mptcp_userspace_pm_lookup_addr_by_id(msk, addr.addr.id); + if (!entry) { + GENL_SET_ERR_MSG(info, "address not found"); + ret = -EINVAL; + goto unlock_fail; + } + + ret = mptcp_nl_fill_addr(msg, entry); + if (ret) + goto unlock_fail; + + genlmsg_end(msg, reply); + ret = genlmsg_reply(msg, info); + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); + sock_put(sk); + return ret; + +unlock_fail: + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); +fail: + nlmsg_free(msg); +out: + sock_put(sk); + return ret; +} diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7833a49f6214..3a1967bc7bad 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -15,7 +15,6 @@ #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/protocol.h> -#include <net/tcp.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> @@ -410,6 +409,7 @@ static void mptcp_close_wake_up(struct sock *sk) sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); } +/* called under the msk socket lock */ static bool mptcp_pending_data_fin_ack(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -441,16 +441,17 @@ static void mptcp_check_data_fin_ack(struct sock *sk) } } +/* can be called with no lock acquired */ static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq) { struct mptcp_sock *msk = mptcp_sk(sk); if (READ_ONCE(msk->rcv_data_fin) && - ((1 << sk->sk_state) & + ((1 << inet_sk_state_load(sk)) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2))) { u64 rcv_data_fin_seq = READ_ONCE(msk->rcv_data_fin_seq); - if (msk->ack_seq == rcv_data_fin_seq) { + if (READ_ONCE(msk->ack_seq) == rcv_data_fin_seq) { if (seq) *seq = rcv_data_fin_seq; @@ -748,7 +749,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) __skb_queue_tail(&sk->sk_receive_queue, skb); } msk->bytes_received += end_seq - msk->ack_seq; - msk->ack_seq = end_seq; + WRITE_ONCE(msk->ack_seq, end_seq); moved = true; } return moved; @@ -985,6 +986,7 @@ static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag) put_page(dfrag->page); } +/* called under both the msk socket lock and the data lock */ static void __mptcp_clean_una(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1033,13 +1035,15 @@ static void __mptcp_clean_una(struct sock *sk) msk->recovery = false; out: - if (snd_una == READ_ONCE(msk->snd_nxt) && - snd_una == READ_ONCE(msk->write_seq)) { + if (snd_una == msk->snd_nxt && snd_una == msk->write_seq) { if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) mptcp_stop_rtx_timer(sk); } else { mptcp_reset_rtx_timer(sk); } + + if (mptcp_pending_data_fin_ack(sk)) + mptcp_schedule_work(sk); } static void __mptcp_clean_una_wakeup(struct sock *sk) @@ -1500,7 +1504,7 @@ static void mptcp_update_post_push(struct mptcp_sock *msk, */ if (likely(after64(snd_nxt_new, msk->snd_nxt))) { msk->bytes_sent += snd_nxt_new - msk->snd_nxt; - msk->snd_nxt = snd_nxt_new; + WRITE_ONCE(msk->snd_nxt, snd_nxt_new); } } @@ -1687,15 +1691,6 @@ out: } } -static void mptcp_set_nospace(struct sock *sk) -{ - /* enable autotune */ - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - - /* will be cleared on avail space */ - set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags); -} - static int mptcp_disconnect(struct sock *sk, int flags); static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, @@ -1766,6 +1761,30 @@ static int do_copy_data_nocache(struct sock *sk, int copy, return 0; } +/* open-code sk_stream_memory_free() plus sent limit computation to + * avoid indirect calls in fast-path. + * Called under the msk socket lock, so we can avoid a bunch of ONCE + * annotations. + */ +static u32 mptcp_send_limit(const struct sock *sk) +{ + const struct mptcp_sock *msk = mptcp_sk(sk); + u32 limit, not_sent; + + if (sk->sk_wmem_queued >= READ_ONCE(sk->sk_sndbuf)) + return 0; + + limit = mptcp_notsent_lowat(sk); + if (limit == UINT_MAX) + return UINT_MAX; + + not_sent = msk->write_seq - msk->snd_nxt; + if (not_sent >= limit) + return 0; + + return limit - not_sent; +} + static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1810,6 +1829,12 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct mptcp_data_frag *dfrag; bool dfrag_collapsed; size_t psize, offset; + u32 copy_limit; + + /* ensure fitting the notsent_lowat() constraint */ + copy_limit = mptcp_send_limit(sk); + if (!copy_limit) + goto wait_for_memory; /* reuse tail pfrag, if possible, or carve a new one from the * page allocator @@ -1817,9 +1842,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) dfrag = mptcp_pending_tail(sk); dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag); if (!dfrag_collapsed) { - if (!sk_stream_memory_free(sk)) - goto wait_for_memory; - if (!mptcp_page_frag_refill(sk, pfrag)) goto wait_for_memory; @@ -1834,6 +1856,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) offset = dfrag->offset + dfrag->data_len; psize = pfrag->size - offset; psize = min_t(size_t, psize, msg_data_left(msg)); + psize = min_t(size_t, psize, copy_limit); total_ts = psize + frag_truesize; if (!sk_wmem_schedule(sk, total_ts)) @@ -1869,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) continue; wait_for_memory: - mptcp_set_nospace(sk); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); __mptcp_push_pending(sk, msg->msg_flags); ret = sk_stream_wait_memory(sk, &timeo); if (ret) @@ -2115,7 +2138,7 @@ static unsigned int mptcp_inq_hint(const struct sock *sk) skb = skb_peek(&msk->receive_queue); if (skb) { - u64 hint_val = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; + u64 hint_val = READ_ONCE(msk->ack_seq) - MPTCP_SKB_CB(skb)->map_seq; if (hint_val >= INT_MAX) return INT_MAX; @@ -2759,7 +2782,7 @@ static void __mptcp_init_sock(struct sock *sk) __skb_queue_head_init(&msk->receive_queue); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; - msk->rmem_fwd_alloc = 0; + WRITE_ONCE(msk->rmem_fwd_alloc, 0); WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; @@ -2975,7 +2998,7 @@ static void __mptcp_destroy_sock(struct sock *sk) sk->sk_prot->destroy(sk); - WARN_ON_ONCE(msk->rmem_fwd_alloc); + WARN_ON_ONCE(READ_ONCE(msk->rmem_fwd_alloc)); WARN_ON_ONCE(msk->rmem_released); sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); @@ -3150,16 +3173,16 @@ static int mptcp_disconnect(struct sock *sk, int flags) WRITE_ONCE(msk->flags, 0); msk->cb_flags = 0; msk->recovery = false; - msk->can_ack = false; - msk->fully_established = false; - msk->rcv_data_fin = false; - msk->snd_data_fin_enable = false; - msk->rcv_fastclose = false; - msk->use_64bit_ack = false; - msk->bytes_consumed = 0; + WRITE_ONCE(msk->can_ack, false); + WRITE_ONCE(msk->fully_established, false); + WRITE_ONCE(msk->rcv_data_fin, false); + WRITE_ONCE(msk->snd_data_fin_enable, false); + WRITE_ONCE(msk->rcv_fastclose, false); + WRITE_ONCE(msk->use_64bit_ack, false); WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); + msk->bytes_consumed = 0; msk->bytes_acked = 0; msk->bytes_received = 0; msk->bytes_sent = 0; @@ -3250,17 +3273,17 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, mptcp_copy_ip_options(nsk, sk); msk = mptcp_sk(nsk); - msk->local_key = subflow_req->local_key; - msk->token = subflow_req->token; + WRITE_ONCE(msk->local_key, subflow_req->local_key); + WRITE_ONCE(msk->token, subflow_req->token); msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) WRITE_ONCE(msk->csum_enabled, true); - msk->write_seq = subflow_req->idsn + 1; - msk->snd_nxt = msk->write_seq; - msk->snd_una = msk->write_seq; - msk->wnd_end = msk->snd_nxt + tcp_sk(ssk)->snd_wnd; + WRITE_ONCE(msk->write_seq, subflow_req->idsn + 1); + WRITE_ONCE(msk->snd_nxt, msk->write_seq); + WRITE_ONCE(msk->snd_una, msk->write_seq); + WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; mptcp_init_sched(msk, mptcp_sk(sk)->sched); @@ -3363,9 +3386,6 @@ void __mptcp_data_acked(struct sock *sk) __mptcp_clean_una(sk); else __set_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->cb_flags); - - if (mptcp_pending_data_fin_ack(sk)) - mptcp_schedule_work(sk); } void __mptcp_check_push(struct sock *sk, struct sock *ssk) @@ -3767,6 +3787,7 @@ static struct proto mptcp_prot = { .unhash = mptcp_unhash, .get_port = mptcp_get_port, .forward_alloc_get = mptcp_forward_alloc_get, + .stream_memory_free = mptcp_stream_memory_free, .sockets_allocated = &mptcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, @@ -3940,12 +3961,12 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; - if (sk_stream_is_writeable(sk)) + if (__mptcp_stream_is_writeable(sk, 1)) return EPOLLOUT | EPOLLWRNORM; - mptcp_set_nospace(sk); - smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */ - if (sk_stream_is_writeable(sk)) + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + smp_mb__after_atomic(); /* NOSPACE is changed by mptcp_write_space() */ + if (__mptcp_stream_is_writeable(sk, 1)) return EPOLLOUT | EPOLLWRNORM; return 0; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 07f6242afc1a..a10ebf3ee10a 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -113,10 +113,9 @@ #define MPTCP_RST_TRANSIENT BIT(0) /* MPTCP socket atomic flags */ -#define MPTCP_NOSPACE 1 -#define MPTCP_WORK_RTX 2 -#define MPTCP_FALLBACK_DONE 4 -#define MPTCP_WORK_CLOSE_SUBFLOW 5 +#define MPTCP_WORK_RTX 1 +#define MPTCP_FALLBACK_DONE 2 +#define MPTCP_WORK_CLOSE_SUBFLOW 3 /* MPTCP socket release cb flags */ #define MPTCP_PUSH_PENDING 1 @@ -260,8 +259,10 @@ struct mptcp_data_frag { struct mptcp_sock { /* inet_connection_sock must be the first member */ struct inet_connection_sock sk; - u64 local_key; - u64 remote_key; + u64 local_key; /* protected by the first subflow socket lock + * lockless access read + */ + u64 remote_key; /* same as above */ u64 write_seq; u64 bytes_sent; u64 snd_nxt; @@ -306,6 +307,7 @@ struct mptcp_sock { in_accept_queue:1, free_first:1, rcvspace_init:1; + u32 notsent_lowat; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -341,12 +343,30 @@ struct mptcp_sock { #define mptcp_for_each_subflow_safe(__msk, __subflow, __tmp) \ list_for_each_entry_safe(__subflow, __tmp, &((__msk)->conn_list), node) +extern struct genl_family mptcp_genl_family; + static inline void msk_owned_by_me(const struct mptcp_sock *msk) { sock_owned_by_me((const struct sock *)msk); } +#ifdef CONFIG_DEBUG_NET +/* MPTCP-specific: we might (indirectly) call this helper with the wrong sk */ +#undef tcp_sk +#define tcp_sk(ptr) ({ \ + typeof(ptr) _ptr = (ptr); \ + WARN_ON(_ptr->sk_protocol != IPPROTO_TCP); \ + container_of_const(_ptr, struct tcp_sock, inet_conn.icsk_inet.sk); \ +}) +#define mptcp_sk(ptr) ({ \ + typeof(ptr) _ptr = (ptr); \ + WARN_ON(_ptr->sk_protocol != IPPROTO_MPTCP); \ + container_of_const(_ptr, struct mptcp_sock, sk.icsk_inet.sk); \ +}) + +#else /* !CONFIG_DEBUG_NET */ #define mptcp_sk(ptr) container_of_const(ptr, struct mptcp_sock, sk.icsk_inet.sk) +#endif /* the msk socket don't use the backlog, also account for the bulk * free memory @@ -400,7 +420,7 @@ static inline struct mptcp_data_frag *mptcp_rtx_head(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - if (msk->snd_una == READ_ONCE(msk->snd_nxt)) + if (msk->snd_una == msk->snd_nxt) return NULL; return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list); @@ -790,14 +810,36 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt); } +static inline u32 mptcp_notsent_lowat(const struct sock *sk) +{ + struct net *net = sock_net(sk); + u32 val; + + val = READ_ONCE(mptcp_sk(sk)->notsent_lowat); + return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); +} + +static inline bool mptcp_stream_memory_free(const struct sock *sk, int wake) +{ + const struct mptcp_sock *msk = mptcp_sk(sk); + u32 notsent_bytes; + + notsent_bytes = READ_ONCE(msk->write_seq) - READ_ONCE(msk->snd_nxt); + return (notsent_bytes << wake) < mptcp_notsent_lowat(sk); +} + +static inline bool __mptcp_stream_is_writeable(const struct sock *sk, int wake) +{ + return mptcp_stream_memory_free(sk, wake) && + __sk_stream_is_writeable(sk, wake); +} + static inline void mptcp_write_space(struct sock *sk) { - if (sk_stream_is_writeable(sk)) { - /* pairs with memory barrier in mptcp_poll */ - smp_mb(); - if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags)) - sk_stream_write_space(sk); - } + /* pairs with memory barrier in mptcp_poll */ + smp_mb(); + if (mptcp_stream_memory_free(sk, 1)) + sk_stream_write_space(sk); } static inline void __mptcp_sync_sndbuf(struct sock *sk) @@ -808,7 +850,7 @@ static inline void __mptcp_sync_sndbuf(struct sock *sk) if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) return; - new_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[0]; + new_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[0]); mptcp_for_each_subflow(mptcp_sk(sk), subflow) { ssk_sndbuf = READ_ONCE(mptcp_subflow_tcp_sock(subflow)->sk_sndbuf); @@ -928,21 +970,15 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex); -int mptcp_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup); -int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup); -int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup); +int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info); +int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info); int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); -void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, - struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); @@ -958,6 +994,8 @@ void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflo const struct mptcp_options_received *mp_opt); void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req); +int mptcp_nl_fill_addr(struct sk_buff *skb, + struct mptcp_pm_addr_entry *entry); static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk) { @@ -1022,6 +1060,15 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); +int mptcp_pm_nl_dump_addr(struct sk_buff *msg, + struct netlink_callback *cb); +int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, + struct netlink_callback *cb); +int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info); +int mptcp_userspace_pm_get_addr(struct sk_buff *skb, + struct genl_info *info); static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow) { diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index c40f1428e602..dcd1c76d2a3b 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -624,20 +624,11 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t return ret; } -static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optval, - unsigned int optlen) +static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - int val; - if (optlen < sizeof(int)) - return -EINVAL; - - if (copy_from_sockptr(&val, optval, sizeof(val))) - return -EFAULT; - - lock_sock(sk); sockopt_seq_inc(msk); msk->cork = !!val; mptcp_for_each_subflow(msk, subflow) { @@ -649,25 +640,15 @@ static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optva } if (!val) mptcp_check_and_set_pending(sk); - release_sock(sk); return 0; } -static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t optval, - unsigned int optlen) +static int __mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, int val) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - int val; - - if (optlen < sizeof(int)) - return -EINVAL; - - if (copy_from_sockptr(&val, optval, sizeof(val))) - return -EFAULT; - lock_sock(sk); sockopt_seq_inc(msk); msk->nodelay = !!val; mptcp_for_each_subflow(msk, subflow) { @@ -679,8 +660,6 @@ static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t op } if (val) mptcp_check_and_set_pending(sk); - release_sock(sk); - return 0; } @@ -803,25 +782,10 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, int ret, val; switch (optname) { - case TCP_INQ: - ret = mptcp_get_int_option(msk, optval, optlen, &val); - if (ret) - return ret; - if (val < 0 || val > 1) - return -EINVAL; - - lock_sock(sk); - msk->recvmsg_inq = !!val; - release_sock(sk); - return 0; case TCP_ULP: return -EOPNOTSUPP; case TCP_CONGESTION: return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen); - case TCP_CORK: - return mptcp_setsockopt_sol_tcp_cork(msk, optval, optlen); - case TCP_NODELAY: - return mptcp_setsockopt_sol_tcp_nodelay(msk, optval, optlen); case TCP_DEFER_ACCEPT: /* See tcp.c: TCP_DEFER_ACCEPT does not fail */ mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen); @@ -834,7 +798,34 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, optval, optlen); } - return -EOPNOTSUPP; + ret = mptcp_get_int_option(msk, optval, optlen, &val); + if (ret) + return ret; + + lock_sock(sk); + switch (optname) { + case TCP_INQ: + if (val < 0 || val > 1) + ret = -EINVAL; + else + msk->recvmsg_inq = !!val; + break; + case TCP_NOTSENT_LOWAT: + WRITE_ONCE(msk->notsent_lowat, val); + mptcp_write_space(sk); + break; + case TCP_CORK: + ret = __mptcp_setsockopt_sol_tcp_cork(msk, val); + break; + case TCP_NODELAY: + ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val); + break; + default: + ret = -ENOPROTOOPT; + } + + release_sock(sk); + return ret; } int mptcp_setsockopt(struct sock *sk, int level, int optname, @@ -942,7 +933,7 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) mptcp_data_unlock(sk); slow = lock_sock_fast(sk); - info->mptcpi_csum_enabled = msk->csum_enabled; + info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); info->mptcpi_token = msk->token; info->mptcpi_write_seq = msk->write_seq; info->mptcpi_retransmits = inet_csk(sk)->icsk_retransmits; @@ -1349,6 +1340,8 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, return mptcp_put_int_option(msk, optval, optlen, msk->cork); case TCP_NODELAY: return mptcp_put_int_option(msk, optval, optlen, msk->nodelay); + case TCP_NOTSENT_LOWAT: + return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat); } return -EOPNOTSUPP; } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 71ba86246ff8..1626dd20c68f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -15,13 +15,11 @@ #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/protocol.h> -#include <net/tcp.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/ip6_route.h> #include <net/transp_v6.h> #endif #include <net/mptcp.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" #include "mib.h" @@ -75,7 +73,8 @@ static void subflow_req_create_thmac(struct mptcp_subflow_request_sock *subflow_ get_random_bytes(&subflow_req->local_nonce, sizeof(u32)); - subflow_generate_hmac(msk->local_key, msk->remote_key, + subflow_generate_hmac(READ_ONCE(msk->local_key), + READ_ONCE(msk->remote_key), subflow_req->local_nonce, subflow_req->remote_nonce, hmac); @@ -714,7 +713,8 @@ static bool subflow_hmac_valid(const struct request_sock *req, if (!msk) return false; - subflow_generate_hmac(msk->remote_key, msk->local_key, + subflow_generate_hmac(READ_ONCE(msk->remote_key), + READ_ONCE(msk->local_key), subflow_req->remote_nonce, subflow_req->local_nonce, hmac); @@ -1548,8 +1548,8 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, mptcp_pm_get_flags_and_ifindex_by_id(msk, local_id, &flags, &ifindex); subflow->remote_key_valid = 1; - subflow->remote_key = msk->remote_key; - subflow->local_key = msk->local_key; + subflow->remote_key = READ_ONCE(msk->remote_key); + subflow->local_key = READ_ONCE(msk->local_key); subflow->token = msk->token; mptcp_info2sockaddr(loc, &addr, ssk->sk_family); diff --git a/net/mptcp/token_test.c b/net/mptcp/token_test.c index bfff53e668da..4fc39fa2e262 100644 --- a/net/mptcp/token_test.c +++ b/net/mptcp/token_test.c @@ -52,14 +52,19 @@ static struct mptcp_subflow_context *build_ctx(struct kunit *test) static struct mptcp_sock *build_msk(struct kunit *test) { struct mptcp_sock *msk; + struct sock *sk; msk = kunit_kzalloc(test, sizeof(struct mptcp_sock), GFP_USER); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, msk); refcount_set(&((struct sock *)msk)->sk_refcnt, 1); sock_net_set((struct sock *)msk, &init_net); + sk = (struct sock *)msk; + /* be sure the token helpers can dereference sk->sk_prot */ - ((struct sock *)msk)->sk_prot = &tcp_prot; + sk->sk_prot = &tcp_prot; + sk->sk_protocol = IPPROTO_MPTCP; + return msk; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 441d1f134110..df2dc21304ef 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -818,7 +818,7 @@ config NETFILTER_XT_TARGET_AUDIT config NETFILTER_XT_TARGET_CHECKSUM tristate "CHECKSUM target support" - depends on IP_NF_MANGLE || IP6_NF_MANGLE + depends on IP_NF_MANGLE || IP6_NF_MANGLE || NFT_COMPAT depends on NETFILTER_ADVANCED help This option adds a `CHECKSUM' target, which can be used in the iptables mangle @@ -869,7 +869,7 @@ config NETFILTER_XT_TARGET_CONNSECMARK config NETFILTER_XT_TARGET_CT tristate '"CT" target support' depends on NF_CONNTRACK - depends on IP_NF_RAW || IP6_NF_RAW + depends on IP_NF_RAW || IP6_NF_RAW || NFT_COMPAT depends on NETFILTER_ADVANCED help This options adds a `CT' target, which allows to specify initial @@ -880,7 +880,7 @@ config NETFILTER_XT_TARGET_CT config NETFILTER_XT_TARGET_DSCP tristate '"DSCP" and "TOS" target support' - depends on IP_NF_MANGLE || IP6_NF_MANGLE + depends on IP_NF_MANGLE || IP6_NF_MANGLE || NFT_COMPAT depends on NETFILTER_ADVANCED help This option adds a `DSCP' target, which allows you to manipulate @@ -896,7 +896,7 @@ config NETFILTER_XT_TARGET_DSCP config NETFILTER_XT_TARGET_HL tristate '"HL" hoplimit target support' - depends on IP_NF_MANGLE || IP6_NF_MANGLE + depends on IP_NF_MANGLE || IP6_NF_MANGLE || NFT_COMPAT depends on NETFILTER_ADVANCED help This option adds the "HL" (for IPv6) and "TTL" (for IPv4) @@ -1080,7 +1080,7 @@ config NETFILTER_XT_TARGET_TPROXY depends on NETFILTER_ADVANCED depends on IPV6 || IPV6=n depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n - depends on IP_NF_MANGLE + depends on IP_NF_MANGLE || NFT_COMPAT select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES != n select NF_TPROXY_IPV4 @@ -1147,7 +1147,7 @@ config NETFILTER_XT_TARGET_TCPMSS config NETFILTER_XT_TARGET_TCPOPTSTRIP tristate '"TCPOPTSTRIP" target support' - depends on IP_NF_MANGLE || IP6_NF_MANGLE + depends on IP_NF_MANGLE || IP6_NF_MANGLE || NFT_COMPAT depends on NETFILTER_ADVANCED help This option adds a "TCPOPTSTRIP" target, which allows you to strip diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index a743db073887..98d7dbe3d787 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1511,9 +1511,7 @@ int __init ip_vs_conn_init(void) return -ENOMEM; /* Allocate ip_vs_conn slab cache */ - ip_vs_conn_cachep = kmem_cache_create("ip_vs_conn", - sizeof(struct ip_vs_conn), 0, - SLAB_HWCACHE_ALIGN, NULL); + ip_vs_conn_cachep = KMEM_CACHE(ip_vs_conn, SLAB_HWCACHE_ALIGN); if (!ip_vs_conn_cachep) { kvfree(ip_vs_conn_tab); return -ENOMEM; diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index 0e4beae421f8..5257d5e7eb09 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type, static const struct bpf_func_proto * bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } const struct bpf_verifier_ops netfilter_verifier_ops = { diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 5d8ed6c90b7e..8715617b02fe 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -605,15 +605,11 @@ static int __init nf_conncount_modinit(void) for (i = 0; i < CONNCOUNT_SLOTS; ++i) spin_lock_init(&nf_conncount_locks[i]); - conncount_conn_cachep = kmem_cache_create("nf_conncount_tuple", - sizeof(struct nf_conncount_tuple), - 0, 0, NULL); + conncount_conn_cachep = KMEM_CACHE(nf_conncount_tuple, 0); if (!conncount_conn_cachep) return -ENOMEM; - conncount_rb_cachep = kmem_cache_create("nf_conncount_rb", - sizeof(struct nf_conncount_rb), - 0, 0, NULL); + conncount_rb_cachep = KMEM_CACHE(nf_conncount_rb, 0); if (!conncount_rb_cachep) { kmem_cache_destroy(conncount_conn_cachep); return -ENOMEM; diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index 475358ec8212..d2492d050fe6 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -467,7 +467,7 @@ __bpf_kfunc int bpf_ct_change_status(struct nf_conn *nfct, u32 status) __bpf_kfunc_end_defs(); -BTF_SET8_START(nf_ct_kfunc_set) +BTF_KFUNCS_START(nf_ct_kfunc_set) BTF_ID_FLAGS(func, bpf_xdp_ct_alloc, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_xdp_ct_lookup, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_skb_ct_alloc, KF_ACQUIRE | KF_RET_NULL) @@ -478,7 +478,7 @@ BTF_ID_FLAGS(func, bpf_ct_set_timeout, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_ct_change_timeout, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_ct_set_status, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_ct_change_status, KF_TRUSTED_ARGS) -BTF_SET8_END(nf_ct_kfunc_set) +BTF_KFUNCS_END(nf_ct_kfunc_set) static const struct btf_kfunc_id_set nf_conntrack_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 5b876fa7f9af..c63868666bd9 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2530,7 +2530,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) * netfilter framework. Roll on, two-stage module * delete... */ - synchronize_net(); + synchronize_rcu_expedited(); i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 81ca348915c9..21fa550966f0 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -722,9 +722,7 @@ int nf_conntrack_expect_init(void) nf_ct_expect_hsize = 1; } nf_ct_expect_max = nf_ct_expect_hsize * 4; - nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect", - sizeof(struct nf_conntrack_expect), - 0, 0, NULL); + nf_ct_expect_cachep = KMEM_CACHE(nf_conntrack_expect, 0); if (!nf_ct_expect_cachep) return -ENOMEM; diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index e16f158388bb..370f8231385c 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -31,10 +31,10 @@ static struct nf_logger *__find_logger(int pf, const char *str_logger) int i; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { - if (loggers[pf][i] == NULL) + log = nft_log_dereference(loggers[pf][i]); + if (!log) continue; - log = nft_log_dereference(loggers[pf][i]); if (!strncasecmp(str_logger, log->name, strlen(log->name))) return log; } @@ -156,6 +156,11 @@ int nf_logger_find_get(int pf, enum nf_log_type type) struct nf_logger *logger; int ret = -ENOENT; + if (pf >= ARRAY_SIZE(loggers)) + return -EINVAL; + if (type >= NF_LOG_TYPE_MAX) + return -EINVAL; + if (pf == NFPROTO_INET) { ret = nf_logger_find_get(NFPROTO_IPV4, type); if (ret < 0) diff --git a/net/netfilter/nf_nat_bpf.c b/net/netfilter/nf_nat_bpf.c index 6e3b2f58855f..481be15609b1 100644 --- a/net/netfilter/nf_nat_bpf.c +++ b/net/netfilter/nf_nat_bpf.c @@ -54,9 +54,9 @@ __bpf_kfunc int bpf_ct_set_nat_info(struct nf_conn___init *nfct, __bpf_kfunc_end_defs(); -BTF_SET8_START(nf_nat_kfunc_set) +BTF_KFUNCS_START(nf_nat_kfunc_set) BTF_ID_FLAGS(func, bpf_ct_set_nat_info, KF_TRUSTED_ARGS) -BTF_SET8_END(nf_nat_kfunc_set) +BTF_KFUNCS_END(nf_nat_kfunc_set) static const struct btf_kfunc_id_set nf_bpf_nat_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index e2f334f70281..7f12e56e6e52 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -248,109 +248,3 @@ int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, return 0; } EXPORT_SYMBOL_GPL(nf_queue); - -static unsigned int nf_iterate(struct sk_buff *skb, - struct nf_hook_state *state, - const struct nf_hook_entries *hooks, - unsigned int *index) -{ - const struct nf_hook_entry *hook; - unsigned int verdict, i = *index; - - while (i < hooks->num_hook_entries) { - hook = &hooks->hooks[i]; -repeat: - verdict = nf_hook_entry_hookfn(hook, skb, state); - if (verdict != NF_ACCEPT) { - *index = i; - if (verdict != NF_REPEAT) - return verdict; - goto repeat; - } - i++; - } - - *index = i; - return NF_ACCEPT; -} - -static struct nf_hook_entries *nf_hook_entries_head(const struct net *net, u8 pf, u8 hooknum) -{ - switch (pf) { -#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE - case NFPROTO_BRIDGE: - return rcu_dereference(net->nf.hooks_bridge[hooknum]); -#endif - case NFPROTO_IPV4: - return rcu_dereference(net->nf.hooks_ipv4[hooknum]); - case NFPROTO_IPV6: - return rcu_dereference(net->nf.hooks_ipv6[hooknum]); - default: - WARN_ON_ONCE(1); - return NULL; - } - - return NULL; -} - -/* Caller must hold rcu read-side lock */ -void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) -{ - const struct nf_hook_entry *hook_entry; - const struct nf_hook_entries *hooks; - struct sk_buff *skb = entry->skb; - const struct net *net; - unsigned int i; - int err; - u8 pf; - - net = entry->state.net; - pf = entry->state.pf; - - hooks = nf_hook_entries_head(net, pf, entry->state.hook); - - i = entry->hook_index; - if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) { - kfree_skb(skb); - nf_queue_entry_free(entry); - return; - } - - hook_entry = &hooks->hooks[i]; - - /* Continue traversal iff userspace said ok... */ - if (verdict == NF_REPEAT) - verdict = nf_hook_entry_hookfn(hook_entry, skb, &entry->state); - - if (verdict == NF_ACCEPT) { - if (nf_reroute(skb, entry) < 0) - verdict = NF_DROP; - } - - if (verdict == NF_ACCEPT) { -next_hook: - ++i; - verdict = nf_iterate(skb, &entry->state, hooks, &i); - } - - switch (verdict & NF_VERDICT_MASK) { - case NF_ACCEPT: - case NF_STOP: - local_bh_disable(); - entry->state.okfn(entry->state.net, entry->state.sk, skb); - local_bh_enable(); - break; - case NF_QUEUE: - err = nf_queue(skb, &entry->state, i, verdict); - if (err == 1) - goto next_hook; - break; - case NF_STOLEN: - break; - default: - kfree_skb(skb); - } - - nf_queue_entry_free(entry); -} -EXPORT_SYMBOL(nf_reinject); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index fbbc4fd37349..5b140c12b7df 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -800,7 +800,7 @@ synproxy_build_ip_ipv6(struct net *net, struct sk_buff *skb, skb_reset_network_header(skb); iph = skb_put(skb, sizeof(*iph)); ip6_flow_hdr(iph, 0, 0); - iph->hop_limit = net->ipv6.devconf_all->hop_limit; + iph->hop_limit = READ_ONCE(net->ipv6.devconf_all->hop_limit); iph->nexthdr = IPPROTO_TCP; iph->saddr = *saddr; iph->daddr = *daddr; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1683dc196b59..e93f905e60b6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1195,8 +1195,10 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table) #define __NFT_TABLE_F_INTERNAL (NFT_TABLE_F_MASK + 1) #define __NFT_TABLE_F_WAS_DORMANT (__NFT_TABLE_F_INTERNAL << 0) #define __NFT_TABLE_F_WAS_AWAKEN (__NFT_TABLE_F_INTERNAL << 1) +#define __NFT_TABLE_F_WAS_ORPHAN (__NFT_TABLE_F_INTERNAL << 2) #define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ - __NFT_TABLE_F_WAS_AWAKEN) + __NFT_TABLE_F_WAS_AWAKEN | \ + __NFT_TABLE_F_WAS_ORPHAN) static int nf_tables_updtable(struct nft_ctx *ctx) { @@ -1216,8 +1218,11 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if ((nft_table_has_owner(ctx->table) && !(flags & NFT_TABLE_F_OWNER)) || - (!nft_table_has_owner(ctx->table) && - flags & NFT_TABLE_F_OWNER)) + (flags & NFT_TABLE_F_OWNER && + !nft_table_is_orphan(ctx->table))) + return -EOPNOTSUPP; + + if ((flags ^ ctx->table->flags) & NFT_TABLE_F_PERSIST) return -EOPNOTSUPP; /* No dormant off/on/off/on games in single transaction */ @@ -1246,6 +1251,13 @@ static int nf_tables_updtable(struct nft_ctx *ctx) } } + if ((flags & NFT_TABLE_F_OWNER) && + !nft_table_has_owner(ctx->table)) { + ctx->table->nlpid = ctx->portid; + ctx->table->flags |= NFT_TABLE_F_OWNER | + __NFT_TABLE_F_WAS_ORPHAN; + } + nft_trans_table_update(trans) = true; nft_trans_commit_list_add_tail(ctx->net, trans); @@ -4238,23 +4250,18 @@ static bool nft_set_ops_candidate(const struct nft_set_type *type, u32 flags) * given, in that case the amount of memory per element is used. */ static const struct nft_set_ops * -nft_select_set_ops(const struct nft_ctx *ctx, - const struct nlattr * const nla[], +nft_select_set_ops(const struct nft_ctx *ctx, u32 flags, const struct nft_set_desc *desc) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; const struct nft_set_type *type; - u32 flags = 0; int i; lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); - if (nla[NFTA_SET_FLAGS] != NULL) - flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); - bops = NULL; best.size = ~0; best.lookup = ~0; @@ -5146,7 +5153,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; - ops = nft_select_set_ops(&ctx, nla, &desc); + ops = nft_select_set_ops(&ctx, flags, &desc); if (IS_ERR(ops)) return PTR_ERR(ops); @@ -10435,6 +10442,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } else if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_AWAKEN) { trans->ctx.table->flags &= ~NFT_TABLE_F_DORMANT; } + if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_ORPHAN) { + trans->ctx.table->flags &= ~NFT_TABLE_F_OWNER; + trans->ctx.table->nlpid = 0; + } trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE; nft_trans_destroy(trans); } else { @@ -11361,6 +11372,10 @@ again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && n->portid == table->nlpid) { + if (table->flags & NFT_TABLE_F_PERSIST) { + table->flags &= ~NFT_TABLE_F_OWNER; + continue; + } __nft_release_hook(net, table); list_del_rcu(&table->list); to_delete[deleted++] = table; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 5cf38fc0a366..00f4bd21c59b 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -225,6 +225,148 @@ find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) return entry; } +static unsigned int nf_iterate(struct sk_buff *skb, + struct nf_hook_state *state, + const struct nf_hook_entries *hooks, + unsigned int *index) +{ + const struct nf_hook_entry *hook; + unsigned int verdict, i = *index; + + while (i < hooks->num_hook_entries) { + hook = &hooks->hooks[i]; +repeat: + verdict = nf_hook_entry_hookfn(hook, skb, state); + if (verdict != NF_ACCEPT) { + *index = i; + if (verdict != NF_REPEAT) + return verdict; + goto repeat; + } + i++; + } + + *index = i; + return NF_ACCEPT; +} + +static struct nf_hook_entries *nf_hook_entries_head(const struct net *net, u8 pf, u8 hooknum) +{ + switch (pf) { +#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE + case NFPROTO_BRIDGE: + return rcu_dereference(net->nf.hooks_bridge[hooknum]); +#endif + case NFPROTO_IPV4: + return rcu_dereference(net->nf.hooks_ipv4[hooknum]); + case NFPROTO_IPV6: + return rcu_dereference(net->nf.hooks_ipv6[hooknum]); + default: + WARN_ON_ONCE(1); + return NULL; + } + + return NULL; +} + +static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) +{ +#ifdef CONFIG_INET + const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); + + if (entry->state.hook == NF_INET_LOCAL_OUT) { + const struct iphdr *iph = ip_hdr(skb); + + if (!(iph->tos == rt_info->tos && + skb->mark == rt_info->mark && + iph->daddr == rt_info->daddr && + iph->saddr == rt_info->saddr)) + return ip_route_me_harder(entry->state.net, entry->state.sk, + skb, RTN_UNSPEC); + } +#endif + return 0; +} + +static int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry) +{ + const struct nf_ipv6_ops *v6ops; + int ret = 0; + + switch (entry->state.pf) { + case AF_INET: + ret = nf_ip_reroute(skb, entry); + break; + case AF_INET6: + v6ops = rcu_dereference(nf_ipv6_ops); + if (v6ops) + ret = v6ops->reroute(skb, entry); + break; + } + return ret; +} + +/* caller must hold rcu read-side lock */ +static void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) +{ + const struct nf_hook_entry *hook_entry; + const struct nf_hook_entries *hooks; + struct sk_buff *skb = entry->skb; + const struct net *net; + unsigned int i; + int err; + u8 pf; + + net = entry->state.net; + pf = entry->state.pf; + + hooks = nf_hook_entries_head(net, pf, entry->state.hook); + + i = entry->hook_index; + if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) { + kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); + nf_queue_entry_free(entry); + return; + } + + hook_entry = &hooks->hooks[i]; + + /* Continue traversal iff userspace said ok... */ + if (verdict == NF_REPEAT) + verdict = nf_hook_entry_hookfn(hook_entry, skb, &entry->state); + + if (verdict == NF_ACCEPT) { + if (nf_reroute(skb, entry) < 0) + verdict = NF_DROP; + } + + if (verdict == NF_ACCEPT) { +next_hook: + ++i; + verdict = nf_iterate(skb, &entry->state, hooks, &i); + } + + switch (verdict & NF_VERDICT_MASK) { + case NF_ACCEPT: + case NF_STOP: + local_bh_disable(); + entry->state.okfn(entry->state.net, entry->state.sk, skb); + local_bh_enable(); + break; + case NF_QUEUE: + err = nf_queue(skb, &entry->state, i, verdict); + if (err == 1) + goto next_hook; + break; + case NF_STOLEN: + break; + default: + kfree_skb(skb); + } + + nf_queue_entry_free(entry); +} + static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_ct_hook *ct_hook; diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index 7f61506e5b44..7fec57ff736f 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -63,7 +63,6 @@ static int nft_osf_init(const struct nft_ctx *ctx, { struct nft_osf *priv = nft_expr_priv(expr); u32 flags; - int err; u8 ttl; if (!tb[NFTA_OSF_DREG]) @@ -83,13 +82,9 @@ static int nft_osf_init(const struct nft_ctx *ctx, priv->flags = flags; } - err = nft_parse_register_store(ctx, tb[NFTA_OSF_DREG], &priv->dreg, - NULL, NFT_DATA_VALUE, - NFT_OSF_MAXGENRELEN); - if (err < 0) - return err; - - return 0; + return nft_parse_register_store(ctx, tb[NFTA_OSF_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, + NFT_OSF_MAXGENRELEN); } static int nft_osf_dump(struct sk_buff *skb, diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index aa1d9e93a9a0..c0ceea068936 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -359,11 +359,13 @@ * * Return: -1 on no match, bit position on 'match_only', 0 otherwise. */ -int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, - union nft_pipapo_map_bucket *mt, bool match_only) +int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules, + unsigned long *dst, + const union nft_pipapo_map_bucket *mt, bool match_only) { unsigned long bitset; - int k, ret = -1; + unsigned int k; + int ret = -1; for (k = 0; k < len; k++) { bitset = map[k]; @@ -412,9 +414,9 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, struct nft_pipapo_scratch *scratch; unsigned long *res_map, *fill_map; u8 genmask = nft_genmask_cur(net); + const struct nft_pipapo_match *m; + const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; - struct nft_pipapo_match *m; - struct nft_pipapo_field *f; bool map_index; int i; @@ -505,6 +507,7 @@ out: * @data: Key data to be matched against existing elements * @genmask: If set, check that element is active in given genmask * @tstamp: timestamp to check for expired elements + * @gfp: the type of memory to allocate (see kmalloc). * * This is essentially the same as the lookup function, except that it matches * key data against the uncommitted copy and doesn't use preallocated maps for @@ -515,22 +518,26 @@ out: static struct nft_pipapo_elem *pipapo_get(const struct net *net, const struct nft_set *set, const u8 *data, u8 genmask, - u64 tstamp) + u64 tstamp, gfp_t gfp) { struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT); struct nft_pipapo *priv = nft_set_priv(set); - struct nft_pipapo_match *m = priv->clone; unsigned long *res_map, *fill_map = NULL; - struct nft_pipapo_field *f; + const struct nft_pipapo_match *m; + const struct nft_pipapo_field *f; int i; - res_map = kmalloc_array(m->bsize_max, sizeof(*res_map), GFP_ATOMIC); + m = priv->clone; + if (m->bsize_max == 0) + return ret; + + res_map = kmalloc_array(m->bsize_max, sizeof(*res_map), gfp); if (!res_map) { ret = ERR_PTR(-ENOMEM); goto out; } - fill_map = kcalloc(m->bsize_max, sizeof(*res_map), GFP_ATOMIC); + fill_map = kcalloc(m->bsize_max, sizeof(*res_map), gfp); if (!fill_map) { ret = ERR_PTR(-ENOMEM); goto out; @@ -608,7 +615,8 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set, struct nft_pipapo_elem *e; e = pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net), get_jiffies_64()); + nft_genmask_cur(net), get_jiffies_64(), + GFP_ATOMIC); if (IS_ERR(e)) return ERR_CAST(e); @@ -616,6 +624,65 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set, } /** + * pipapo_realloc_mt() - Reallocate mapping table if needed upon resize + * @f: Field containing mapping table + * @old_rules: Amount of existing mapped rules + * @rules: Amount of new rules to map + * + * Return: 0 on success, negative error code on failure. + */ +static int pipapo_realloc_mt(struct nft_pipapo_field *f, + unsigned int old_rules, unsigned int rules) +{ + union nft_pipapo_map_bucket *new_mt = NULL, *old_mt = f->mt; + const unsigned int extra = PAGE_SIZE / sizeof(*new_mt); + unsigned int rules_alloc = rules; + + might_sleep(); + + if (unlikely(rules == 0)) + goto out_free; + + /* growing and enough space left, no action needed */ + if (rules > old_rules && f->rules_alloc > rules) + return 0; + + /* downsize and extra slack has not grown too large */ + if (rules < old_rules) { + unsigned int remove = f->rules_alloc - rules; + + if (remove < (2u * extra)) + return 0; + } + + /* If set needs more than one page of memory for rules then + * allocate another extra page to avoid frequent reallocation. + */ + if (rules > extra && + check_add_overflow(rules, extra, &rules_alloc)) + return -EOVERFLOW; + + new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL); + if (!new_mt) + return -ENOMEM; + + if (old_mt) + memcpy(new_mt, old_mt, min(old_rules, rules) * sizeof(*new_mt)); + + if (rules > old_rules) { + memset(new_mt + old_rules, 0, + (rules - old_rules) * sizeof(*new_mt)); + } +out_free: + f->rules_alloc = rules_alloc; + f->mt = new_mt; + + kvfree(old_mt); + + return 0; +} + +/** * pipapo_resize() - Resize lookup or mapping table, or both * @f: Field containing lookup and mapping tables * @old_rules: Previous amount of rules in field @@ -627,12 +694,15 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set, * * Return: 0 on success, -ENOMEM on allocation failure. */ -static int pipapo_resize(struct nft_pipapo_field *f, int old_rules, int rules) +static int pipapo_resize(struct nft_pipapo_field *f, + unsigned int old_rules, unsigned int rules) { long *new_lt = NULL, *new_p, *old_lt = f->lt, *old_p; - union nft_pipapo_map_bucket *new_mt, *old_mt = f->mt; - size_t new_bucket_size, copy; - int group, bucket; + unsigned int new_bucket_size, copy; + int group, bucket, err; + + if (rules >= NFT_PIPAPO_RULE0_MAX) + return -ENOSPC; new_bucket_size = DIV_ROUND_UP(rules, BITS_PER_LONG); #ifdef NFT_PIPAPO_ALIGN @@ -672,27 +742,18 @@ static int pipapo_resize(struct nft_pipapo_field *f, int old_rules, int rules) } mt: - new_mt = kvmalloc(rules * sizeof(*new_mt), GFP_KERNEL); - if (!new_mt) { + err = pipapo_realloc_mt(f, old_rules, rules); + if (err) { kvfree(new_lt); - return -ENOMEM; - } - - memcpy(new_mt, f->mt, min(old_rules, rules) * sizeof(*new_mt)); - if (rules > old_rules) { - memset(new_mt + old_rules, 0, - (rules - old_rules) * sizeof(*new_mt)); + return err; } if (new_lt) { f->bsize = new_bucket_size; - NFT_PIPAPO_LT_ASSIGN(f, new_lt); + f->lt = new_lt; kvfree(old_lt); } - f->mt = new_mt; - kvfree(old_mt); - return 0; } @@ -843,8 +904,8 @@ static void pipapo_lt_8b_to_4b(int old_groups, int bsize, */ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f) { + unsigned int groups, bb; unsigned long *new_lt; - int groups, bb; size_t lt_size; lt_size = f->groups * NFT_PIPAPO_BUCKETS(f->bb) * f->bsize * @@ -894,7 +955,7 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f) f->groups = groups; f->bb = bb; kvfree(f->lt); - NFT_PIPAPO_LT_ASSIGN(f, new_lt); + f->lt = new_lt; } /** @@ -911,7 +972,7 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f) static int pipapo_insert(struct nft_pipapo_field *f, const uint8_t *k, int mask_bits) { - int rule = f->rules, group, ret, bit_offset = 0; + unsigned int rule = f->rules, group, ret, bit_offset = 0; ret = pipapo_resize(f, f->rules, f->rules + 1); if (ret) @@ -1216,7 +1277,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, else end = start; - dup = pipapo_get(net, set, start, genmask, tstamp); + dup = pipapo_get(net, set, start, genmask, tstamp, GFP_KERNEL); if (!IS_ERR(dup)) { /* Check if we already have the same exact entry */ const struct nft_data *dup_key, *dup_end; @@ -1238,7 +1299,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (PTR_ERR(dup) == -ENOENT) { /* Look for partially overlapping entries */ - dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp); + dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp, + GFP_KERNEL); } if (PTR_ERR(dup) != -ENOENT) { @@ -1251,8 +1313,14 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, /* Validate */ start_p = start; end_p = end; + + /* some helpers return -1, or 0 >= for valid rule pos, + * so we cannot support more than INT_MAX rules at this time. + */ + BUILD_BUG_ON(NFT_PIPAPO_RULE0_MAX > INT_MAX); + nft_pipapo_for_each_field(f, i, m) { - if (f->rules >= (unsigned long)NFT_PIPAPO_RULE0_MAX) + if (f->rules >= NFT_PIPAPO_RULE0_MAX) return -ENOSPC; if (memcmp(start_p, end_p, @@ -1358,18 +1426,25 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) if (!new_lt) goto out_lt; - NFT_PIPAPO_LT_ASSIGN(dst, new_lt); + dst->lt = new_lt; memcpy(NFT_PIPAPO_LT_ALIGN(new_lt), NFT_PIPAPO_LT_ALIGN(src->lt), src->bsize * sizeof(*dst->lt) * src->groups * NFT_PIPAPO_BUCKETS(src->bb)); - dst->mt = kvmalloc(src->rules * sizeof(*src->mt), GFP_KERNEL); - if (!dst->mt) - goto out_mt; + if (src->rules > 0) { + dst->mt = kvmalloc_array(src->rules_alloc, + sizeof(*src->mt), GFP_KERNEL); + if (!dst->mt) + goto out_mt; + + memcpy(dst->mt, src->mt, src->rules * sizeof(*src->mt)); + } else { + dst->mt = NULL; + dst->rules_alloc = 0; + } - memcpy(dst->mt, src->mt, src->rules * sizeof(*src->mt)); src++; dst++; } @@ -1423,10 +1498,10 @@ out_scratch: * * Return: Number of rules that originated from the same entry as @first. */ -static int pipapo_rules_same_key(struct nft_pipapo_field *f, int first) +static unsigned int pipapo_rules_same_key(struct nft_pipapo_field *f, unsigned int first) { struct nft_pipapo_elem *e = NULL; /* Keep gcc happy */ - int r; + unsigned int r; for (r = first; r < f->rules; r++) { if (r != first && e != f->mt[r].e) @@ -1479,8 +1554,9 @@ static int pipapo_rules_same_key(struct nft_pipapo_field *f, int first) * 0 1 2 * element pointers: 0x42 0x42 0x44 */ -static void pipapo_unmap(union nft_pipapo_map_bucket *mt, int rules, - int start, int n, int to_offset, bool is_last) +static void pipapo_unmap(union nft_pipapo_map_bucket *mt, unsigned int rules, + unsigned int start, unsigned int n, + unsigned int to_offset, bool is_last) { int i; @@ -1586,8 +1662,8 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); + unsigned int rules_f0, first_rule = 0; u64 tstamp = nft_net_tstamp(net); - int rules_f0, first_rule = 0; struct nft_pipapo_elem *e; struct nft_trans_gc *gc; @@ -1597,8 +1673,8 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; - struct nft_pipapo_field *f; - int i, start, rules_fx; + const struct nft_pipapo_field *f; + unsigned int i, start, rules_fx; start = first_rule; rules_fx = rules_f0; @@ -1792,7 +1868,8 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set, { struct nft_pipapo_elem *e; - e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net)); + e = pipapo_get(net, set, data, nft_genmask_next(net), + nft_net_tstamp(net), GFP_KERNEL); if (IS_ERR(e)) return NULL; @@ -1976,7 +2053,7 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; - int rules_f0, first_rule = 0; + unsigned int rules_f0, first_rule = 0; struct nft_pipapo_elem *e; const u8 *data; @@ -2039,9 +2116,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, { struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); - struct nft_pipapo_match *m; - struct nft_pipapo_field *f; - int i, r; + const struct nft_pipapo_match *m; + const struct nft_pipapo_field *f; + unsigned int i, r; rcu_read_lock(); if (iter->genmask == nft_genmask_cur(net)) @@ -2145,6 +2222,9 @@ static int nft_pipapo_init(const struct nft_set *set, field_count = desc->field_count ? : 1; + BUILD_BUG_ON(NFT_PIPAPO_MAX_FIELDS > 255); + BUILD_BUG_ON(NFT_PIPAPO_MAX_FIELDS != NFT_REG32_COUNT); + if (field_count > NFT_PIPAPO_MAX_FIELDS) return -EINVAL; @@ -2166,7 +2246,11 @@ static int nft_pipapo_init(const struct nft_set *set, rcu_head_init(&m->rcu); nft_pipapo_for_each_field(f, i, m) { - int len = desc->field_len[i] ? : set->klen; + unsigned int len = desc->field_len[i] ? : set->klen; + + /* f->groups is u8 */ + BUILD_BUG_ON((NFT_PIPAPO_MAX_BYTES * + BITS_PER_BYTE / NFT_PIPAPO_GROUP_BITS_LARGE_SET) >= 256); f->bb = NFT_PIPAPO_GROUP_BITS_INIT; f->groups = len * NFT_PIPAPO_GROUPS_PER_BYTE(f); @@ -2175,7 +2259,8 @@ static int nft_pipapo_init(const struct nft_set *set, f->bsize = 0; f->rules = 0; - NFT_PIPAPO_LT_ASSIGN(f, NULL); + f->rules_alloc = 0; + f->lt = NULL; f->mt = NULL; } @@ -2211,7 +2296,7 @@ static void nft_set_pipapo_match_destroy(const struct nft_ctx *ctx, struct nft_pipapo_match *m) { struct nft_pipapo_field *f; - int i, r; + unsigned int i, r; for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) ; diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 3842c7341a9f..24cd1ff73f98 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -70,15 +70,9 @@ #define NFT_PIPAPO_ALIGN_HEADROOM \ (NFT_PIPAPO_ALIGN - ARCH_KMALLOC_MINALIGN) #define NFT_PIPAPO_LT_ALIGN(lt) (PTR_ALIGN((lt), NFT_PIPAPO_ALIGN)) -#define NFT_PIPAPO_LT_ASSIGN(field, x) \ - do { \ - (field)->lt_aligned = NFT_PIPAPO_LT_ALIGN(x); \ - (field)->lt = (x); \ - } while (0) #else #define NFT_PIPAPO_ALIGN_HEADROOM 0 #define NFT_PIPAPO_LT_ALIGN(lt) (lt) -#define NFT_PIPAPO_LT_ASSIGN(field, x) ((field)->lt = (x)) #endif /* NFT_PIPAPO_ALIGN */ #define nft_pipapo_for_each_field(field, index, match) \ @@ -110,22 +104,20 @@ union nft_pipapo_map_bucket { /** * struct nft_pipapo_field - Lookup, mapping tables and related data for a field - * @groups: Amount of bit groups * @rules: Number of inserted rules * @bsize: Size of each bucket in lookup table, in longs + * @rules_alloc: Number of allocated rules, always >= rules + * @groups: Amount of bit groups * @bb: Number of bits grouped together in lookup table buckets * @lt: Lookup table: 'groups' rows of buckets - * @lt_aligned: Version of @lt aligned to NFT_PIPAPO_ALIGN bytes * @mt: Mapping table: one bucket per rule */ struct nft_pipapo_field { - int groups; - unsigned long rules; - size_t bsize; - int bb; -#ifdef NFT_PIPAPO_ALIGN - unsigned long *lt_aligned; -#endif + unsigned int rules; + unsigned int bsize; + unsigned int rules_alloc; + u8 groups; + u8 bb; unsigned long *lt; union nft_pipapo_map_bucket *mt; }; @@ -145,15 +137,15 @@ struct nft_pipapo_scratch { /** * struct nft_pipapo_match - Data used for lookup and matching * @field_count: Amount of fields in set - * @scratch: Preallocated per-CPU maps for partial matching results * @bsize_max: Maximum lookup table bucket size of all fields, in longs + * @scratch: Preallocated per-CPU maps for partial matching results * @rcu: Matching data is swapped on commits * @f: Fields, with lookup and mapping tables */ struct nft_pipapo_match { - int field_count; + u8 field_count; + unsigned int bsize_max; struct nft_pipapo_scratch * __percpu *scratch; - size_t bsize_max; struct rcu_head rcu; struct nft_pipapo_field f[] __counted_by(field_count); }; @@ -186,8 +178,9 @@ struct nft_pipapo_elem { struct nft_set_ext ext; }; -int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, - union nft_pipapo_map_bucket *mt, bool match_only); +int pipapo_refill(unsigned long *map, unsigned int len, unsigned int rules, + unsigned long *dst, + const union nft_pipapo_map_bucket *mt, bool match_only); /** * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets @@ -195,7 +188,7 @@ int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, * @dst: Area to store result * @data: Input data selecting table buckets */ -static inline void pipapo_and_field_buckets_4bit(struct nft_pipapo_field *f, +static inline void pipapo_and_field_buckets_4bit(const struct nft_pipapo_field *f, unsigned long *dst, const u8 *data) { @@ -223,7 +216,7 @@ static inline void pipapo_and_field_buckets_4bit(struct nft_pipapo_field *f, * @dst: Area to store result * @data: Input data selecting table buckets */ -static inline void pipapo_and_field_buckets_8bit(struct nft_pipapo_field *f, +static inline void pipapo_and_field_buckets_8bit(const struct nft_pipapo_field *f, unsigned long *dst, const u8 *data) { diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index a3a8ddca9918..d08407d589ea 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -212,8 +212,9 @@ static int nft_pipapo_avx2_refill(int offset, unsigned long *map, * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_4b_2(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; u8 pg[2] = { pkt[0] >> 4, pkt[0] & 0xf }; @@ -274,8 +275,9 @@ nothing: * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_4b_4(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; u8 pg[4] = { pkt[0] >> 4, pkt[0] & 0xf, pkt[1] >> 4, pkt[1] & 0xf }; @@ -350,8 +352,9 @@ nothing: * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_4b_8(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { u8 pg[8] = { pkt[0] >> 4, pkt[0] & 0xf, pkt[1] >> 4, pkt[1] & 0xf, pkt[2] >> 4, pkt[2] & 0xf, pkt[3] >> 4, pkt[3] & 0xf, @@ -445,8 +448,9 @@ nothing: * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_4b_12(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { u8 pg[12] = { pkt[0] >> 4, pkt[0] & 0xf, pkt[1] >> 4, pkt[1] & 0xf, pkt[2] >> 4, pkt[2] & 0xf, pkt[3] >> 4, pkt[3] & 0xf, @@ -534,8 +538,9 @@ nothing: * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_4b_32(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { u8 pg[32] = { pkt[0] >> 4, pkt[0] & 0xf, pkt[1] >> 4, pkt[1] & 0xf, pkt[2] >> 4, pkt[2] & 0xf, pkt[3] >> 4, pkt[3] & 0xf, @@ -669,8 +674,9 @@ nothing: * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_8b_1(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; unsigned long *lt = f->lt, bsize = f->bsize; @@ -726,8 +732,9 @@ nothing: * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_8b_2(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; unsigned long *lt = f->lt, bsize = f->bsize; @@ -790,8 +797,9 @@ nothing: * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_8b_4(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; unsigned long *lt = f->lt, bsize = f->bsize; @@ -865,8 +873,9 @@ nothing: * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; unsigned long *lt = f->lt, bsize = f->bsize; @@ -950,8 +959,9 @@ nothing: * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { int i, ret = -1, m256_size = f->bsize / NFT_PIPAPO_LONGS_PER_M256, b; unsigned long *lt = f->lt, bsize = f->bsize; @@ -1042,8 +1052,9 @@ nothing: * word index to be checked next (i.e. first filled word). */ static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill, - struct nft_pipapo_field *f, int offset, - const u8 *pkt, bool first, bool last) + const struct nft_pipapo_field *f, + int offset, const u8 *pkt, + bool first, bool last) { unsigned long bsize = f->bsize; int i, ret = -1, b; @@ -1119,9 +1130,9 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); + const struct nft_pipapo_match *m; + const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; - struct nft_pipapo_match *m; - struct nft_pipapo_field *f; unsigned long *res, *fill; bool map_index; int i, ret = 0; diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index acef4155f0da..008419db815a 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -179,43 +179,6 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, } EXPORT_SYMBOL_GPL(nf_route); -static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) -{ -#ifdef CONFIG_INET - const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); - - if (entry->state.hook == NF_INET_LOCAL_OUT) { - const struct iphdr *iph = ip_hdr(skb); - - if (!(iph->tos == rt_info->tos && - skb->mark == rt_info->mark && - iph->daddr == rt_info->daddr && - iph->saddr == rt_info->saddr)) - return ip_route_me_harder(entry->state.net, entry->state.sk, - skb, RTN_UNSPEC); - } -#endif - return 0; -} - -int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry) -{ - const struct nf_ipv6_ops *v6ops; - int ret = 0; - - switch (entry->state.pf) { - case AF_INET: - ret = nf_ip_reroute(skb, entry); - break; - case AF_INET6: - v6ops = rcu_dereference(nf_ipv6_ops); - if (v6ops) - ret = v6ops->reroute(skb, entry); - break; - } - return ret; -} - /* Only get and check the lengths, not do any hop-by-hop stuff. */ int nf_ip6_check_hbh_len(struct sk_buff *skb, u32 *plen) { diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 21624d68314f..da5d929c7c85 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1142,7 +1142,8 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, if (target->compat_from_user) target->compat_from_user(t->data, ct->data); else - memcpy(t->data, ct->data, tsize - sizeof(*ct)); + unsafe_memcpy(t->data, ct->data, tsize - sizeof(*ct), + /* UAPI 0-sized destination */); tsize += off; t->u.user.target_size = tsize; diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 27511c90a26f..1ba4f58e1d35 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -610,7 +610,7 @@ int netlbl_catmap_walk(struct netlbl_lsm_catmap *catmap, u32 offset) struct netlbl_lsm_catmap *iter; u32 idx; u32 bit; - NETLBL_CATMAP_MAPTYPE bitmap; + u64 bitmap; iter = _netlbl_catmap_getnode(&catmap, offset, _CM_F_WALK, 0); if (iter == NULL) @@ -666,8 +666,8 @@ int netlbl_catmap_walkrng(struct netlbl_lsm_catmap *catmap, u32 offset) struct netlbl_lsm_catmap *prev = NULL; u32 idx; u32 bit; - NETLBL_CATMAP_MAPTYPE bitmask; - NETLBL_CATMAP_MAPTYPE bitmap; + u64 bitmask; + u64 bitmap; iter = _netlbl_catmap_getnode(&catmap, offset, _CM_F_WALK, 0); if (iter == NULL) @@ -857,7 +857,7 @@ int netlbl_catmap_setlong(struct netlbl_lsm_catmap **catmap, offset -= iter->startbit; idx = offset / NETLBL_CATMAP_MAPSIZE; - iter->bitmap[idx] |= (NETLBL_CATMAP_MAPTYPE)bitmap + iter->bitmap[idx] |= (u64)bitmap << (offset % NETLBL_CATMAP_MAPSIZE); return 0; @@ -876,7 +876,7 @@ int netlbl_catmap_setlong(struct netlbl_lsm_catmap **catmap, * Description: * Starting at @offset, walk the bitmap from left to right until either the * desired bit is found or we reach the end. Return the bit offset, -1 if - * not found, or -2 if error. + * not found. */ int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len, u32 offset, u8 state) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index ff315351269f..7554803218a2 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -130,7 +130,7 @@ static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = { "nlk_cb_mutex-MAX_LINKS" }; -static int netlink_dump(struct sock *sk); +static int netlink_dump(struct sock *sk, bool lock_taken); /* nl_table locking explained: * Lookup and traversal are protected with an RCU read-side lock. Insertion @@ -636,7 +636,7 @@ static struct proto netlink_proto = { }; static int __netlink_create(struct net *net, struct socket *sock, - struct mutex *cb_mutex, int protocol, + struct mutex *dump_cb_mutex, int protocol, int kern) { struct sock *sk; @@ -651,15 +651,11 @@ static int __netlink_create(struct net *net, struct socket *sock, sock_init_data(sock, sk); nlk = nlk_sk(sk); - if (cb_mutex) { - nlk->cb_mutex = cb_mutex; - } else { - nlk->cb_mutex = &nlk->cb_def_mutex; - mutex_init(nlk->cb_mutex); - lockdep_set_class_and_name(nlk->cb_mutex, + mutex_init(&nlk->nl_cb_mutex); + lockdep_set_class_and_name(&nlk->nl_cb_mutex, nlk_cb_mutex_keys + protocol, nlk_cb_mutex_key_strings[protocol]); - } + nlk->dump_cb_mutex = dump_cb_mutex; init_waitqueue_head(&nlk->wait); sk->sk_destruct = netlink_sock_destruct; @@ -1206,23 +1202,21 @@ struct sock *netlink_getsockbyfilp(struct file *filp) struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast) { + size_t head_size = SKB_HEAD_ALIGN(size); struct sk_buff *skb; void *data; - if (size <= NLMSG_GOODSIZE || broadcast) + if (head_size <= PAGE_SIZE || broadcast) return alloc_skb(size, GFP_KERNEL); - size = SKB_DATA_ALIGN(size) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - - data = vmalloc(size); - if (data == NULL) + data = kvmalloc(head_size, GFP_KERNEL); + if (!data) return NULL; - skb = __build_skb(data, size); - if (skb == NULL) - vfree(data); - else + skb = __build_skb(data, head_size); + if (!skb) + kvfree(data); + else if (is_vmalloc_addr(data)) skb->destructor = netlink_skb_destructor; return skb; @@ -1779,6 +1773,9 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, netlink_unlock_table(); return err; } + case NETLINK_LISTEN_ALL_NSID: + flag = NETLINK_F_LISTEN_ALL_NSID; + break; case NETLINK_CAP_ACK: flag = NETLINK_F_CAP_ACK; break; @@ -1987,7 +1984,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (READ_ONCE(nlk->cb_running) && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { - ret = netlink_dump(sk); + ret = netlink_dump(sk, false); if (ret) { WRITE_ONCE(sk->sk_err, -ret); sk_error_report(sk); @@ -2196,7 +2193,7 @@ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, return 0; } -static int netlink_dump(struct sock *sk) +static int netlink_dump(struct sock *sk, bool lock_taken) { struct netlink_sock *nlk = nlk_sk(sk); struct netlink_ext_ack extack = {}; @@ -2208,7 +2205,8 @@ static int netlink_dump(struct sock *sk) int alloc_min_size; int alloc_size; - mutex_lock(nlk->cb_mutex); + if (!lock_taken) + mutex_lock(&nlk->nl_cb_mutex); if (!nlk->cb_running) { err = -EINVAL; goto errout_skb; @@ -2260,14 +2258,33 @@ static int netlink_dump(struct sock *sk) netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { + struct mutex *extra_mutex = nlk->dump_cb_mutex; + cb->extack = &extack; + + if (cb->flags & RTNL_FLAG_DUMP_UNLOCKED) + extra_mutex = NULL; + if (extra_mutex) + mutex_lock(extra_mutex); nlk->dump_done_errno = cb->dump(skb, cb); + if (extra_mutex) + mutex_unlock(extra_mutex); + + /* EMSGSIZE plus something already in the skb means + * that there's more to dump but current skb has filled up. + * If the callback really wants to return EMSGSIZE to user space + * it needs to do so again, on the next cb->dump() call, + * without putting data in the skb. + */ + if (nlk->dump_done_errno == -EMSGSIZE && skb->len) + nlk->dump_done_errno = skb->len; + cb->extack = NULL; } if (nlk->dump_done_errno > 0 || skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { - mutex_unlock(nlk->cb_mutex); + mutex_unlock(&nlk->nl_cb_mutex); if (sk_filter(sk, skb)) kfree_skb(skb); @@ -2301,13 +2318,13 @@ static int netlink_dump(struct sock *sk) WRITE_ONCE(nlk->cb_running, false); module = cb->module; skb = cb->skb; - mutex_unlock(nlk->cb_mutex); + mutex_unlock(&nlk->nl_cb_mutex); module_put(module); consume_skb(skb); return 0; errout_skb: - mutex_unlock(nlk->cb_mutex); + mutex_unlock(&nlk->nl_cb_mutex); kfree_skb(skb); return err; } @@ -2330,7 +2347,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, } nlk = nlk_sk(sk); - mutex_lock(nlk->cb_mutex); + mutex_lock(&nlk->nl_cb_mutex); /* A dump is in progress... */ if (nlk->cb_running) { ret = -EBUSY; @@ -2350,6 +2367,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->data = control->data; cb->module = control->module; cb->min_dump_alloc = control->min_dump_alloc; + cb->flags = control->flags; cb->skb = skb; cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); @@ -2365,9 +2383,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, WRITE_ONCE(nlk->cb_running, true); nlk->dump_done_errno = INT_MAX; - mutex_unlock(nlk->cb_mutex); - - ret = netlink_dump(sk); + ret = netlink_dump(sk, true); sock_put(sk); @@ -2383,7 +2399,7 @@ error_put: module_put(control->module); error_unlock: sock_put(sk); - mutex_unlock(nlk->cb_mutex); + mutex_unlock(&nlk->nl_cb_mutex); error_free: kfree_skb(skb); return ret; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 2145979b9986..9751e29d4bbb 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -39,8 +39,9 @@ struct netlink_sock { bool cb_running; int dump_done_errno; struct netlink_callback cb; - struct mutex *cb_mutex; - struct mutex cb_def_mutex; + struct mutex nl_cb_mutex; + + struct mutex *dump_cb_mutex; void (*netlink_rcv)(struct sk_buff *skb); int (*netlink_bind)(struct net *net, int group); void (*netlink_unbind)(struct net *net, int group); diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 1eeff9422856..61981e01fd6f 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -207,7 +207,7 @@ static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) err = __netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num); } - return err < 0 ? err : skb->len; + return err <= 0 ? err : skb->len; } static int netlink_diag_dump_done(struct netlink_callback *cb) @@ -241,6 +241,7 @@ static int netlink_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler netlink_diag_handler = { + .owner = THIS_MODULE, .family = AF_NETLINK, .dump = netlink_diag_handler_dump, }; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 8c7af02f8454..3b7666944b11 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1232,7 +1232,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); if (hdr == NULL) - return -1; + return -EMSGSIZE; if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) || nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id) || @@ -1355,6 +1355,7 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); int fams_to_skip = cb->args[0]; unsigned int id; + int err = 0; idr_for_each_entry(&genl_fam_idr, rt, id) { if (!rt->netnsok && !net_eq(net, &init_net)) @@ -1363,16 +1364,17 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) if (n++ < fams_to_skip) continue; - if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - skb, CTRL_CMD_NEWFAMILY) < 0) { + err = ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + skb, CTRL_CMD_NEWFAMILY); + if (err) { n--; break; } } cb->args[0] = n; - return skb->len; + return err; } static struct sk_buff *ctrl_build_family_msg(const struct genl_family *family, @@ -1836,6 +1838,9 @@ static int genl_bind(struct net *net, int group) !ns_capable(net->user_ns, CAP_SYS_ADMIN)) ret = -EPERM; + if (family->bind) + family->bind(i); + break; } @@ -1843,12 +1848,39 @@ static int genl_bind(struct net *net, int group) return ret; } +static void genl_unbind(struct net *net, int group) +{ + const struct genl_family *family; + unsigned int id; + + down_read(&cb_lock); + + idr_for_each_entry(&genl_fam_idr, family, id) { + int i; + + if (family->n_mcgrps == 0) + continue; + + i = group - family->mcgrp_offset; + if (i < 0 || i >= family->n_mcgrps) + continue; + + if (family->unbind) + family->unbind(i); + + break; + } + + up_read(&cb_lock); +} + static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, .bind = genl_bind, + .unbind = genl_unbind, .release = genl_release, }; diff --git a/net/nfc/core.c b/net/nfc/core.c index eb2c0959e5b6..e58dc6405054 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -1015,7 +1015,7 @@ static void nfc_check_pres_timeout(struct timer_list *t) schedule_work(&dev->check_pres_work); } -struct class nfc_class = { +const struct class nfc_class = { .name = "nfc", .dev_release = nfc_release, }; diff --git a/net/nfc/hci/llc.c b/net/nfc/hci/llc.c index 2140f6724644..ba91284f4086 100644 --- a/net/nfc/hci/llc.c +++ b/net/nfc/hci/llc.c @@ -30,15 +30,19 @@ exit: return r; } +static void nfc_llc_del_engine(struct nfc_llc_engine *llc_engine) +{ + list_del(&llc_engine->entry); + kfree_const(llc_engine->name); + kfree(llc_engine); +} + void nfc_llc_exit(void) { struct nfc_llc_engine *llc_engine, *n; - list_for_each_entry_safe(llc_engine, n, &llc_engines, entry) { - list_del(&llc_engine->entry); - kfree(llc_engine->name); - kfree(llc_engine); - } + list_for_each_entry_safe(llc_engine, n, &llc_engines, entry) + nfc_llc_del_engine(llc_engine); } int nfc_llc_register(const char *name, const struct nfc_llc_ops *ops) @@ -49,7 +53,7 @@ int nfc_llc_register(const char *name, const struct nfc_llc_ops *ops) if (llc_engine == NULL) return -ENOMEM; - llc_engine->name = kstrdup(name, GFP_KERNEL); + llc_engine->name = kstrdup_const(name, GFP_KERNEL); if (llc_engine->name == NULL) { kfree(llc_engine); return -ENOMEM; @@ -82,9 +86,7 @@ void nfc_llc_unregister(const char *name) if (llc_engine == NULL) return; - list_del(&llc_engine->entry); - kfree(llc_engine->name); - kfree(llc_engine); + nfc_llc_del_engine(llc_engine); } struct nfc_llc *nfc_llc_allocate(const char *name, struct nfc_hci_dev *hdev, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c9bbc2686690..61270826b9ac 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2057,7 +2057,7 @@ retry: skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; - + skb->mono_delivery_time = !!skb->tstamp; skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) @@ -2318,7 +2318,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { - if (po->copy_thresh && + if (READ_ONCE(po->copy_thresh) && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); @@ -2586,6 +2586,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; + skb->mono_delivery_time = !!skb->tstamp; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -3064,6 +3065,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; + skb->mono_delivery_time = !!skb->tstamp; if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -3834,7 +3836,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; - pkt_sk(sk)->copy_thresh = val; + WRITE_ONCE(pkt_sk(sk)->copy_thresh, val); return 0; } case PACKET_VERSION: @@ -4088,6 +4090,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, case PACKET_VNET_HDR_SZ: val = READ_ONCE(po->vnet_hdr_sz); break; + case PACKET_COPY_THRESH: + val = READ_ONCE(pkt_sk(sk)->copy_thresh); + break; case PACKET_VERSION: val = po->tp_version; break; diff --git a/net/packet/diag.c b/net/packet/diag.c index 9a7980e3309d..47f69f3dbf73 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -17,7 +17,7 @@ static int pdiag_put_info(const struct packet_sock *po, struct sk_buff *nlskb) pinfo.pdi_index = po->ifindex; pinfo.pdi_version = po->tp_version; pinfo.pdi_reserve = po->tp_reserve; - pinfo.pdi_copy_thresh = po->copy_thresh; + pinfo.pdi_copy_thresh = READ_ONCE(po->copy_thresh); pinfo.pdi_tstamp = READ_ONCE(po->tp_tstamp); pinfo.pdi_flags = 0; @@ -245,6 +245,7 @@ static int packet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler packet_diag_handler = { + .owner = THIS_MODULE, .family = AF_PACKET, .dump = packet_diag_handler_dump, }; diff --git a/net/rds/connection.c b/net/rds/connection.c index b4cc699c5fad..c749c5525b40 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -829,9 +829,7 @@ int rds_conn_init(void) if (ret) return ret; - rds_conn_slab = kmem_cache_create("rds_connection", - sizeof(struct rds_connection), - 0, 0, NULL); + rds_conn_slab = KMEM_CACHE(rds_connection, 0); if (!rds_conn_slab) { rds_loop_net_exit(); return -ENOMEM; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 465bfe5eb061..5222bc97d192 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -487,7 +487,7 @@ EXPORT_SYMBOL(rxrpc_kernel_new_call_notification); * rxrpc_kernel_set_max_life - Set maximum lifespan on a call * @sock: The socket the call is on * @call: The call to configure - * @hard_timeout: The maximum lifespan of the call in jiffies + * @hard_timeout: The maximum lifespan of the call in ms * * Set the maximum lifespan of a call. The call will end with ETIME or * ETIMEDOUT if it takes longer than this. @@ -495,14 +495,14 @@ EXPORT_SYMBOL(rxrpc_kernel_new_call_notification); void rxrpc_kernel_set_max_life(struct socket *sock, struct rxrpc_call *call, unsigned long hard_timeout) { - unsigned long now; + ktime_t delay = ms_to_ktime(hard_timeout), expect_term_by; mutex_lock(&call->user_mutex); - now = jiffies; - hard_timeout += now; - WRITE_ONCE(call->expect_term_by, hard_timeout); - rxrpc_reduce_call_timer(call, hard_timeout, now, rxrpc_timer_set_for_hard); + expect_term_by = ktime_add(ktime_get_real(), delay); + WRITE_ONCE(call->expect_term_by, expect_term_by); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard); + rxrpc_poke_call(call, rxrpc_call_poke_set_timeout); mutex_unlock(&call->user_mutex); } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7818aae1be8e..08c0a32db8c7 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -198,8 +198,8 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ union { + struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ struct { u16 offset; /* Offset of data */ u16 len; /* Length of data */ @@ -208,9 +208,12 @@ struct rxrpc_skb_priv { }; struct { rxrpc_seq_t first_ack; /* First packet in acks table */ + rxrpc_seq_t prev_ack; /* Highest seq seen */ + rxrpc_serial_t acked_serial; /* Packet in response to (or 0) */ + u8 reason; /* Reason for ack */ u8 nr_acks; /* Number of acks+nacks */ u8 nr_nacks; /* Number of nacks */ - }; + } ack; }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; @@ -248,10 +251,9 @@ struct rxrpc_security { struct rxrpc_key_token *); /* Work out how much data we can store in a packet, given an estimate - * of the amount of data remaining. + * of the amount of data remaining and allocate a data buffer. */ - int (*how_much_data)(struct rxrpc_call *, size_t, - size_t *, size_t *, size_t *); + struct rxrpc_txbuf *(*alloc_txbuf)(struct rxrpc_call *call, size_t remaining, gfp_t gfp); /* impose security on a packet */ int (*secure_packet)(struct rxrpc_call *, struct rxrpc_txbuf *); @@ -292,6 +294,7 @@ struct rxrpc_local { struct socket *socket; /* my UDP socket */ struct task_struct *io_thread; struct completion io_thread_ready; /* Indication that the I/O thread started */ + struct page_frag_cache tx_alloc; /* Tx control packet allocation (I/O thread only) */ struct rxrpc_sock *service; /* Service(s) listening on this endpoint */ #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY struct sk_buff_head rx_delay_queue; /* Delay injection queue */ @@ -352,8 +355,8 @@ struct rxrpc_peer { u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ - u32 rto_j; /* Retransmission timeout in jiffies */ - u8 backoff; /* Backoff timeout */ + u32 rto_us; /* Retransmission timeout in usec */ + u8 backoff; /* Backoff timeout (as shift) */ u8 cong_ssthresh; /* Congestion slow-start threshold */ }; @@ -500,6 +503,8 @@ struct rxrpc_connection { struct list_head proc_link; /* link in procfs list */ struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ + struct page_frag_cache tx_data_alloc; /* Tx DATA packet allocation */ + struct mutex tx_data_alloc_lock; struct mutex security_lock; /* Lock for security management */ const struct rxrpc_security *security; /* applied security module */ @@ -618,17 +623,17 @@ struct rxrpc_call { const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ struct sockaddr_rxrpc dest_srx; /* Destination address */ - unsigned long delay_ack_at; /* When DELAY ACK needs to happen */ - unsigned long ack_lost_at; /* When ACK is figured as lost */ - unsigned long resend_at; /* When next resend needs to happen */ - unsigned long ping_at; /* When next to send a ping */ - unsigned long keepalive_at; /* When next to send a keepalive ping */ - unsigned long expect_rx_by; /* When we expect to get a packet by */ - unsigned long expect_req_by; /* When we expect to get a request DATA packet by */ - unsigned long expect_term_by; /* When we expect call termination by */ - u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ - u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ - u32 hard_timo; /* Maximum lifetime or 0 (jif) */ + ktime_t delay_ack_at; /* When DELAY ACK needs to happen */ + ktime_t ack_lost_at; /* When ACK is figured as lost */ + ktime_t resend_at; /* When next resend needs to happen */ + ktime_t ping_at; /* When next to send a ping */ + ktime_t keepalive_at; /* When next to send a keepalive ping */ + ktime_t expect_rx_by; /* When we expect to get a packet by */ + ktime_t expect_req_by; /* When we expect to get a request DATA packet by */ + ktime_t expect_term_by; /* When we expect call termination by */ + u32 next_rx_timo; /* Timeout for next Rx packet (ms) */ + u32 next_req_timo; /* Timeout for next Rx request packet (ms) */ + u32 hard_timo; /* Maximum lifetime or 0 (s) */ struct timer_list timer; /* Combined event timer */ struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ @@ -673,7 +678,7 @@ struct rxrpc_call { rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ rxrpc_seq_t tx_prepared; /* Highest Tx slot prepared. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ - u16 tx_backoff; /* Delay to insert due to Tx failure */ + u16 tx_backoff; /* Delay to insert due to Tx failure (ms) */ u8 tx_winsize; /* Maximum size of Tx window */ #define RXRPC_TX_MAX_WINDOW 128 ktime_t tx_last_sent; /* Last time a transmission occurred */ @@ -788,40 +793,30 @@ struct rxrpc_send_params { * Buffer of data to be output as a packet. */ struct rxrpc_txbuf { - struct rcu_head rcu; struct list_head call_link; /* Link in call->tx_sendmsg/tx_buffer */ struct list_head tx_link; /* Link in live Enc queue or Tx queue */ ktime_t last_sent; /* Time at which last transmitted */ refcount_t ref; rxrpc_seq_t seq; /* Sequence number of this packet */ + rxrpc_serial_t serial; /* Last serial number transmitted with */ unsigned int call_debug_id; unsigned int debug_id; unsigned int len; /* Amount of data in buffer */ unsigned int space; /* Remaining data space */ unsigned int offset; /* Offset of fill point */ - unsigned long flags; -#define RXRPC_TXBUF_LAST 0 /* Set if last packet in Tx phase */ -#define RXRPC_TXBUF_RESENT 1 /* Set if has been resent */ + unsigned int flags; +#define RXRPC_TXBUF_WIRE_FLAGS 0xff /* The wire protocol flags */ +#define RXRPC_TXBUF_RESENT 0x100 /* Set if has been resent */ + __be16 cksum; /* Checksum to go in header */ + unsigned short ack_rwind; /* ACK receive window */ u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ - struct { - /* The packet for encrypting and DMA'ing. We align it such - * that data[] aligns correctly for any crypto blocksize. - */ - u8 pad[64 - sizeof(struct rxrpc_wire_header)]; - struct rxrpc_wire_header wire; /* Network-ready header */ - union { - u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ - struct { - struct rxrpc_ackpacket ack; - DECLARE_FLEX_ARRAY(u8, acks); - }; - }; - } __aligned(64); + u8 nr_kvec; /* Amount of kvec[] used */ + struct kvec kvec[3]; }; static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) { - return txb->wire.flags & RXRPC_CLIENT_INITIATED; + return txb->flags & RXRPC_CLIENT_INITIATED; } static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) @@ -869,17 +864,11 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); */ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why); -void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb); -void rxrpc_reduce_call_timer(struct rxrpc_call *call, - unsigned long expire_at, - unsigned long now, - enum rxrpc_timer_trace why); - bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); /* @@ -1160,9 +1149,9 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) /* * output.c */ -int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb); +void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why); int rxrpc_send_abort_packet(struct rxrpc_call *); -int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_send_conn_abort(struct rxrpc_connection *conn); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); @@ -1223,7 +1212,7 @@ static inline int rxrpc_abort_eproto(struct rxrpc_call *call, */ void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); -unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool); +ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans); void rxrpc_peer_init_rtt(struct rxrpc_peer *); /* @@ -1295,8 +1284,9 @@ static inline void rxrpc_sysctl_exit(void) {} * txbuf.c */ extern atomic_t rxrpc_nr_txbuf; -struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, - gfp_t gfp); +struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size, + size_t data_align, gfp_t gfp); +struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_size); void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 0f78544d043b..7bbb68504766 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -23,14 +23,14 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why) { - unsigned long now = jiffies; - unsigned long ping_at = now + rxrpc_idle_ack_delay; - - if (time_before(ping_at, call->ping_at)) { - WRITE_ONCE(call->ping_at, ping_at); - rxrpc_reduce_call_timer(call, ping_at, now, - rxrpc_timer_set_for_ping); - trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial); + ktime_t delay = ms_to_ktime(READ_ONCE(rxrpc_idle_ack_delay)); + ktime_t now = ktime_get_real(); + ktime_t ping_at = ktime_add(now, delay); + + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial); + if (ktime_before(ping_at, call->ping_at)) { + call->ping_at = ping_at; + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_ping); } } @@ -40,62 +40,18 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) { - unsigned long expiry = rxrpc_soft_ack_delay; - unsigned long now = jiffies, ack_at; - - if (rxrpc_soft_ack_delay < expiry) - expiry = rxrpc_soft_ack_delay; - if (call->peer->srtt_us != 0) - ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); - else - ack_at = expiry; - - ack_at += READ_ONCE(call->tx_backoff); - ack_at += now; - if (time_before(ack_at, call->delay_ack_at)) { - WRITE_ONCE(call->delay_ack_at, ack_at); - rxrpc_reduce_call_timer(call, ack_at, now, - rxrpc_timer_set_for_ack); - } + ktime_t now = ktime_get_real(), delay; trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial); -} - -/* - * Queue an ACK for immediate transmission. - */ -void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, - rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) -{ - struct rxrpc_txbuf *txb; - - if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) - return; - - rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); - txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_ACK, - rcu_read_lock_held() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS); - if (!txb) { - kleave(" = -ENOMEM"); - return; - } + if (call->peer->srtt_us) + delay = (call->peer->srtt_us >> 3) * NSEC_PER_USEC; + else + delay = ms_to_ktime(READ_ONCE(rxrpc_soft_ack_delay)); + ktime_add_ms(delay, call->tx_backoff); - txb->ack_why = why; - txb->wire.seq = 0; - txb->wire.type = RXRPC_PACKET_TYPE_ACK; - txb->wire.flags |= RXRPC_SLOW_START_OK; - txb->ack.bufferSpace = 0; - txb->ack.maxSkew = 0; - txb->ack.firstPacket = 0; - txb->ack.previousPacket = 0; - txb->ack.serial = htonl(serial); - txb->ack.reason = ack_reason; - txb->ack.nAcks = 0; - - trace_rxrpc_send_ack(call, why, ack_reason, serial); - rxrpc_send_ack_packet(call, txb); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); + call->delay_ack_at = ktime_add(now, delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_delayed_ack); } /* @@ -114,25 +70,19 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) struct rxrpc_ackpacket *ack = NULL; struct rxrpc_skb_priv *sp; struct rxrpc_txbuf *txb; - unsigned long resend_at; - rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); - ktime_t now, max_age, oldest, ack_ts; - bool unacked = false; + rxrpc_seq_t transmitted = call->tx_transmitted; + ktime_t next_resend = KTIME_MAX, rto = ns_to_ktime(call->peer->rto_us * NSEC_PER_USEC); + ktime_t resend_at = KTIME_MAX, now, delay; + bool unacked = false, did_send = false; unsigned int i; - LIST_HEAD(retrans_queue); _enter("{%d,%d}", call->acks_hard_ack, call->tx_top); now = ktime_get_real(); - max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); - oldest = now; if (list_empty(&call->tx_buffer)) goto no_resend; - if (list_empty(&call->tx_buffer)) - goto no_further_resend; - trace_rxrpc_resend(call, ack_skb); txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link); @@ -143,12 +93,12 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) sp = rxrpc_skb(ack_skb); ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); - for (i = 0; i < sp->nr_acks; i++) { + for (i = 0; i < sp->ack.nr_acks; i++) { rxrpc_seq_t seq; if (ack->acks[i] & 1) continue; - seq = sp->first_ack + i; + seq = sp->ack.first_ack + i; if (after(txb->seq, transmitted)) break; if (after(txb->seq, seq)) @@ -160,19 +110,23 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) goto no_further_resend; found_txb: - if (after(ntohl(txb->wire.serial), call->acks_highest_serial)) + resend_at = ktime_add(txb->last_sent, rto); + if (after(txb->serial, call->acks_highest_serial)) { + if (ktime_after(resend_at, now) && + ktime_before(resend_at, next_resend)) + next_resend = resend_at; continue; /* Ack point not yet reached */ + } rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); - if (list_empty(&txb->tx_link)) { - list_add_tail(&txb->tx_link, &retrans_queue); - set_bit(RXRPC_TXBUF_RESENT, &txb->flags); - } + trace_rxrpc_retransmit(call, txb->seq, txb->serial, + ktime_sub(resend_at, now)); - trace_rxrpc_retransmit(call, txb->seq, - ktime_to_ns(ktime_sub(txb->last_sent, - max_age))); + txb->flags |= RXRPC_TXBUF_RESENT; + rxrpc_transmit_one(call, txb); + did_send = true; + now = ktime_get_real(); if (list_is_last(&txb->call_link, &call->tx_buffer)) goto no_further_resend; @@ -184,43 +138,46 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) * seen. Anything between the soft-ACK table and that point will get * ACK'd or NACK'd in due course, so don't worry about it here; here we * need to consider retransmitting anything beyond that point. - * - * Note that ACK for a packet can beat the update of tx_transmitted. */ - if (after_eq(READ_ONCE(call->acks_prev_seq), READ_ONCE(call->tx_transmitted))) + if (after_eq(call->acks_prev_seq, call->tx_transmitted)) goto no_further_resend; list_for_each_entry_from(txb, &call->tx_buffer, call_link) { - if (before_eq(txb->seq, READ_ONCE(call->acks_prev_seq))) + resend_at = ktime_add(txb->last_sent, rto); + + if (before_eq(txb->seq, call->acks_prev_seq)) continue; - if (after(txb->seq, READ_ONCE(call->tx_transmitted))) + if (after(txb->seq, call->tx_transmitted)) break; /* Not transmitted yet */ if (ack && ack->reason == RXRPC_ACK_PING_RESPONSE && - before(ntohl(txb->wire.serial), ntohl(ack->serial))) + before(txb->serial, ntohl(ack->serial))) goto do_resend; /* Wasn't accounted for by a more recent ping. */ - if (ktime_after(txb->last_sent, max_age)) { - if (ktime_before(txb->last_sent, oldest)) - oldest = txb->last_sent; + if (ktime_after(resend_at, now)) { + if (ktime_before(resend_at, next_resend)) + next_resend = resend_at; continue; } do_resend: unacked = true; - if (list_empty(&txb->tx_link)) { - list_add_tail(&txb->tx_link, &retrans_queue); - set_bit(RXRPC_TXBUF_RESENT, &txb->flags); - rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); - } + + txb->flags |= RXRPC_TXBUF_RESENT; + rxrpc_transmit_one(call, txb); + did_send = true; + rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); + now = ktime_get_real(); } no_further_resend: no_resend: - resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); - resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, - !list_empty(&retrans_queue)); - WRITE_ONCE(call->resend_at, resend_at); + if (resend_at < KTIME_MAX) { + delay = rxrpc_get_rto_backoff(call->peer, did_send); + resend_at = ktime_add(resend_at, delay); + trace_rxrpc_timer_set(call, resend_at - now, rxrpc_timer_trace_resend_reset); + } + call->resend_at = resend_at; if (unacked) rxrpc_congestion_timeout(call); @@ -229,25 +186,15 @@ no_resend: * that an ACK got lost somewhere. Send a ping to find out instead of * retransmitting data. */ - if (list_empty(&retrans_queue)) { - rxrpc_reduce_call_timer(call, resend_at, jiffies, - rxrpc_timer_set_for_resend); - ack_ts = ktime_sub(now, call->acks_latest_ts); - if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3)) - goto out; - rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, - rxrpc_propose_ack_ping_for_lost_ack); - goto out; - } + if (!did_send) { + ktime_t next_ping = ktime_add_us(call->acks_latest_ts, + call->peer->srtt_us >> 3); - /* Retransmit the queue */ - while ((txb = list_first_entry_or_null(&retrans_queue, - struct rxrpc_txbuf, tx_link))) { - list_del_init(&txb->tx_link); - rxrpc_transmit_one(call, txb); + if (ktime_sub(next_ping, now) <= 0) + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_0_retrans); } -out: _leave(""); } @@ -257,13 +204,11 @@ out: */ static void rxrpc_begin_service_reply(struct rxrpc_call *call) { - unsigned long now = jiffies; - rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SEND_REPLY); - WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); if (call->ackr_reason == RXRPC_ACK_DELAY) call->ackr_reason = 0; - trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); + call->delay_ack_at = KTIME_MAX; + trace_rxrpc_timer_can(call, rxrpc_timer_trace_delayed_ack); } /* @@ -320,7 +265,7 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) call->tx_top = txb->seq; list_add_tail(&txb->call_link, &call->tx_buffer); - if (txb->wire.flags & RXRPC_LAST_PACKET) + if (txb->flags & RXRPC_LAST_PACKET) rxrpc_close_tx_phase(call); rxrpc_transmit_one(call, txb); @@ -372,8 +317,8 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call) */ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) { - unsigned long now, next, t; - bool resend = false, expired = false; + ktime_t now, t; + bool resend = false; s32 abort_code; rxrpc_see_call(call, rxrpc_call_see_input); @@ -397,70 +342,73 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) if (skb && skb->mark == RXRPC_SKB_MARK_ERROR) goto out; + if (skb) + rxrpc_input_call_packet(call, skb); + /* If we see our async-event poke, check for timeout trippage. */ - now = jiffies; - t = READ_ONCE(call->expect_rx_by); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_normal, now); - expired = true; + now = ktime_get_real(); + t = ktime_sub(call->expect_rx_by, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_expect_rx); + goto expired; } - t = READ_ONCE(call->expect_req_by); - if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST && - time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now); - expired = true; + t = ktime_sub(call->expect_req_by, now); + if (t <= 0) { + call->expect_req_by = KTIME_MAX; + if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_idle); + goto expired; + } } - t = READ_ONCE(call->expect_term_by); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_hard, now); - expired = true; + t = ktime_sub(READ_ONCE(call->expect_term_by), now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_hard); + goto expired; } - t = READ_ONCE(call->delay_ack_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now); - cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->delay_ack_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_delayed_ack); + call->delay_ack_at = KTIME_MAX; rxrpc_send_ACK(call, RXRPC_ACK_DELAY, 0, - rxrpc_propose_ack_ping_for_lost_ack); + rxrpc_propose_ack_delayed_ack); } - t = READ_ONCE(call->ack_lost_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_lost_ack, now); - cmpxchg(&call->ack_lost_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->ack_lost_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_lost_ack); + call->ack_lost_at = KTIME_MAX; set_bit(RXRPC_CALL_EV_ACK_LOST, &call->events); } - t = READ_ONCE(call->keepalive_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now); - cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->ping_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_ping); + call->ping_at = KTIME_MAX; rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_keepalive); } - t = READ_ONCE(call->ping_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now); - cmpxchg(&call->ping_at, t, now + MAX_JIFFY_OFFSET); - rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, - rxrpc_propose_ack_ping_for_keepalive); - } - - t = READ_ONCE(call->resend_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_resend, now); - cmpxchg(&call->resend_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->resend_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_resend); + call->resend_at = KTIME_MAX; resend = true; } - if (skb) - rxrpc_input_call_packet(call, skb); - rxrpc_transmit_some_data(call); + now = ktime_get_real(); + t = ktime_sub(call->keepalive_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_keepalive); + call->keepalive_at = KTIME_MAX; + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); + } + if (skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -472,24 +420,13 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_send_initial_ping(call); /* Process events */ - if (expired) { - if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && - (int)call->conn->hi_serial - (int)call->rx_serial > 0) { - trace_rxrpc_call_reset(call); - rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET, - rxrpc_abort_call_reset); - } else { - rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME, - rxrpc_abort_call_timeout); - } - goto out; - } - if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_lost_ack); - if (resend && __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY) + if (resend && + __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY && + !test_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags)) rxrpc_resend(call, NULL); if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) @@ -511,23 +448,33 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) /* Make sure the timer is restarted */ if (!__rxrpc_call_is_complete(call)) { - next = call->expect_rx_by; + ktime_t next = READ_ONCE(call->expect_term_by), delay; -#define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; } +#define set(T) { ktime_t _t = (T); if (ktime_before(_t, next)) next = _t; } set(call->expect_req_by); - set(call->expect_term_by); + set(call->expect_rx_by); set(call->delay_ack_at); set(call->ack_lost_at); set(call->resend_at); set(call->keepalive_at); set(call->ping_at); - now = jiffies; - if (time_after_eq(now, next)) + now = ktime_get_real(); + delay = ktime_sub(next, now); + if (delay <= 0) { rxrpc_poke_call(call, rxrpc_call_poke_timer_now); - - rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); + } else { + unsigned long nowj = jiffies, delayj, nextj; + + delayj = max(nsecs_to_jiffies(delay), 1); + nextj = nowj + delayj; + if (time_before(nextj, call->timer.expires) || + !timer_pending(&call->timer)) { + trace_rxrpc_timer_restart(call, delay, delayj); + timer_reduce(&call->timer, nextj); + } + } } out: @@ -542,4 +489,16 @@ out: rxrpc_shrink_call_tx_buffer(call); _leave(""); return true; + +expired: + if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && + (int)call->conn->hi_serial - (int)call->rx_serial > 0) { + trace_rxrpc_call_reset(call); + rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET, + rxrpc_abort_call_reset); + } else { + rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME, + rxrpc_abort_call_timeout); + } + goto out; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 9fc9a6c3f685..01fa71e8b1f7 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -70,20 +70,11 @@ static void rxrpc_call_timer_expired(struct timer_list *t) _enter("%d", call->debug_id); if (!__rxrpc_call_is_complete(call)) { - trace_rxrpc_timer_expired(call, jiffies); + trace_rxrpc_timer_expired(call); rxrpc_poke_call(call, rxrpc_call_poke_timer); } } -void rxrpc_reduce_call_timer(struct rxrpc_call *call, - unsigned long expire_at, - unsigned long now, - enum rxrpc_timer_trace why) -{ - trace_rxrpc_timer(call, why, now); - timer_reduce(&call->timer, expire_at); -} - static struct lock_class_key rxrpc_call_user_mutex_lock_class_key; static void rxrpc_destroy_call(struct work_struct *); @@ -163,12 +154,20 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, spin_lock_init(&call->notify_lock); spin_lock_init(&call->tx_lock); refcount_set(&call->ref, 1); - call->debug_id = debug_id; - call->tx_total_len = -1; - call->next_rx_timo = 20 * HZ; - call->next_req_timo = 1 * HZ; - call->ackr_window = 1; - call->ackr_wtop = 1; + call->debug_id = debug_id; + call->tx_total_len = -1; + call->next_rx_timo = 20 * HZ; + call->next_req_timo = 1 * HZ; + call->ackr_window = 1; + call->ackr_wtop = 1; + call->delay_ack_at = KTIME_MAX; + call->ack_lost_at = KTIME_MAX; + call->resend_at = KTIME_MAX; + call->ping_at = KTIME_MAX; + call->keepalive_at = KTIME_MAX; + call->expect_rx_by = KTIME_MAX; + call->expect_req_by = KTIME_MAX; + call->expect_term_by = KTIME_MAX; memset(&call->sock_node, 0xed, sizeof(call->sock_node)); @@ -226,11 +225,11 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, __set_bit(RXRPC_CALL_EXCLUSIVE, &call->flags); if (p->timeouts.normal) - call->next_rx_timo = min(msecs_to_jiffies(p->timeouts.normal), 1UL); + call->next_rx_timo = min(p->timeouts.normal, 1); if (p->timeouts.idle) - call->next_req_timo = min(msecs_to_jiffies(p->timeouts.idle), 1UL); + call->next_req_timo = min(p->timeouts.idle, 1); if (p->timeouts.hard) - call->hard_timo = p->timeouts.hard * HZ; + call->hard_timo = p->timeouts.hard; ret = rxrpc_init_client_call_security(call); if (ret < 0) { @@ -253,18 +252,13 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, */ void rxrpc_start_call_timer(struct rxrpc_call *call) { - unsigned long now = jiffies; - unsigned long j = now + MAX_JIFFY_OFFSET; - - call->delay_ack_at = j; - call->ack_lost_at = j; - call->resend_at = j; - call->ping_at = j; - call->keepalive_at = j; - call->expect_rx_by = j; - call->expect_req_by = j; - call->expect_term_by = j + call->hard_timo; - call->timer.expires = now; + if (call->hard_timo) { + ktime_t delay = ms_to_ktime(call->hard_timo * 1000); + + call->expect_term_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard); + } + call->timer.expires = jiffies; } /* diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3b9b267a4431..d25bf1cf3670 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -636,7 +636,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { unsigned long final_ack_at = jiffies + 2; - WRITE_ONCE(chan->final_ack_at, final_ack_at); + chan->final_ack_at = final_ack_at; smp_wmb(); /* vs rxrpc_process_delayed_final_acks() */ set_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags); rxrpc_reduce_conn_timer(conn, final_ack_at); @@ -770,7 +770,7 @@ next: conn_expires_at = conn->idle_timestamp + expiry; - now = READ_ONCE(jiffies); + now = jiffies; if (time_after(conn_expires_at, now)) goto not_yet_expired; } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 1f251d758cb9..598b4ee389fc 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -88,7 +88,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct rxrpc_ackpacket ack; }; } __attribute__((packed)) pkt; - struct rxrpc_ackinfo ack_info; + struct rxrpc_acktrailer trailer; size_t len; int ret, ioc; u32 serial, mtu, call_id, padding; @@ -122,8 +122,8 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, iov[0].iov_len = sizeof(pkt.whdr); iov[1].iov_base = &padding; iov[1].iov_len = 3; - iov[2].iov_base = &ack_info; - iov[2].iov_len = sizeof(ack_info); + iov[2].iov_base = &trailer; + iov[2].iov_len = sizeof(trailer); serial = rxrpc_get_next_serial(conn); @@ -158,14 +158,14 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, pkt.ack.serial = htonl(skb ? sp->hdr.serial : 0); pkt.ack.reason = skb ? RXRPC_ACK_DUPLICATE : RXRPC_ACK_IDLE; pkt.ack.nAcks = 0; - ack_info.rxMTU = htonl(rxrpc_rx_mtu); - ack_info.maxMTU = htonl(mtu); - ack_info.rwind = htonl(rxrpc_rx_window_size); - ack_info.jumbo_max = htonl(rxrpc_rx_jumbo_max); + trailer.maxMTU = htonl(rxrpc_rx_mtu); + trailer.ifMTU = htonl(mtu); + trailer.rwind = htonl(rxrpc_rx_window_size); + trailer.jumbo_max = htonl(rxrpc_rx_jumbo_max); pkt.whdr.flags |= RXRPC_SLOW_START_OK; padding = 0; iov[0].iov_len += sizeof(pkt.ack); - len += sizeof(pkt.ack) + 3 + sizeof(ack_info); + len += sizeof(pkt.ack) + 3 + sizeof(trailer); ioc = 3; trace_rxrpc_tx_ack(chan->call_debug_id, serial, diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index df8a271948a1..0af4642aeec4 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -68,6 +68,7 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); mutex_init(&conn->security_lock); + mutex_init(&conn->tx_data_alloc_lock); skb_queue_head_init(&conn->rx_queue); conn->rxnet = rxnet; conn->security = &rxrpc_no_security; @@ -341,6 +342,9 @@ static void rxrpc_clean_up_connection(struct work_struct *work) */ rxrpc_purge_queue(&conn->rx_queue); + if (conn->tx_data_alloc.va) + __page_frag_cache_drain(virt_to_page(conn->tx_data_alloc.va), + conn->tx_data_alloc.pagecnt_bias); call_rcu(&conn->rcu, rxrpc_rcu_free_connection); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9691de00ade7..3dedb8c0618c 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -212,7 +212,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { if (before_eq(txb->seq, call->acks_hard_ack)) continue; - if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) { + if (txb->flags & RXRPC_LAST_PACKET) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; } @@ -252,6 +252,9 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, { ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); + call->resend_at = KTIME_MAX; + trace_rxrpc_timer_can(call, rxrpc_timer_trace_resend); + if (unlikely(call->cong_last_nack)) { rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack); call->cong_last_nack = NULL; @@ -288,15 +291,11 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, static bool rxrpc_receiving_reply(struct rxrpc_call *call) { struct rxrpc_ack_summary summary = { 0 }; - unsigned long now, timo; rxrpc_seq_t top = READ_ONCE(call->tx_top); if (call->ackr_reason) { - now = jiffies; - timo = now + MAX_JIFFY_OFFSET; - - WRITE_ONCE(call->delay_ack_at, timo); - trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); + call->delay_ack_at = KTIME_MAX; + trace_rxrpc_timer_can(call, rxrpc_timer_trace_delayed_ack); } if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { @@ -329,7 +328,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) case RXRPC_CALL_SERVER_RECV_REQUEST: rxrpc_set_call_state(call, RXRPC_CALL_SERVER_ACK_REQUEST); - call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; + call->expect_req_by = KTIME_MAX; rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_processing_op); break; @@ -589,14 +588,12 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_CALL_SERVER_RECV_REQUEST: { unsigned long timo = READ_ONCE(call->next_req_timo); - unsigned long now, expect_req_by; if (timo) { - now = jiffies; - expect_req_by = now + timo; - WRITE_ONCE(call->expect_req_by, expect_req_by); - rxrpc_reduce_call_timer(call, expect_req_by, now, - rxrpc_timer_set_for_idle); + ktime_t delay = ms_to_ktime(timo); + + call->expect_req_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_idle); } break; } @@ -670,14 +667,14 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, /* * Process the extra information that may be appended to an ACK packet */ -static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, - struct rxrpc_ackinfo *ackinfo) +static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb, + struct rxrpc_acktrailer *trailer) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_peer *peer; unsigned int mtu; bool wake = false; - u32 rwind = ntohl(ackinfo->rwind); + u32 rwind = ntohl(trailer->rwind); if (rwind > RXRPC_TX_MAX_WINDOW) rwind = RXRPC_TX_MAX_WINDOW; @@ -691,7 +688,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, if (call->cong_ssthresh > rwind) call->cong_ssthresh = rwind; - mtu = min(ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU)); + mtu = min(ntohl(trailer->maxMTU), ntohl(trailer->ifMTU)); peer = call->peer; if (mtu < peer->maxdata) { @@ -713,20 +710,19 @@ static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call, rxrpc_seq_t seq) { struct sk_buff *skb = call->cong_last_nack; - struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int i, new_acks = 0, retained_nacks = 0; - rxrpc_seq_t old_seq = sp->first_ack; - u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(ack); + rxrpc_seq_t old_seq = sp->ack.first_ack; + u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); - if (after_eq(seq, old_seq + sp->nr_acks)) { - summary->nr_new_acks += sp->nr_nacks; - summary->nr_new_acks += seq - (old_seq + sp->nr_acks); + if (after_eq(seq, old_seq + sp->ack.nr_acks)) { + summary->nr_new_acks += sp->ack.nr_nacks; + summary->nr_new_acks += seq - (old_seq + sp->ack.nr_acks); summary->nr_retained_nacks = 0; } else if (seq == old_seq) { - summary->nr_retained_nacks = sp->nr_nacks; + summary->nr_retained_nacks = sp->ack.nr_nacks; } else { - for (i = 0; i < sp->nr_acks; i++) { + for (i = 0; i < sp->ack.nr_acks; i++) { if (acks[i] == RXRPC_ACK_TYPE_NACK) { if (before(old_seq + i, seq)) new_acks++; @@ -739,7 +735,7 @@ static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call, summary->nr_retained_nacks = retained_nacks; } - return old_seq + sp->nr_acks; + return old_seq + sp->ack.nr_acks; } /* @@ -759,10 +755,10 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int i, old_nacks = 0; - rxrpc_seq_t lowest_nak = seq + sp->nr_acks; + rxrpc_seq_t lowest_nak = seq + sp->ack.nr_acks; u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); - for (i = 0; i < sp->nr_acks; i++) { + for (i = 0; i < sp->ack.nr_acks; i++) { if (acks[i] == RXRPC_ACK_TYPE_ACK) { summary->nr_acks++; if (after_eq(seq, since)) @@ -774,7 +770,7 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, old_nacks++; } else { summary->nr_new_nacks++; - sp->nr_nacks++; + sp->ack.nr_nacks++; } if (before(seq, lowest_nak)) @@ -835,38 +831,32 @@ static bool rxrpc_is_ack_valid(struct rxrpc_call *call, static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; - struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_ackinfo info; + struct rxrpc_acktrailer trailer; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since; int nr_acks, offset, ioffset; _enter(""); - offset = sizeof(struct rxrpc_wire_header); - if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) - return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack); - offset += sizeof(ack); - - ack_serial = sp->hdr.serial; - acked_serial = ntohl(ack.serial); - first_soft_ack = ntohl(ack.firstPacket); - prev_pkt = ntohl(ack.previousPacket); - hard_ack = first_soft_ack - 1; - nr_acks = ack.nAcks; - sp->first_ack = first_soft_ack; - sp->nr_acks = nr_acks; - summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ? - ack.reason : RXRPC_ACK__INVALID); + offset = sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); + + ack_serial = sp->hdr.serial; + acked_serial = sp->ack.acked_serial; + first_soft_ack = sp->ack.first_ack; + prev_pkt = sp->ack.prev_ack; + nr_acks = sp->ack.nr_acks; + hard_ack = first_soft_ack - 1; + summary.ack_reason = (sp->ack.reason < RXRPC_ACK__INVALID ? + sp->ack.reason : RXRPC_ACK__INVALID); trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); - rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]); + rxrpc_inc_stat(call->rxnet, stat_rx_acks[summary.ack_reason]); if (acked_serial != 0) { - switch (ack.reason) { + switch (summary.ack_reason) { case RXRPC_ACK_PING_RESPONSE: rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, rxrpc_rtt_rx_ping_response); @@ -886,7 +876,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicates that the client address changed due to NAT. The server * lost the call because it switched to a different peer. */ - if (unlikely(ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && + if (unlikely(summary.ack_reason == RXRPC_ACK_EXCEEDS_WINDOW) && first_soft_ack == 1 && prev_pkt == 0 && rxrpc_is_client_call(call)) { @@ -899,7 +889,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicate a change of address. However, we can retransmit the call * if we still have it buffered to the beginning. */ - if (unlikely(ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && + if (unlikely(summary.ack_reason == RXRPC_ACK_OUT_OF_SEQUENCE) && first_soft_ack == 1 && prev_pkt == 0 && call->acks_hard_ack == 0 && @@ -917,11 +907,11 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto send_response; } - info.rxMTU = 0; + trailer.maxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(info) && - skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) - return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info); + if (skb->len >= ioffset + sizeof(trailer) && + skb_copy_bits(skb, ioffset, &trailer, sizeof(trailer)) < 0) + return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_trailer); if (nr_acks > 0) skb_condense(skb); @@ -940,7 +930,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) call->acks_first_seq = first_soft_ack; call->acks_prev_seq = prev_pkt; - switch (ack.reason) { + switch (summary.ack_reason) { case RXRPC_ACK_PING: break; default: @@ -950,8 +940,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } /* Parse rwind and mtu sizes if provided. */ - if (info.rxMTU) - rxrpc_input_ackinfo(call, skb, &info); + if (trailer.maxMTU) + rxrpc_input_ack_trailer(call, skb, &trailer); if (first_soft_ack == 0) return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero); @@ -997,7 +987,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_congestion_management(call, skb, &summary, acked_serial); send_response: - if (ack.reason == RXRPC_ACK_PING) + if (summary.ack_reason == RXRPC_ACK_PING) rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, rxrpc_propose_ack_respond_to_ping); else if (sp->hdr.flags & RXRPC_REQUEST_ACK) @@ -1048,12 +1038,10 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) timo = READ_ONCE(call->next_rx_timo); if (timo) { - unsigned long now = jiffies, expect_rx_by; + ktime_t delay = ms_to_ktime(timo); - expect_rx_by = now + timo; - WRITE_ONCE(call->expect_rx_by, expect_rx_by); - rxrpc_reduce_call_timer(call, expect_rx_by, now, - rxrpc_timer_set_for_normal); + call->expect_rx_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_expect_rx); } switch (sp->hdr.type) { diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 34353b6e584b..f2701068ed9e 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -15,14 +15,11 @@ static int none_init_connection_security(struct rxrpc_connection *conn, } /* - * Work out how much data we can put in an unsecured packet. + * Allocate an appropriately sized buffer for the amount of data remaining. */ -static int none_how_much_data(struct rxrpc_call *call, size_t remain, - size_t *_buf_size, size_t *_data_size, size_t *_offset) +static struct rxrpc_txbuf *none_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp) { - *_buf_size = *_data_size = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); - *_offset = 0; - return 0; + return rxrpc_alloc_data_txbuf(call, min_t(size_t, remain, RXRPC_JUMBO_DATALEN), 0, gfp); } static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) @@ -79,7 +76,7 @@ const struct rxrpc_security rxrpc_no_security = { .exit = none_exit, .init_connection_security = none_init_connection_security, .free_call_crypto = none_free_call_crypto, - .how_much_data = none_how_much_data, + .alloc_txbuf = none_alloc_txbuf, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, .respond_to_challenge = none_respond_to_challenge, diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 4a3a08a0e2cd..0300baa9afcd 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -124,6 +124,7 @@ static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) { struct rxrpc_wire_header whdr; + struct rxrpc_ackpacket ack; /* dig out the RxRPC connection details */ if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) @@ -141,6 +142,16 @@ static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp, sp->hdr.securityIndex = whdr.securityIndex; sp->hdr._rsvd = ntohs(whdr._rsvd); sp->hdr.serviceId = ntohs(whdr.serviceId); + + if (sp->hdr.type == RXRPC_PACKET_TYPE_ACK) { + if (skb_copy_bits(skb, sizeof(whdr), &ack, sizeof(ack)) < 0) + return rxrpc_bad_message(skb, rxrpc_badmsg_short_ack); + sp->ack.first_ack = ntohl(ack.firstPacket); + sp->ack.prev_ack = ntohl(ack.previousPacket); + sp->ack.acked_serial = ntohl(ack.serial); + sp->ack.reason = ack.reason; + sp->ack.nr_acks = ack.nAcks; + } return true; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 34d307368135..504453c688d7 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -452,6 +452,9 @@ void rxrpc_destroy_local(struct rxrpc_local *local) #endif rxrpc_purge_queue(&local->rx_queue); rxrpc_purge_client_connections(local); + if (local->tx_alloc.va) + __page_frag_cache_drain(virt_to_page(local->tx_alloc.va), + local->tx_alloc.pagecnt_bias); } /* diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 825b81183046..657cf35089a6 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -17,22 +17,22 @@ unsigned int rxrpc_max_backlog __read_mostly = 10; /* - * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). + * How long to wait before scheduling an ACK with subtype DELAY (in ms). * * We use this when we've received new data packets. If those packets aren't * all consumed within this time we will send a DELAY ACK if an ACK was not * requested to let the sender know it doesn't need to resend. */ -unsigned long rxrpc_soft_ack_delay = HZ; +unsigned long rxrpc_soft_ack_delay = 1000; /* - * How long to wait before scheduling an ACK with subtype IDLE (in jiffies). + * How long to wait before scheduling an ACK with subtype IDLE (in ms). * * We use this when we've consumed some previously soft-ACK'd packets when * further packets aren't immediately received to decide when to send an IDLE * ACK let the other end know that it can free up its Tx buffer space. */ -unsigned long rxrpc_idle_ack_delay = HZ / 2; +unsigned long rxrpc_idle_ack_delay = 500; /* * Receive window size in packets. This indicates the maximum number of diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 4a292f860ae3..5ea9601efd05 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -48,12 +48,10 @@ static const char rxrpc_keepalive_string[] = ""; static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) { if (ret < 0) { - u16 tx_backoff = READ_ONCE(call->tx_backoff); - - if (tx_backoff < HZ) - WRITE_ONCE(call->tx_backoff, tx_backoff + 1); + if (call->tx_backoff < 1000) + call->tx_backoff += 100; } else { - WRITE_ONCE(call->tx_backoff, 0); + call->tx_backoff = 0; } } @@ -65,84 +63,92 @@ static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) * Receiving a response to the ping will prevent the ->expect_rx_by timer from * expiring. */ -static void rxrpc_set_keepalive(struct rxrpc_call *call) +static void rxrpc_set_keepalive(struct rxrpc_call *call, ktime_t now) { - unsigned long now = jiffies, keepalive_at = call->next_rx_timo / 6; + ktime_t delay = ms_to_ktime(READ_ONCE(call->next_rx_timo) / 6); - keepalive_at += now; - WRITE_ONCE(call->keepalive_at, keepalive_at); - rxrpc_reduce_call_timer(call, keepalive_at, now, - rxrpc_timer_set_for_keepalive); + call->keepalive_at = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_keepalive); } /* * Fill out an ACK packet. */ -static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, - struct rxrpc_call *call, - struct rxrpc_txbuf *txb, - u16 *_rwind) +static void rxrpc_fill_out_ack(struct rxrpc_call *call, + struct rxrpc_txbuf *txb, + u8 ack_reason, + rxrpc_serial_t serial) { - struct rxrpc_ackinfo ackinfo; + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxrpc_acktrailer *trailer = txb->kvec[2].iov_base + 3; + struct rxrpc_ackpacket *ack = (struct rxrpc_ackpacket *)(whdr + 1); unsigned int qsize, sack, wrap, to; rxrpc_seq_t window, wtop; int rsize; u32 mtu, jmax; - u8 *ackp = txb->acks; + u8 *filler = txb->kvec[2].iov_base; + u8 *sackp = txb->kvec[1].iov_base; - call->ackr_nr_unacked = 0; - atomic_set(&call->ackr_nr_consumed, 0); rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); - clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags); window = call->ackr_window; wtop = call->ackr_wtop; sack = call->ackr_sack_base % RXRPC_SACK_SIZE; - txb->ack.firstPacket = htonl(window); - txb->ack.nAcks = wtop - window; + + whdr->seq = 0; + whdr->type = RXRPC_PACKET_TYPE_ACK; + txb->flags |= RXRPC_SLOW_START_OK; + ack->bufferSpace = 0; + ack->maxSkew = 0; + ack->firstPacket = htonl(window); + ack->previousPacket = htonl(call->rx_highest_seq); + ack->serial = htonl(serial); + ack->reason = ack_reason; + ack->nAcks = wtop - window; + filler[0] = 0; + filler[1] = 0; + filler[2] = 0; + + if (ack_reason == RXRPC_ACK_PING) + txb->flags |= RXRPC_REQUEST_ACK; if (after(wtop, window)) { + txb->len += ack->nAcks; + txb->kvec[1].iov_base = sackp; + txb->kvec[1].iov_len = ack->nAcks; + wrap = RXRPC_SACK_SIZE - sack; - to = min_t(unsigned int, txb->ack.nAcks, RXRPC_SACK_SIZE); + to = min_t(unsigned int, ack->nAcks, RXRPC_SACK_SIZE); - if (sack + txb->ack.nAcks <= RXRPC_SACK_SIZE) { - memcpy(txb->acks, call->ackr_sack_table + sack, txb->ack.nAcks); + if (sack + ack->nAcks <= RXRPC_SACK_SIZE) { + memcpy(sackp, call->ackr_sack_table + sack, ack->nAcks); } else { - memcpy(txb->acks, call->ackr_sack_table + sack, wrap); - memcpy(txb->acks + wrap, call->ackr_sack_table, - to - wrap); + memcpy(sackp, call->ackr_sack_table + sack, wrap); + memcpy(sackp + wrap, call->ackr_sack_table, to - wrap); } - - ackp += to; } else if (before(wtop, window)) { pr_warn("ack window backward %x %x", window, wtop); - } else if (txb->ack.reason == RXRPC_ACK_DELAY) { - txb->ack.reason = RXRPC_ACK_IDLE; + } else if (ack->reason == RXRPC_ACK_DELAY) { + ack->reason = RXRPC_ACK_IDLE; } - mtu = conn->peer->if_mtu; - mtu -= conn->peer->hdrsize; + mtu = call->peer->if_mtu; + mtu -= call->peer->hdrsize; jmax = rxrpc_rx_jumbo_max; qsize = (window - 1) - call->rx_consumed; rsize = max_t(int, call->rx_winsize - qsize, 0); - *_rwind = rsize; - ackinfo.rxMTU = htonl(rxrpc_rx_mtu); - ackinfo.maxMTU = htonl(mtu); - ackinfo.rwind = htonl(rsize); - ackinfo.jumbo_max = htonl(jmax); - - *ackp++ = 0; - *ackp++ = 0; - *ackp++ = 0; - memcpy(ackp, &ackinfo, sizeof(ackinfo)); - return txb->ack.nAcks + 3 + sizeof(ackinfo); + txb->ack_rwind = rsize; + trailer->maxMTU = htonl(rxrpc_rx_mtu); + trailer->ifMTU = htonl(mtu); + trailer->rwind = htonl(rsize); + trailer->jumbo_max = htonl(jmax); } /* * Record the beginning of an RTT probe. */ -static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, - enum rxrpc_rtt_tx_trace why) +static void rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, + ktime_t now, enum rxrpc_rtt_tx_trace why) { unsigned long avail = call->rtt_avail; int rtt_slot = 9; @@ -155,47 +161,31 @@ static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, goto no_slot; call->rtt_serial[rtt_slot] = serial; - call->rtt_sent_at[rtt_slot] = ktime_get_real(); + call->rtt_sent_at[rtt_slot] = now; smp_wmb(); /* Write data before avail bit */ set_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); trace_rxrpc_rtt_tx(call, why, rtt_slot, serial); - return rtt_slot; + return; no_slot: trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_no_slot, rtt_slot, serial); - return -1; -} - -/* - * Cancel an RTT probe. - */ -static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, - rxrpc_serial_t serial, int rtt_slot) -{ - if (rtt_slot != -1) { - clear_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); - smp_wmb(); /* Clear pending bit before setting slot */ - set_bit(rtt_slot, &call->rtt_avail); - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_cancel, rtt_slot, serial); - } } /* * Transmit an ACK packet. */ -int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +static void rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; struct rxrpc_connection *conn; + struct rxrpc_ackpacket *ack = (struct rxrpc_ackpacket *)(whdr + 1); struct msghdr msg; - struct kvec iov[1]; - rxrpc_serial_t serial; - size_t len, n; - int ret, rtt_slot = -1; - u16 rwind; + ktime_t now; + int ret; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) - return -ECONNRESET; + return; conn = call->conn; @@ -203,55 +193,68 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) msg.msg_namelen = call->peer->srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; - msg.msg_flags = 0; - - if (txb->ack.reason == RXRPC_ACK_PING) - txb->wire.flags |= RXRPC_REQUEST_ACK; - - n = rxrpc_fill_out_ack(conn, call, txb, &rwind); - if (n == 0) - return 0; - - iov[0].iov_base = &txb->wire; - iov[0].iov_len = sizeof(txb->wire) + sizeof(txb->ack) + n; - len = iov[0].iov_len; + msg.msg_flags = MSG_SPLICE_PAGES; - serial = rxrpc_get_next_serial(conn); - txb->wire.serial = htonl(serial); - trace_rxrpc_tx_ack(call->debug_id, serial, - ntohl(txb->ack.firstPacket), - ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks, - rwind); + whdr->flags = txb->flags & RXRPC_TXBUF_WIRE_FLAGS; - if (txb->ack.reason == RXRPC_ACK_PING) - rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); + txb->serial = rxrpc_get_next_serial(conn); + whdr->serial = htonl(txb->serial); + trace_rxrpc_tx_ack(call->debug_id, txb->serial, + ntohl(ack->firstPacket), + ntohl(ack->serial), ack->reason, ack->nAcks, + txb->ack_rwind); rxrpc_inc_stat(call->rxnet, stat_tx_ack_send); - /* Grab the highest received seq as late as possible */ - txb->ack.previousPacket = htonl(call->rx_highest_seq); - - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); - ret = do_udp_sendmsg(conn->local->socket, &msg, len); + iov_iter_kvec(&msg.msg_iter, WRITE, txb->kvec, txb->nr_kvec, txb->len); + rxrpc_local_dont_fragment(conn->local, false); + ret = do_udp_sendmsg(conn->local->socket, &msg, txb->len); call->peer->last_tx_at = ktime_get_seconds(); if (ret < 0) { - trace_rxrpc_tx_fail(call->debug_id, serial, ret, + trace_rxrpc_tx_fail(call->debug_id, txb->serial, ret, rxrpc_tx_point_call_ack); } else { - trace_rxrpc_tx_packet(call->debug_id, &txb->wire, + trace_rxrpc_tx_packet(call->debug_id, whdr, rxrpc_tx_point_call_ack); - if (txb->wire.flags & RXRPC_REQUEST_ACK) - call->peer->rtt_last_req = ktime_get_real(); + now = ktime_get_real(); + if (ack->reason == RXRPC_ACK_PING) + rxrpc_begin_rtt_probe(call, txb->serial, now, rxrpc_rtt_tx_ping); + if (txb->flags & RXRPC_REQUEST_ACK) + call->peer->rtt_last_req = now; + rxrpc_set_keepalive(call, now); } rxrpc_tx_backoff(call, ret); +} - if (!__rxrpc_call_is_complete(call)) { - if (ret < 0) - rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - rxrpc_set_keepalive(call); +/* + * Queue an ACK for immediate transmission. + */ +void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) +{ + struct rxrpc_txbuf *txb; + + if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) + return; + + rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); + + txb = rxrpc_alloc_ack_txbuf(call, call->ackr_wtop - call->ackr_window); + if (!txb) { + kleave(" = -ENOMEM"); + return; } - return ret; + txb->ack_why = why; + + rxrpc_fill_out_ack(call, txb, ack_reason, serial); + call->ackr_nr_unacked = 0; + atomic_set(&call->ackr_nr_consumed, 0); + clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags); + + trace_rxrpc_send_ack(call, why, ack_reason, serial); + rxrpc_send_ack_packet(call, txb); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); } /* @@ -319,38 +322,22 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) } /* - * send a packet through the transport endpoint + * Prepare a (sub)packet for transmission. */ -int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +static void rxrpc_prepare_data_subpacket(struct rxrpc_call *call, struct rxrpc_txbuf *txb, + rxrpc_serial_t serial) { + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; enum rxrpc_req_ack_trace why; struct rxrpc_connection *conn = call->conn; - struct msghdr msg; - struct kvec iov[1]; - rxrpc_serial_t serial; - size_t len; - int ret, rtt_slot = -1; _enter("%x,{%d}", txb->seq, txb->len); - /* Each transmission of a Tx packet needs a new serial number */ - serial = rxrpc_get_next_serial(conn); - txb->wire.serial = htonl(serial); + txb->serial = serial; if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) && txb->seq == 1) - txb->wire.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; - - iov[0].iov_base = &txb->wire; - iov[0].iov_len = sizeof(txb->wire) + txb->len; - len = iov[0].iov_len; - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); - - msg.msg_name = &call->peer->srx.transport; - msg.msg_namelen = call->peer->srx.transport_len; - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = 0; + whdr->userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; /* If our RTT cache needs working on, request an ACK. Also request * ACKs if a DATA packet appears to have been lost. @@ -359,13 +346,13 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) * service call, lest OpenAFS incorrectly send us an ACK with some * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if (txb->wire.flags & RXRPC_REQUEST_ACK) + if (txb->flags & RXRPC_REQUEST_ACK) why = rxrpc_reqack_already_on; - else if (test_bit(RXRPC_TXBUF_LAST, &txb->flags) && rxrpc_sending_to_client(txb)) + else if ((txb->flags & RXRPC_LAST_PACKET) && rxrpc_sending_to_client(txb)) why = rxrpc_reqack_no_srv_last; else if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) why = rxrpc_reqack_ack_lost; - else if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) + else if (txb->flags & RXRPC_TXBUF_RESENT) why = rxrpc_reqack_retrans; else if (call->cong_mode == RXRPC_CALL_SLOW_START && call->cong_cwnd <= 2) why = rxrpc_reqack_slow_start; @@ -381,42 +368,116 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_inc_stat(call->rxnet, stat_why_req_ack[why]); trace_rxrpc_req_ack(call->debug_id, txb->seq, why); if (why != rxrpc_reqack_no_srv_last) - txb->wire.flags |= RXRPC_REQUEST_ACK; + txb->flags |= RXRPC_REQUEST_ACK; dont_set_request_ack: + whdr->flags = txb->flags & RXRPC_TXBUF_WIRE_FLAGS; + whdr->serial = htonl(txb->serial); + whdr->cksum = txb->cksum; + + trace_rxrpc_tx_data(call, txb->seq, txb->serial, txb->flags, false); +} + +/* + * Prepare a packet for transmission. + */ +static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + rxrpc_serial_t serial; + + /* Each transmission of a Tx packet needs a new serial number */ + serial = rxrpc_get_next_serial(call->conn); + + rxrpc_prepare_data_subpacket(call, txb, serial); + + return txb->len; +} + +/* + * Set timeouts after transmitting a packet. + */ +static void rxrpc_tstamp_data_packets(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + ktime_t now = ktime_get_real(); + bool ack_requested = txb->flags & RXRPC_REQUEST_ACK; + + call->tx_last_sent = now; + txb->last_sent = now; + + if (ack_requested) { + rxrpc_begin_rtt_probe(call, txb->serial, now, rxrpc_rtt_tx_data); + + call->peer->rtt_last_req = now; + if (call->peer->rtt_count > 1) { + ktime_t delay = rxrpc_get_rto_backoff(call->peer, false); + + call->ack_lost_at = ktime_add(now, delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_lost_ack); + } + } + + if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) { + ktime_t delay = ms_to_ktime(READ_ONCE(call->next_rx_timo)); + + call->expect_rx_by = ktime_add(now, delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_expect_rx); + } + + rxrpc_set_keepalive(call, now); +} + +/* + * send a packet through the transport endpoint + */ +static int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxrpc_connection *conn = call->conn; + enum rxrpc_tx_point frag; + struct msghdr msg; + size_t len; + int ret; + + _enter("%x,{%d}", txb->seq, txb->len); + + len = rxrpc_prepare_data_packet(call, txb); + if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { static int lose; if ((lose++ & 7) == 7) { ret = 0; - trace_rxrpc_tx_data(call, txb->seq, serial, - txb->wire.flags, - test_bit(RXRPC_TXBUF_RESENT, &txb->flags), - true); + trace_rxrpc_tx_data(call, txb->seq, txb->serial, + txb->flags, true); goto done; } } - trace_rxrpc_tx_data(call, txb->seq, serial, txb->wire.flags, - test_bit(RXRPC_TXBUF_RESENT, &txb->flags), false); + iov_iter_kvec(&msg.msg_iter, WRITE, txb->kvec, txb->nr_kvec, len); + + msg.msg_name = &call->peer->srx.transport; + msg.msg_namelen = call->peer->srx.transport_len; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = MSG_SPLICE_PAGES; /* Track what we've attempted to transmit at least once so that the * retransmission algorithm doesn't try to resend what we haven't sent - * yet. However, this can race as we can receive an ACK before we get - * to this point. But, OTOH, if we won't get an ACK mentioning this - * packet unless the far side received it (though it could have - * discarded it anyway and NAK'd it). + * yet. */ - cmpxchg(&call->tx_transmitted, txb->seq - 1, txb->seq); + if (txb->seq == call->tx_transmitted + 1) + call->tx_transmitted = txb->seq; /* send the packet with the don't fragment bit set if we currently * think it's small enough */ - if (txb->len >= call->peer->maxdata) - goto send_fragmentable; - - txb->last_sent = ktime_get_real(); - if (txb->wire.flags & RXRPC_REQUEST_ACK) - rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); + if (txb->len >= call->peer->maxdata) { + rxrpc_local_dont_fragment(conn->local, false); + frag = rxrpc_tx_point_call_data_frag; + } else { + rxrpc_local_dont_fragment(conn->local, true); + frag = rxrpc_tx_point_call_data_nofrag; + } +retry: /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet * to go out of the interface @@ -429,46 +490,21 @@ dont_set_request_ack: if (ret < 0) { rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); - rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_point_call_data_nofrag); + trace_rxrpc_tx_fail(call->debug_id, txb->serial, ret, frag); } else { - trace_rxrpc_tx_packet(call->debug_id, &txb->wire, - rxrpc_tx_point_call_data_nofrag); + trace_rxrpc_tx_packet(call->debug_id, whdr, frag); } rxrpc_tx_backoff(call, ret); - if (ret == -EMSGSIZE) - goto send_fragmentable; + if (ret == -EMSGSIZE && frag == rxrpc_tx_point_call_data_frag) { + rxrpc_local_dont_fragment(conn->local, false); + frag = rxrpc_tx_point_call_data_frag; + goto retry; + } done: if (ret >= 0) { - call->tx_last_sent = txb->last_sent; - if (txb->wire.flags & RXRPC_REQUEST_ACK) { - call->peer->rtt_last_req = txb->last_sent; - if (call->peer->rtt_count > 1) { - unsigned long nowj = jiffies, ack_lost_at; - - ack_lost_at = rxrpc_get_rto_backoff(call->peer, false); - ack_lost_at += nowj; - WRITE_ONCE(call->ack_lost_at, ack_lost_at); - rxrpc_reduce_call_timer(call, ack_lost_at, nowj, - rxrpc_timer_set_for_lost_ack); - } - } - - if (txb->seq == 1 && - !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, - &call->flags)) { - unsigned long nowj = jiffies, expect_rx_by; - - expect_rx_by = nowj + call->next_rx_timo; - WRITE_ONCE(call->expect_rx_by, expect_rx_by); - rxrpc_reduce_call_timer(call, expect_rx_by, nowj, - rxrpc_timer_set_for_normal); - } - - rxrpc_set_keepalive(call); + rxrpc_tstamp_data_packets(call, txb); } else { /* Cancel the call if the initial transmission fails, * particularly if that's due to network routing issues that @@ -482,41 +518,6 @@ done: _leave(" = %d [%u]", ret, call->peer->maxdata); return ret; - -send_fragmentable: - /* attempt to send this message with fragmentation enabled */ - _debug("send fragment"); - - txb->last_sent = ktime_get_real(); - if (txb->wire.flags & RXRPC_REQUEST_ACK) - rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); - - switch (conn->local->srx.transport.family) { - case AF_INET6: - case AF_INET: - rxrpc_local_dont_fragment(conn->local, false); - rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag); - ret = do_udp_sendmsg(conn->local->socket, &msg, len); - conn->peer->last_tx_at = ktime_get_seconds(); - - rxrpc_local_dont_fragment(conn->local, true); - break; - - default: - BUG(); - } - - if (ret < 0) { - rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); - rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_point_call_data_frag); - } else { - trace_rxrpc_tx_packet(call->debug_id, &txb->wire, - rxrpc_tx_point_call_data_frag); - } - rxrpc_tx_backoff(call, ret); - goto done; } /* @@ -723,11 +724,9 @@ void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_instant_resend(call, txb); } } else { - unsigned long now = jiffies; - unsigned long resend_at = now + call->peer->rto_j; + ktime_t delay = ns_to_ktime(call->peer->rto_us * NSEC_PER_USEC); - WRITE_ONCE(call->resend_at, resend_at); - rxrpc_reduce_call_timer(call, resend_at, now, - rxrpc_timer_set_for_send); + call->resend_at = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_resend_tx); } } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 26dc2f26d92d..263a2251e3d2 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -52,9 +52,9 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); enum rxrpc_call_state state; - unsigned long timeout = 0; rxrpc_seq_t acks_hard_ack; char lbuff[50], rbuff[50]; + long timeout = 0; if (v == &rxnet->calls) { seq_puts(seq, @@ -76,10 +76,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) sprintf(rbuff, "%pISpc", &call->dest_srx.transport); state = rxrpc_call_state(call); - if (state != RXRPC_CALL_SERVER_PREALLOC) { - timeout = READ_ONCE(call->expect_rx_by); - timeout -= jiffies; - } + if (state != RXRPC_CALL_SERVER_PREALLOC) + timeout = ktime_ms_delta(READ_ONCE(call->expect_rx_by), ktime_get_real()); acks_hard_ack = READ_ONCE(call->acks_hard_ack); seq_printf(seq, @@ -309,7 +307,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) peer->mtu, now - peer->last_tx_at, peer->srtt_us >> 3, - jiffies_to_usecs(peer->rto_j)); + peer->rto_us); return 0; } diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index e8ee4af43ca8..4fe6b4d20ada 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -135,9 +135,9 @@ struct rxrpc_ackpacket { /* * ACK packets can have a further piece of information tagged on the end */ -struct rxrpc_ackinfo { - __be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ - __be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ +struct rxrpc_acktrailer { + __be32 maxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ + __be32 ifMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ __be32 rwind; /* Rx window size (packets) [AFS 3.4] */ __be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */ }; diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c index be61d6f5be8d..cdab7b7d08a0 100644 --- a/net/rxrpc/rtt.c +++ b/net/rxrpc/rtt.c @@ -11,8 +11,8 @@ #include <linux/net.h> #include "ar-internal.h" -#define RXRPC_RTO_MAX ((unsigned)(120 * HZ)) -#define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ +#define RXRPC_RTO_MAX (120 * USEC_PER_SEC) +#define RXRPC_TIMEOUT_INIT ((unsigned int)(1 * MSEC_PER_SEC)) /* RFC6298 2.1 initial RTO value */ #define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) @@ -22,7 +22,7 @@ static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer) { - return usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us); + return (peer->srtt_us >> 3) + peer->rttvar_us; } static u32 rxrpc_bound_rto(u32 rto) @@ -124,7 +124,7 @@ static void rxrpc_set_rto(struct rxrpc_peer *peer) /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo * guarantees that rto is higher. */ - peer->rto_j = rxrpc_bound_rto(rto); + peer->rto_us = rxrpc_bound_rto(rto); } static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us) @@ -163,33 +163,33 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, spin_unlock(&peer->rtt_input_lock); trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, - peer->srtt_us >> 3, peer->rto_j); + peer->srtt_us >> 3, peer->rto_us); } /* - * Get the retransmission timeout to set in jiffies, backing it off each time - * we retransmit. + * Get the retransmission timeout to set in nanoseconds, backing it off each + * time we retransmit. */ -unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans) +ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans) { - u64 timo_j; - u8 backoff = READ_ONCE(peer->backoff); + u64 timo_us; + u32 backoff = READ_ONCE(peer->backoff); - timo_j = peer->rto_j; - timo_j <<= backoff; - if (retrans && timo_j * 2 <= RXRPC_RTO_MAX) + timo_us = peer->rto_us; + timo_us <<= backoff; + if (retrans && timo_us * 2 <= RXRPC_RTO_MAX) WRITE_ONCE(peer->backoff, backoff + 1); - if (timo_j < 1) - timo_j = 1; + if (timo_us < 1) + timo_us = 1; - return timo_j; + return ns_to_ktime(timo_us * NSEC_PER_USEC); } void rxrpc_peer_init_rtt(struct rxrpc_peer *peer) { - peer->rto_j = RXRPC_TIMEOUT_INIT; - peer->mdev_us = jiffies_to_usecs(RXRPC_TIMEOUT_INIT); + peer->rto_us = RXRPC_TIMEOUT_INIT; + peer->mdev_us = RXRPC_TIMEOUT_INIT; peer->backoff = 0; //minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U); } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 6b32d61d4cdc..f1a68270862d 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -145,16 +145,17 @@ error: /* * Work out how much data we can put in a packet. */ -static int rxkad_how_much_data(struct rxrpc_call *call, size_t remain, - size_t *_buf_size, size_t *_data_size, size_t *_offset) +static struct rxrpc_txbuf *rxkad_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp) { - size_t shdr, buf_size, chunk; + struct rxrpc_txbuf *txb; + size_t shdr, space; + + remain = min(remain, 65535 - sizeof(struct rxrpc_wire_header)); switch (call->conn->security_level) { default: - buf_size = chunk = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); - shdr = 0; - goto out; + space = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); + return rxrpc_alloc_data_txbuf(call, space, 0, gfp); case RXRPC_SECURITY_AUTH: shdr = sizeof(struct rxkad_level1_hdr); break; @@ -163,17 +164,16 @@ static int rxkad_how_much_data(struct rxrpc_call *call, size_t remain, break; } - buf_size = round_down(RXRPC_JUMBO_DATALEN, RXKAD_ALIGN); + space = min_t(size_t, round_down(RXRPC_JUMBO_DATALEN, RXKAD_ALIGN), remain + shdr); + space = round_up(space, RXKAD_ALIGN); - chunk = buf_size - shdr; - if (remain < chunk) - buf_size = round_up(shdr + remain, RXKAD_ALIGN); + txb = rxrpc_alloc_data_txbuf(call, space, RXKAD_ALIGN, gfp); + if (!txb) + return NULL; -out: - *_buf_size = buf_size; - *_data_size = chunk; - *_offset = shdr; - return 0; + txb->offset += shdr; + txb->space -= shdr; + return txb; } /* @@ -251,7 +251,8 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, struct rxrpc_txbuf *txb, struct skcipher_request *req) { - struct rxkad_level1_hdr *hdr = (void *)txb->data; + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxkad_level1_hdr *hdr = (void *)(whdr + 1); struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -259,7 +260,7 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, _enter(""); - check = txb->seq ^ ntohl(txb->wire.callNumber); + check = txb->seq ^ call->call_id; hdr->data_size = htonl((u32)check << 16 | txb->len); txb->len += sizeof(struct rxkad_level1_hdr); @@ -267,14 +268,14 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; if (pad) { - memset(txb->data + txb->offset, 0, pad); + memset(txb->kvec[0].iov_base + txb->offset, 0, pad); txb->len += pad; } /* start the encryption afresh */ memset(&iv, 0, sizeof(iv)); - sg_init_one(&sg, txb->data, 8); + sg_init_one(&sg, hdr, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); @@ -293,7 +294,8 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, struct skcipher_request *req) { const struct rxrpc_key_token *token; - struct rxkad_level2_hdr *rxkhdr = (void *)txb->data; + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxkad_level2_hdr *rxkhdr = (void *)(whdr + 1); struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -302,7 +304,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, _enter(""); - check = txb->seq ^ ntohl(txb->wire.callNumber); + check = txb->seq ^ call->call_id; rxkhdr->data_size = htonl(txb->len | (u32)check << 16); rxkhdr->checksum = 0; @@ -312,7 +314,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; if (pad) { - memset(txb->data + txb->offset, 0, pad); + memset(txb->kvec[0].iov_base + txb->offset, 0, pad); txb->len += pad; } @@ -320,7 +322,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, token = call->conn->key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); - sg_init_one(&sg, txb->data, txb->len); + sg_init_one(&sg, rxkhdr, txb->len); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, txb->len, iv.x); @@ -362,9 +364,9 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv)); /* calculate the security checksum */ - x = (ntohl(txb->wire.cid) & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); + x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); x |= txb->seq & 0x3fffffff; - crypto.buf[0] = txb->wire.callNumber; + crypto.buf[0] = htonl(call->call_id); crypto.buf[1] = htonl(x); sg_init_one(&sg, crypto.buf, 8); @@ -378,7 +380,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) y = (y >> 16) & 0xffff; if (y == 0) y = 1; /* zero checksums are not permitted */ - txb->wire.cksum = htons(y); + txb->cksum = htons(y); switch (call->conn->security_level) { case RXRPC_SECURITY_PLAIN: @@ -726,7 +728,6 @@ static int rxkad_send_response(struct rxrpc_connection *conn, rxrpc_local_dont_fragment(conn->local, false); ret = kernel_sendmsg(conn->local->socket, &msg, iov, 3, len); - rxrpc_local_dont_fragment(conn->local, true); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, rxrpc_tx_point_rxkad_response); @@ -1256,7 +1257,7 @@ const struct rxrpc_security rxkad = { .free_preparse_server_key = rxkad_free_preparse_server_key, .destroy_server_key = rxkad_destroy_server_key, .init_connection_security = rxkad_init_connection_security, - .how_much_data = rxkad_how_much_data, + .alloc_txbuf = rxkad_alloc_txbuf, .secure_packet = rxkad_secure_packet, .verify_packet = rxkad_verify_packet, .free_call_crypto = rxkad_free_call_crypto, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 5677d5690a02..6f765768c49c 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -240,7 +240,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_notify_end_tx_t notify_end_tx) { rxrpc_seq_t seq = txb->seq; - bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke; + bool poke, last = txb->flags & RXRPC_LAST_PACKET; rxrpc_inc_stat(call->rxnet, stat_tx_data); @@ -336,7 +336,7 @@ reload: do { if (!txb) { - size_t remain, bufsize, chunk, offset; + size_t remain; _debug("alloc"); @@ -348,23 +348,11 @@ reload: * region (enc blocksize), but the trailer is not. */ remain = more ? INT_MAX : msg_data_left(msg); - ret = call->conn->security->how_much_data(call, remain, - &bufsize, &chunk, &offset); - if (ret < 0) + txb = call->conn->security->alloc_txbuf(call, remain, sk->sk_allocation); + if (IS_ERR(txb)) { + ret = PTR_ERR(txb); goto maybe_error; - - _debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset); - - /* create a buffer that we can retain until it's ACK'd */ - ret = -ENOMEM; - txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_DATA, - GFP_KERNEL); - if (!txb) - goto maybe_error; - - txb->offset = offset; - txb->space -= offset; - txb->space = min_t(size_t, chunk, txb->space); + } } _debug("append"); @@ -374,8 +362,8 @@ reload: size_t copy = min_t(size_t, txb->space, msg_data_left(msg)); _debug("add %zu", copy); - if (!copy_from_iter_full(txb->data + txb->offset, copy, - &msg->msg_iter)) + if (!copy_from_iter_full(txb->kvec[0].iov_base + txb->offset, + copy, &msg->msg_iter)) goto efault; _debug("added"); txb->space -= copy; @@ -394,18 +382,18 @@ reload: /* add the packet to the send queue if it's now full */ if (!txb->space || (msg_data_left(msg) == 0 && !more)) { - if (msg_data_left(msg) == 0 && !more) { - txb->wire.flags |= RXRPC_LAST_PACKET; - __set_bit(RXRPC_TXBUF_LAST, &txb->flags); - } + if (msg_data_left(msg) == 0 && !more) + txb->flags |= RXRPC_LAST_PACKET; else if (call->tx_top - call->acks_hard_ack < call->tx_winsize) - txb->wire.flags |= RXRPC_MORE_PACKETS; + txb->flags |= RXRPC_MORE_PACKETS; ret = call->security->secure_packet(call, txb); if (ret < 0) goto out; + txb->kvec[0].iov_len += txb->len; + txb->len = txb->kvec[0].iov_len; rxrpc_queue_packet(rx, call, txb, notify_end_tx); txb = NULL; } @@ -621,7 +609,6 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) { struct rxrpc_call *call; - unsigned long now, j; bool dropped_lock = false; int ret; @@ -699,25 +686,21 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) switch (p.call.nr_timeouts) { case 3: - j = msecs_to_jiffies(p.call.timeouts.normal); - if (p.call.timeouts.normal > 0 && j == 0) - j = 1; - WRITE_ONCE(call->next_rx_timo, j); + WRITE_ONCE(call->next_rx_timo, p.call.timeouts.normal); fallthrough; case 2: - j = msecs_to_jiffies(p.call.timeouts.idle); - if (p.call.timeouts.idle > 0 && j == 0) - j = 1; - WRITE_ONCE(call->next_req_timo, j); + WRITE_ONCE(call->next_req_timo, p.call.timeouts.idle); fallthrough; case 1: if (p.call.timeouts.hard > 0) { - j = p.call.timeouts.hard * HZ; - now = jiffies; - j += now; - WRITE_ONCE(call->expect_term_by, j); - rxrpc_reduce_call_timer(call, j, now, - rxrpc_timer_set_for_hard); + ktime_t delay = ms_to_ktime(p.call.timeouts.hard * MSEC_PER_SEC); + + WRITE_ONCE(call->expect_term_by, + ktime_add(p.call.timeouts.hard, + ktime_get_real())); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard); + rxrpc_poke_call(call, rxrpc_call_poke_set_timeout); + } break; } diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index ecaeb4ecfb58..c9bedd0e2d86 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -15,6 +15,8 @@ static const unsigned int four = 4; static const unsigned int max_backlog = RXRPC_BACKLOG_MAX - 1; static const unsigned int n_65535 = 65535; static const unsigned int n_max_acks = 255; +static const unsigned long one_ms = 1; +static const unsigned long max_ms = 1000; static const unsigned long one_jiffy = 1; static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY @@ -28,24 +30,24 @@ static const unsigned long max_500 = 500; * information on the individual parameters. */ static struct ctl_table rxrpc_sysctl_table[] = { - /* Values measured in milliseconds but used in jiffies */ + /* Values measured in milliseconds */ { .procname = "soft_ack_delay", .data = &rxrpc_soft_ack_delay, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, + .proc_handler = proc_doulongvec_minmax, + .extra1 = (void *)&one_ms, + .extra2 = (void *)&max_ms, }, { .procname = "idle_ack_delay", .data = &rxrpc_idle_ack_delay, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, + .proc_handler = proc_doulongvec_minmax, + .extra1 = (void *)&one_ms, + .extra2 = (void *)&max_ms, }, { .procname = "idle_conn_expiry", diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index d43be8512386..b2a82ab756c2 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -14,45 +14,146 @@ static atomic_t rxrpc_txbuf_debug_ids; atomic_t rxrpc_nr_txbuf; /* - * Allocate and partially initialise an I/O request structure. + * Allocate and partially initialise a data transmission buffer. */ -struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, - gfp_t gfp) +struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size, + size_t data_align, gfp_t gfp) { + struct rxrpc_wire_header *whdr; struct rxrpc_txbuf *txb; + size_t total, hoff = 0; + void *buf; txb = kmalloc(sizeof(*txb), gfp); - if (txb) { - INIT_LIST_HEAD(&txb->call_link); - INIT_LIST_HEAD(&txb->tx_link); - refcount_set(&txb->ref, 1); - txb->call_debug_id = call->debug_id; - txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); - txb->space = sizeof(txb->data); - txb->len = 0; - txb->offset = 0; - txb->flags = 0; - txb->ack_why = 0; - txb->seq = call->tx_prepared + 1; - txb->wire.epoch = htonl(call->conn->proto.epoch); - txb->wire.cid = htonl(call->cid); - txb->wire.callNumber = htonl(call->call_id); - txb->wire.seq = htonl(txb->seq); - txb->wire.type = packet_type; - txb->wire.flags = call->conn->out_clientflag; - txb->wire.userStatus = 0; - txb->wire.securityIndex = call->security_ix; - txb->wire._rsvd = 0; - txb->wire.serviceId = htons(call->dest_srx.srx_service); - - trace_rxrpc_txbuf(txb->debug_id, - txb->call_debug_id, txb->seq, 1, - packet_type == RXRPC_PACKET_TYPE_DATA ? - rxrpc_txbuf_alloc_data : - rxrpc_txbuf_alloc_ack); - atomic_inc(&rxrpc_nr_txbuf); + if (!txb) + return NULL; + + if (data_align) + hoff = round_up(sizeof(*whdr), data_align) - sizeof(*whdr); + total = hoff + sizeof(*whdr) + data_size; + + mutex_lock(&call->conn->tx_data_alloc_lock); + buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp, + ~(data_align - 1) & ~(L1_CACHE_BYTES - 1)); + mutex_unlock(&call->conn->tx_data_alloc_lock); + if (!buf) { + kfree(txb); + return NULL; + } + + whdr = buf + hoff; + + INIT_LIST_HEAD(&txb->call_link); + INIT_LIST_HEAD(&txb->tx_link); + refcount_set(&txb->ref, 1); + txb->last_sent = KTIME_MIN; + txb->call_debug_id = call->debug_id; + txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->space = data_size; + txb->len = 0; + txb->offset = sizeof(*whdr); + txb->flags = call->conn->out_clientflag; + txb->ack_why = 0; + txb->seq = call->tx_prepared + 1; + txb->serial = 0; + txb->cksum = 0; + txb->nr_kvec = 1; + txb->kvec[0].iov_base = whdr; + txb->kvec[0].iov_len = sizeof(*whdr); + + whdr->epoch = htonl(call->conn->proto.epoch); + whdr->cid = htonl(call->cid); + whdr->callNumber = htonl(call->call_id); + whdr->seq = htonl(txb->seq); + whdr->type = RXRPC_PACKET_TYPE_DATA; + whdr->flags = 0; + whdr->userStatus = 0; + whdr->securityIndex = call->security_ix; + whdr->_rsvd = 0; + whdr->serviceId = htons(call->dest_srx.srx_service); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 1, + rxrpc_txbuf_alloc_data); + + atomic_inc(&rxrpc_nr_txbuf); + return txb; +} + +/* + * Allocate and partially initialise an ACK packet. + */ +struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_size) +{ + struct rxrpc_wire_header *whdr; + struct rxrpc_acktrailer *trailer; + struct rxrpc_ackpacket *ack; + struct rxrpc_txbuf *txb; + gfp_t gfp = rcu_read_lock_held() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS; + void *buf, *buf2 = NULL; + u8 *filler; + + txb = kmalloc(sizeof(*txb), gfp); + if (!txb) + return NULL; + + buf = page_frag_alloc(&call->local->tx_alloc, + sizeof(*whdr) + sizeof(*ack) + 1 + 3 + sizeof(*trailer), gfp); + if (!buf) { + kfree(txb); + return NULL; + } + + if (sack_size) { + buf2 = page_frag_alloc(&call->local->tx_alloc, sack_size, gfp); + if (!buf2) { + page_frag_free(buf); + kfree(txb); + return NULL; + } } + whdr = buf; + ack = buf + sizeof(*whdr); + filler = buf + sizeof(*whdr) + sizeof(*ack) + 1; + trailer = buf + sizeof(*whdr) + sizeof(*ack) + 1 + 3; + + INIT_LIST_HEAD(&txb->call_link); + INIT_LIST_HEAD(&txb->tx_link); + refcount_set(&txb->ref, 1); + txb->call_debug_id = call->debug_id; + txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->space = 0; + txb->len = sizeof(*whdr) + sizeof(*ack) + 3 + sizeof(*trailer); + txb->offset = 0; + txb->flags = call->conn->out_clientflag; + txb->ack_rwind = 0; + txb->seq = 0; + txb->serial = 0; + txb->cksum = 0; + txb->nr_kvec = 3; + txb->kvec[0].iov_base = whdr; + txb->kvec[0].iov_len = sizeof(*whdr) + sizeof(*ack); + txb->kvec[1].iov_base = buf2; + txb->kvec[1].iov_len = sack_size; + txb->kvec[2].iov_base = filler; + txb->kvec[2].iov_len = 3 + sizeof(*trailer); + + whdr->epoch = htonl(call->conn->proto.epoch); + whdr->cid = htonl(call->cid); + whdr->callNumber = htonl(call->call_id); + whdr->seq = 0; + whdr->type = RXRPC_PACKET_TYPE_ACK; + whdr->flags = 0; + whdr->userStatus = 0; + whdr->securityIndex = call->security_ix; + whdr->_rsvd = 0; + whdr->serviceId = htons(call->dest_srx.srx_service); + + get_page(virt_to_head_page(trailer)); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 1, + rxrpc_txbuf_alloc_ack); + atomic_inc(&rxrpc_nr_txbuf); return txb; } @@ -71,12 +172,15 @@ void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r, what); } -static void rxrpc_free_txbuf(struct rcu_head *rcu) +static void rxrpc_free_txbuf(struct rxrpc_txbuf *txb) { - struct rxrpc_txbuf *txb = container_of(rcu, struct rxrpc_txbuf, rcu); + int i; trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 0, rxrpc_txbuf_free); + for (i = 0; i < txb->nr_kvec; i++) + if (txb->kvec[i].iov_base) + page_frag_free(txb->kvec[i].iov_base); kfree(txb); atomic_dec(&rxrpc_nr_txbuf); } @@ -95,7 +199,7 @@ void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) dead = __refcount_dec_and_test(&txb->ref, &r); trace_rxrpc_txbuf(debug_id, call_debug_id, seq, r - 1, what); if (dead) - call_rcu(&txb->rcu, rxrpc_free_txbuf); + rxrpc_free_txbuf(txb); } } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 470c70deffe2..8180d0c12fce 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -737,16 +737,6 @@ config NET_ACT_SAMPLE To compile this code as a module, choose M here: the module will be called act_sample. -config NET_ACT_IPT - tristate "IPtables targets" - depends on NET_CLS_ACT && NETFILTER && NETFILTER_XTABLES - help - Say Y here to be able to invoke iptables targets after successful - classification. - - To compile this code as a module, choose M here: the - module will be called act_ipt. - config NET_ACT_NAT tristate "Stateless NAT" depends on NET_CLS_ACT diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 3e30d7260493..9ee622fb1160 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1363,7 +1363,7 @@ struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, u32 flags, if (rtnl_held) rtnl_unlock(); - request_module("act_%s", act_name); + request_module(NET_ACT_ALIAS_PREFIX "%s", act_name); if (rtnl_held) rtnl_lock(); diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 6cfee6658103..0e3cf11ae5fc 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -401,6 +401,7 @@ static struct tc_action_ops act_bpf_ops __read_mostly = { .init = tcf_bpf_init, .size = sizeof(struct tcf_bpf), }; +MODULE_ALIAS_NET_ACT("bpf"); static __net_init int bpf_init_net(struct net *net) { diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index f8762756657d..0fce631e7c91 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -242,6 +242,7 @@ static struct tc_action_ops act_connmark_ops = { .cleanup = tcf_connmark_cleanup, .size = sizeof(struct tcf_connmark_info), }; +MODULE_ALIAS_NET_ACT("connmark"); static __net_init int connmark_init_net(struct net *net) { diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 7f8b1f2f2ed9..5cc8e407e791 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -709,6 +709,7 @@ static struct tc_action_ops act_csum_ops = { .offload_act_setup = tcf_csum_offload_act_setup, .size = sizeof(struct tcf_csum), }; +MODULE_ALIAS_NET_ACT("csum"); static __net_init int csum_init_net(struct net *net) { diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 6124d8b128d1..baac083fd8f1 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1600,6 +1600,7 @@ static struct tc_action_ops act_ct_ops = { .offload_act_setup = tcf_ct_offload_act_setup, .size = sizeof(struct tcf_ct), }; +MODULE_ALIAS_NET_ACT("ct"); static __net_init int ct_init_net(struct net *net) { diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index e620f9a84afe..5dd41a012110 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -363,6 +363,7 @@ static struct tc_action_ops act_ctinfo_ops = { .cleanup= tcf_ctinfo_cleanup, .size = sizeof(struct tcf_ctinfo), }; +MODULE_ALIAS_NET_ACT("ctinfo"); static __net_init int ctinfo_init_net(struct net *net) { diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 4af3b7ec249f..e949280eb800 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -296,6 +296,7 @@ static struct tc_action_ops act_gact_ops = { .offload_act_setup = tcf_gact_offload_act_setup, .size = sizeof(struct tcf_gact), }; +MODULE_ALIAS_NET_ACT("gact"); static __net_init int gact_init_net(struct net *net) { diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index c681cd011afd..1dd74125398a 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -645,6 +645,7 @@ static struct tc_action_ops act_gate_ops = { .offload_act_setup = tcf_gate_offload_act_setup, .size = sizeof(struct tcf_gate), }; +MODULE_ALIAS_NET_ACT("gate"); static __net_init int gate_init_net(struct net *net) { diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 0e867d13beb5..107c6d83dc5c 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -889,6 +889,7 @@ static struct tc_action_ops act_ife_ops = { .init = tcf_ife_init, .size = sizeof(struct tcf_ife_info), }; +MODULE_ALIAS_NET_ACT("ife"); static __net_init int ife_init_net(struct net *net) { diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 6faa7d00da09..5b3814365924 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -635,6 +635,7 @@ static struct tc_action_ops act_mirred_ops = { .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, }; +MODULE_ALIAS_NET_ACT("mirred"); static __net_init int mirred_init_net(struct net *net) { diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 34b8edb6cc77..44a37a71ae92 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -452,6 +452,7 @@ static struct tc_action_ops act_mpls_ops = { .offload_act_setup = tcf_mpls_offload_act_setup, .size = sizeof(struct tcf_mpls), }; +MODULE_ALIAS_NET_ACT("mpls"); static __net_init int mpls_init_net(struct net *net) { diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index a180e724634e..d541f553805f 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -324,6 +324,7 @@ static struct tc_action_ops act_nat_ops = { .cleanup = tcf_nat_cleanup, .size = sizeof(struct tcf_nat), }; +MODULE_ALIAS_NET_ACT("nat"); static __net_init int nat_init_net(struct net *net) { diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 2ef22969f274..fc0a35a7b62a 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -515,11 +515,11 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, spin_unlock_bh(&p->tcf_lock); return -ENOBUFS; } + opt->nkeys = parms->tcfp_nkeys; memcpy(opt->keys, parms->tcfp_keys, flex_array_size(opt, keys, parms->tcfp_nkeys)); opt->index = p->tcf_index; - opt->nkeys = parms->tcfp_nkeys; opt->flags = parms->tcfp_flags; opt->action = p->tcf_action; opt->refcnt = refcount_read(&p->tcf_refcnt) - ref; @@ -620,6 +620,7 @@ static struct tc_action_ops act_pedit_ops = { .offload_act_setup = tcf_pedit_offload_act_setup, .size = sizeof(struct tcf_pedit), }; +MODULE_ALIAS_NET_ACT("pedit"); static __net_init int pedit_init_net(struct net *net) { diff --git a/net/sched/act_police.c b/net/sched/act_police.c index e119b4a3db9f..8555125ed34d 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -502,6 +502,7 @@ static struct tc_action_ops act_police_ops = { .offload_act_setup = tcf_police_offload_act_setup, .size = sizeof(struct tcf_police), }; +MODULE_ALIAS_NET_ACT("police"); static __net_init int police_init_net(struct net *net) { diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index c5c61efe6db4..a69b53d54039 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -316,6 +316,7 @@ static struct tc_action_ops act_sample_ops = { .offload_act_setup = tcf_sample_offload_act_setup, .size = sizeof(struct tcf_sample), }; +MODULE_ALIAS_NET_ACT("sample"); static __net_init int sample_init_net(struct net *net) { diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 0a3e92888295..f3abe0545989 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -209,6 +209,7 @@ static struct tc_action_ops act_simp_ops = { .init = tcf_simp_init, .size = sizeof(struct tcf_defact), }; +MODULE_ALIAS_NET_ACT("simple"); static __net_init int simp_init_net(struct net *net) { diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 754f78b35bb8..1f1d9ce3e968 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -426,6 +426,7 @@ static struct tc_action_ops act_skbedit_ops = { .offload_act_setup = tcf_skbedit_offload_act_setup, .size = sizeof(struct tcf_skbedit), }; +MODULE_ALIAS_NET_ACT("skbedit"); static __net_init int skbedit_init_net(struct net *net) { diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index bcb673ab0008..39945b139c48 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -287,6 +287,7 @@ static struct tc_action_ops act_skbmod_ops = { .cleanup = tcf_skbmod_cleanup, .size = sizeof(struct tcf_skbmod), }; +MODULE_ALIAS_NET_ACT("skbmod"); static __net_init int skbmod_init_net(struct net *net) { diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 300b08aa8283..1536f8b16f1b 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -842,6 +842,7 @@ static struct tc_action_ops act_tunnel_key_ops = { .offload_act_setup = tcf_tunnel_key_offload_act_setup, .size = sizeof(struct tcf_tunnel_key), }; +MODULE_ALIAS_NET_ACT("tunnel_key"); static __net_init int tunnel_key_init_net(struct net *net) { diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 836183011a7c..22f4b1e8ade9 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -427,6 +427,7 @@ static struct tc_action_ops act_vlan_ops = { .offload_act_setup = tcf_vlan_offload_act_setup, .size = sizeof(struct tcf_vlan), }; +MODULE_ALIAS_NET_ACT("vlan"); static __net_init int vlan_init_net(struct net *net) { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ff3d396a65aa..ca5676b2668e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -257,7 +257,7 @@ tcf_proto_lookup_ops(const char *kind, bool rtnl_held, #ifdef CONFIG_MODULES if (rtnl_held) rtnl_unlock(); - request_module("cls_%s", kind); + request_module(NET_CLS_ALIAS_PREFIX "%s", kind); if (rtnl_held) rtnl_lock(); ops = __tcf_proto_lookup_ops(kind); diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index a1f56931330c..ecfaa4f9a04e 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -328,6 +328,7 @@ static struct tcf_proto_ops cls_basic_ops __read_mostly = { .bind_class = basic_bind_class, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("basic"); static int __init init_basic(void) { diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 382c7a71f81f..5e83e890f6a4 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -693,6 +693,7 @@ static struct tcf_proto_ops cls_bpf_ops __read_mostly = { .dump = cls_bpf_dump, .bind_class = cls_bpf_bind_class, }; +MODULE_ALIAS_NET_CLS("bpf"); static int __init cls_bpf_init_mod(void) { diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 7ee8dbf49ed0..424252982d6a 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -209,6 +209,7 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = { .dump = cls_cgroup_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("cgroup"); static int __init init_cgroup_cls(void) { diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 6ab317b48d6c..5502998aace7 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -702,6 +702,7 @@ static struct tcf_proto_ops cls_flow_ops __read_mostly = { .walk = flow_walk, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("flow"); static int __init cls_flow_init(void) { diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6ee7064c82fc..e1314674b4a9 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -3659,6 +3659,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .owner = THIS_MODULE, .flags = TCF_PROTO_OPS_DOIT_UNLOCKED, }; +MODULE_ALIAS_NET_CLS("flower"); static int __init cls_fl_init(void) { diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index afc534ee0a18..cdddc8695228 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -433,6 +433,7 @@ static struct tcf_proto_ops cls_fw_ops __read_mostly = { .bind_class = fw_bind_class, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("fw"); static int __init init_fw(void) { diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index c4ed11df6254..9f1e62ca508d 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -398,6 +398,7 @@ static struct tcf_proto_ops cls_mall_ops __read_mostly = { .bind_class = mall_bind_class, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("matchall"); static int __init cls_mall_init(void) { diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 12a505db4183..b9c58c040c30 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -671,6 +671,7 @@ static struct tcf_proto_ops cls_route4_ops __read_mostly = { .bind_class = route4_bind_class, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("route"); static int __init init_route4(void) { diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 289e1755c26b..9412d88a99bc 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1453,6 +1453,7 @@ static struct tcf_proto_ops cls_u32_ops __read_mostly = { .bind_class = u32_bind_class, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_CLS("u32"); static int __init init_u32(void) { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 87f6e3c6daa8..65e05b0c98e4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -228,7 +228,7 @@ int qdisc_set_default(const char *name) if (!ops) { /* Not found, drop lock and try to load module */ write_unlock(&qdisc_mod_lock); - request_module("sch_%s", name); + request_module(NET_SCH_ALIAS_PREFIX "%s", name); write_lock(&qdisc_mod_lock); ops = qdisc_lookup_default(name); @@ -1275,7 +1275,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, * go away in the mean time. */ rtnl_unlock(); - request_module("sch_%s", name); + request_module(NET_SCH_ALIAS_PREFIX "%s", name); rtnl_lock(); ops = qdisc_lookup_ops(kind); if (ops != NULL) { diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 9cff99558694..edee926ccde8 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -3103,6 +3103,7 @@ static struct Qdisc_ops cake_qdisc_ops __read_mostly = { .dump_stats = cake_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("cake"); static int __init cake_module_init(void) { diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index beece8e82c23..69001eff0315 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -546,6 +546,7 @@ static struct Qdisc_ops cbs_qdisc_ops __read_mostly = { .dump = cbs_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("cbs"); static struct notifier_block cbs_device_notifier = { .notifier_call = cbs_dev_notifier, diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index ae1da08e268f..ea108030c6b4 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -498,6 +498,7 @@ static struct Qdisc_ops choke_qdisc_ops __read_mostly = { .dump_stats = choke_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("choke"); static int __init choke_module_init(void) { diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index d7a4874543de..ecb3f164bb25 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Codel - The Controlled-Delay Active Queue Management algorithm * @@ -7,37 +8,6 @@ * Implemented on linux by : * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions, and the following disclaimer, - * without modification. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. The names of the authors may not be used to endorse or promote products - * derived from this software without specific prior written permission. - * - * Alternatively, provided that this notice is retained in full, this - * software may be distributed under the terms of the GNU General - * Public License ("GPL") version 2, in which case the provisions of the - * GPL apply INSTEAD OF those given above. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH - * DAMAGE. - * */ #include <linux/module.h> @@ -287,6 +257,7 @@ static struct Qdisc_ops codel_qdisc_ops __read_mostly = { .dump_stats = codel_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("codel"); static int __init codel_module_init(void) { diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 097740a9afea..c69b999fae17 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -481,6 +481,7 @@ static struct Qdisc_ops drr_qdisc_ops __read_mostly = { .destroy = drr_destroy_qdisc, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("drr"); static int __init drr_init(void) { diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index 4808159a5466..2e4bef713b6a 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -500,6 +500,7 @@ static struct Qdisc_ops etf_qdisc_ops __read_mostly = { .dump = etf_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("etf"); static int __init etf_module_init(void) { diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index f7c88495946b..835b4460b448 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -812,6 +812,7 @@ static struct Qdisc_ops ets_qdisc_ops __read_mostly = { .dump = ets_qdisc_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("ets"); static int __init ets_init(void) { diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 3a31c47fea9b..cdf23ff16f40 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -1264,6 +1264,7 @@ static struct Qdisc_ops fq_qdisc_ops __read_mostly = { .dump_stats = fq_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("fq"); static int __init fq_module_init(void) { diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 8c4fee063436..79f9d6de6c85 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -717,6 +717,7 @@ static struct Qdisc_ops fq_codel_qdisc_ops __read_mostly = { .dump_stats = fq_codel_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("fq_codel"); static int __init fq_codel_module_init(void) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 9b3e9262040b..ff5336493777 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -27,6 +27,7 @@ #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> +#include <net/hotdata.h> #include <trace/events/qdisc.h> #include <trace/events/net.h> #include <net/xfrm.h> @@ -409,7 +410,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) void __qdisc_run(struct Qdisc *q) { - int quota = READ_ONCE(dev_tx_weight); + int quota = READ_ONCE(net_hotdata.dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 8c61eb3dc943..79ba9dc70254 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -930,6 +930,7 @@ static struct Qdisc_ops gred_qdisc_ops __read_mostly = { .dump = gred_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("gred"); static int __init gred_module_init(void) { diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 16c45da4036a..4e626df742d7 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1679,6 +1679,7 @@ static struct Qdisc_ops hfsc_qdisc_ops __read_mostly = { .priv_size = sizeof(struct hfsc_sched), .owner = THIS_MODULE }; +MODULE_ALIAS_NET_SCH("hfsc"); static int __init hfsc_init(void) diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index d26cd436cbe3..3f906df1435b 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -702,6 +702,7 @@ static struct Qdisc_ops hhf_qdisc_ops __read_mostly = { .dump_stats = hhf_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("hhf"); static int __init hhf_module_init(void) { diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 7349233eaa9b..93e6fb56f3b5 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -2166,6 +2166,7 @@ static struct Qdisc_ops htb_qdisc_ops __read_mostly = { .dump = htb_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("htb"); static int __init htb_module_init(void) { diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 5fa9eaa79bfc..c2ef9dcf91d2 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -168,6 +168,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .ingress_block_get = ingress_ingress_block_get, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("ingress"); struct clsact_sched_data { struct tcf_block *ingress_block; @@ -344,6 +345,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .egress_block_get = clsact_egress_block_get, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("clsact"); static int __init ingress_module_init(void) { @@ -368,6 +370,5 @@ static void __exit ingress_module_exit(void) module_init(ingress_module_init); module_exit(ingress_module_exit); -MODULE_ALIAS("sch_clsact"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Ingress and clsact based ingress and egress qdiscs"); diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 43e53ee00a56..225353fbb3f1 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -774,6 +774,7 @@ static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { .dump = mqprio_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("mqprio"); static int __init mqprio_module_init(void) { diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index d66d5f0ec080..79e93a19d5fa 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -395,6 +395,7 @@ static struct Qdisc_ops multiq_qdisc_ops __read_mostly = { .dump = multiq_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("multiq"); static int __init multiq_module_init(void) { diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index fa678eb88528..edc72962ae63 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -1293,6 +1293,7 @@ static struct Qdisc_ops netem_qdisc_ops __read_mostly = { .dump = netem_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("netem"); static int __init netem_module_init(void) diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 2da6250ec346..1764059b0635 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -556,6 +556,7 @@ static struct Qdisc_ops pie_qdisc_ops __read_mostly = { .dump_stats = pie_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("pie"); static int __init pie_module_init(void) { diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index 992f0c8d7988..cefb65201e17 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -213,6 +213,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = { .reset = qdisc_reset_queue, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("plug"); static int __init plug_module_init(void) { diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 8ecdd3ef6f8e..cc30f7a32f1a 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -418,6 +418,7 @@ static struct Qdisc_ops prio_qdisc_ops __read_mostly = { .dump = prio_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("prio"); static int __init prio_module_init(void) { diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 48a604c320c7..d584c0c25899 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1521,6 +1521,7 @@ static struct Qdisc_ops qfq_qdisc_ops __read_mostly = { .destroy = qfq_destroy_qdisc, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("qfq"); static int __init qfq_init(void) { diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 607b6c8b3a9b..b5f096588fae 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -548,6 +548,7 @@ static struct Qdisc_ops red_qdisc_ops __read_mostly = { .dump_stats = red_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("red"); static int __init red_module_init(void) { diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 1871a1c0224d..b717e15a3a17 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -709,6 +709,7 @@ static struct Qdisc_ops sfb_qdisc_ops __read_mostly = { .dump_stats = sfb_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("sfb"); static int __init sfb_module_init(void) { diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index eb77558fa367..e66f4afb920d 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -925,6 +925,7 @@ static struct Qdisc_ops sfq_qdisc_ops __read_mostly = { .dump = sfq_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("sfq"); static int __init sfq_module_init(void) { diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 28beb11762d8..b4dd626c309c 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -292,6 +292,7 @@ static struct Qdisc_ops skbprio_qdisc_ops __read_mostly = { .destroy = skbprio_destroy, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("skbprio"); static int __init skbprio_module_init(void) { diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 31a8252bd09c..c5de70efdc86 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -40,6 +40,8 @@ static struct static_key_false taprio_have_working_mqprio; #define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) #define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) +#define TAPRIO_SUPPORTED_FLAGS \ + (TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST | TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) #define TAPRIO_FLAGS_INVALID U32_MAX struct sched_entry { @@ -408,19 +410,6 @@ static bool is_valid_interval(struct sk_buff *skb, struct Qdisc *sch) return entry; } -static bool taprio_flags_valid(u32 flags) -{ - /* Make sure no other flag bits are set. */ - if (flags & ~(TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST | - TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)) - return false; - /* txtime-assist and full offload are mutually exclusive */ - if ((flags & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) && - (flags & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)) - return false; - return true; -} - /* This returns the tstamp value set by TCP in terms of the set clock. */ static ktime_t get_tcp_tstamp(struct taprio_sched *q, struct sk_buff *skb) { @@ -1031,7 +1020,8 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range), [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, - [TCA_TAPRIO_ATTR_FLAGS] = { .type = NLA_U32 }, + [TCA_TAPRIO_ATTR_FLAGS] = + NLA_POLICY_MASK(NLA_U32, TAPRIO_SUPPORTED_FLAGS), [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, [TCA_TAPRIO_ATTR_TC_ENTRY] = { .type = NLA_NESTED }, }; @@ -1815,33 +1805,6 @@ static int taprio_mqprio_cmp(const struct net_device *dev, return 0; } -/* The semantics of the 'flags' argument in relation to 'change()' - * requests, are interpreted following two rules (which are applied in - * this order): (1) an omitted 'flags' argument is interpreted as - * zero; (2) the 'flags' of a "running" taprio instance cannot be - * changed. - */ -static int taprio_new_flags(const struct nlattr *attr, u32 old, - struct netlink_ext_ack *extack) -{ - u32 new = 0; - - if (attr) - new = nla_get_u32(attr); - - if (old != TAPRIO_FLAGS_INVALID && old != new) { - NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported"); - return -EOPNOTSUPP; - } - - if (!taprio_flags_valid(new)) { - NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid"); - return -EINVAL; - } - - return new; -} - static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -1852,6 +1815,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); struct tc_mqprio_qopt *mqprio = NULL; unsigned long flags; + u32 taprio_flags; ktime_t start; int i, err; @@ -1863,12 +1827,28 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_TAPRIO_ATTR_PRIOMAP]) mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]); - err = taprio_new_flags(tb[TCA_TAPRIO_ATTR_FLAGS], - q->flags, extack); - if (err < 0) - return err; + /* The semantics of the 'flags' argument in relation to 'change()' + * requests, are interpreted following two rules (which are applied in + * this order): (1) an omitted 'flags' argument is interpreted as + * zero; (2) the 'flags' of a "running" taprio instance cannot be + * changed. + */ + taprio_flags = tb[TCA_TAPRIO_ATTR_FLAGS] ? nla_get_u32(tb[TCA_TAPRIO_ATTR_FLAGS]) : 0; - q->flags = err; + /* txtime-assist and full offload are mutually exclusive */ + if ((taprio_flags & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) && + (taprio_flags & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)) { + NL_SET_ERR_MSG_ATTR(extack, tb[TCA_TAPRIO_ATTR_FLAGS], + "TXTIME_ASSIST and FULL_OFFLOAD are mutually exclusive"); + return -EINVAL; + } + + if (q->flags != TAPRIO_FLAGS_INVALID && q->flags != taprio_flags) { + NL_SET_ERR_MSG_MOD(extack, + "Changing 'flags' of a running schedule is not supported"); + return -EOPNOTSUPP; + } + q->flags = taprio_flags; err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags); if (err < 0) @@ -2548,6 +2528,7 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { .dump_stats = taprio_dump_stats, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("taprio"); static struct notifier_block taprio_device_notifier = { .notifier_call = taprio_dev_notifier, diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index dd6b1a723bf7..f1d09183ae63 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -608,6 +608,7 @@ static struct Qdisc_ops tbf_qdisc_ops __read_mostly = { .dump = tbf_dump, .owner = THIS_MODULE, }; +MODULE_ALIAS_NET_SCH("tbf"); static int __init tbf_module_init(void) { diff --git a/net/sctp/diag.c b/net/sctp/diag.c index eb05131ff1dd..23359e522273 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -507,6 +507,7 @@ done: } static const struct inet_diag_handler sctp_diag_handler = { + .owner = THIS_MODULE, .dump = sctp_diag_dump, .dump_one = sctp_diag_dump_one, .idiag_get_info = sctp_diag_get_info, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 94c6dd53cd62..e849f368ed91 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1495,17 +1495,11 @@ static __init int sctp_init(void) /* Allocate bind_bucket and chunk caches. */ status = -ENOBUFS; - sctp_bucket_cachep = kmem_cache_create("sctp_bind_bucket", - sizeof(struct sctp_bind_bucket), - 0, SLAB_HWCACHE_ALIGN, - NULL); + sctp_bucket_cachep = KMEM_CACHE(sctp_bind_bucket, SLAB_HWCACHE_ALIGN); if (!sctp_bucket_cachep) goto out; - sctp_chunk_cachep = kmem_cache_create("sctp_chunk", - sizeof(struct sctp_chunk), - 0, SLAB_HWCACHE_ALIGN, - NULL); + sctp_chunk_cachep = KMEM_CACHE(sctp_chunk, SLAB_HWCACHE_ALIGN); if (!sctp_chunk_cachep) goto err_chunk_cachep; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6b9fcdb0952a..c67679a41044 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -67,6 +67,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> +#include <net/rps.h> /* Forward declarations for internal helper functions. */ static bool sctp_writeable(const struct sock *sk); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 0f53a5c6fd9d..4b52b3b159c0 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1046,7 +1046,7 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc, int rc = SMC_CLC_DECL_NOSMCDDEV; struct smcd_dev *smcd; int i = 1, entry = 1; - bool is_virtual; + bool is_emulated; u16 chid; if (smcd_indicated(ini->smc_type_v1)) @@ -1058,12 +1058,12 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc, chid = smc_ism_get_chid(smcd); if (!smc_find_ism_v2_is_unique_chid(chid, ini, i)) continue; - is_virtual = __smc_ism_is_virtual(chid); + is_emulated = __smc_ism_is_emulated(chid); if (!smc_pnet_is_pnetid_set(smcd->pnetid) || smc_pnet_is_ndev_pnetid(sock_net(&smc->sk), smcd->pnetid)) { - if (is_virtual && entry == SMCD_CLC_MAX_V2_GID_ENTRIES) + if (is_emulated && entry == SMCD_CLC_MAX_V2_GID_ENTRIES) /* It's the last GID-CHID entry left in CLC - * Proposal SMC-Dv2 extension, but a virtual + * Proposal SMC-Dv2 extension, but an Emulated- * ISM device will take two entries. So give * up it and try the next potential ISM device. */ @@ -1073,7 +1073,7 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc, ini->is_smcd = true; rc = 0; i++; - entry = is_virtual ? entry + 2 : entry + 1; + entry = is_emulated ? entry + 2 : entry + 1; if (entry > SMCD_CLC_MAX_V2_GID_ENTRIES) break; } @@ -1414,10 +1414,10 @@ static int smc_connect_ism(struct smc_sock *smc, if (rc) return rc; - if (__smc_ism_is_virtual(ini->ism_chid[ini->ism_selected])) + if (__smc_ism_is_emulated(ini->ism_chid[ini->ism_selected])) ini->ism_peer_gid[ini->ism_selected].gid_ext = ntohll(aclc->d1.gid_ext); - /* for non-virtual ISM devices, peer gid_ext remains 0. */ + /* for non-Emulated-ISM devices, peer gid_ext remains 0. */ } ini->ism_peer_gid[ini->ism_selected].gid = ntohll(aclc->d0.gid); @@ -2118,10 +2118,10 @@ static void smc_check_ism_v2_match(struct smc_init_info *ini, if (smc_ism_get_chid(smcd) == proposed_chid && !smc_ism_cantalk(proposed_gid, ISM_RESERVED_VLANID, smcd)) { ini->ism_peer_gid[*matches].gid = proposed_gid->gid; - if (__smc_ism_is_virtual(proposed_chid)) + if (__smc_ism_is_emulated(proposed_chid)) ini->ism_peer_gid[*matches].gid_ext = proposed_gid->gid_ext; - /* non-virtual ISM's peer gid_ext remains 0. */ + /* non-Emulated-ISM's peer gid_ext remains 0. */ ini->ism_dev[*matches] = smcd; (*matches)++; break; @@ -2171,10 +2171,10 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, smcd_gid.gid = ntohll(smcd_v2_ext->gidchid[i].gid); smcd_gid.gid_ext = 0; chid = ntohs(smcd_v2_ext->gidchid[i].chid); - if (__smc_ism_is_virtual(chid)) { + if (__smc_ism_is_emulated(chid)) { if ((i + 1) == smc_v2_ext->hdr.ism_gid_cnt || chid != ntohs(smcd_v2_ext->gidchid[i + 1].chid)) - /* each virtual ISM device takes two GID-CHID + /* each Emulated-ISM device takes two GID-CHID * entries and CHID of the second entry repeats * that of the first entry. * diff --git a/net/smc/smc.h b/net/smc/smc.h index df64efd2dee8..18c8b7870198 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -56,11 +56,11 @@ enum smc_state { /* possible states of an SMC socket */ }; enum smc_supplemental_features { - SMC_SPF_VIRT_ISM_DEV = 0, + SMC_SPF_EMULATED_ISM_DEV = 0, }; #define SMC_FEATURE_MASK \ - (BIT(SMC_SPF_VIRT_ISM_DEV)) + (BIT(SMC_SPF_EMULATED_ISM_DEV)) struct smc_link_group; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 9a13709bea1c..e55026c7529c 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -952,8 +952,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) gidchids[entry].chid = htons(smc_ism_get_chid(ini->ism_dev[i])); gidchids[entry].gid = htonll(smcd_gid.gid); - if (smc_ism_is_virtual(smcd)) { - /* a virtual ISM device takes two + if (smc_ism_is_emulated(smcd)) { + /* an Emulated-ISM device takes two * entries. CHID of the second entry * repeats that of the first entry. */ @@ -1055,7 +1055,7 @@ smcd_clc_prep_confirm_accept(struct smc_connection *conn, clc->d1.chid = htons(chid); if (eid && eid[0]) memcpy(clc->d1.eid, eid, SMC_MAX_EID_LEN); - if (__smc_ism_is_virtual(chid)) + if (__smc_ism_is_emulated(chid)) clc->d1.gid_ext = htonll(smcd_gid.gid_ext); len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; if (first_contact) { diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index a9f9bdd26dcd..7cc7070b9772 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -175,7 +175,7 @@ struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ #define SMCD_CLC_MAX_V2_GID_ENTRIES 8 /* max # of CHID-GID entries in CLC * proposal SMC-Dv2 extension. * each ISM device takes one entry and - * each virtual ISM takes two entries. + * each Emulated-ISM takes two entries */ struct smc_clc_msg_proposal_area { diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index e4c858411207..9b84d5897aa5 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1535,7 +1535,7 @@ void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid, list_for_each_entry_safe(lgr, l, &dev->lgr_list, list) { if ((!peer_gid->gid || (lgr->peer_gid.gid == peer_gid->gid && - !smc_ism_is_virtual(dev) ? 1 : + !smc_ism_is_emulated(dev) ? 1 : lgr->peer_gid.gid_ext == peer_gid->gid_ext)) && (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) { if (peer_gid->gid) /* peer triggered termination */ @@ -1881,7 +1881,7 @@ static bool smcd_lgr_match(struct smc_link_group *lgr, lgr->smcd != smcismdev) return false; - if (smc_ism_is_virtual(smcismdev) && + if (smc_ism_is_emulated(smcismdev) && lgr->peer_gid.gid_ext != peer_gid->gid_ext) return false; diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 5a33908015f3..6fdb2d96777a 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -255,6 +255,7 @@ static int smc_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler smc_diag_handler = { + .owner = THIS_MODULE, .family = AF_SMC, .dump = smc_diag_handler_dump, }; diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index ffff40c30a06..165cd013404b 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -15,7 +15,7 @@ #include "smc.h" -#define SMC_VIRTUAL_ISM_CHID_MASK 0xFF00 +#define SMC_EMULATED_ISM_CHID_MASK 0xFF00 #define SMC_ISM_IDENT_MASK 0x00FFFF struct smcd_dev_list { /* List of SMCD devices */ @@ -66,10 +66,10 @@ static inline int smc_ism_write(struct smcd_dev *smcd, u64 dmb_tok, return rc < 0 ? rc : 0; } -static inline bool __smc_ism_is_virtual(u16 chid) +static inline bool __smc_ism_is_emulated(u16 chid) { /* CHIDs in range of 0xFF00 to 0xFFFF are reserved - * for virtual ISM device. + * for Emulated-ISM device. * * loopback-ism: 0xFFFF * virtio-ism: 0xFF00 ~ 0xFFFE @@ -77,11 +77,11 @@ static inline bool __smc_ism_is_virtual(u16 chid) return ((chid & 0xFF00) == 0xFF00); } -static inline bool smc_ism_is_virtual(struct smcd_dev *smcd) +static inline bool smc_ism_is_emulated(struct smcd_dev *smcd) { u16 chid = smcd->ops->get_chid(smcd); - return __smc_ism_is_virtual(chid); + return __smc_ism_is_emulated(chid); } #endif diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 9f2c58c5a86b..2adb92b8c469 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -806,6 +806,16 @@ static void smc_pnet_create_pnetids_list(struct net *net) u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; + /* Newly created netns do not have devices. + * Do not even acquire rtnl. + */ + if (list_empty(&net->dev_base_head)) + return; + + /* Note: This might not be needed, because smc_pnet_netdev_event() + * is also calling smc_pnet_add_base_pnetid() when handling + * NETDEV_UP event. + */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); diff --git a/net/socket.c b/net/socket.c index ed3df2f749bf..7e9c8fc9a5b4 100644 --- a/net/socket.c +++ b/net/socket.c @@ -343,7 +343,7 @@ static void init_inodecache(void) 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD | SLAB_ACCOUNT), + SLAB_ACCOUNT), init_once); BUG_ON(sock_inode_cachep == NULL); } diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index be1c4003d67d..bb0d71eb02a6 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -32,16 +32,17 @@ config TIPC_MEDIA_UDP bool "IP/UDP media type support" depends on TIPC select NET_UDP_TUNNEL + default y help Saying Y here will enable support for running TIPC over IP/UDP - bool - default y + config TIPC_CRYPTO bool "TIPC encryption support" depends on TIPC select CRYPTO select CRYPTO_AES select CRYPTO_GCM + default y help Saying Y here will enable support for TIPC encryption. All TIPC messages will be encrypted/decrypted by using the currently most @@ -49,8 +50,6 @@ config TIPC_CRYPTO entering the TIPC stack. Key setting from user-space is performed via netlink by a user program (e.g. the iproute2 'tipc' tool). - bool - default y config TIPC_DIAG tristate "TIPC: socket monitoring interface" diff --git a/net/tipc/Makefile b/net/tipc/Makefile index ee49a9f1dd4f..18e1636aa036 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -18,5 +18,5 @@ tipc-$(CONFIG_TIPC_MEDIA_IB) += ib_media.o tipc-$(CONFIG_SYSCTL) += sysctl.o tipc-$(CONFIG_TIPC_CRYPTO) += crypto.o - -obj-$(CONFIG_TIPC_DIAG) += diag.o +obj-$(CONFIG_TIPC_DIAG) += tipc_diag.o +tipc_diag-y += diag.o diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 878415c43527..5a526ebafeb4 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1079,30 +1079,27 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); b = tipc_bearer_find(net, name); if (!b) { - rtnl_unlock(); NL_SET_ERR_MSG(info->extack, "Bearer not found"); - return -EINVAL; + err = -EINVAL; + goto out; } #ifdef CONFIG_TIPC_MEDIA_UDP if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) { if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { - rtnl_unlock(); NL_SET_ERR_MSG(info->extack, "UDP option is unsupported"); - return -EINVAL; + err = -EINVAL; + goto out; } err = tipc_udp_nl_bearer_add(b, attrs[TIPC_NLA_BEARER_UDP_OPTS]); - if (err) { - rtnl_unlock(); - return err; - } } #endif +out: rtnl_unlock(); - return 0; + return err; } int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) diff --git a/net/tipc/diag.c b/net/tipc/diag.c index 18733451c9e0..54dde8c4e4d4 100644 --- a/net/tipc/diag.c +++ b/net/tipc/diag.c @@ -95,6 +95,7 @@ static int tipc_sock_diag_handler_dump(struct sk_buff *skb, } static const struct sock_diag_handler tipc_sock_diag_handler = { + .owner = THIS_MODULE, .family = AF_TIPC, .dump = tipc_sock_diag_handler_dump, }; diff --git a/net/tipc/node.c b/net/tipc/node.c index 3105abe97bb9..c1e890a82434 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -86,8 +86,6 @@ struct tipc_bclink_entry { * @lock: rwlock governing access to structure * @net: the applicable net namespace * @hash: links to adjacent nodes in unsorted hash chain - * @inputq: pointer to input queue containing messages for msg event - * @namedq: pointer to name table input queue with name table messages * @active_links: bearer ids of active links, used as index into links[] array * @links: array containing references to all links to node * @bc_entry: broadcast link entry diff --git a/net/tipc/socket.c b/net/tipc/socket.c index bb1118d02f95..7e4135db5816 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -80,7 +80,6 @@ struct sockaddr_pair { * @phdr: preformatted message header used when sending messages * @cong_links: list of congested links * @publications: list of publications for port - * @blocking_link: address of the congested link we are currently sleeping on * @pub_count: total # of publications port has made during its lifetime * @conn_timeout: the time we can wait for an unresponded setup request * @probe_unacked: probe has not received ack yet diff --git a/net/unix/Kconfig b/net/unix/Kconfig index 28b232f281ab..8b5d04210d7c 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -16,11 +16,6 @@ config UNIX Say Y unless you know what you are doing. -config UNIX_SCM - bool - depends on UNIX - default y - config AF_UNIX_OOB bool depends on UNIX diff --git a/net/unix/Makefile b/net/unix/Makefile index 20491825b4d0..4ddd125c4642 100644 --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -11,5 +11,3 @@ unix-$(CONFIG_BPF_SYSCALL) += unix_bpf.o obj-$(CONFIG_UNIX_DIAG) += unix_diag.o unix_diag-y := diag.o - -obj-$(CONFIG_UNIX_SCM) += scm.o diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0748e7ea5210..5b41e2321209 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -118,8 +118,6 @@ #include <linux/btf_ids.h> #include <linux/bpf-cgroup.h> -#include "scm.h" - static atomic_long_t unix_nr_socks; static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2]; static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2]; @@ -980,11 +978,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_write_space = unix_write_space; sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen; sk->sk_destruct = unix_sock_destructor; - u = unix_sk(sk); + u = unix_sk(sk); + u->inflight = 0; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ @@ -1775,6 +1773,52 @@ out: return err; } +/* The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + +static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + /* Need to duplicate file references for the sake of garbage + * collection. Otherwise a socket in the fps might become a + * candidate for GC while the skb is not yet queued. + */ + UNIXCB(skb).fp = scm_fp_dup(scm->fp); + if (!UNIXCB(skb).fp) + return -ENOMEM; + + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->user, scm->fp->fp[i]); + + return 0; +} + +static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + + scm->fp = UNIXCB(skb).fp; + UNIXCB(skb).fp = NULL; + + for (i = scm->fp->count - 1; i >= 0; i--) + unix_notinflight(scm->fp->user, scm->fp->fp[i]); +} + static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) { scm->fp = scm_fp_dup(UNIXCB(skb).fp); @@ -1822,6 +1866,21 @@ static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) spin_unlock(&unix_gc_lock); } +static void unix_destruct_scm(struct sk_buff *skb) +{ + struct scm_cookie scm; + + memset(&scm, 0, sizeof(scm)); + scm.pid = UNIXCB(skb).pid; + if (UNIXCB(skb).fp) + unix_detach_fds(&scm, skb); + + /* Alas, it calls VFS */ + /* So fscking what? fput() had been SMP-safe since the last Summer */ + scm_destroy(&scm); + sock_wfree(skb); +} + static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) { int err = 0; @@ -1908,11 +1967,12 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, long timeo; int err; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; + wait_for_unix_gc(scm.fp); + err = -EOPNOTSUPP; if (msg->msg_flags&MSG_OOB) goto out; @@ -2184,11 +2244,12 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, bool fds_sent = false; int data_len; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; + wait_for_unix_gc(scm.fp); + err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) { #if IS_ENABLED(CONFIG_AF_UNIX_OOB) diff --git a/net/unix/diag.c b/net/unix/diag.c index be19827eca36..ae39538c5042 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -322,6 +322,7 @@ static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler unix_diag_handler = { + .owner = THIS_MODULE, .family = AF_UNIX, .dump = unix_diag_handler_dump, }; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 2a81880dac7b..fa39b6265238 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -81,12 +81,80 @@ #include <net/scm.h> #include <net/tcp_states.h> -#include "scm.h" +struct unix_sock *unix_get_socket(struct file *filp) +{ + struct inode *inode = file_inode(filp); + + /* Socket ? */ + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { + struct socket *sock = SOCKET_I(inode); + const struct proto_ops *ops; + struct sock *sk = sock->sk; + + ops = READ_ONCE(sock->ops); -/* Internal data structures and random procedures: */ + /* PF_UNIX ? */ + if (sk && ops && ops->family == PF_UNIX) + return unix_sk(sk); + } + + return NULL; +} +DEFINE_SPINLOCK(unix_gc_lock); +unsigned int unix_tot_inflight; static LIST_HEAD(gc_candidates); -static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); +static LIST_HEAD(gc_inflight_list); + +/* Keep the number of times in flight count for the file + * descriptor if it is for an AF_UNIX socket. + */ +void unix_inflight(struct user_struct *user, struct file *filp) +{ + struct unix_sock *u = unix_get_socket(filp); + + spin_lock(&unix_gc_lock); + + if (u) { + if (!u->inflight) { + WARN_ON_ONCE(!list_empty(&u->link)); + list_add_tail(&u->link, &gc_inflight_list); + } else { + WARN_ON_ONCE(list_empty(&u->link)); + } + u->inflight++; + + /* Paired with READ_ONCE() in wait_for_unix_gc() */ + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); + } + + WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); + + spin_unlock(&unix_gc_lock); +} + +void unix_notinflight(struct user_struct *user, struct file *filp) +{ + struct unix_sock *u = unix_get_socket(filp); + + spin_lock(&unix_gc_lock); + + if (u) { + WARN_ON_ONCE(!u->inflight); + WARN_ON_ONCE(list_empty(&u->link)); + + u->inflight--; + if (!u->inflight) + list_del_init(&u->link); + + /* Paired with READ_ONCE() in wait_for_unix_gc() */ + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); + } + + WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); + + spin_unlock(&unix_gc_lock); +} static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) @@ -105,20 +173,15 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), while (nfd--) { /* Get the socket the fd matches if it indeed does so */ - struct sock *sk = unix_get_socket(*fp++); - - if (sk) { - struct unix_sock *u = unix_sk(sk); + struct unix_sock *u = unix_get_socket(*fp++); - /* Ignore non-candidates, they could - * have been added to the queues after - * starting the garbage collection - */ - if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { - hit = true; + /* Ignore non-candidates, they could have been added + * to the queues after starting the garbage collection + */ + if (u && test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { + hit = true; - func(u); - } + func(u); } } if (hit && hitlist != NULL) { @@ -151,7 +214,7 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), /* An embryo cannot be in-flight, so it's safe * to use the list link. */ - BUG_ON(!list_empty(&u->link)); + WARN_ON_ONCE(!list_empty(&u->link)); list_add_tail(&u->link, &embryos); } spin_unlock(&x->sk_receive_queue.lock); @@ -166,17 +229,18 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), static void dec_inflight(struct unix_sock *usk) { - atomic_long_dec(&usk->inflight); + usk->inflight--; } static void inc_inflight(struct unix_sock *usk) { - atomic_long_inc(&usk->inflight); + usk->inflight++; } static void inc_inflight_move_tail(struct unix_sock *u) { - atomic_long_inc(&u->inflight); + u->inflight++; + /* If this still might be part of a cycle, move it to the end * of the list, so that it's checked even if it was already * passed over @@ -186,40 +250,16 @@ static void inc_inflight_move_tail(struct unix_sock *u) } static bool gc_in_progress; -#define UNIX_INFLIGHT_TRIGGER_GC 16000 - -void wait_for_unix_gc(void) -{ - /* If number of inflight sockets is insane, - * force a garbage collect right now. - * Paired with the WRITE_ONCE() in unix_inflight(), - * unix_notinflight() and gc_in_progress(). - */ - if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && - !READ_ONCE(gc_in_progress)) - unix_gc(); - wait_event(unix_gc_wait, gc_in_progress == false); -} -/* The external entry point: unix_gc() */ -void unix_gc(void) +static void __unix_gc(struct work_struct *work) { - struct sk_buff *next_skb, *skb; - struct unix_sock *u; - struct unix_sock *next; struct sk_buff_head hitlist; - struct list_head cursor; + struct unix_sock *u, *next; LIST_HEAD(not_cycle_list); + struct list_head cursor; spin_lock(&unix_gc_lock); - /* Avoid a recursive GC. */ - if (gc_in_progress) - goto out; - - /* Paired with READ_ONCE() in wait_for_unix_gc(). */ - WRITE_ONCE(gc_in_progress, true); - /* First, select candidates for garbage collection. Only * in-flight sockets are considered, and from those only ones * which don't have any external reference. @@ -237,14 +277,12 @@ void unix_gc(void) */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { long total_refs; - long inflight_refs; total_refs = file_count(u->sk.sk_socket->file); - inflight_refs = atomic_long_read(&u->inflight); - BUG_ON(inflight_refs < 1); - BUG_ON(total_refs < inflight_refs); - if (total_refs == inflight_refs) { + WARN_ON_ONCE(!u->inflight); + WARN_ON_ONCE(total_refs < u->inflight); + if (total_refs == u->inflight) { list_move_tail(&u->link, &gc_candidates); __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); @@ -271,7 +309,7 @@ void unix_gc(void) /* Move cursor to after the current position. */ list_move(&cursor, &u->link); - if (atomic_long_read(&u->inflight) > 0) { + if (u->inflight) { list_move_tail(&u->link, ¬_cycle_list); __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); scan_children(&u->sk, inc_inflight_move_tail, NULL); @@ -306,38 +344,50 @@ void unix_gc(void) spin_unlock(&unix_gc_lock); - /* We need io_uring to clean its registered files, ignore all io_uring - * originated skbs. It's fine as io_uring doesn't keep references to - * other io_uring instances and so killing all other files in the cycle - * will put all io_uring references forcing it to go through normal - * release.path eventually putting registered files. - */ - skb_queue_walk_safe(&hitlist, skb, next_skb) { - if (skb->destructor == io_uring_destruct_scm) { - __skb_unlink(skb, &hitlist); - skb_queue_tail(&skb->sk->sk_receive_queue, skb); - } - } - /* Here we are. Hitlist is filled. Die. */ __skb_queue_purge(&hitlist); spin_lock(&unix_gc_lock); - /* There could be io_uring registered files, just push them back to - * the inflight list - */ - list_for_each_entry_safe(u, next, &gc_candidates, link) - list_move_tail(&u->link, &gc_inflight_list); - /* All candidates should have been detached by now. */ - BUG_ON(!list_empty(&gc_candidates)); + WARN_ON_ONCE(!list_empty(&gc_candidates)); /* Paired with READ_ONCE() in wait_for_unix_gc(). */ WRITE_ONCE(gc_in_progress, false); - wake_up(&unix_gc_wait); - - out: spin_unlock(&unix_gc_lock); } + +static DECLARE_WORK(unix_gc_work, __unix_gc); + +void unix_gc(void) +{ + WRITE_ONCE(gc_in_progress, true); + queue_work(system_unbound_wq, &unix_gc_work); +} + +#define UNIX_INFLIGHT_TRIGGER_GC 16000 +#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8) + +void wait_for_unix_gc(struct scm_fp_list *fpl) +{ + /* If number of inflight sockets is insane, + * force a garbage collect right now. + * + * Paired with the WRITE_ONCE() in unix_inflight(), + * unix_notinflight(), and __unix_gc(). + */ + if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && + !READ_ONCE(gc_in_progress)) + unix_gc(); + + /* Penalise users who want to send AF_UNIX sockets + * but whose sockets have not been received yet. + */ + if (!fpl || !fpl->count_unix || + READ_ONCE(fpl->user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) + return; + + if (READ_ONCE(gc_in_progress)) + flush_work(&unix_gc_work); +} diff --git a/net/unix/scm.c b/net/unix/scm.c deleted file mode 100644 index 822ce0d0d791..000000000000 --- a/net/unix/scm.c +++ /dev/null @@ -1,159 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/socket.h> -#include <linux/net.h> -#include <linux/fs.h> -#include <net/af_unix.h> -#include <net/scm.h> -#include <linux/init.h> -#include <linux/io_uring.h> - -#include "scm.h" - -unsigned int unix_tot_inflight; -EXPORT_SYMBOL(unix_tot_inflight); - -LIST_HEAD(gc_inflight_list); -EXPORT_SYMBOL(gc_inflight_list); - -DEFINE_SPINLOCK(unix_gc_lock); -EXPORT_SYMBOL(unix_gc_lock); - -struct sock *unix_get_socket(struct file *filp) -{ - struct sock *u_sock = NULL; - struct inode *inode = file_inode(filp); - - /* Socket ? */ - if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { - struct socket *sock = SOCKET_I(inode); - const struct proto_ops *ops = READ_ONCE(sock->ops); - struct sock *s = sock->sk; - - /* PF_UNIX ? */ - if (s && ops && ops->family == PF_UNIX) - u_sock = s; - } - - return u_sock; -} -EXPORT_SYMBOL(unix_get_socket); - -/* Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. - */ -void unix_inflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - if (atomic_long_inc_return(&u->inflight) == 1) { - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &gc_inflight_list); - } else { - BUG_ON(list_empty(&u->link)); - } - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); - } - WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); - spin_unlock(&unix_gc_lock); -} - -void unix_notinflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - BUG_ON(!atomic_long_read(&u->inflight)); - BUG_ON(list_empty(&u->link)); - - if (atomic_long_dec_and_test(&u->inflight)) - list_del_init(&u->link); - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); - } - WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); - spin_unlock(&unix_gc_lock); -} - -/* - * The "user->unix_inflight" variable is protected by the garbage - * collection lock, and we just read it locklessly here. If you go - * over the limit, there might be a tiny race in actually noticing - * it across threads. Tough. - */ -static inline bool too_many_unix_fds(struct task_struct *p) -{ - struct user_struct *user = current_user(); - - if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) - return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); - return false; -} - -int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - if (too_many_unix_fds(current)) - return -ETOOMANYREFS; - - /* - * Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. - */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; - - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); - return 0; -} -EXPORT_SYMBOL(unix_attach_fds); - -void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - scm->fp = UNIXCB(skb).fp; - UNIXCB(skb).fp = NULL; - - for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->user, scm->fp->fp[i]); -} -EXPORT_SYMBOL(unix_detach_fds); - -void unix_destruct_scm(struct sk_buff *skb) -{ - struct scm_cookie scm; - - memset(&scm, 0, sizeof(scm)); - scm.pid = UNIXCB(skb).pid; - if (UNIXCB(skb).fp) - unix_detach_fds(&scm, skb); - - /* Alas, it calls VFS */ - /* So fscking what? fput() had been SMP-safe since the last Summer */ - scm_destroy(&scm); - sock_wfree(skb); -} -EXPORT_SYMBOL(unix_destruct_scm); - -void io_uring_destruct_scm(struct sk_buff *skb) -{ - unix_destruct_scm(skb); -} -EXPORT_SYMBOL(io_uring_destruct_scm); diff --git a/net/unix/scm.h b/net/unix/scm.h deleted file mode 100644 index 5a255a477f16..000000000000 --- a/net/unix/scm.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef NET_UNIX_SCM_H -#define NET_UNIX_SCM_H - -extern struct list_head gc_inflight_list; -extern spinlock_t unix_gc_lock; - -int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb); -void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb); - -#endif diff --git a/net/vmw_vsock/diag.c b/net/vmw_vsock/diag.c index 2e29994f92ff..ab87ef66c1e8 100644 --- a/net/vmw_vsock/diag.c +++ b/net/vmw_vsock/diag.c @@ -157,6 +157,7 @@ static int vsock_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) } static const struct sock_diag_handler vsock_diag_handler = { + .owner = THIS_MODULE, .family = AF_VSOCK, .dump = vsock_diag_handler_dump, }; diff --git a/net/wireless/chan.c b/net/wireless/chan.c index ceb9174c5c3d..3414b2c3abcc 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 2018-2023 Intel Corporation + * Copyright 2018-2024 Intel Corporation */ #include <linux/export.h> @@ -27,11 +27,10 @@ void cfg80211_chandef_create(struct cfg80211_chan_def *chandef, if (WARN_ON(!chan)) return; - chandef->chan = chan; - chandef->freq1_offset = chan->freq_offset; - chandef->center_freq2 = 0; - chandef->edmg.bw_config = 0; - chandef->edmg.channels = 0; + *chandef = (struct cfg80211_chan_def) { + .chan = chan, + .freq1_offset = chan->freq_offset, + }; switch (chan_type) { case NL80211_CHAN_NO_HT: @@ -56,6 +55,73 @@ void cfg80211_chandef_create(struct cfg80211_chan_def *chandef, } EXPORT_SYMBOL(cfg80211_chandef_create); +struct cfg80211_per_bw_puncturing_values { + u8 len; + const u16 *valid_values; +}; + +static const u16 puncturing_values_80mhz[] = { + 0x8, 0x4, 0x2, 0x1 +}; + +static const u16 puncturing_values_160mhz[] = { + 0x80, 0x40, 0x20, 0x10, 0x8, 0x4, 0x2, 0x1, 0xc0, 0x30, 0xc, 0x3 +}; + +static const u16 puncturing_values_320mhz[] = { + 0xc000, 0x3000, 0xc00, 0x300, 0xc0, 0x30, 0xc, 0x3, 0xf000, 0xf00, + 0xf0, 0xf, 0xfc00, 0xf300, 0xf0c0, 0xf030, 0xf00c, 0xf003, 0xc00f, + 0x300f, 0xc0f, 0x30f, 0xcf, 0x3f +}; + +#define CFG80211_PER_BW_VALID_PUNCTURING_VALUES(_bw) \ + { \ + .len = ARRAY_SIZE(puncturing_values_ ## _bw ## mhz), \ + .valid_values = puncturing_values_ ## _bw ## mhz \ + } + +static const struct cfg80211_per_bw_puncturing_values per_bw_puncturing[] = { + CFG80211_PER_BW_VALID_PUNCTURING_VALUES(80), + CFG80211_PER_BW_VALID_PUNCTURING_VALUES(160), + CFG80211_PER_BW_VALID_PUNCTURING_VALUES(320) +}; + +static bool valid_puncturing_bitmap(const struct cfg80211_chan_def *chandef) +{ + u32 idx, i, start_freq, primary_center = chandef->chan->center_freq; + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_80: + idx = 0; + start_freq = chandef->center_freq1 - 40; + break; + case NL80211_CHAN_WIDTH_160: + idx = 1; + start_freq = chandef->center_freq1 - 80; + break; + case NL80211_CHAN_WIDTH_320: + idx = 2; + start_freq = chandef->center_freq1 - 160; + break; + default: + return chandef->punctured == 0; + } + + if (!chandef->punctured) + return true; + + /* check if primary channel is punctured */ + if (chandef->punctured & (u16)BIT((primary_center - start_freq) / 20)) + return false; + + for (i = 0; i < per_bw_puncturing[idx].len; i++) { + if (per_bw_puncturing[idx].valid_values[i] == chandef->punctured) + return true; + } + + return false; +} + static bool cfg80211_edmg_chandef_valid(const struct cfg80211_chan_def *chandef) { int max_contiguous = 0; @@ -317,72 +383,81 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) !cfg80211_edmg_chandef_valid(chandef)) return false; - return true; + return valid_puncturing_bitmap(chandef); } EXPORT_SYMBOL(cfg80211_chandef_valid); -static void chandef_primary_freqs(const struct cfg80211_chan_def *c, - u32 *pri40, u32 *pri80, u32 *pri160) +int cfg80211_chandef_primary(const struct cfg80211_chan_def *c, + enum nl80211_chan_width primary_chan_width, + u16 *punctured) { - int tmp; + int pri_width = nl80211_chan_width_to_mhz(primary_chan_width); + int width = cfg80211_chandef_get_width(c); + u32 control = c->chan->center_freq; + u32 center = c->center_freq1; + u16 _punct = 0; - switch (c->width) { - case NL80211_CHAN_WIDTH_40: - *pri40 = c->center_freq1; - *pri80 = 0; - *pri160 = 0; - break; - case NL80211_CHAN_WIDTH_80: - case NL80211_CHAN_WIDTH_80P80: - *pri160 = 0; - *pri80 = c->center_freq1; - /* n_P20 */ - tmp = (30 + c->chan->center_freq - c->center_freq1)/20; - /* n_P40 */ - tmp /= 2; - /* freq_P40 */ - *pri40 = c->center_freq1 - 20 + 40 * tmp; - break; - case NL80211_CHAN_WIDTH_160: - *pri160 = c->center_freq1; - /* n_P20 */ - tmp = (70 + c->chan->center_freq - c->center_freq1)/20; - /* n_P40 */ - tmp /= 2; - /* freq_P40 */ - *pri40 = c->center_freq1 - 60 + 40 * tmp; - /* n_P80 */ - tmp /= 2; - *pri80 = c->center_freq1 - 40 + 80 * tmp; - break; - case NL80211_CHAN_WIDTH_320: - /* n_P20 */ - tmp = (150 + c->chan->center_freq - c->center_freq1) / 20; - /* n_P40 */ - tmp /= 2; - /* freq_P40 */ - *pri40 = c->center_freq1 - 140 + 40 * tmp; - /* n_P80 */ - tmp /= 2; - *pri80 = c->center_freq1 - 120 + 80 * tmp; - /* n_P160 */ - tmp /= 2; - *pri160 = c->center_freq1 - 80 + 160 * tmp; - break; - default: - WARN_ON_ONCE(1); + if (WARN_ON_ONCE(pri_width < 0 || width < 0)) + return -1; + + /* not intended to be called this way, can't determine */ + if (WARN_ON_ONCE(pri_width > width)) + return -1; + + if (!punctured) + punctured = &_punct; + + *punctured = c->punctured; + + while (width > pri_width) { + unsigned int bits_to_drop = width / 20 / 2; + + if (control > center) { + center += width / 4; + *punctured >>= bits_to_drop; + } else { + center -= width / 4; + *punctured &= (1 << bits_to_drop) - 1; + } + width /= 2; } + + return center; } +EXPORT_SYMBOL(cfg80211_chandef_primary); -const struct cfg80211_chan_def * -cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1, - const struct cfg80211_chan_def *c2) +static const struct cfg80211_chan_def * +check_chandef_primary_compat(const struct cfg80211_chan_def *c1, + const struct cfg80211_chan_def *c2, + enum nl80211_chan_width primary_chan_width) { - u32 c1_pri40, c1_pri80, c2_pri40, c2_pri80, c1_pri160, c2_pri160; + u16 punct_c1 = 0, punct_c2 = 0; + + /* check primary is compatible -> error if not */ + if (cfg80211_chandef_primary(c1, primary_chan_width, &punct_c1) != + cfg80211_chandef_primary(c2, primary_chan_width, &punct_c2)) + return ERR_PTR(-EINVAL); + + if (punct_c1 != punct_c2) + return ERR_PTR(-EINVAL); + + /* assumes c1 is smaller width, if that was just checked -> done */ + if (c1->width == primary_chan_width) + return c2; + + /* otherwise continue checking the next width */ + return NULL; +} + +static const struct cfg80211_chan_def * +_cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1, + const struct cfg80211_chan_def *c2) +{ + const struct cfg80211_chan_def *ret; /* If they are identical, return */ if (cfg80211_chandef_identical(c1, c2)) - return c1; + return c2; /* otherwise, must have same control channel */ if (c1->chan != c2->chan) @@ -396,53 +471,76 @@ cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1, return NULL; /* - * can't be compatible if one of them is 5 or 10 MHz, + * can't be compatible if one of them is 5/10 MHz or S1G * but they don't have the same width. */ - if (c1->width == NL80211_CHAN_WIDTH_5 || - c1->width == NL80211_CHAN_WIDTH_10 || - c2->width == NL80211_CHAN_WIDTH_5 || - c2->width == NL80211_CHAN_WIDTH_10) +#define NARROW_OR_S1G(width) ((width) == NL80211_CHAN_WIDTH_5 || \ + (width) == NL80211_CHAN_WIDTH_10 || \ + (width) == NL80211_CHAN_WIDTH_1 || \ + (width) == NL80211_CHAN_WIDTH_2 || \ + (width) == NL80211_CHAN_WIDTH_4 || \ + (width) == NL80211_CHAN_WIDTH_8 || \ + (width) == NL80211_CHAN_WIDTH_16) + + if (NARROW_OR_S1G(c1->width) || NARROW_OR_S1G(c2->width)) return NULL; - if (c1->width == NL80211_CHAN_WIDTH_20_NOHT || - c1->width == NL80211_CHAN_WIDTH_20) + /* + * Make sure that c1 is always the narrower one, so that later + * we either return NULL or c2 and don't have to check both + * directions. + */ + if (c1->width > c2->width) + swap(c1, c2); + + /* + * No further checks needed if the "narrower" one is only 20 MHz. + * Here "narrower" includes being a 20 MHz non-HT channel vs. a + * 20 MHz HT (or later) one. + */ + if (c1->width <= NL80211_CHAN_WIDTH_20) return c2; - if (c2->width == NL80211_CHAN_WIDTH_20_NOHT || - c2->width == NL80211_CHAN_WIDTH_20) - return c1; + ret = check_chandef_primary_compat(c1, c2, NL80211_CHAN_WIDTH_40); + if (ret) + return ret; - chandef_primary_freqs(c1, &c1_pri40, &c1_pri80, &c1_pri160); - chandef_primary_freqs(c2, &c2_pri40, &c2_pri80, &c2_pri160); + ret = check_chandef_primary_compat(c1, c2, NL80211_CHAN_WIDTH_80); + if (ret) + return ret; - if (c1_pri40 != c2_pri40) + /* + * If c1 is 80+80, then c2 is 160 or higher, but that cannot + * match. If c2 was also 80+80 it was already either accepted + * or rejected above (identical or not, respectively.) + */ + if (c1->width == NL80211_CHAN_WIDTH_80P80) return NULL; - if (c1->width == NL80211_CHAN_WIDTH_40) - return c2; - - if (c2->width == NL80211_CHAN_WIDTH_40) - return c1; + ret = check_chandef_primary_compat(c1, c2, NL80211_CHAN_WIDTH_160); + if (ret) + return ret; - if (c1_pri80 != c2_pri80) - return NULL; + /* + * Getting here would mean they're both wider than 160, have the + * same primary 160, but are not identical - this cannot happen + * since they must be 320 (no wider chandefs exist, at least yet.) + */ + WARN_ON_ONCE(1); - if (c1->width == NL80211_CHAN_WIDTH_80 && - c2->width > NL80211_CHAN_WIDTH_80) - return c2; + return NULL; +} - if (c2->width == NL80211_CHAN_WIDTH_80 && - c1->width > NL80211_CHAN_WIDTH_80) - return c1; +const struct cfg80211_chan_def * +cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1, + const struct cfg80211_chan_def *c2) +{ + const struct cfg80211_chan_def *ret; - WARN_ON(!c1_pri160 && !c2_pri160); - if (c1_pri160 && c2_pri160 && c1_pri160 != c2_pri160) + ret = _cfg80211_chandef_compatible(c1, c2); + if (IS_ERR(ret)) return NULL; - - if (c1->width > c2->width) - return c1; - return c2; + return ret; } EXPORT_SYMBOL(cfg80211_chandef_compatible); @@ -1047,7 +1145,7 @@ EXPORT_SYMBOL(cfg80211_chandef_dfs_cac_time); static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, u32 center_freq, u32 bandwidth, - u32 prohibited_flags) + u32 prohibited_flags, bool monitor) { struct ieee80211_channel *c; u32 freq, start_freq, end_freq; @@ -1057,7 +1155,11 @@ static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, for (freq = start_freq; freq <= end_freq; freq += MHZ_TO_KHZ(20)) { c = ieee80211_get_channel_khz(wiphy, freq); - if (!c || c->flags & prohibited_flags) + if (!c) + return false; + if (monitor && c->flags & IEEE80211_CHAN_CAN_MONITOR) + continue; + if (c->flags & prohibited_flags) return false; } @@ -1117,9 +1219,9 @@ static bool cfg80211_edmg_usable(struct wiphy *wiphy, u8 edmg_channels, return true; } -bool cfg80211_chandef_usable(struct wiphy *wiphy, - const struct cfg80211_chan_def *chandef, - u32 prohibited_flags) +bool _cfg80211_chandef_usable(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + u32 prohibited_flags, bool monitor) { struct ieee80211_sta_ht_cap *ht_cap; struct ieee80211_sta_vht_cap *vht_cap; @@ -1281,14 +1383,22 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, if (!cfg80211_secondary_chans_ok(wiphy, ieee80211_chandef_to_khz(chandef), - width, prohibited_flags)) + width, prohibited_flags, monitor)) return false; if (!chandef->center_freq2) return true; return cfg80211_secondary_chans_ok(wiphy, MHZ_TO_KHZ(chandef->center_freq2), - width, prohibited_flags); + width, prohibited_flags, monitor); +} + +bool cfg80211_chandef_usable(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + u32 prohibited_flags) +{ + return _cfg80211_chandef_usable(wiphy, chandef, prohibited_flags, + false); } EXPORT_SYMBOL(cfg80211_chandef_usable); @@ -1532,72 +1642,3 @@ struct cfg80211_chan_def *wdev_chandef(struct wireless_dev *wdev, } } EXPORT_SYMBOL(wdev_chandef); - -struct cfg80211_per_bw_puncturing_values { - u8 len; - const u16 *valid_values; -}; - -static const u16 puncturing_values_80mhz[] = { - 0x8, 0x4, 0x2, 0x1 -}; - -static const u16 puncturing_values_160mhz[] = { - 0x80, 0x40, 0x20, 0x10, 0x8, 0x4, 0x2, 0x1, 0xc0, 0x30, 0xc, 0x3 -}; - -static const u16 puncturing_values_320mhz[] = { - 0xc000, 0x3000, 0xc00, 0x300, 0xc0, 0x30, 0xc, 0x3, 0xf000, 0xf00, - 0xf0, 0xf, 0xfc00, 0xf300, 0xf0c0, 0xf030, 0xf00c, 0xf003, 0xc00f, - 0x300f, 0xc0f, 0x30f, 0xcf, 0x3f -}; - -#define CFG80211_PER_BW_VALID_PUNCTURING_VALUES(_bw) \ - { \ - .len = ARRAY_SIZE(puncturing_values_ ## _bw ## mhz), \ - .valid_values = puncturing_values_ ## _bw ## mhz \ - } - -static const struct cfg80211_per_bw_puncturing_values per_bw_puncturing[] = { - CFG80211_PER_BW_VALID_PUNCTURING_VALUES(80), - CFG80211_PER_BW_VALID_PUNCTURING_VALUES(160), - CFG80211_PER_BW_VALID_PUNCTURING_VALUES(320) -}; - -bool cfg80211_valid_disable_subchannel_bitmap(u16 *bitmap, - const struct cfg80211_chan_def *chandef) -{ - u32 idx, i, start_freq; - - switch (chandef->width) { - case NL80211_CHAN_WIDTH_80: - idx = 0; - start_freq = chandef->center_freq1 - 40; - break; - case NL80211_CHAN_WIDTH_160: - idx = 1; - start_freq = chandef->center_freq1 - 80; - break; - case NL80211_CHAN_WIDTH_320: - idx = 2; - start_freq = chandef->center_freq1 - 160; - break; - default: - *bitmap = 0; - break; - } - - if (!*bitmap) - return true; - - /* check if primary channel is punctured */ - if (*bitmap & (u16)BIT((chandef->chan->center_freq - start_freq) / 20)) - return false; - - for (i = 0; i < per_bw_puncturing[idx].len; i++) - if (per_bw_puncturing[idx].valid_values[i] == *bitmap) - return true; - - return false; -} -EXPORT_SYMBOL(cfg80211_valid_disable_subchannel_bitmap); diff --git a/net/wireless/core.h b/net/wireless/core.h index 13657a85cf61..118f2f619828 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) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #ifndef __NET_WIRELESS_CORE_H #define __NET_WIRELESS_CORE_H @@ -362,7 +362,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, struct cfg80211_auth_request *req); int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, struct net_device *dev, - struct cfg80211_assoc_request *req); + struct cfg80211_assoc_request *req, + struct netlink_ext_ack *extack); int cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *bssid, const u8 *ie, int ie_len, u16 reason, @@ -491,6 +492,9 @@ bool cfg80211_is_sub_chan(struct cfg80211_chan_def *chandef, bool cfg80211_wdev_on_sub_chan(struct wireless_dev *wdev, struct ieee80211_channel *chan, bool primary_only); +bool _cfg80211_chandef_usable(struct wiphy *wiphy, + const struct cfg80211_chan_def *chandef, + u32 prohibited_flags, bool monitor); static inline unsigned int elapsed_jiffies_msecs(unsigned long start) { @@ -549,9 +553,53 @@ int cfg80211_remove_virtual_intf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask); +/** + * struct cfg80211_colocated_ap - colocated AP information + * + * @list: linked list to all colocated APs + * @bssid: BSSID of the reported AP + * @ssid: SSID of the reported AP + * @ssid_len: length of the ssid + * @center_freq: frequency the reported AP is on + * @unsolicited_probe: the reported AP is part of an ESS, where all the APs + * that operate in the same channel as the reported AP and that might be + * detected by a STA receiving this frame, are transmitting unsolicited + * Probe Response frames every 20 TUs + * @oct_recommended: OCT is recommended to exchange MMPDUs with the reported AP + * @same_ssid: the reported AP has the same SSID as the reporting AP + * @multi_bss: the reported AP is part of a multiple BSSID set + * @transmitted_bssid: the reported AP is the transmitting BSSID + * @colocated_ess: all the APs that share the same ESS as the reported AP are + * colocated and can be discovered via legacy bands. + * @short_ssid_valid: short_ssid is valid and can be used + * @short_ssid: the short SSID for this SSID + * @psd_20: The 20MHz PSD EIRP of the primary 20MHz channel for the reported AP + */ +struct cfg80211_colocated_ap { + struct list_head list; + u8 bssid[ETH_ALEN]; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + size_t ssid_len; + u32 short_ssid; + u32 center_freq; + u8 unsolicited_probe:1, + oct_recommended:1, + same_ssid:1, + multi_bss:1, + transmitted_bssid:1, + colocated_ess:1, + short_ssid_valid:1; + s8 psd_20; +}; + #if IS_ENABLED(CONFIG_CFG80211_KUNIT_TEST) #define EXPORT_SYMBOL_IF_CFG80211_KUNIT(sym) EXPORT_SYMBOL_IF_KUNIT(sym) #define VISIBLE_IF_CFG80211_KUNIT +void cfg80211_free_coloc_ap_list(struct list_head *coloc_ap_list); + +int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, + struct list_head *list); + size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen, const u8 *subie, size_t subie_len, u8 *new_ie, size_t new_ie_len); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index f635a8b6ca2e..4052041a19ea 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -4,7 +4,7 @@ * * Copyright (c) 2009, Jouni Malinen <j@w1.fi> * Copyright (c) 2015 Intel Deutschland GmbH - * Copyright (C) 2019-2020, 2022-2023 Intel Corporation + * Copyright (C) 2019-2020, 2022-2024 Intel Corporation */ #include <linux/kernel.h> @@ -241,12 +241,12 @@ void cfg80211_michael_mic_failure(struct net_device *dev, const u8 *addr, char *buf = kmalloc(128, gfp); if (buf) { - sprintf(buf, "MLME-MICHAELMICFAILURE.indication(" - "keyid=%d %scast addr=%pM)", key_id, - key_type == NL80211_KEYTYPE_GROUP ? "broad" : "uni", - addr); memset(&wrqu, 0, sizeof(wrqu)); - wrqu.data.length = strlen(buf); + wrqu.data.length = + sprintf(buf, "MLME-MICHAELMICFAILURE." + "indication(keyid=%d %scast addr=%pM)", + key_id, key_type == NL80211_KEYTYPE_GROUP + ? "broad" : "uni", addr); wireless_send_event(dev, IWEVCUSTOM, &wrqu, buf); kfree(buf); } @@ -325,28 +325,136 @@ void cfg80211_oper_and_vht_capa(struct ieee80211_vht_cap *vht_capa, p1[i] &= p2[i]; } -/* Note: caller must cfg80211_put_bss() regardless of result */ -int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, - struct net_device *dev, - struct cfg80211_assoc_request *req) +static int +cfg80211_mlme_check_mlo_compat(const struct ieee80211_multi_link_elem *mle_a, + const struct ieee80211_multi_link_elem *mle_b, + struct netlink_ext_ack *extack) { - struct wireless_dev *wdev = dev->ieee80211_ptr; - int err, i, j; + const struct ieee80211_mle_basic_common_info *common_a, *common_b; - lockdep_assert_wiphy(wdev->wiphy); + common_a = (const void *)mle_a->variable; + common_b = (const void *)mle_b->variable; + + if (memcmp(common_a->mld_mac_addr, common_b->mld_mac_addr, ETH_ALEN)) { + NL_SET_ERR_MSG(extack, "AP MLD address mismatch"); + return -EINVAL; + } + + if (ieee80211_mle_get_eml_med_sync_delay((const u8 *)mle_a) != + ieee80211_mle_get_eml_med_sync_delay((const u8 *)mle_b)) { + NL_SET_ERR_MSG(extack, "link EML medium sync delay mismatch"); + return -EINVAL; + } + + if (ieee80211_mle_get_eml_cap((const u8 *)mle_a) != + ieee80211_mle_get_eml_cap((const u8 *)mle_b)) { + NL_SET_ERR_MSG(extack, "link EML capabilities mismatch"); + return -EINVAL; + } + + if (ieee80211_mle_get_mld_capa_op((const u8 *)mle_a) != + ieee80211_mle_get_mld_capa_op((const u8 *)mle_b)) { + NL_SET_ERR_MSG(extack, "link MLD capabilities/ops mismatch"); + return -EINVAL; + } + + return 0; +} + +static int cfg80211_mlme_check_mlo(struct net_device *dev, + struct cfg80211_assoc_request *req, + struct netlink_ext_ack *extack) +{ + const struct ieee80211_multi_link_elem *mles[ARRAY_SIZE(req->links)] = {}; + int i; + + if (req->link_id < 0) + return 0; + + if (!req->links[req->link_id].bss) { + NL_SET_ERR_MSG(extack, "no BSS for assoc link"); + return -EINVAL; + } + + rcu_read_lock(); + for (i = 0; i < ARRAY_SIZE(req->links); i++) { + const struct cfg80211_bss_ies *ies; + const struct element *ml; - for (i = 1; i < ARRAY_SIZE(req->links); i++) { if (!req->links[i].bss) continue; - for (j = 0; j < i; j++) { - if (req->links[i].bss == req->links[j].bss) - return -EINVAL; + + if (ether_addr_equal(req->links[i].bss->bssid, dev->dev_addr)) { + NL_SET_ERR_MSG(extack, "BSSID must not be our address"); + req->links[i].error = -EINVAL; + goto error; } - if (ether_addr_equal(req->links[i].bss->bssid, dev->dev_addr)) - return -EINVAL; + ies = rcu_dereference(req->links[i].bss->ies); + ml = cfg80211_find_ext_elem(WLAN_EID_EXT_EHT_MULTI_LINK, + ies->data, ies->len); + if (!ml) { + NL_SET_ERR_MSG(extack, "MLO BSS w/o ML element"); + req->links[i].error = -EINVAL; + goto error; + } + + if (!ieee80211_mle_type_ok(ml->data + 1, + IEEE80211_ML_CONTROL_TYPE_BASIC, + ml->datalen - 1)) { + NL_SET_ERR_MSG(extack, "BSS with invalid ML element"); + req->links[i].error = -EINVAL; + goto error; + } + + mles[i] = (const void *)(ml->data + 1); + + if (ieee80211_mle_get_link_id((const u8 *)mles[i]) != i) { + NL_SET_ERR_MSG(extack, "link ID mismatch"); + req->links[i].error = -EINVAL; + goto error; + } + } + + if (WARN_ON(!mles[req->link_id])) + goto error; + + for (i = 0; i < ARRAY_SIZE(req->links); i++) { + if (i == req->link_id || !req->links[i].bss) + continue; + + if (WARN_ON(!mles[i])) + goto error; + + if (cfg80211_mlme_check_mlo_compat(mles[req->link_id], mles[i], + extack)) { + req->links[i].error = -EINVAL; + goto error; + } } + rcu_read_unlock(); + return 0; +error: + rcu_read_unlock(); + return -EINVAL; +} + +/* Note: caller must cfg80211_put_bss() regardless of result */ +int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_assoc_request *req, + struct netlink_ext_ack *extack) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + int err; + + lockdep_assert_wiphy(wdev->wiphy); + + err = cfg80211_mlme_check_mlo(dev, req, extack); + if (err) + return err; + if (wdev->connected && (!req->prev_bssid || !ether_addr_equal(wdev->u.client.connected_addr, req->prev_bssid))) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index bd54a928bab4..b4edba6b0b7b 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.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) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include <linux/if.h> @@ -581,7 +581,11 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_PRIVACY] = { .type = NLA_FLAG }, [NL80211_ATTR_STATUS_CODE] = { .type = NLA_U16 }, [NL80211_ATTR_CIPHER_SUITE_GROUP] = { .type = NLA_U32 }, - [NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 }, + [NL80211_ATTR_WPA_VERSIONS] = + NLA_POLICY_RANGE(NLA_U32, 0, + NL80211_WPA_VERSION_1 | + NL80211_WPA_VERSION_2 | + NL80211_WPA_VERSION_3), [NL80211_ATTR_PID] = { .type = NLA_U32 }, [NL80211_ATTR_4ADDR] = { .type = NLA_U8 }, [NL80211_ATTR_PMKID] = NLA_POLICY_EXACT_LEN_WARN(WLAN_PMKID_LEN), @@ -821,6 +825,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA] = { .type = NLA_FLAG }, [NL80211_ATTR_MLO_TTLM_DLINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8), [NL80211_ATTR_MLO_TTLM_ULINK] = NLA_POLICY_EXACT_LEN(sizeof(u16) * 8), + [NL80211_ATTR_ASSOC_SPP_AMSDU] = { .type = NLA_FLAG }, }; /* policy for the key attributes */ @@ -906,22 +911,11 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { }; static const struct nla_policy -nl80211_match_band_rssi_policy[NUM_NL80211_BANDS] = { - [NL80211_BAND_2GHZ] = { .type = NLA_S32 }, - [NL80211_BAND_5GHZ] = { .type = NLA_S32 }, - [NL80211_BAND_6GHZ] = { .type = NLA_S32 }, - [NL80211_BAND_60GHZ] = { .type = NLA_S32 }, - [NL80211_BAND_LC] = { .type = NLA_S32 }, -}; - -static const struct nla_policy nl80211_match_policy[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1] = { [NL80211_SCHED_SCAN_MATCH_ATTR_SSID] = { .type = NLA_BINARY, .len = IEEE80211_MAX_SSID_LEN }, [NL80211_SCHED_SCAN_MATCH_ATTR_BSSID] = NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN), [NL80211_SCHED_SCAN_MATCH_ATTR_RSSI] = { .type = NLA_U32 }, - [NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI] = - NLA_POLICY_NESTED(nl80211_match_band_rssi_policy), }; static const struct nla_policy @@ -1204,11 +1198,11 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_DFS_CONCURRENT) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_DFS_CONCURRENT)) goto nla_put_failure; - if ((chan->flags & IEEE80211_CHAN_NO_UHB_VLP_CLIENT) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_UHB_VLP_CLIENT)) + if ((chan->flags & IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_6GHZ_VLP_CLIENT)) goto nla_put_failure; - if ((chan->flags & IEEE80211_CHAN_NO_UHB_AFC_CLIENT) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_UHB_AFC_CLIENT)) + if ((chan->flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT)) goto nla_put_failure; } @@ -3224,24 +3218,9 @@ static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) wdev->iftype == NL80211_IFTYPE_P2P_GO; } -static int nl80211_parse_punct_bitmap(struct cfg80211_registered_device *rdev, - struct genl_info *info, - const struct cfg80211_chan_def *chandef, - u16 *punct_bitmap) -{ - if (!wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_PUNCT)) - return -EINVAL; - - *punct_bitmap = nla_get_u32(info->attrs[NL80211_ATTR_PUNCT_BITMAP]); - if (!cfg80211_valid_disable_subchannel_bitmap(punct_bitmap, chandef)) - return -EINVAL; - - return 0; -} - -int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, - struct genl_info *info, - struct cfg80211_chan_def *chandef) +static int _nl80211_parse_chandef(struct cfg80211_registered_device *rdev, + struct genl_info *info, bool monitor, + struct cfg80211_chan_def *chandef) { struct netlink_ext_ack *extack = info->extack; struct nlattr **attrs = info->attrs; @@ -3266,10 +3245,9 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, chandef->freq1_offset = control_freq % 1000; chandef->center_freq2 = 0; - /* Primary channel not allowed */ - if (!chandef->chan || chandef->chan->flags & IEEE80211_CHAN_DISABLED) { + if (!chandef->chan) { NL_SET_ERR_MSG_ATTR(extack, attrs[NL80211_ATTR_WIPHY_FREQ], - "Channel is disabled"); + "Unknown channel"); return -EINVAL; } @@ -3346,13 +3324,27 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, chandef->edmg.channels = 0; } + if (info->attrs[NL80211_ATTR_PUNCT_BITMAP]) { + chandef->punctured = + nla_get_u32(info->attrs[NL80211_ATTR_PUNCT_BITMAP]); + + if (chandef->punctured && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_PUNCT)) { + NL_SET_ERR_MSG(extack, + "driver doesn't support puncturing"); + return -EINVAL; + } + } + if (!cfg80211_chandef_valid(chandef)) { NL_SET_ERR_MSG(extack, "invalid channel definition"); return -EINVAL; } - if (!cfg80211_chandef_usable(&rdev->wiphy, chandef, - IEEE80211_CHAN_DISABLED)) { + if (!_cfg80211_chandef_usable(&rdev->wiphy, chandef, + IEEE80211_CHAN_DISABLED, + monitor)) { NL_SET_ERR_MSG(extack, "(extension) channel is disabled"); return -EINVAL; } @@ -3367,6 +3359,13 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, return 0; } +int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, + struct genl_info *info, + struct cfg80211_chan_def *chandef) +{ + return _nl80211_parse_chandef(rdev, info, false, chandef); +} + static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, struct net_device *dev, struct genl_info *info, @@ -3391,7 +3390,9 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, link_id = 0; } - result = nl80211_parse_chandef(rdev, info, &chandef); + result = _nl80211_parse_chandef(rdev, info, + iftype == NL80211_IFTYPE_MONITOR, + &chandef); if (result) return result; @@ -3822,6 +3823,10 @@ int nl80211_send_chandef(struct sk_buff *msg, const struct cfg80211_chan_def *ch if (chandef->center_freq2 && nla_put_u32(msg, NL80211_ATTR_CENTER_FREQ2, chandef->center_freq2)) return -ENOBUFS; + if (chandef->punctured && + nla_put_u32(msg, NL80211_ATTR_PUNCT_BITMAP, chandef->punctured)) + return -ENOBUFS; + return 0; } EXPORT_SYMBOL(nl80211_send_chandef); @@ -4202,8 +4207,6 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) if (netif_running(dev)) return -EBUSY; - BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != - IEEE80211_MAX_MESH_ID_LEN); wdev->u.mesh.id_up_len = nla_len(info->attrs[NL80211_ATTR_MESH_ID]); memcpy(wdev->u.mesh.id, @@ -4309,8 +4312,6 @@ static int _nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) case NL80211_IFTYPE_MESH_POINT: if (!info->attrs[NL80211_ATTR_MESH_ID]) break; - BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != - IEEE80211_MAX_MESH_ID_LEN); wdev->u.mesh.id_up_len = nla_len(info->attrs[NL80211_ATTR_MESH_ID]); memcpy(wdev->u.mesh.id, @@ -6069,14 +6070,6 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) goto out; } - if (info->attrs[NL80211_ATTR_PUNCT_BITMAP]) { - err = nl80211_parse_punct_bitmap(rdev, info, - ¶ms->chandef, - ¶ms->punct_bitmap); - if (err) - goto out; - } - if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, ¶ms->chandef, wdev->iftype)) { err = -EINVAL; @@ -6876,7 +6869,7 @@ int cfg80211_check_station_change(struct wiphy *wiphy, return -EINVAL; /* When you run into this, adjust the code below for the new flag */ - BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7); + BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 8); switch (statype) { case CFG80211_STA_MESH_PEER_KERNEL: @@ -6936,6 +6929,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy, params->link_sta_params.he_capa || params->link_sta_params.eht_capa) return -EINVAL; + if (params->sta_flags_mask & BIT(NL80211_STA_FLAG_SPP_AMSDU)) + return -EINVAL; } if (statype != CFG80211_STA_AP_CLIENT && @@ -6959,7 +6954,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy, BIT(NL80211_STA_FLAG_ASSOCIATED) | BIT(NL80211_STA_FLAG_SHORT_PREAMBLE) | BIT(NL80211_STA_FLAG_WME) | - BIT(NL80211_STA_FLAG_MFP))) + BIT(NL80211_STA_FLAG_MFP) | + BIT(NL80211_STA_FLAG_SPP_AMSDU))) return -EINVAL; /* but authenticated/associated only if driver handles it */ @@ -7518,7 +7514,7 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) return -EINVAL; /* When you run into this, adjust the code below for the new flag */ - BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 7); + BUILD_BUG_ON(NL80211_STA_FLAG_MAX != 8); switch (dev->ieee80211_ptr->iftype) { case NL80211_IFTYPE_AP: @@ -7542,6 +7538,11 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.sta_flags_mask & auth_assoc) return -EINVAL; + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SPP_AMSDU_SUPPORT) && + params.sta_flags_mask & BIT(NL80211_STA_FLAG_SPP_AMSDU)) + return -EINVAL; + /* Older userspace, or userspace wanting to be compatible with * !NL80211_FEATURE_FULL_AP_CLIENT_STATE, will not set the auth * and assoc flags in the mask, but assumes the station will be @@ -7630,14 +7631,16 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; struct station_del_parameters params; + int link_id = nl80211_link_id_or_invalid(info->attrs); memset(¶ms, 0, sizeof(params)); if (info->attrs[NL80211_ATTR_MAC]) params.mac = nla_data(info->attrs[NL80211_ATTR_MAC]); - switch (dev->ieee80211_ptr->iftype) { + switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MESH_POINT: @@ -7678,6 +7681,17 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) params.reason_code = WLAN_REASON_PREV_AUTH_NOT_VALID; } + /* Link ID not expected in case of non-ML operation */ + if (!wdev->valid_links && link_id != -1) + return -EINVAL; + + /* If given, a valid link ID should be passed during MLO */ + if (wdev->valid_links && link_id >= 0 && + !(wdev->valid_links & BIT(link_id))) + return -EINVAL; + + params.link_id = link_id; + return rdev_del_station(rdev, dev, ¶ms); } @@ -9483,41 +9497,6 @@ nl80211_parse_sched_scan_plans(struct wiphy *wiphy, int n_plans, return 0; } -static int -nl80211_parse_sched_scan_per_band_rssi(struct wiphy *wiphy, - struct cfg80211_match_set *match_sets, - struct nlattr *tb_band_rssi, - s32 rssi_thold) -{ - struct nlattr *attr; - int i, tmp, ret = 0; - - if (!wiphy_ext_feature_isset(wiphy, - NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD)) { - if (tb_band_rssi) - ret = -EOPNOTSUPP; - else - for (i = 0; i < NUM_NL80211_BANDS; i++) - match_sets->per_band_rssi_thold[i] = - NL80211_SCAN_RSSI_THOLD_OFF; - return ret; - } - - for (i = 0; i < NUM_NL80211_BANDS; i++) - match_sets->per_band_rssi_thold[i] = rssi_thold; - - nla_for_each_nested(attr, tb_band_rssi, tmp) { - enum nl80211_band band = nla_type(attr); - - if (band < 0 || band >= NUM_NL80211_BANDS) - return -EINVAL; - - match_sets->per_band_rssi_thold[band] = nla_get_s32(attr); - } - - return 0; -} - static struct cfg80211_sched_scan_request * nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, struct nlattr **attrs, int max_match_sets) @@ -9792,15 +9771,6 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, if (rssi) request->match_sets[i].rssi_thold = nla_get_s32(rssi); - - /* Parse per band RSSI attribute */ - err = nl80211_parse_sched_scan_per_band_rssi(wiphy, - &request->match_sets[i], - tb[NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI], - request->match_sets[i].rssi_thold); - if (err) - goto out_free; - i++; } @@ -10080,6 +10050,42 @@ static int nl80211_notify_radar_detection(struct sk_buff *skb, return 0; } +static int nl80211_parse_counter_offsets(struct cfg80211_registered_device *rdev, + const u8 *data, size_t datalen, + int first_count, struct nlattr *attr, + const u16 **offsets, unsigned int *n_offsets) +{ + int i; + + *n_offsets = 0; + + if (!attr) + return 0; + + if (!nla_len(attr) || (nla_len(attr) % sizeof(u16))) + return -EINVAL; + + *n_offsets = nla_len(attr) / sizeof(u16); + if (rdev->wiphy.max_num_csa_counters && + (*n_offsets > rdev->wiphy.max_num_csa_counters)) + return -EINVAL; + + *offsets = nla_data(attr); + + /* sanity checks - counters should fit and be the same */ + for (i = 0; i < *n_offsets; i++) { + u16 offset = (*offsets)[i]; + + if (offset >= datalen) + return -EINVAL; + + if (first_count != -1 && data[offset] != first_count) + return -EINVAL; + } + + return 0; +} + static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -10091,7 +10097,6 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) int err; bool need_new_beacon = false; bool need_handle_dfs_flag = true; - int len, i; u32 cs_count; if (!rdev->ops->channel_switch || @@ -10176,72 +10181,23 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) goto free; } - len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]); - if (!len || (len % sizeof(u16))) { - err = -EINVAL; + err = nl80211_parse_counter_offsets(rdev, params.beacon_csa.tail, + params.beacon_csa.tail_len, + params.count, + csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON], + ¶ms.counter_offsets_beacon, + ¶ms.n_counter_offsets_beacon); + if (err) goto free; - } - params.n_counter_offsets_beacon = len / sizeof(u16); - if (rdev->wiphy.max_num_csa_counters && - (params.n_counter_offsets_beacon > - rdev->wiphy.max_num_csa_counters)) { - err = -EINVAL; + err = nl80211_parse_counter_offsets(rdev, params.beacon_csa.probe_resp, + params.beacon_csa.probe_resp_len, + params.count, + csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP], + ¶ms.counter_offsets_presp, + ¶ms.n_counter_offsets_presp); + if (err) goto free; - } - - params.counter_offsets_beacon = - nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]); - - /* sanity checks - counters should fit and be the same */ - for (i = 0; i < params.n_counter_offsets_beacon; i++) { - u16 offset = params.counter_offsets_beacon[i]; - - if (offset >= params.beacon_csa.tail_len) { - err = -EINVAL; - goto free; - } - - if (params.beacon_csa.tail[offset] != params.count) { - err = -EINVAL; - goto free; - } - } - - if (csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]) { - len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]); - if (!len || (len % sizeof(u16))) { - err = -EINVAL; - goto free; - } - - params.n_counter_offsets_presp = len / sizeof(u16); - if (rdev->wiphy.max_num_csa_counters && - (params.n_counter_offsets_presp > - rdev->wiphy.max_num_csa_counters)) { - err = -EINVAL; - goto free; - } - - params.counter_offsets_presp = - nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]); - - /* sanity checks - counters should fit and be the same */ - for (i = 0; i < params.n_counter_offsets_presp; i++) { - u16 offset = params.counter_offsets_presp[i]; - - if (offset >= params.beacon_csa.probe_resp_len) { - err = -EINVAL; - goto free; - } - - if (params.beacon_csa.probe_resp[offset] != - params.count) { - err = -EINVAL; - goto free; - } - } - } skip_beacons: err = nl80211_parse_chandef(rdev, info, ¶ms.chandef); @@ -10272,14 +10228,7 @@ skip_beacons: if (info->attrs[NL80211_ATTR_CH_SWITCH_BLOCK_TX]) params.block_tx = true; - if (info->attrs[NL80211_ATTR_PUNCT_BITMAP]) { - err = nl80211_parse_punct_bitmap(rdev, info, - ¶ms.chandef, - ¶ms.punct_bitmap); - if (err) - goto free; - } - + params.link_id = link_id; err = rdev_channel_switch(rdev, dev, ¶ms); free: @@ -10652,13 +10601,6 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) return res; } -static bool nl80211_valid_wpa_versions(u32 wpa_versions) -{ - return !(wpa_versions & ~(NL80211_WPA_VERSION_1 | - NL80211_WPA_VERSION_2 | - NL80211_WPA_VERSION_3)); -} - static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; @@ -10884,12 +10826,9 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, return -EINVAL; } - if (info->attrs[NL80211_ATTR_WPA_VERSIONS]) { + if (info->attrs[NL80211_ATTR_WPA_VERSIONS]) settings->wpa_versions = nla_get_u32(info->attrs[NL80211_ATTR_WPA_VERSIONS]); - if (!nl80211_valid_wpa_versions(settings->wpa_versions)) - return -EINVAL; - } if (info->attrs[NL80211_ATTR_AKM_SUITES]) { void *data; @@ -11104,6 +11043,15 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) sizeof(req.s1g_capa)); } + if (nla_get_flag(info->attrs[NL80211_ATTR_ASSOC_SPP_AMSDU])) { + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SPP_AMSDU_SUPPORT)) { + GENL_SET_ERR_MSG(info, "SPP A-MSDUs not supported"); + return -EINVAL; + } + req.flags |= ASSOC_REQ_SPP_AMSDU; + } + req.link_id = nl80211_link_id_or_invalid(info->attrs); if (info->attrs[NL80211_ATTR_MLO_LINKS]) { @@ -11229,7 +11177,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) struct nlattr *link; int rem = 0; - err = cfg80211_mlme_assoc(rdev, dev, &req); + err = cfg80211_mlme_assoc(rdev, dev, &req, + info->extack); if (!err && info->attrs[NL80211_ATTR_SOCKET_OWNER]) { dev->ieee80211_ptr->conn_owner_nlportid = @@ -12677,23 +12626,12 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) params.buf = nla_data(info->attrs[NL80211_ATTR_FRAME]); params.len = nla_len(info->attrs[NL80211_ATTR_FRAME]); - if (info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]) { - int len = nla_len(info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]); - int i; - - if (len % sizeof(u16)) - return -EINVAL; - - params.n_csa_offsets = len / sizeof(u16); - params.csa_offsets = - nla_data(info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]); - - /* check that all the offsets fit the frame */ - for (i = 0; i < params.n_csa_offsets; i++) { - if (params.csa_offsets[i] >= params.len) - return -EINVAL; - } - } + err = nl80211_parse_counter_offsets(rdev, NULL, params.len, -1, + info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX], + ¶ms.csa_offsets, + ¶ms.n_csa_offsets); + if (err) + return err; if (!params.dont_wait_for_ack) { msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); @@ -16830,6 +16768,10 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_del_station, .flags = GENL_UNS_ADMIN_PERM, + /* cannot use NL80211_FLAG_MLO_VALID_LINK_ID, depends on + * whether MAC address is passed or not. If MAC address is + * passed, then even during MLO, link ID is not required. + */ .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), }, { @@ -19400,7 +19342,7 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef, gfp_t gfp, enum nl80211_commands notif, - u8 count, bool quiet, u16 punct_bitmap) + u8 count, bool quiet) { struct wireless_dev *wdev = netdev->ieee80211_ptr; struct sk_buff *msg; @@ -19434,9 +19376,6 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, goto nla_put_failure; } - if (nla_put_u32(msg, NL80211_ATTR_PUNCT_BITMAP, punct_bitmap)) - goto nla_put_failure; - genlmsg_end(msg, hdr); genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, @@ -19449,7 +19388,7 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev, void cfg80211_ch_switch_notify(struct net_device *dev, struct cfg80211_chan_def *chandef, - unsigned int link_id, u16 punct_bitmap) + unsigned int link_id) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; @@ -19458,7 +19397,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev, lockdep_assert_wiphy(wdev->wiphy); WARN_INVALID_LINK_ID(wdev, link_id); - trace_cfg80211_ch_switch_notify(dev, chandef, link_id, punct_bitmap); + trace_cfg80211_ch_switch_notify(dev, chandef, link_id); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: @@ -19487,15 +19426,14 @@ void cfg80211_ch_switch_notify(struct net_device *dev, cfg80211_sched_dfs_chan_update(rdev); nl80211_ch_switch_notify(rdev, dev, link_id, chandef, GFP_KERNEL, - NL80211_CMD_CH_SWITCH_NOTIFY, 0, false, - punct_bitmap); + NL80211_CMD_CH_SWITCH_NOTIFY, 0, false); } EXPORT_SYMBOL(cfg80211_ch_switch_notify); void cfg80211_ch_switch_started_notify(struct net_device *dev, struct cfg80211_chan_def *chandef, unsigned int link_id, u8 count, - bool quiet, u16 punct_bitmap) + bool quiet) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; @@ -19504,13 +19442,12 @@ void cfg80211_ch_switch_started_notify(struct net_device *dev, lockdep_assert_wiphy(wdev->wiphy); WARN_INVALID_LINK_ID(wdev, link_id); - trace_cfg80211_ch_switch_started_notify(dev, chandef, link_id, - punct_bitmap); + trace_cfg80211_ch_switch_started_notify(dev, chandef, link_id); nl80211_ch_switch_notify(rdev, dev, link_id, chandef, GFP_KERNEL, NL80211_CMD_CH_SWITCH_STARTED_NOTIFY, - count, quiet, punct_bitmap); + count, quiet); } EXPORT_SYMBOL(cfg80211_ch_switch_started_notify); @@ -19887,6 +19824,11 @@ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev, NL80211_WOWLAN_TRIG_WAKEUP_TCP_NOMORETOKENS)) goto free_msg; + if (wakeup->unprot_deauth_disassoc && + nla_put_flag(msg, + NL80211_WOWLAN_TRIG_UNPROTECTED_DEAUTH_DISASSOC)) + goto free_msg; + if (wakeup->packet) { u32 pkt_attr = NL80211_WOWLAN_TRIG_WAKEUP_PKT_80211; u32 len_attr = NL80211_WOWLAN_TRIG_WAKEUP_PKT_80211_LEN; @@ -20167,9 +20109,26 @@ int cfg80211_external_auth_request(struct net_device *dev, if (!hdr) goto nla_put_failure; + /* Some historical mistakes in drivers <-> userspace interface (notably + * between drivers and wpa_supplicant) led to a big-endian conversion + * being needed on NL80211_ATTR_AKM_SUITES _only_ when its value is + * WLAN_AKM_SUITE_SAE. This is now fixed on userspace side, but for the + * benefit of older wpa_supplicant versions, send this particular value + * in big-endian. Note that newer wpa_supplicant will also detect this + * particular value in big endian still, so it all continues to work. + */ + if (params->key_mgmt_suite == WLAN_AKM_SUITE_SAE) { + if (nla_put_be32(msg, NL80211_ATTR_AKM_SUITES, + cpu_to_be32(WLAN_AKM_SUITE_SAE))) + goto nla_put_failure; + } else { + if (nla_put_u32(msg, NL80211_ATTR_AKM_SUITES, + params->key_mgmt_suite)) + goto nla_put_failure; + } + if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || - nla_put_u32(msg, NL80211_ATTR_AKM_SUITES, params->key_mgmt_suite) || nla_put_u32(msg, NL80211_ATTR_EXTERNAL_AUTH_ACTION, params->action) || nla_put(msg, NL80211_ATTR_BSSID, ETH_ALEN, params->bssid) || diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 2741b626919a..753f8e9aa4b1 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -5,7 +5,7 @@ * Copyright 2008-2011 Luis R. Rodriguez <mcgrof@qca.qualcomm.com> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2023 Intel Corporation + * Copyright (C) 2018 - 2024 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -57,6 +57,8 @@ #include <linux/verification.h> #include <linux/moduleparam.h> #include <linux/firmware.h> +#include <linux/units.h> + #include <net/cfg80211.h> #include "core.h" #include "reg.h" @@ -1289,20 +1291,17 @@ static bool is_valid_rd(const struct ieee80211_regdomain *rd) static bool freq_in_rule_band(const struct ieee80211_freq_range *freq_range, u32 freq_khz) { -#define ONE_GHZ_IN_KHZ 1000000 /* * From 802.11ad: directional multi-gigabit (DMG): * Pertaining to operation in a frequency band containing a channel * with the Channel starting frequency above 45 GHz. */ - u32 limit = freq_khz > 45 * ONE_GHZ_IN_KHZ ? - 20 * ONE_GHZ_IN_KHZ : 2 * ONE_GHZ_IN_KHZ; + u32 limit = freq_khz > 45 * KHZ_PER_GHZ ? 20 * KHZ_PER_GHZ : 2 * KHZ_PER_GHZ; if (abs(freq_khz - freq_range->start_freq_khz) <= limit) return true; if (abs(freq_khz - freq_range->end_freq_khz) <= limit) return true; return false; -#undef ONE_GHZ_IN_KHZ } /* @@ -1595,10 +1594,10 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_EHT; if (rd_flags & NL80211_RRF_DFS_CONCURRENT) channel_flags |= IEEE80211_CHAN_DFS_CONCURRENT; - if (rd_flags & NL80211_RRF_NO_UHB_VLP_CLIENT) - channel_flags |= IEEE80211_CHAN_NO_UHB_VLP_CLIENT; - if (rd_flags & NL80211_RRF_NO_UHB_AFC_CLIENT) - channel_flags |= IEEE80211_CHAN_NO_UHB_AFC_CLIENT; + if (rd_flags & NL80211_RRF_NO_6GHZ_VLP_CLIENT) + channel_flags |= IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT; + if (rd_flags & NL80211_RRF_NO_6GHZ_AFC_CLIENT) + channel_flags |= IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT; if (rd_flags & NL80211_RRF_PSD) channel_flags |= IEEE80211_CHAN_PSD; return channel_flags; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 389a52c29bfc..5a5dd3ce497f 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) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include <linux/kernel.h> #include <linux/slab.h> @@ -77,45 +77,6 @@ MODULE_PARM_DESC(bss_entries_limit, #define IEEE80211_SCAN_RESULT_EXPIRE (30 * HZ) -/** - * struct cfg80211_colocated_ap - colocated AP information - * - * @list: linked list to all colocated aPS - * @bssid: BSSID of the reported AP - * @ssid: SSID of the reported AP - * @ssid_len: length of the ssid - * @center_freq: frequency the reported AP is on - * @unsolicited_probe: the reported AP is part of an ESS, where all the APs - * that operate in the same channel as the reported AP and that might be - * detected by a STA receiving this frame, are transmitting unsolicited - * Probe Response frames every 20 TUs - * @oct_recommended: OCT is recommended to exchange MMPDUs with the reported AP - * @same_ssid: the reported AP has the same SSID as the reporting AP - * @multi_bss: the reported AP is part of a multiple BSSID set - * @transmitted_bssid: the reported AP is the transmitting BSSID - * @colocated_ess: all the APs that share the same ESS as the reported AP are - * colocated and can be discovered via legacy bands. - * @short_ssid_valid: short_ssid is valid and can be used - * @short_ssid: the short SSID for this SSID - * @psd_20: The 20MHz PSD EIRP of the primary 20MHz channel for the reported AP - */ -struct cfg80211_colocated_ap { - struct list_head list; - u8 bssid[ETH_ALEN]; - u8 ssid[IEEE80211_MAX_SSID_LEN]; - size_t ssid_len; - u32 short_ssid; - u32 center_freq; - u8 unsolicited_probe:1, - oct_recommended:1, - same_ssid:1, - multi_bss:1, - transmitted_bssid:1, - colocated_ess:1, - short_ssid_valid:1; - s8 psd_20; -}; - static void bss_free(struct cfg80211_internal_bss *bss) { struct cfg80211_bss_ies *ies; @@ -566,7 +527,8 @@ static int cfg80211_calc_short_ssid(const struct cfg80211_bss_ies *ies, return 0; } -static void cfg80211_free_coloc_ap_list(struct list_head *coloc_ap_list) +VISIBLE_IF_CFG80211_KUNIT void +cfg80211_free_coloc_ap_list(struct list_head *coloc_ap_list) { struct cfg80211_colocated_ap *ap, *tmp_ap; @@ -575,6 +537,7 @@ static void cfg80211_free_coloc_ap_list(struct list_head *coloc_ap_list) kfree(ap); } } +EXPORT_SYMBOL_IF_CFG80211_KUNIT(cfg80211_free_coloc_ap_list); static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry, const u8 *pos, u8 length, @@ -648,104 +611,140 @@ static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry, return 0; } -static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, - struct list_head *list) +bool cfg80211_iter_rnr(const u8 *elems, size_t elems_len, + enum cfg80211_rnr_iter_ret + (*iter)(void *data, u8 type, + const struct ieee80211_neighbor_ap_info *info, + const u8 *tbtt_info, u8 tbtt_info_len), + void *iter_data) { - struct ieee80211_neighbor_ap_info *ap_info; - const struct element *elem, *ssid_elem; + const struct element *rnr; const u8 *pos, *end; - u32 s_ssid_tmp; - int n_coloc = 0, ret; - LIST_HEAD(ap_list); - ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp); - if (ret) - return 0; + for_each_element_id(rnr, WLAN_EID_REDUCED_NEIGHBOR_REPORT, + elems, elems_len) { + const struct ieee80211_neighbor_ap_info *info; - for_each_element_id(elem, WLAN_EID_REDUCED_NEIGHBOR_REPORT, - ies->data, ies->len) { - pos = elem->data; - end = elem->data + elem->datalen; + pos = rnr->data; + end = rnr->data + rnr->datalen; /* RNR IE may contain more than one NEIGHBOR_AP_INFO */ - while (pos + sizeof(*ap_info) <= end) { - enum nl80211_band band; - int freq; + while (sizeof(*info) <= end - pos) { u8 length, i, count; + u8 type; - ap_info = (void *)pos; - count = u8_get_bits(ap_info->tbtt_info_hdr, - IEEE80211_AP_INFO_TBTT_HDR_COUNT) + 1; - length = ap_info->tbtt_info_len; + info = (void *)pos; + count = u8_get_bits(info->tbtt_info_hdr, + IEEE80211_AP_INFO_TBTT_HDR_COUNT) + + 1; + length = info->tbtt_info_len; - pos += sizeof(*ap_info); + pos += sizeof(*info); - if (!ieee80211_operating_class_to_band(ap_info->op_class, - &band)) - break; + if (count * length > end - pos) + return false; - freq = ieee80211_channel_to_frequency(ap_info->channel, - band); + type = u8_get_bits(info->tbtt_info_hdr, + IEEE80211_AP_INFO_TBTT_HDR_TYPE); - if (end - pos < count * length) - break; + for (i = 0; i < count; i++) { + switch (iter(iter_data, type, info, + pos, length)) { + case RNR_ITER_CONTINUE: + break; + case RNR_ITER_BREAK: + return true; + case RNR_ITER_ERROR: + return false; + } - if (u8_get_bits(ap_info->tbtt_info_hdr, - IEEE80211_AP_INFO_TBTT_HDR_TYPE) != - IEEE80211_TBTT_INFO_TYPE_TBTT) { - pos += count * length; - continue; + pos += length; } + } - /* TBTT info must include bss param + BSSID + - * (short SSID or same_ssid bit to be set). - * ignore other options, and move to the - * next AP info - */ - if (band != NL80211_BAND_6GHZ || - !(length == offsetofend(struct ieee80211_tbtt_info_7_8_9, - bss_params) || - length == sizeof(struct ieee80211_tbtt_info_7_8_9) || - length >= offsetofend(struct ieee80211_tbtt_info_ge_11, - bss_params))) { - pos += count * length; - continue; - } + if (pos != end) + return false; + } - for (i = 0; i < count; i++) { - struct cfg80211_colocated_ap *entry; + return true; +} +EXPORT_SYMBOL_GPL(cfg80211_iter_rnr); + +struct colocated_ap_data { + const struct element *ssid_elem; + struct list_head ap_list; + u32 s_ssid_tmp; + int n_coloc; +}; - entry = kzalloc(sizeof(*entry) + IEEE80211_MAX_SSID_LEN, - GFP_ATOMIC); +static enum cfg80211_rnr_iter_ret +cfg80211_parse_colocated_ap_iter(void *_data, u8 type, + const struct ieee80211_neighbor_ap_info *info, + const u8 *tbtt_info, u8 tbtt_info_len) +{ + struct colocated_ap_data *data = _data; + struct cfg80211_colocated_ap *entry; + enum nl80211_band band; - if (!entry) - goto error; + if (type != IEEE80211_TBTT_INFO_TYPE_TBTT) + return RNR_ITER_CONTINUE; - entry->center_freq = freq; + if (!ieee80211_operating_class_to_band(info->op_class, &band)) + return RNR_ITER_CONTINUE; - if (!cfg80211_parse_ap_info(entry, pos, length, - ssid_elem, - s_ssid_tmp)) { - n_coloc++; - list_add_tail(&entry->list, &ap_list); - } else { - kfree(entry); - } + /* TBTT info must include bss param + BSSID + (short SSID or + * same_ssid bit to be set). Ignore other options, and move to + * the next AP info + */ + if (band != NL80211_BAND_6GHZ || + !(tbtt_info_len == offsetofend(struct ieee80211_tbtt_info_7_8_9, + bss_params) || + tbtt_info_len == sizeof(struct ieee80211_tbtt_info_7_8_9) || + tbtt_info_len >= offsetofend(struct ieee80211_tbtt_info_ge_11, + bss_params))) + return RNR_ITER_CONTINUE; + + entry = kzalloc(sizeof(*entry) + IEEE80211_MAX_SSID_LEN, GFP_ATOMIC); + if (!entry) + return RNR_ITER_ERROR; + + entry->center_freq = + ieee80211_channel_to_frequency(info->channel, band); + + if (!cfg80211_parse_ap_info(entry, tbtt_info, tbtt_info_len, + data->ssid_elem, data->s_ssid_tmp)) { + data->n_coloc++; + list_add_tail(&entry->list, &data->ap_list); + } else { + kfree(entry); + } - pos += length; - } - } + return RNR_ITER_CONTINUE; +} -error: - if (pos != end) { - cfg80211_free_coloc_ap_list(&ap_list); - return 0; - } +VISIBLE_IF_CFG80211_KUNIT int +cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, + struct list_head *list) +{ + struct colocated_ap_data data = {}; + int ret; + + INIT_LIST_HEAD(&data.ap_list); + + ret = cfg80211_calc_short_ssid(ies, &data.ssid_elem, &data.s_ssid_tmp); + if (ret) + return 0; + + if (!cfg80211_iter_rnr(ies->data, ies->len, + cfg80211_parse_colocated_ap_iter, &data)) { + cfg80211_free_coloc_ap_list(&data.ap_list); + return 0; } - list_splice_tail(&ap_list, list); - return n_coloc; + list_splice_tail(&data.ap_list, list); + return data.n_coloc; } +EXPORT_SYMBOL_IF_CFG80211_KUNIT(cfg80211_parse_colocated_ap); static void cfg80211_scan_req_add_chan(struct cfg80211_scan_request *request, struct ieee80211_channel *chan, @@ -2122,6 +2121,35 @@ struct cfg80211_inform_single_bss_data { u64 cannot_use_reasons; }; +static bool cfg80211_6ghz_power_type_valid(const u8 *ie, size_t ielen, + const u32 flags) +{ + const struct element *tmp; + struct ieee80211_he_operation *he_oper; + + tmp = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ielen); + if (tmp && tmp->datalen >= sizeof(*he_oper) + 1) { + const struct ieee80211_he_6ghz_oper *he_6ghz_oper; + + he_oper = (void *)&tmp->data[1]; + he_6ghz_oper = ieee80211_he_6ghz_oper(he_oper); + + if (!he_6ghz_oper) + return false; + + switch (u8_get_bits(he_6ghz_oper->control, + IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { + case IEEE80211_6GHZ_CTRL_REG_LPI_AP: + return true; + case IEEE80211_6GHZ_CTRL_REG_SP_AP: + return !(flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT); + case IEEE80211_6GHZ_CTRL_REG_VLP_AP: + return !(flags & IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT); + } + } + return false; +} + /* Returned bss is reference counted and must be cleaned up appropriately. */ static struct cfg80211_bss * cfg80211_inform_single_bss_data(struct wiphy *wiphy, @@ -2154,6 +2182,14 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, if (!channel) return NULL; + if (channel->band == NL80211_BAND_6GHZ && + !cfg80211_6ghz_power_type_valid(data->ie, data->ielen, + channel->flags)) { + data->use_for = 0; + data->cannot_use_reasons = + NL80211_BSS_CANNOT_USE_6GHZ_PWR_MISMATCH; + } + memcpy(tmp.pub.bssid, data->bssid, ETH_ALEN); tmp.pub.channel = channel; if (data->bss_source != BSS_SOURCE_STA_PROFILE) @@ -2165,6 +2201,9 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, tmp.ts_boottime = drv_data->boottime_ns; tmp.parent_tsf = drv_data->parent_tsf; ether_addr_copy(tmp.parent_bssid, drv_data->parent_bssid); + tmp.pub.chains = drv_data->chains; + memcpy(tmp.pub.chain_signal, drv_data->chain_signal, + IEEE80211_MAX_CHAINS); tmp.pub.use_for = data->use_for; tmp.pub.cannot_use_reasons = data->cannot_use_reasons; @@ -2208,6 +2247,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, switch (data->ftype) { case CFG80211_BSS_FTYPE_BEACON: + case CFG80211_BSS_FTYPE_S1G_BEACON: ies->from_beacon = true; fallthrough; case CFG80211_BSS_FTYPE_UNKNOWN: @@ -2464,16 +2504,22 @@ ssize_t cfg80211_defragment_element(const struct element *elem, const u8 *ies, if (elem->id == WLAN_EID_EXTENSION) { copied = elem->datalen - 1; - if (copied > data_len) - return -ENOSPC; - memmove(data, elem->data + 1, copied); + if (data) { + if (copied > data_len) + return -ENOSPC; + + memmove(data, elem->data + 1, copied); + } } else { copied = elem->datalen; - if (copied > data_len) - return -ENOSPC; - memmove(data, elem->data, copied); + if (data) { + if (copied > data_len) + return -ENOSPC; + + memmove(data, elem->data, copied); + } } /* Fragmented elements must have 255 bytes */ @@ -2492,10 +2538,13 @@ ssize_t cfg80211_defragment_element(const struct element *elem, const u8 *ies, elem_datalen = elem->datalen; - if (copied + elem_datalen > data_len) - return -ENOSPC; + if (data) { + if (copied + elem_datalen > data_len) + return -ENOSPC; + + memmove(data + copied, elem->data, elem_datalen); + } - memmove(data + copied, elem->data, elem_datalen); copied += elem_datalen; /* Only the last fragment may be short */ @@ -2601,77 +2650,168 @@ error: return NULL; } +struct tbtt_info_iter_data { + const struct ieee80211_neighbor_ap_info *ap_info; + u8 param_ch_count; + u32 use_for; + u8 mld_id, link_id; +}; + +static enum cfg80211_rnr_iter_ret +cfg802121_mld_ap_rnr_iter(void *_data, u8 type, + const struct ieee80211_neighbor_ap_info *info, + const u8 *tbtt_info, u8 tbtt_info_len) +{ + const struct ieee80211_rnr_mld_params *mld_params; + struct tbtt_info_iter_data *data = _data; + u8 link_id; + + if (type == IEEE80211_TBTT_INFO_TYPE_TBTT && + tbtt_info_len >= offsetofend(struct ieee80211_tbtt_info_ge_11, + mld_params)) + mld_params = (void *)(tbtt_info + + offsetof(struct ieee80211_tbtt_info_ge_11, + mld_params)); + else if (type == IEEE80211_TBTT_INFO_TYPE_MLD && + tbtt_info_len >= sizeof(struct ieee80211_rnr_mld_params)) + mld_params = (void *)tbtt_info; + else + return RNR_ITER_CONTINUE; + + link_id = le16_get_bits(mld_params->params, + IEEE80211_RNR_MLD_PARAMS_LINK_ID); + + if (data->mld_id != mld_params->mld_id) + return RNR_ITER_CONTINUE; + + if (data->link_id != link_id) + return RNR_ITER_CONTINUE; + + data->ap_info = info; + data->param_ch_count = + le16_get_bits(mld_params->params, + IEEE80211_RNR_MLD_PARAMS_BSS_CHANGE_COUNT); + + if (type == IEEE80211_TBTT_INFO_TYPE_TBTT) + data->use_for = NL80211_BSS_USE_FOR_ALL; + else + data->use_for = NL80211_BSS_USE_FOR_MLD_LINK; + return RNR_ITER_BREAK; +} + static u8 -cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, - const struct ieee80211_neighbor_ap_info **ap_info, - const u8 **tbtt_info) +cfg80211_rnr_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, + const struct ieee80211_neighbor_ap_info **ap_info, + u8 *param_ch_count) { - const struct ieee80211_neighbor_ap_info *info; - const struct element *rnr; - const u8 *pos, *end; + struct tbtt_info_iter_data data = { + .mld_id = mld_id, + .link_id = link_id, + }; - for_each_element_id(rnr, WLAN_EID_REDUCED_NEIGHBOR_REPORT, ie, ielen) { - pos = rnr->data; - end = rnr->data + rnr->datalen; + cfg80211_iter_rnr(ie, ielen, cfg802121_mld_ap_rnr_iter, &data); - /* RNR IE may contain more than one NEIGHBOR_AP_INFO */ - while (sizeof(*info) <= end - pos) { - const struct ieee80211_rnr_mld_params *mld_params; - u16 params; - u8 length, i, count, mld_params_offset; - u8 type, lid; - u32 use_for; + *ap_info = data.ap_info; + *param_ch_count = data.param_ch_count; - info = (void *)pos; - count = u8_get_bits(info->tbtt_info_hdr, - IEEE80211_AP_INFO_TBTT_HDR_COUNT) + 1; - length = info->tbtt_info_len; + return data.use_for; +} - pos += sizeof(*info); +static struct element * +cfg80211_gen_reporter_rnr(struct cfg80211_bss *source_bss, bool is_mbssid, + bool same_mld, u8 link_id, u8 bss_change_count, + gfp_t gfp) +{ + const struct cfg80211_bss_ies *ies; + struct ieee80211_neighbor_ap_info ap_info; + struct ieee80211_tbtt_info_ge_11 tbtt_info; + u32 short_ssid; + const struct element *elem; + struct element *res; - if (count * length > end - pos) - return 0; + /* + * We only generate the RNR to permit ML lookups. For that we do not + * need an entry for the corresponding transmitting BSS, lets just skip + * it even though it would be easy to add. + */ + if (!same_mld) + return NULL; - type = u8_get_bits(info->tbtt_info_hdr, - IEEE80211_AP_INFO_TBTT_HDR_TYPE); + /* We could use tx_data->ies if we change cfg80211_calc_short_ssid */ + rcu_read_lock(); + ies = rcu_dereference(source_bss->ies); - if (type == IEEE80211_TBTT_INFO_TYPE_TBTT && - length >= - offsetofend(struct ieee80211_tbtt_info_ge_11, - mld_params)) { - mld_params_offset = - offsetof(struct ieee80211_tbtt_info_ge_11, mld_params); - use_for = NL80211_BSS_USE_FOR_ALL; - } else if (type == IEEE80211_TBTT_INFO_TYPE_MLD && - length >= sizeof(struct ieee80211_rnr_mld_params)) { - mld_params_offset = 0; - use_for = NL80211_BSS_USE_FOR_MLD_LINK; - } else { - pos += count * length; - continue; - } + ap_info.tbtt_info_len = offsetofend(typeof(tbtt_info), mld_params); + ap_info.tbtt_info_hdr = + u8_encode_bits(IEEE80211_TBTT_INFO_TYPE_TBTT, + IEEE80211_AP_INFO_TBTT_HDR_TYPE) | + u8_encode_bits(0, IEEE80211_AP_INFO_TBTT_HDR_COUNT); - for (i = 0; i < count; i++) { - mld_params = (void *)pos + mld_params_offset; - params = le16_to_cpu(mld_params->params); + ap_info.channel = ieee80211_frequency_to_channel(source_bss->channel->center_freq); - lid = u16_get_bits(params, - IEEE80211_RNR_MLD_PARAMS_LINK_ID); + /* operating class */ + elem = cfg80211_find_elem(WLAN_EID_SUPPORTED_REGULATORY_CLASSES, + ies->data, ies->len); + if (elem && elem->datalen >= 1) { + ap_info.op_class = elem->data[0]; + } else { + struct cfg80211_chan_def chandef; - if (mld_id == mld_params->mld_id && - link_id == lid) { - *ap_info = info; - *tbtt_info = pos; + /* The AP is not providing us with anything to work with. So + * make up a somewhat reasonable operating class, but don't + * bother with it too much as no one will ever use the + * information. + */ + cfg80211_chandef_create(&chandef, source_bss->channel, + NL80211_CHAN_NO_HT); - return use_for; - } + if (!ieee80211_chandef_to_operating_class(&chandef, + &ap_info.op_class)) + goto out_unlock; + } - pos += length; - } - } + /* Just set TBTT offset and PSD 20 to invalid/unknown */ + tbtt_info.tbtt_offset = 255; + tbtt_info.psd_20 = IEEE80211_RNR_TBTT_PARAMS_PSD_RESERVED; + + memcpy(tbtt_info.bssid, source_bss->bssid, ETH_ALEN); + if (cfg80211_calc_short_ssid(ies, &elem, &short_ssid)) + goto out_unlock; + + rcu_read_unlock(); + + tbtt_info.short_ssid = cpu_to_le32(short_ssid); + + tbtt_info.bss_params = IEEE80211_RNR_TBTT_PARAMS_SAME_SSID; + + if (is_mbssid) { + tbtt_info.bss_params |= IEEE80211_RNR_TBTT_PARAMS_MULTI_BSSID; + tbtt_info.bss_params |= IEEE80211_RNR_TBTT_PARAMS_TRANSMITTED_BSSID; } - return 0; + tbtt_info.mld_params.mld_id = 0; + tbtt_info.mld_params.params = + le16_encode_bits(link_id, IEEE80211_RNR_MLD_PARAMS_LINK_ID) | + le16_encode_bits(bss_change_count, + IEEE80211_RNR_MLD_PARAMS_BSS_CHANGE_COUNT); + + res = kzalloc(struct_size(res, data, + sizeof(ap_info) + ap_info.tbtt_info_len), + gfp); + if (!res) + return NULL; + + /* Copy the data */ + res->id = WLAN_EID_REDUCED_NEIGHBOR_REPORT; + res->datalen = sizeof(ap_info) + ap_info.tbtt_info_len; + memcpy(res->data, &ap_info, sizeof(ap_info)); + memcpy(res->data + sizeof(ap_info), &tbtt_info, ap_info.tbtt_info_len); + + return res; + +out_unlock: + rcu_read_unlock(); + return NULL; } static void @@ -2687,25 +2827,25 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, .source_bss = source_bss, .bss_source = BSS_SOURCE_STA_PROFILE, }; + struct element *reporter_rnr = NULL; struct ieee80211_multi_link_elem *ml_elem; struct cfg80211_mle *mle; u16 control; u8 ml_common_len; - u8 *new_ie; + u8 *new_ie = NULL; struct cfg80211_bss *bss; - int mld_id; + u8 mld_id, reporter_link_id, bss_change_count; u16 seen_links = 0; - const u8 *pos; u8 i; - if (!ieee80211_mle_size_ok(elem->data + 1, elem->datalen - 1)) + if (!ieee80211_mle_type_ok(elem->data + 1, + IEEE80211_ML_CONTROL_TYPE_BASIC, + elem->datalen - 1)) return; - ml_elem = (void *)elem->data + 1; + ml_elem = (void *)(elem->data + 1); control = le16_to_cpu(ml_elem->control); - if (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE) != - IEEE80211_ML_CONTROL_TYPE_BASIC) - return; + ml_common_len = ml_elem->variable[0]; /* Must be present when transmitted by an AP (in a probe response) */ if (!(control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) || @@ -2713,18 +2853,8 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, !(control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)) return; - ml_common_len = ml_elem->variable[0]; - - /* length + MLD MAC address + link ID info + BSS Params Change Count */ - pos = ml_elem->variable + 1 + 6 + 1 + 1; - - if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)) - pos += 2; - if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_EML_CAPA)) - pos += 2; - - /* MLD capabilities and operations */ - pos += 2; + reporter_link_id = ieee80211_mle_get_link_id(elem->data + 1); + bss_change_count = ieee80211_mle_get_bss_param_ch_cnt(elem->data + 1); /* * The MLD ID of the reporting AP is always zero. It is set if the AP @@ -2732,32 +2862,35 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, * relating to a nontransmitted BSS (matching the Multi-BSSID Index, * Draft P802.11be_D3.2, 35.3.4.2) */ - if (u16_get_bits(control, IEEE80211_MLC_BASIC_PRES_MLD_ID)) { - mld_id = *pos; - pos += 1; - } else { - mld_id = 0; - } - - /* Extended MLD capabilities and operations */ - pos += 2; + mld_id = ieee80211_mle_get_mld_id(elem->data + 1); /* Fully defrag the ML element for sta information/profile iteration */ mle = cfg80211_defrag_mle(elem, tx_data->ie, tx_data->ielen, gfp); if (!mle) return; + /* No point in doing anything if there is no per-STA profile */ + if (!mle->sta_prof[0]) + goto out; + new_ie = kmalloc(IEEE80211_MAX_DATA_LEN, gfp); if (!new_ie) goto out; + reporter_rnr = cfg80211_gen_reporter_rnr(source_bss, + u16_get_bits(control, + IEEE80211_MLC_BASIC_PRES_MLD_ID), + mld_id == 0, reporter_link_id, + bss_change_count, + gfp); + for (i = 0; i < ARRAY_SIZE(mle->sta_prof) && mle->sta_prof[i]; i++) { const struct ieee80211_neighbor_ap_info *ap_info; enum nl80211_band band; u32 freq; const u8 *profile; - const u8 *tbtt_info; ssize_t profile_len; + u8 param_ch_count; u8 link_id, use_for; if (!ieee80211_mle_basic_sta_prof_size_ok((u8 *)mle->sta_prof[i], @@ -2800,10 +2933,11 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, profile_len -= 2; /* Find in RNR to look up channel information */ - use_for = cfg80211_tbtt_info_for_mld_ap(tx_data->ie, - tx_data->ielen, - mld_id, link_id, - &ap_info, &tbtt_info); + use_for = cfg80211_rnr_info_for_mld_ap(tx_data->ie, + tx_data->ielen, + mld_id, link_id, + &ap_info, + ¶m_ch_count); if (!use_for) continue; @@ -2846,7 +2980,8 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, continue; /* Copy the Basic Multi-Link element including the common - * information, and then fix up the link ID. + * information, and then fix up the link ID and BSS param + * change count. * Note that the ML element length has been verified and we * also checked that it contains the link ID. */ @@ -2857,10 +2992,21 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, sizeof(*ml_elem) + ml_common_len); new_ie[data.ielen + sizeof(*ml_elem) + 1 + ETH_ALEN] = link_id; + new_ie[data.ielen + sizeof(*ml_elem) + 1 + ETH_ALEN + 1] = + param_ch_count; data.ielen += sizeof(*ml_elem) + ml_common_len; - /* TODO: Add an RNR containing only the reporting AP */ + if (reporter_rnr && (use_for & NL80211_BSS_USE_FOR_NORMAL)) { + if (data.ielen + sizeof(struct element) + + reporter_rnr->datalen > IEEE80211_MAX_DATA_LEN) + continue; + + memcpy(new_ie + data.ielen, reporter_rnr, + sizeof(struct element) + reporter_rnr->datalen); + data.ielen += sizeof(struct element) + + reporter_rnr->datalen; + } bss = cfg80211_inform_single_bss_data(wiphy, &data, gfp); if (!bss) @@ -2869,6 +3015,7 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, } out: + kfree(reporter_rnr); kfree(new_ie); kfree(mle); } @@ -2921,6 +3068,10 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, if (!res) return NULL; + /* don't do any further MBSSID/ML handling for S1G */ + if (ftype == CFG80211_BSS_FTYPE_S1G_BEACON) + return res; + cfg80211_parse_mbssid_data(wiphy, &inform_data, res, gfp); cfg80211_parse_ml_sta_data(wiphy, &inform_data, res, gfp); @@ -2929,59 +3080,22 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, } EXPORT_SYMBOL(cfg80211_inform_bss_data); -static bool cfg80211_uhb_power_type_valid(const u8 *ie, - size_t ielen, - const u32 flags) -{ - const struct element *tmp; - struct ieee80211_he_operation *he_oper; - - tmp = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ielen); - if (tmp && tmp->datalen >= sizeof(*he_oper) + 1) { - const struct ieee80211_he_6ghz_oper *he_6ghz_oper; - - he_oper = (void *)&tmp->data[1]; - he_6ghz_oper = ieee80211_he_6ghz_oper(he_oper); - - if (!he_6ghz_oper) - return false; - - switch (u8_get_bits(he_6ghz_oper->control, - IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { - case IEEE80211_6GHZ_CTRL_REG_LPI_AP: - return true; - case IEEE80211_6GHZ_CTRL_REG_SP_AP: - return !(flags & IEEE80211_CHAN_NO_UHB_AFC_CLIENT); - case IEEE80211_6GHZ_CTRL_REG_VLP_AP: - return !(flags & IEEE80211_CHAN_NO_UHB_VLP_CLIENT); - } - } - return false; -} - -/* cfg80211_inform_bss_width_frame helper */ -static struct cfg80211_bss * -cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, - struct cfg80211_inform_bss *data, - struct ieee80211_mgmt *mgmt, size_t len, - gfp_t gfp) +struct cfg80211_bss * +cfg80211_inform_bss_frame_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len, + gfp_t gfp) { - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - struct cfg80211_internal_bss tmp = {}, *res; - struct cfg80211_bss_ies *ies; - struct ieee80211_channel *channel; - bool signal_valid; + size_t min_hdr_len = offsetof(struct ieee80211_mgmt, + u.probe_resp.variable); struct ieee80211_ext *ext = NULL; - u8 *bssid, *variable; - u16 capability, beacon_int; - size_t ielen, min_hdr_len = offsetof(struct ieee80211_mgmt, - u.probe_resp.variable); - int bss_type; - - BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) != - offsetof(struct ieee80211_mgmt, u.beacon.variable)); - - trace_cfg80211_inform_bss_frame(wiphy, data, mgmt, len); + enum cfg80211_bss_frame_type ftype; + u16 beacon_interval; + const u8 *bssid; + u16 capability; + const u8 *ie; + size_t ielen; + u64 tsf; if (WARN_ON(!mgmt)) return NULL; @@ -2989,9 +3103,10 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, if (WARN_ON(!wiphy)) return NULL; - if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC && - (data->signal < 0 || data->signal > 100))) - return NULL; + BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) != + offsetof(struct ieee80211_mgmt, u.beacon.variable)); + + trace_cfg80211_inform_bss_frame(wiphy, data, mgmt, len); if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { ext = (void *) mgmt; @@ -3005,32 +3120,17 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, return NULL; ielen = len - min_hdr_len; - variable = mgmt->u.probe_resp.variable; - if (ext) { - if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) - variable = ext->u.s1g_short_beacon.variable; - else - variable = ext->u.s1g_beacon.variable; - } - - channel = cfg80211_get_bss_channel(wiphy, variable, ielen, data->chan); - if (!channel) - return NULL; - - if (channel->band == NL80211_BAND_6GHZ && - !cfg80211_uhb_power_type_valid(variable, ielen, channel->flags)) { - data->restrict_use = 1; - data->use_for = 0; - data->cannot_use_reasons = - NL80211_BSS_CANNOT_USE_UHB_PWR_MISMATCH; - } - + ie = mgmt->u.probe_resp.variable; if (ext) { const struct ieee80211_s1g_bcn_compat_ie *compat; const struct element *elem; - elem = cfg80211_find_elem(WLAN_EID_S1G_BCN_COMPAT, - variable, ielen); + if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) + ie = ext->u.s1g_short_beacon.variable; + else + ie = ext->u.s1g_beacon.variable; + + elem = cfg80211_find_elem(WLAN_EID_S1G_BCN_COMPAT, ie, ielen); if (!elem) return NULL; if (elem->datalen < sizeof(*compat)) @@ -3038,112 +3138,26 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, compat = (void *)elem->data; bssid = ext->u.s1g_beacon.sa; capability = le16_to_cpu(compat->compat_info); - beacon_int = le16_to_cpu(compat->beacon_int); + beacon_interval = le16_to_cpu(compat->beacon_int); } else { bssid = mgmt->bssid; - beacon_int = le16_to_cpu(mgmt->u.probe_resp.beacon_int); + beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int); capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); } - if (channel->band == NL80211_BAND_60GHZ) { - bss_type = capability & WLAN_CAPABILITY_DMG_TYPE_MASK; - if (bss_type == WLAN_CAPABILITY_DMG_TYPE_AP || - bss_type == WLAN_CAPABILITY_DMG_TYPE_PBSS) - regulatory_hint_found_beacon(wiphy, channel, gfp); - } else { - if (capability & WLAN_CAPABILITY_ESS) - regulatory_hint_found_beacon(wiphy, channel, gfp); - } - - ies = kzalloc(sizeof(*ies) + ielen, gfp); - if (!ies) - return NULL; - ies->len = ielen; - ies->tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp); - ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control) || - ieee80211_is_s1g_beacon(mgmt->frame_control); - memcpy(ies->data, variable, ielen); + tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp); if (ieee80211_is_probe_resp(mgmt->frame_control)) - rcu_assign_pointer(tmp.pub.proberesp_ies, ies); + ftype = CFG80211_BSS_FTYPE_PRESP; + else if (ext) + ftype = CFG80211_BSS_FTYPE_S1G_BEACON; else - rcu_assign_pointer(tmp.pub.beacon_ies, ies); - rcu_assign_pointer(tmp.pub.ies, ies); + ftype = CFG80211_BSS_FTYPE_BEACON; - memcpy(tmp.pub.bssid, bssid, ETH_ALEN); - tmp.pub.beacon_interval = beacon_int; - tmp.pub.capability = capability; - tmp.pub.channel = channel; - tmp.pub.signal = data->signal; - tmp.ts_boottime = data->boottime_ns; - tmp.parent_tsf = data->parent_tsf; - tmp.pub.chains = data->chains; - memcpy(tmp.pub.chain_signal, data->chain_signal, IEEE80211_MAX_CHAINS); - ether_addr_copy(tmp.parent_bssid, data->parent_bssid); - tmp.pub.use_for = data->restrict_use ? - data->use_for : - NL80211_BSS_USE_FOR_ALL; - tmp.pub.cannot_use_reasons = data->cannot_use_reasons; - - signal_valid = data->chan == channel; - spin_lock_bh(&rdev->bss_lock); - res = __cfg80211_bss_update(rdev, &tmp, signal_valid, jiffies); - if (!res) - goto drop; - - rdev_inform_bss(rdev, &res->pub, ies, data->drv_data); - - spin_unlock_bh(&rdev->bss_lock); - - trace_cfg80211_return_bss(&res->pub); - /* __cfg80211_bss_update gives us a referenced result */ - return &res->pub; - -drop: - spin_unlock_bh(&rdev->bss_lock); - return NULL; -} - -struct cfg80211_bss * -cfg80211_inform_bss_frame_data(struct wiphy *wiphy, - struct cfg80211_inform_bss *data, - struct ieee80211_mgmt *mgmt, size_t len, - gfp_t gfp) -{ - struct cfg80211_inform_single_bss_data inform_data = { - .drv_data = data, - .ie = mgmt->u.probe_resp.variable, - .ielen = len - offsetof(struct ieee80211_mgmt, - u.probe_resp.variable), - .use_for = data->restrict_use ? - data->use_for : - NL80211_BSS_USE_FOR_ALL, - .cannot_use_reasons = data->cannot_use_reasons, - }; - struct cfg80211_bss *res; - - res = cfg80211_inform_single_bss_frame_data(wiphy, data, mgmt, - len, gfp); - if (!res) - return NULL; - - /* don't do any further MBSSID/ML handling for S1G */ - if (ieee80211_is_s1g_beacon(mgmt->frame_control)) - return res; - - inform_data.ftype = ieee80211_is_beacon(mgmt->frame_control) ? - CFG80211_BSS_FTYPE_BEACON : CFG80211_BSS_FTYPE_PRESP; - memcpy(inform_data.bssid, mgmt->bssid, ETH_ALEN); - inform_data.tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp); - inform_data.beacon_interval = - le16_to_cpu(mgmt->u.probe_resp.beacon_int); - - /* process each non-transmitting bss */ - cfg80211_parse_mbssid_data(wiphy, &inform_data, res, gfp); - - cfg80211_parse_ml_sta_data(wiphy, &inform_data, res, gfp); - - return res; + return cfg80211_inform_bss_data(wiphy, data, ftype, + bssid, tsf, capability, + beacon_interval, ie, ielen, + gfp); } EXPORT_SYMBOL(cfg80211_inform_bss_frame_data); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 195c8532734b..82e3ce42206c 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -209,7 +209,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev, if (!req.bss) { err = -ENOENT; } else { - err = cfg80211_mlme_assoc(rdev, wdev->netdev, &req); + err = cfg80211_mlme_assoc(rdev, wdev->netdev, + &req, NULL); cfg80211_put_bss(&rdev->wiphy, req.bss); } diff --git a/net/wireless/tests/Makefile b/net/wireless/tests/Makefile index 1f6622fcb758..c364e63b508e 100644 --- a/net/wireless/tests/Makefile +++ b/net/wireless/tests/Makefile @@ -1,3 +1,3 @@ -cfg80211-tests-y += module.o fragmentation.o scan.o util.o +cfg80211-tests-y += module.o fragmentation.o scan.o util.o chan.o obj-$(CONFIG_CFG80211_KUNIT_TEST) += cfg80211-tests.o diff --git a/net/wireless/tests/chan.c b/net/wireless/tests/chan.c new file mode 100644 index 000000000000..d02258ac2dab --- /dev/null +++ b/net/wireless/tests/chan.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KUnit tests for channel helper functions + * + * Copyright (C) 2023-2024 Intel Corporation + */ +#include <net/cfg80211.h> +#include <kunit/test.h> + +MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING); + +static struct ieee80211_channel chan_6ghz_1 = { + .band = NL80211_BAND_6GHZ, + .center_freq = 5955, +}; + +static struct ieee80211_channel chan_6ghz_5 = { + .band = NL80211_BAND_6GHZ, + .center_freq = 5975, +}; + +static struct ieee80211_channel chan_6ghz_105 = { + .band = NL80211_BAND_6GHZ, + .center_freq = 6475, +}; + +static const struct chandef_compat_case { + const char *desc; + /* leave c1 empty for tests for identical */ + struct cfg80211_chan_def c1, c2; + /* we test both ways around, so c2 should always be the compat one */ + bool compat; +} chandef_compat_cases[] = { + { + .desc = "identical non-HT", + .c2 = { + .width = NL80211_CHAN_WIDTH_20_NOHT, + .chan = &chan_6ghz_1, + .center_freq1 = 5955, + }, + .compat = true, + }, + { + .desc = "identical 20 MHz", + .c2 = { + .width = NL80211_CHAN_WIDTH_20, + .chan = &chan_6ghz_1, + .center_freq1 = 5955, + }, + .compat = true, + }, + { + .desc = "identical 40 MHz", + .c2 = { + .width = NL80211_CHAN_WIDTH_40, + .chan = &chan_6ghz_1, + .center_freq1 = 5955 + 10, + }, + .compat = true, + }, + { + .desc = "identical 80 MHz", + .c2 = { + .width = NL80211_CHAN_WIDTH_80, + .chan = &chan_6ghz_1, + .center_freq1 = 5955 + 10 + 20, + }, + .compat = true, + }, + { + .desc = "identical 160 MHz", + .c2 = { + .width = NL80211_CHAN_WIDTH_160, + .chan = &chan_6ghz_1, + .center_freq1 = 5955 + 10 + 20 + 40, + }, + .compat = true, + }, + { + .desc = "identical 320 MHz", + .c2 = { + .width = NL80211_CHAN_WIDTH_320, + .chan = &chan_6ghz_1, + .center_freq1 = 5955 + 10 + 20 + 40 + 80, + }, + .compat = true, + }, + { + .desc = "20 MHz in 320 MHz\n", + .c1 = { + .width = NL80211_CHAN_WIDTH_20, + .chan = &chan_6ghz_1, + .center_freq1 = 5955, + }, + .c2 = { + .width = NL80211_CHAN_WIDTH_320, + .chan = &chan_6ghz_1, + .center_freq1 = 5955 + 10 + 20 + 40 + 80, + }, + .compat = true, + }, + { + .desc = "different 20 MHz", + .c1 = { + .width = NL80211_CHAN_WIDTH_20, + .chan = &chan_6ghz_1, + .center_freq1 = 5955, + }, + .c2 = { + .width = NL80211_CHAN_WIDTH_20, + .chan = &chan_6ghz_5, + .center_freq1 = 5975, + }, + }, + { + .desc = "different primary 160 MHz", + .c1 = { + .width = NL80211_CHAN_WIDTH_320, + .chan = &chan_6ghz_105, + .center_freq1 = 6475 + 150, + }, + .c2 = { + .width = NL80211_CHAN_WIDTH_320, + .chan = &chan_6ghz_105, + .center_freq1 = 6475 - 10, + }, + }, + { + /* similar to previous test but one has lower BW */ + .desc = "matching primary 160 MHz", + .c1 = { + .width = NL80211_CHAN_WIDTH_160, + .chan = &chan_6ghz_105, + .center_freq1 = 6475 + 70, + }, + .c2 = { + .width = NL80211_CHAN_WIDTH_320, + .chan = &chan_6ghz_105, + .center_freq1 = 6475 - 10, + }, + .compat = true, + }, + { + .desc = "matching primary 160 MHz & punctured secondary 160 Mhz", + .c1 = { + .width = NL80211_CHAN_WIDTH_160, + .chan = &chan_6ghz_105, + .center_freq1 = 6475 + 70, + }, + .c2 = { + .width = NL80211_CHAN_WIDTH_320, + .chan = &chan_6ghz_105, + .center_freq1 = 6475 - 10, + .punctured = 0xf, + }, + .compat = true, + }, + { + .desc = "matching primary 160 MHz & punctured matching", + .c1 = { + .width = NL80211_CHAN_WIDTH_160, + .chan = &chan_6ghz_105, + .center_freq1 = 6475 + 70, + .punctured = 0xc0, + }, + .c2 = { + .width = NL80211_CHAN_WIDTH_320, + .chan = &chan_6ghz_105, + .center_freq1 = 6475 - 10, + .punctured = 0xc000, + }, + .compat = true, + }, + { + .desc = "matching primary 160 MHz & punctured not matching", + .c1 = { + .width = NL80211_CHAN_WIDTH_160, + .chan = &chan_6ghz_105, + .center_freq1 = 6475 + 70, + .punctured = 0x80, + }, + .c2 = { + .width = NL80211_CHAN_WIDTH_320, + .chan = &chan_6ghz_105, + .center_freq1 = 6475 - 10, + .punctured = 0xc000, + }, + }, +}; + +KUNIT_ARRAY_PARAM_DESC(chandef_compat, chandef_compat_cases, desc) + +static void test_chandef_compat(struct kunit *test) +{ + const struct chandef_compat_case *params = test->param_value; + const struct cfg80211_chan_def *ret, *expect; + struct cfg80211_chan_def c1 = params->c1; + + /* tests with identical ones */ + if (!params->c1.chan) + c1 = params->c2; + + KUNIT_EXPECT_EQ(test, cfg80211_chandef_valid(&c1), true); + KUNIT_EXPECT_EQ(test, cfg80211_chandef_valid(¶ms->c2), true); + + expect = params->compat ? ¶ms->c2 : NULL; + + ret = cfg80211_chandef_compatible(&c1, ¶ms->c2); + KUNIT_EXPECT_PTR_EQ(test, ret, expect); + + if (!params->c1.chan) + expect = &c1; + + ret = cfg80211_chandef_compatible(¶ms->c2, &c1); + KUNIT_EXPECT_PTR_EQ(test, ret, expect); +} + +static struct kunit_case chandef_compat_test_cases[] = { + KUNIT_CASE_PARAM(test_chandef_compat, chandef_compat_gen_params), + {} +}; + +static struct kunit_suite chandef_compat = { + .name = "cfg80211-chandef-compat", + .test_cases = chandef_compat_test_cases, +}; + +kunit_test_suite(chandef_compat); diff --git a/net/wireless/tests/fragmentation.c b/net/wireless/tests/fragmentation.c index 49a339ca8880..411fae18cd88 100644 --- a/net/wireless/tests/fragmentation.c +++ b/net/wireless/tests/fragmentation.c @@ -2,7 +2,7 @@ /* * KUnit tests for element fragmentation * - * Copyright (C) 2023 Intel Corporation + * Copyright (C) 2023-2024 Intel Corporation */ #include <linux/ieee80211.h> #include <net/cfg80211.h> @@ -27,7 +27,12 @@ static void defragment_0(struct kunit *test) ret = cfg80211_defragment_element((void *)input, input, sizeof(input), - data, sizeof(input), + NULL, 0, + WLAN_EID_FRAGMENT); + KUNIT_EXPECT_EQ(test, ret, 253); + ret = cfg80211_defragment_element((void *)input, + input, sizeof(input), + data, ret, WLAN_EID_FRAGMENT); KUNIT_EXPECT_EQ(test, ret, 253); KUNIT_EXPECT_MEMEQ(test, data, input + 3, 253); @@ -63,7 +68,12 @@ static void defragment_1(struct kunit *test) ret = cfg80211_defragment_element((void *)input, input, sizeof(input), - data, sizeof(input), + NULL, 0, + WLAN_EID_FRAGMENT); + KUNIT_EXPECT_EQ(test, ret, 254 + 7); + ret = cfg80211_defragment_element((void *)input, + input, sizeof(input), + data, ret, WLAN_EID_FRAGMENT); /* this means the last fragment was not used */ KUNIT_EXPECT_EQ(test, ret, 254 + 7); @@ -106,10 +116,15 @@ static void defragment_2(struct kunit *test) ret = cfg80211_defragment_element((void *)input, input, sizeof(input), - data, sizeof(input), + NULL, 0, WLAN_EID_FRAGMENT); /* this means the last fragment was not used */ KUNIT_EXPECT_EQ(test, ret, 254 + 255 + 1); + ret = cfg80211_defragment_element((void *)input, + input, sizeof(input), + data, ret, + WLAN_EID_FRAGMENT); + KUNIT_EXPECT_EQ(test, ret, 254 + 255 + 1); KUNIT_EXPECT_MEMEQ(test, data, input + 3, 254); KUNIT_EXPECT_MEMEQ(test, data + 254, input + 257 + 2, 255); KUNIT_EXPECT_MEMEQ(test, data + 254 + 255, input + 2 * 257 + 2, 1); @@ -134,7 +149,12 @@ static void defragment_at_end(struct kunit *test) ret = cfg80211_defragment_element((void *)input, input, sizeof(input), - data, sizeof(input), + NULL, 0, + WLAN_EID_FRAGMENT); + KUNIT_EXPECT_EQ(test, ret, 254 + 7); + ret = cfg80211_defragment_element((void *)input, + input, sizeof(input), + data, ret, WLAN_EID_FRAGMENT); KUNIT_EXPECT_EQ(test, ret, 254 + 7); KUNIT_EXPECT_MEMEQ(test, data, input + 3, 254); diff --git a/net/wireless/tests/scan.c b/net/wireless/tests/scan.c index 77854161cd22..9f458be71659 100644 --- a/net/wireless/tests/scan.c +++ b/net/wireless/tests/scan.c @@ -2,7 +2,7 @@ /* * KUnit tests for inform_bss functions * - * Copyright (C) 2023 Intel Corporation + * Copyright (C) 2023-2024 Intel Corporation */ #include <linux/ieee80211.h> #include <net/cfg80211.h> @@ -406,9 +406,32 @@ static struct inform_bss_ml_sta_case { const char *desc; int mld_id; bool sta_prof_vendor_elems; + bool include_oper_class; + bool nstr; } inform_bss_ml_sta_cases[] = { - { .desc = "no_mld_id", .mld_id = 0, .sta_prof_vendor_elems = false }, - { .desc = "mld_id_eq_1", .mld_id = 1, .sta_prof_vendor_elems = true }, + { + .desc = "zero_mld_id", + .mld_id = 0, + .sta_prof_vendor_elems = false, + }, { + .desc = "zero_mld_id_with_oper_class", + .mld_id = 0, + .sta_prof_vendor_elems = false, + .include_oper_class = true, + }, { + .desc = "mld_id_eq_1", + .mld_id = 1, + .sta_prof_vendor_elems = true, + }, { + .desc = "mld_id_eq_1_with_oper_class", + .mld_id = 1, + .sta_prof_vendor_elems = true, + .include_oper_class = true, + }, { + .desc = "nstr", + .mld_id = 0, + .nstr = true, + }, }; KUNIT_ARRAY_PARAM_DESC(inform_bss_ml_sta, inform_bss_ml_sta_cases, desc) @@ -440,7 +463,7 @@ static void test_inform_bss_ml_sta(struct kunit *test) struct { struct ieee80211_neighbor_ap_info info; struct ieee80211_tbtt_info_ge_11 ap; - } __packed rnr = { + } __packed rnr_normal = { .info = { .tbtt_info_hdr = u8_encode_bits(0, IEEE80211_AP_INFO_TBTT_HDR_COUNT), .tbtt_info_len = sizeof(struct ieee80211_tbtt_info_ge_11), @@ -460,6 +483,28 @@ static void test_inform_bss_ml_sta(struct kunit *test) } }; struct { + struct ieee80211_neighbor_ap_info info; + struct ieee80211_rnr_mld_params mld_params; + } __packed rnr_nstr = { + .info = { + .tbtt_info_hdr = + u8_encode_bits(0, IEEE80211_AP_INFO_TBTT_HDR_COUNT) | + u8_encode_bits(IEEE80211_TBTT_INFO_TYPE_MLD, + IEEE80211_AP_INFO_TBTT_HDR_TYPE), + .tbtt_info_len = sizeof(struct ieee80211_rnr_mld_params), + .op_class = 81, + .channel = 11, + }, + .mld_params = { + .mld_id = params->mld_id, + .params = + le16_encode_bits(link_id, + IEEE80211_RNR_MLD_PARAMS_LINK_ID), + } + }; + size_t rnr_len = params->nstr ? sizeof(rnr_nstr) : sizeof(rnr_normal); + void *rnr = params->nstr ? (void *)&rnr_nstr : (void *)&rnr_normal; + struct { __le16 control; u8 var_len; u8 mld_mac_addr[ETH_ALEN]; @@ -498,7 +543,7 @@ static void test_inform_bss_ml_sta(struct kunit *test) u16_encode_bits(link_id, IEEE80211_MLE_STA_CONTROL_LINK_ID)), .var_len = sizeof(sta_prof) - 2 - 2, - .bssid = { *rnr.ap.bssid }, + .bssid = { *rnr_normal.ap.bssid }, .beacon_int = cpu_to_le16(101), .tsf_offset = cpu_to_le64(-123ll), .capabilities = cpu_to_le16(0xdead), @@ -515,9 +560,15 @@ static void test_inform_bss_ml_sta(struct kunit *test) skb_put_u8(input, 4); skb_put_data(input, "TEST", 4); + if (params->include_oper_class) { + skb_put_u8(input, WLAN_EID_SUPPORTED_REGULATORY_CLASSES); + skb_put_u8(input, 1); + skb_put_u8(input, 81); + } + skb_put_u8(input, WLAN_EID_REDUCED_NEIGHBOR_REPORT); - skb_put_u8(input, sizeof(rnr)); - skb_put_data(input, &rnr, sizeof(rnr)); + skb_put_u8(input, rnr_len); + skb_put_data(input, rnr, rnr_len); /* build a multi-link element */ skb_put_u8(input, WLAN_EID_EXTENSION); @@ -563,9 +614,10 @@ static void test_inform_bss_ml_sta(struct kunit *test) KUNIT_EXPECT_EQ(test, ctx.inform_bss_count, 2); /* Check link_bss *****************************************************/ - link_bss = cfg80211_get_bss(wiphy, NULL, sta_prof.bssid, NULL, 0, - IEEE80211_BSS_TYPE_ANY, - IEEE80211_PRIVACY_ANY); + link_bss = __cfg80211_get_bss(wiphy, NULL, sta_prof.bssid, NULL, 0, + IEEE80211_BSS_TYPE_ANY, + IEEE80211_PRIVACY_ANY, + 0); KUNIT_ASSERT_NOT_NULL(test, link_bss); KUNIT_EXPECT_EQ(test, link_bss->signal, 0); KUNIT_EXPECT_EQ(test, link_bss->beacon_interval, @@ -576,21 +628,43 @@ static void test_inform_bss_ml_sta(struct kunit *test) KUNIT_EXPECT_PTR_EQ(test, link_bss->channel, ieee80211_get_channel_khz(wiphy, MHZ_TO_KHZ(2462))); + /* Test wiphy does not set WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY */ + if (params->nstr) { + KUNIT_EXPECT_EQ(test, link_bss->use_for, 0); + KUNIT_EXPECT_EQ(test, link_bss->cannot_use_reasons, + NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY); + KUNIT_EXPECT_NULL(test, + cfg80211_get_bss(wiphy, NULL, sta_prof.bssid, + NULL, 0, + IEEE80211_BSS_TYPE_ANY, + IEEE80211_PRIVACY_ANY)); + } else { + KUNIT_EXPECT_EQ(test, link_bss->use_for, + NL80211_BSS_USE_FOR_ALL); + KUNIT_EXPECT_EQ(test, link_bss->cannot_use_reasons, 0); + } + rcu_read_lock(); ies = rcu_dereference(link_bss->ies); KUNIT_EXPECT_NOT_NULL(test, ies); KUNIT_EXPECT_EQ(test, ies->tsf, tsf + le64_to_cpu(sta_prof.tsf_offset)); /* Resulting length should be: * SSID (inherited) + RNR (inherited) + vendor element(s) + + * operating class (if requested) + + * generated RNR (if MLD ID == 0 and not NSTR) + * MLE common info + MLE header and control */ if (params->sta_prof_vendor_elems) KUNIT_EXPECT_EQ(test, ies->len, - 6 + 2 + sizeof(rnr) + 2 + 160 + 2 + 165 + + 6 + 2 + rnr_len + 2 + 160 + 2 + 165 + + (params->include_oper_class ? 3 : 0) + + (!params->mld_id && !params->nstr ? 22 : 0) + mle_basic_common_info.var_len + 5); else KUNIT_EXPECT_EQ(test, ies->len, - 6 + 2 + sizeof(rnr) + 2 + 155 + + 6 + 2 + rnr_len + 2 + 155 + + (params->include_oper_class ? 3 : 0) + + (!params->mld_id && !params->nstr ? 22 : 0) + mle_basic_common_info.var_len + 5); rcu_read_unlock(); @@ -598,6 +672,172 @@ static void test_inform_bss_ml_sta(struct kunit *test) cfg80211_put_bss(wiphy, link_bss); } +static struct cfg80211_parse_colocated_ap_case { + const char *desc; + u8 op_class; + u8 channel; + struct ieee80211_neighbor_ap_info info; + union { + struct ieee80211_tbtt_info_ge_11 tbtt_long; + struct ieee80211_tbtt_info_7_8_9 tbtt_short; + }; + bool add_junk; + bool same_ssid; + bool valid; +} cfg80211_parse_colocated_ap_cases[] = { + { + .desc = "wrong_band", + .info.op_class = 81, + .info.channel = 11, + .tbtt_long = { + .bssid = { 0x00, 0x11, 0x22, 0x33, 0x44, 0x55 }, + .bss_params = IEEE80211_RNR_TBTT_PARAMS_COLOC_AP, + }, + .valid = false, + }, + { + .desc = "wrong_type", + /* IEEE80211_AP_INFO_TBTT_HDR_TYPE is in the least significant bits */ + .info.tbtt_info_hdr = IEEE80211_TBTT_INFO_TYPE_MLD, + .tbtt_long = { + .bssid = { 0x00, 0x11, 0x22, 0x33, 0x44, 0x55 }, + .bss_params = IEEE80211_RNR_TBTT_PARAMS_COLOC_AP, + }, + .valid = false, + }, + { + .desc = "colocated_invalid_len_short", + .info.tbtt_info_len = 6, + .tbtt_short = { + .bssid = { 0x00, 0x11, 0x22, 0x33, 0x44, 0x55 }, + .bss_params = IEEE80211_RNR_TBTT_PARAMS_COLOC_AP | + IEEE80211_RNR_TBTT_PARAMS_SAME_SSID, + }, + .valid = false, + }, + { + .desc = "colocated_invalid_len_short_mld", + .info.tbtt_info_len = 10, + .tbtt_long = { + .bssid = { 0x00, 0x11, 0x22, 0x33, 0x44, 0x55 }, + .bss_params = IEEE80211_RNR_TBTT_PARAMS_COLOC_AP, + }, + .valid = false, + }, + { + .desc = "colocated_non_mld", + .info.tbtt_info_len = sizeof(struct ieee80211_tbtt_info_7_8_9), + .tbtt_short = { + .bssid = { 0x00, 0x11, 0x22, 0x33, 0x44, 0x55 }, + .bss_params = IEEE80211_RNR_TBTT_PARAMS_COLOC_AP | + IEEE80211_RNR_TBTT_PARAMS_SAME_SSID, + }, + .same_ssid = true, + .valid = true, + }, + { + .desc = "colocated_non_mld_invalid_bssid", + .info.tbtt_info_len = sizeof(struct ieee80211_tbtt_info_7_8_9), + .tbtt_short = { + .bssid = { 0xff, 0x11, 0x22, 0x33, 0x44, 0x55 }, + .bss_params = IEEE80211_RNR_TBTT_PARAMS_COLOC_AP | + IEEE80211_RNR_TBTT_PARAMS_SAME_SSID, + }, + .same_ssid = true, + .valid = false, + }, + { + .desc = "colocated_mld", + .tbtt_long = { + .bssid = { 0x00, 0x11, 0x22, 0x33, 0x44, 0x55 }, + .bss_params = IEEE80211_RNR_TBTT_PARAMS_COLOC_AP, + }, + .valid = true, + }, + { + .desc = "colocated_mld", + .tbtt_long = { + .bssid = { 0x00, 0x11, 0x22, 0x33, 0x44, 0x55 }, + .bss_params = IEEE80211_RNR_TBTT_PARAMS_COLOC_AP, + }, + .add_junk = true, + .valid = false, + }, + { + .desc = "colocated_disabled_mld", + .tbtt_long = { + .bssid = { 0x00, 0x11, 0x22, 0x33, 0x44, 0x55 }, + .bss_params = IEEE80211_RNR_TBTT_PARAMS_COLOC_AP, + .mld_params.params = cpu_to_le16(IEEE80211_RNR_MLD_PARAMS_DISABLED_LINK), + }, + .valid = false, + }, +}; +KUNIT_ARRAY_PARAM_DESC(cfg80211_parse_colocated_ap, cfg80211_parse_colocated_ap_cases, desc) + +static void test_cfg80211_parse_colocated_ap(struct kunit *test) +{ + const struct cfg80211_parse_colocated_ap_case *params = test->param_value; + struct sk_buff *input = kunit_zalloc_skb(test, 1024, GFP_KERNEL); + struct cfg80211_bss_ies *ies; + struct ieee80211_neighbor_ap_info info; + LIST_HEAD(coloc_ap_list); + int count; + + KUNIT_ASSERT_NOT_NULL(test, input); + + info = params->info; + + /* Reasonable values for a colocated AP */ + if (!info.tbtt_info_len) + info.tbtt_info_len = sizeof(params->tbtt_long); + if (!info.op_class) + info.op_class = 131; + if (!info.channel) + info.channel = 33; + /* Zero is the correct default for .btt_info_hdr (one entry, TBTT type) */ + + skb_put_u8(input, WLAN_EID_SSID); + skb_put_u8(input, 4); + skb_put_data(input, "TEST", 4); + + skb_put_u8(input, WLAN_EID_REDUCED_NEIGHBOR_REPORT); + skb_put_u8(input, sizeof(info) + info.tbtt_info_len + (params->add_junk ? 3 : 0)); + skb_put_data(input, &info, sizeof(info)); + skb_put_data(input, ¶ms->tbtt_long, info.tbtt_info_len); + + if (params->add_junk) + skb_put_data(input, "123", 3); + + ies = kunit_kzalloc(test, struct_size(ies, data, input->len), GFP_KERNEL); + ies->len = input->len; + memcpy(ies->data, input->data, input->len); + + count = cfg80211_parse_colocated_ap(ies, &coloc_ap_list); + + KUNIT_EXPECT_EQ(test, count, params->valid); + KUNIT_EXPECT_EQ(test, list_count_nodes(&coloc_ap_list), params->valid); + + if (params->valid && !list_empty(&coloc_ap_list)) { + struct cfg80211_colocated_ap *ap; + + ap = list_first_entry(&coloc_ap_list, typeof(*ap), list); + if (info.tbtt_info_len <= sizeof(params->tbtt_short)) + KUNIT_EXPECT_MEMEQ(test, ap->bssid, params->tbtt_short.bssid, ETH_ALEN); + else + KUNIT_EXPECT_MEMEQ(test, ap->bssid, params->tbtt_long.bssid, ETH_ALEN); + + if (params->same_ssid) { + KUNIT_EXPECT_EQ(test, ap->ssid_len, 4); + KUNIT_EXPECT_MEMEQ(test, ap->ssid, "TEST", 4); + } else { + KUNIT_EXPECT_EQ(test, ap->ssid_len, 0); + } + } + + cfg80211_free_coloc_ap_list(&coloc_ap_list); +} + static struct kunit_case gen_new_ie_test_cases[] = { KUNIT_CASE_PARAM(test_gen_new_ie, gen_new_ie_gen_params), KUNIT_CASE(test_gen_new_ie_malformed), @@ -623,3 +863,16 @@ static struct kunit_suite inform_bss = { }; kunit_test_suite(inform_bss); + +static struct kunit_case scan_6ghz_cases[] = { + KUNIT_CASE_PARAM(test_cfg80211_parse_colocated_ap, + cfg80211_parse_colocated_ap_gen_params), + {} +}; + +static struct kunit_suite scan_6ghz = { + .name = "cfg80211-scan-6ghz", + .test_cases = scan_6ghz_cases, +}; + +kunit_test_suite(scan_6ghz); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 1f374c8a17a5..e039e66ab377 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1,4 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Portions of this file + * Copyright(c) 2016-2017 Intel Deutschland GmbH + * Copyright (C) 2018, 2020-2024 Intel Corporation + */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cfg80211 @@ -135,7 +140,8 @@ __field(u32, width) \ __field(u32, center_freq1) \ __field(u32, freq1_offset) \ - __field(u32, center_freq2) + __field(u32, center_freq2) \ + __field(u16, punctured) #define CHAN_DEF_ASSIGN(chandef) \ do { \ if ((chandef) && (chandef)->chan) { \ @@ -148,6 +154,7 @@ __entry->center_freq1 = (chandef)->center_freq1;\ __entry->freq1_offset = (chandef)->freq1_offset;\ __entry->center_freq2 = (chandef)->center_freq2;\ + __entry->punctured = (chandef)->punctured; \ } else { \ __entry->band = 0; \ __entry->control_freq = 0; \ @@ -156,14 +163,15 @@ __entry->center_freq1 = 0; \ __entry->freq1_offset = 0; \ __entry->center_freq2 = 0; \ + __entry->punctured = 0; \ } \ } while (0) #define CHAN_DEF_PR_FMT \ - "band: %d, control freq: %u.%03u, width: %d, cf1: %u.%03u, cf2: %u" + "band: %d, control freq: %u.%03u, width: %d, cf1: %u.%03u, cf2: %u, punct: 0x%x" #define CHAN_DEF_PR_ARG __entry->band, __entry->control_freq, \ __entry->freq_offset, __entry->width, \ __entry->center_freq1, __entry->freq1_offset, \ - __entry->center_freq2 + __entry->center_freq2, __entry->punctured #define FILS_AAD_ASSIGN(fa) \ do { \ @@ -810,8 +818,8 @@ DECLARE_EVENT_CLASS(station_add_change, params->link_sta_params.opmode_notif_used; ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: %pM" - ", station flags mask: %u, station flags set: %u, " - "station modify mask: %u, listen interval: %d, aid: %u, " + ", station flags mask: 0x%x, station flags set: 0x%x, " + "station modify mask: 0x%x, listen interval: %d, aid: %u, " "plink action: %u, plink state: %u, uapsd queues: %u, vlan:%s", WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->sta_mac, __entry->sta_flags_mask, __entry->sta_flags_set, @@ -859,6 +867,7 @@ DECLARE_EVENT_CLASS(station_del, MAC_ENTRY(sta_mac) __field(u8, subtype) __field(u16, reason_code) + __field(int, link_id) ), TP_fast_assign( WIPHY_ASSIGN; @@ -866,11 +875,13 @@ DECLARE_EVENT_CLASS(station_del, MAC_ASSIGN(sta_mac, params->mac); __entry->subtype = params->subtype; __entry->reason_code = params->reason_code; + __entry->link_id = params->link_id; ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: %pM" - ", subtype: %u, reason_code: %u", + ", subtype: %u, reason_code: %u, link_id: %d", WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->sta_mac, - __entry->subtype, __entry->reason_code) + __entry->subtype, __entry->reason_code, + __entry->link_id) ); DEFINE_EVENT(station_del, rdev_del_station, @@ -1064,7 +1075,7 @@ TRACE_EVENT(rdev_return_int_mpath_info, ), TP_printk(WIPHY_PR_FMT ", returned %d. mpath info - generation: %d, " "filled: %u, frame qlen: %u, sn: %u, metric: %u, exptime: %u," - " discovery timeout: %u, discovery retries: %u, flags: %u", + " discovery timeout: %u, discovery retries: %u, flags: 0x%x", WIPHY_PR_ARG, __entry->ret, __entry->generation, __entry->filled, __entry->frame_qlen, __entry->sn, __entry->metric, __entry->exptime, __entry->discovery_timeout, @@ -1306,7 +1317,7 @@ TRACE_EVENT(rdev_assoc, req->fils_nonces, 2 * FILS_NONCE_LEN); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: %pM" - ", previous bssid: %pM, use mfp: %s, flags: %u", + ", previous bssid: %pM, use mfp: %s, flags: 0x%x", WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->bssid, __entry->prev_bssid, BOOL_TO_STR(__entry->use_mfp), __entry->flags) @@ -1428,7 +1439,7 @@ TRACE_EVENT(rdev_connect, ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: %pM" ", ssid: %s, auth type: %d, privacy: %s, wpa versions: %u, " - "flags: %u, previous bssid: %pM", + "flags: 0x%x, previous bssid: %pM", WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->bssid, __entry->ssid, __entry->auth_type, BOOL_TO_STR(__entry->privacy), __entry->wpa_versions, __entry->flags, __entry->prev_bssid) @@ -2324,6 +2335,7 @@ TRACE_EVENT(rdev_channel_switch, __field(u8, count) __dynamic_array(u16, bcn_ofs, params->n_counter_offsets_beacon) __dynamic_array(u16, pres_ofs, params->n_counter_offsets_presp) + __field(u8, link_id) ), TP_fast_assign( WIPHY_ASSIGN; @@ -2341,11 +2353,13 @@ TRACE_EVENT(rdev_channel_switch, memcpy(__get_dynamic_array(pres_ofs), params->counter_offsets_presp, params->n_counter_offsets_presp * sizeof(u16)); + __entry->link_id = params->link_id; ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT - ", block_tx: %d, count: %u, radar_required: %d", + ", block_tx: %d, count: %u, radar_required: %d, link_id: %d", WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG, - __entry->block_tx, __entry->count, __entry->radar_required) + __entry->block_tx, __entry->count, __entry->radar_required, + __entry->link_id) ); TRACE_EVENT(rdev_set_qos_map, @@ -3267,47 +3281,39 @@ TRACE_EVENT(cfg80211_chandef_dfs_required, TRACE_EVENT(cfg80211_ch_switch_notify, TP_PROTO(struct net_device *netdev, struct cfg80211_chan_def *chandef, - unsigned int link_id, - u16 punct_bitmap), - TP_ARGS(netdev, chandef, link_id, punct_bitmap), + unsigned int link_id), + TP_ARGS(netdev, chandef, link_id), TP_STRUCT__entry( NETDEV_ENTRY CHAN_DEF_ENTRY __field(unsigned int, link_id) - __field(u16, punct_bitmap) ), TP_fast_assign( NETDEV_ASSIGN; CHAN_DEF_ASSIGN(chandef); __entry->link_id = link_id; - __entry->punct_bitmap = punct_bitmap; ), - TP_printk(NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT ", link:%d, punct_bitmap:%u", - NETDEV_PR_ARG, CHAN_DEF_PR_ARG, __entry->link_id, - __entry->punct_bitmap) + TP_printk(NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT ", link:%d", + NETDEV_PR_ARG, CHAN_DEF_PR_ARG, __entry->link_id) ); TRACE_EVENT(cfg80211_ch_switch_started_notify, TP_PROTO(struct net_device *netdev, struct cfg80211_chan_def *chandef, - unsigned int link_id, - u16 punct_bitmap), - TP_ARGS(netdev, chandef, link_id, punct_bitmap), + unsigned int link_id), + TP_ARGS(netdev, chandef, link_id), TP_STRUCT__entry( NETDEV_ENTRY CHAN_DEF_ENTRY __field(unsigned int, link_id) - __field(u16, punct_bitmap) ), TP_fast_assign( NETDEV_ASSIGN; CHAN_DEF_ASSIGN(chandef); __entry->link_id = link_id; - __entry->punct_bitmap = punct_bitmap; ), - TP_printk(NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT ", link:%d, punct_bitmap:%u", - NETDEV_PR_ARG, CHAN_DEF_PR_ARG, __entry->link_id, - __entry->punct_bitmap) + TP_printk(NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT ", link:%d", + NETDEV_PR_ARG, CHAN_DEF_PR_ARG, __entry->link_id) ); TRACE_EVENT(cfg80211_radar_event, diff --git a/net/wireless/util.c b/net/wireless/util.c index d1ce3bee2797..2bde8a354631 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -791,15 +791,19 @@ ieee80211_amsdu_subframe_length(void *field, u8 mesh_flags, u8 hdr_type) bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr) { - int offset = 0, remaining, subframe_len, padding; + int offset = 0, subframe_len, padding; for (offset = 0; offset < skb->len; offset += subframe_len + padding) { + int remaining = skb->len - offset; struct { __be16 len; u8 mesh_flags; } hdr; u16 len; + if (sizeof(hdr) > remaining) + return false; + if (skb_copy_bits(skb, offset + 2 * ETH_ALEN, &hdr, sizeof(hdr)) < 0) return false; @@ -807,7 +811,6 @@ bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr) mesh_hdr); subframe_len = sizeof(struct ethhdr) + len; padding = (4 - subframe_len) & 0x3; - remaining = skb->len - offset; if (subframe_len > remaining) return false; @@ -825,7 +828,7 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, { unsigned int hlen = ALIGN(extra_headroom, 4); struct sk_buff *frame = NULL; - int offset = 0, remaining; + int offset = 0; struct { struct ethhdr eth; uint8_t flags; @@ -839,10 +842,14 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, copy_len = sizeof(hdr); while (!last) { + int remaining = skb->len - offset; unsigned int subframe_len; int len, mesh_len = 0; u8 padding; + if (copy_len > remaining) + goto purge; + skb_copy_bits(skb, offset, &hdr, copy_len); if (iftype == NL80211_IFTYPE_MESH_POINT) mesh_len = __ieee80211_get_mesh_hdrlen(hdr.flags); @@ -852,7 +859,6 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, padding = (4 - subframe_len) & 0x3; /* the last MSDU has no padding */ - remaining = skb->len - offset; if (subframe_len > remaining) goto purge; /* mitigate A-MSDU aggregation injection attacks */ @@ -2073,6 +2079,82 @@ bool ieee80211_operating_class_to_band(u8 operating_class, } EXPORT_SYMBOL(ieee80211_operating_class_to_band); +bool ieee80211_operating_class_to_chandef(u8 operating_class, + struct ieee80211_channel *chan, + struct cfg80211_chan_def *chandef) +{ + u32 control_freq, offset = 0; + enum nl80211_band band; + + if (!ieee80211_operating_class_to_band(operating_class, &band) || + !chan || band != chan->band) + return false; + + control_freq = chan->center_freq; + chandef->chan = chan; + + if (control_freq >= 5955) + offset = control_freq - 5955; + else if (control_freq >= 5745) + offset = control_freq - 5745; + else if (control_freq >= 5180) + offset = control_freq - 5180; + offset /= 20; + + switch (operating_class) { + case 81: /* 2 GHz band; 20 MHz; channels 1..13 */ + case 82: /* 2 GHz band; 20 MHz; channel 14 */ + case 115: /* 5 GHz band; 20 MHz; channels 36,40,44,48 */ + case 118: /* 5 GHz band; 20 MHz; channels 52,56,60,64 */ + case 121: /* 5 GHz band; 20 MHz; channels 100..144 */ + case 124: /* 5 GHz band; 20 MHz; channels 149,153,157,161 */ + case 125: /* 5 GHz band; 20 MHz; channels 149..177 */ + case 131: /* 6 GHz band; 20 MHz; channels 1..233*/ + case 136: /* 6 GHz band; 20 MHz; channel 2 */ + chandef->center_freq1 = control_freq; + chandef->width = NL80211_CHAN_WIDTH_20; + return true; + case 83: /* 2 GHz band; 40 MHz; channels 1..9 */ + case 116: /* 5 GHz band; 40 MHz; channels 36,44 */ + case 119: /* 5 GHz band; 40 MHz; channels 52,60 */ + case 122: /* 5 GHz band; 40 MHz; channels 100,108,116,124,132,140 */ + case 126: /* 5 GHz band; 40 MHz; channels 149,157,165,173 */ + chandef->center_freq1 = control_freq + 10; + chandef->width = NL80211_CHAN_WIDTH_40; + return true; + case 84: /* 2 GHz band; 40 MHz; channels 5..13 */ + case 117: /* 5 GHz band; 40 MHz; channels 40,48 */ + case 120: /* 5 GHz band; 40 MHz; channels 56,64 */ + case 123: /* 5 GHz band; 40 MHz; channels 104,112,120,128,136,144 */ + case 127: /* 5 GHz band; 40 MHz; channels 153,161,169,177 */ + chandef->center_freq1 = control_freq - 10; + chandef->width = NL80211_CHAN_WIDTH_40; + return true; + case 132: /* 6 GHz band; 40 MHz; channels 1,5,..,229*/ + chandef->center_freq1 = control_freq + 10 - (offset & 1) * 20; + chandef->width = NL80211_CHAN_WIDTH_40; + return true; + case 128: /* 5 GHz band; 80 MHz; channels 36..64,100..144,149..177 */ + case 133: /* 6 GHz band; 80 MHz; channels 1,5,..,229 */ + chandef->center_freq1 = control_freq + 30 - (offset & 3) * 20; + chandef->width = NL80211_CHAN_WIDTH_80; + return true; + case 129: /* 5 GHz band; 160 MHz; channels 36..64,100..144,149..177 */ + case 134: /* 6 GHz band; 160 MHz; channels 1,5,..,229 */ + chandef->center_freq1 = control_freq + 70 - (offset & 7) * 20; + chandef->width = NL80211_CHAN_WIDTH_160; + return true; + case 130: /* 5 GHz band; 80+80 MHz; channels 36..64,100..144,149..177 */ + case 135: /* 6 GHz band; 80+80 MHz; channels 1,5,..,229 */ + /* The center_freq2 of 80+80 MHz is unknown */ + case 137: /* 6 GHz band; 320 MHz; channels 1,5,..,229 */ + /* 320-1 or 320-2 channelization is unknown */ + default: + return false; + } +} +EXPORT_SYMBOL(ieee80211_operating_class_to_chandef); + bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class) { diff --git a/net/x25/Kconfig b/net/x25/Kconfig index 68729aa3a5d5..dc72302cbd07 100644 --- a/net/x25/Kconfig +++ b/net/x25/Kconfig @@ -17,8 +17,6 @@ config X25 if you want that) and the lower level data link layer protocol LAPB (say Y to "LAPB Data Link Driver" below if you want that). - You can read more about X.25 at <https://www.sangoma.com/tutorials/x25/> and - <http://docwiki.cisco.com/wiki/X.25>. Information about X.25 for Linux is contained in the files <file:Documentation/networking/x25.rst> and <file:Documentation/networking/x25-iface.rst>. diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index f7a7c7798c3b..d18d51412cc0 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -460,12 +460,12 @@ static int x25_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) goto out; - len = min_t(unsigned int, len, sizeof(int)); - rc = -EINVAL; if (len < 0) goto out; + len = min_t(unsigned int, len, sizeof(int)); + rc = -EFAULT; if (put_user(len, optlen)) goto out; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index b78c0e095e22..3404d076a8a3 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -313,10 +313,13 @@ static bool xsk_is_bound(struct xdp_sock *xs) static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { + struct net_device *dev = xdp->rxq->dev; + u32 qid = xdp->rxq->queue_index; + if (!xsk_is_bound(xs)) return -ENXIO; - if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) + if (!dev->_rx[qid].pool || xs->umem != dev->_rx[qid].pool->umem) return -EINVAL; if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) { diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c index 9f8955367275..09dcea0cbbed 100644 --- a/net/xdp/xsk_diag.c +++ b/net/xdp/xsk_diag.c @@ -194,6 +194,7 @@ static int xsk_diag_handler_dump(struct sk_buff *nlskb, struct nlmsghdr *hdr) } static const struct sock_diag_handler xsk_diag_handler = { + .owner = THIS_MODULE, .family = AF_XDP, .dump = xsk_diag_handler_dump, }; diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index d3b3f9e720b3..fe82e2d07300 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -10,6 +10,7 @@ #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6_stubs.h> #endif +#include <net/hotdata.h> static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, struct sock *sk) @@ -169,7 +170,8 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb) { struct espintcp_ctx *ctx = espintcp_getctx(sk); - if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog)) + if (skb_queue_len(&ctx->out_queue) >= + READ_ONCE(net_hotdata.max_backlog)) return -ENOBUFS; __skb_queue_tail(&ctx->out_queue, skb); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index bd4ce21d76d7..161f535c8b94 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -21,6 +21,7 @@ #include <net/ip_tunnels.h> #include <net/ip6_tunnel.h> #include <net/dst_metadata.h> +#include <net/hotdata.h> #include "xfrm_inout.h" @@ -764,7 +765,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, trans = this_cpu_ptr(&xfrm_trans_tasklet); - if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog)) + if (skb_queue_len(&trans->queue) >= READ_ONCE(net_hotdata.max_backlog)) return -ENOBUFS; BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c index 7d5e920141e9..5ea15037ebd1 100644 --- a/net/xfrm/xfrm_interface_bpf.c +++ b/net/xfrm/xfrm_interface_bpf.c @@ -93,10 +93,10 @@ __bpf_kfunc int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, const struct bp __bpf_kfunc_end_defs(); -BTF_SET8_START(xfrm_ifc_kfunc_set) +BTF_KFUNCS_START(xfrm_ifc_kfunc_set) BTF_ID_FLAGS(func, bpf_skb_get_xfrm_info) BTF_ID_FLAGS(func, bpf_skb_set_xfrm_info) -BTF_SET8_END(xfrm_ifc_kfunc_set) +BTF_KFUNCS_END(xfrm_ifc_kfunc_set) static const struct btf_kfunc_id_set xfrm_interface_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 21d50d75c260..4df5c06e3ece 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -240,7 +240,6 @@ static void xfrmi_dev_free(struct net_device *dev) struct xfrm_if *xi = netdev_priv(dev); gro_cells_destroy(&xi->gro_cells); - free_percpu(dev->tstats); } static int xfrmi_create(struct net_device *dev) @@ -727,7 +726,7 @@ static int xfrmi_get_iflink(const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); - return xi->p.link; + return READ_ONCE(xi->p.link); } static const struct net_device_ops xfrmi_netdev_ops = { @@ -749,6 +748,7 @@ static void xfrmi_dev_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->needs_free_netdev = true; dev->priv_destructor = xfrmi_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); eth_broadcast_addr(dev->broadcast); @@ -765,15 +765,9 @@ static int xfrmi_dev_init(struct net_device *dev) struct net_device *phydev = __dev_get_by_index(xi->net, xi->p.link); int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - err = gro_cells_init(&xi->gro_cells, dev); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } dev->features |= NETIF_F_LLTX; dev->features |= XFRMI_FEATURES; @@ -957,12 +951,12 @@ static struct rtnl_link_ops xfrmi_link_ops __read_mostly = { .get_link_net = xfrmi_get_link_net, }; -static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list) +static void __net_exit xfrmi_exit_batch_rtnl(struct list_head *net_exit_list, + struct list_head *dev_to_kill) { struct net *net; - LIST_HEAD(list); - rtnl_lock(); + ASSERT_RTNL(); list_for_each_entry(net, net_exit_list, exit_list) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); struct xfrm_if __rcu **xip; @@ -973,18 +967,16 @@ static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list) for (xip = &xfrmn->xfrmi[i]; (xi = rtnl_dereference(*xip)) != NULL; xip = &xi->next) - unregister_netdevice_queue(xi->dev, &list); + unregister_netdevice_queue(xi->dev, dev_to_kill); } xi = rtnl_dereference(xfrmn->collect_md_xfrmi); if (xi) - unregister_netdevice_queue(xi->dev, &list); + unregister_netdevice_queue(xi->dev, dev_to_kill); } - unregister_netdevice_many(&list); - rtnl_unlock(); } static struct pernet_operations xfrmi_net_ops = { - .exit_batch = xfrmi_exit_batch_net, + .exit_batch_rtnl = xfrmi_exit_batch_rtnl, .id = &xfrmi_net_id, .size = sizeof(struct xfrmi_net), }; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index da6ecc6b3e15..6affe5cd85d8 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -29,6 +29,7 @@ #include <linux/audit.h> #include <linux/rhashtable.h> #include <linux/if_tunnel.h> +#include <linux/icmp.h> #include <net/dst.h> #include <net/flow.h> #include <net/inet_ecn.h> @@ -3505,6 +3506,128 @@ static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int return 0; } +static bool icmp_err_packet(const struct flowi *fl, unsigned short family) +{ + const struct flowi4 *fl4 = &fl->u.ip4; + + if (family == AF_INET && + fl4->flowi4_proto == IPPROTO_ICMP && + (fl4->fl4_icmp_type == ICMP_DEST_UNREACH || + fl4->fl4_icmp_type == ICMP_TIME_EXCEEDED)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) { + const struct flowi6 *fl6 = &fl->u.ip6; + + if (fl6->flowi6_proto == IPPROTO_ICMPV6 && + (fl6->fl6_icmp_type == ICMPV6_DEST_UNREACH || + fl6->fl6_icmp_type == ICMPV6_PKT_TOOBIG || + fl6->fl6_icmp_type == ICMPV6_TIME_EXCEED)) + return true; + } +#endif + return false; +} + +static bool xfrm_icmp_flow_decode(struct sk_buff *skb, unsigned short family, + const struct flowi *fl, struct flowi *fl1) +{ + bool ret = true; + struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); + int hl = family == AF_INET ? (sizeof(struct iphdr) + sizeof(struct icmphdr)) : + (sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr)); + + if (!newskb) + return true; + + if (!pskb_pull(newskb, hl)) + goto out; + + skb_reset_network_header(newskb); + + if (xfrm_decode_session_reverse(dev_net(skb->dev), newskb, fl1, family) < 0) + goto out; + + fl1->flowi_oif = fl->flowi_oif; + fl1->flowi_mark = fl->flowi_mark; + fl1->flowi_tos = fl->flowi_tos; + nf_nat_decode_session(newskb, fl1, family); + ret = false; + +out: + consume_skb(newskb); + return ret; +} + +static bool xfrm_selector_inner_icmp_match(struct sk_buff *skb, unsigned short family, + const struct xfrm_selector *sel, + const struct flowi *fl) +{ + bool ret = false; + + if (icmp_err_packet(fl, family)) { + struct flowi fl1; + + if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) + return ret; + + ret = xfrm_selector_match(sel, &fl1, family); + } + + return ret; +} + +static inline struct +xfrm_policy *xfrm_in_fwd_icmp(struct sk_buff *skb, + const struct flowi *fl, unsigned short family, + u32 if_id) +{ + struct xfrm_policy *pol = NULL; + + if (icmp_err_packet(fl, family)) { + struct flowi fl1; + struct net *net = dev_net(skb->dev); + + if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) + return pol; + + pol = xfrm_policy_lookup(net, &fl1, family, XFRM_POLICY_FWD, if_id); + } + + return pol; +} + +static inline struct +dst_entry *xfrm_out_fwd_icmp(struct sk_buff *skb, struct flowi *fl, + unsigned short family, struct dst_entry *dst) +{ + if (icmp_err_packet(fl, family)) { + struct net *net = dev_net(skb->dev); + struct dst_entry *dst2; + struct flowi fl1; + + if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) + return dst; + + dst_hold(dst); + + dst2 = xfrm_lookup(net, dst, &fl1, NULL, (XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_ICMP)); + + if (IS_ERR(dst2)) + return dst; + + if (dst2->xfrm) { + dst_release(dst); + dst = dst2; + } else { + dst_release(dst2); + } + } + + return dst; +} + int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { @@ -3551,9 +3674,17 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, for (i = sp->len - 1; i >= 0; i--) { struct xfrm_state *x = sp->xvec[i]; + int ret = 0; + if (!xfrm_selector_match(&x->sel, &fl, family)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); - return 0; + ret = 1; + if (x->props.flags & XFRM_STATE_ICMP && + xfrm_selector_inner_icmp_match(skb, family, &x->sel, &fl)) + ret = 0; + if (ret) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); + return 0; + } } } } @@ -3576,6 +3707,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 0; } + if (!pol && dir == XFRM_POLICY_FWD) + pol = xfrm_in_fwd_icmp(skb, &fl, family, if_id); + if (!pol) { if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); @@ -3709,6 +3843,10 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) res = 0; dst = NULL; } + + if (dst && !dst->xfrm) + dst = xfrm_out_fwd_icmp(skb, &fl, family, dst); + skb_dst_set(skb, dst); return res; } @@ -4027,10 +4165,7 @@ static int __net_init xfrm_policy_init(struct net *net) int dir, err; if (net_eq(net, &init_net)) { - xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", - sizeof(struct xfrm_dst), - 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, - NULL); + xfrm_dst_cache = KMEM_CACHE(xfrm_dst, SLAB_HWCACHE_ALIGN | SLAB_PANIC); err = rhashtable_init(&xfrm_policy_inexact_table, &xfrm_pol_inexact_params); BUG_ON(err); diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index fee9b5cf37a7..5f9bf8e5c933 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -52,6 +52,7 @@ static int xfrm_statistics_seq_show(struct seq_file *seq, void *v) memset(buff, 0, sizeof(unsigned long) * LINUX_MIB_XFRMMAX); + xfrm_state_update_stats(net); snmp_get_cpu_field_batch(buff, xfrm_mib_list, net->mib.xfrm_statistics); for (i = 0; xfrm_mib_list[i].name; i++) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index bda5327bf34d..0c306473a79d 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -570,7 +570,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) int err = 0; spin_lock(&x->lock); - xfrm_dev_state_update_curlft(x); + xfrm_dev_state_update_stats(x); if (x->km.state == XFRM_STATE_DEAD) goto out; @@ -1935,7 +1935,7 @@ EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { - xfrm_dev_state_update_curlft(x); + xfrm_dev_state_update_stats(x); if (!READ_ONCE(x->curlft.use_time)) WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); @@ -1957,6 +1957,19 @@ int xfrm_state_check_expire(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_check_expire); +void xfrm_state_update_stats(struct net *net) +{ + struct xfrm_state *x; + int i; + + spin_lock_bh(&net->xfrm.xfrm_state_lock); + for (i = 0; i <= net->xfrm.state_hmask; i++) { + hlist_for_each_entry(x, net->xfrm.state_bydst + i, bydst) + xfrm_dev_state_update_stats(x); + } + spin_unlock_bh(&net->xfrm.xfrm_state_lock); +} + struct xfrm_state * xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) diff --git a/net/xfrm/xfrm_state_bpf.c b/net/xfrm/xfrm_state_bpf.c index 9e20d4a377f7..2248eda741f8 100644 --- a/net/xfrm/xfrm_state_bpf.c +++ b/net/xfrm/xfrm_state_bpf.c @@ -117,10 +117,10 @@ __bpf_kfunc void bpf_xdp_xfrm_state_release(struct xfrm_state *x) __bpf_kfunc_end_defs(); -BTF_SET8_START(xfrm_state_kfunc_set) +BTF_KFUNCS_START(xfrm_state_kfunc_set) BTF_ID_FLAGS(func, bpf_xdp_get_xfrm_state, KF_RET_NULL | KF_ACQUIRE) BTF_ID_FLAGS(func, bpf_xdp_xfrm_state_release, KF_RELEASE) -BTF_SET8_END(xfrm_state_kfunc_set) +BTF_KFUNCS_END(xfrm_state_kfunc_set) static const struct btf_kfunc_id_set xfrm_state_xdp_kfunc_set = { .owner = THIS_MODULE, diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 912c1189ba41..810b520493f3 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -902,7 +902,7 @@ static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p) memcpy(&p->sel, &x->sel, sizeof(p->sel)); memcpy(&p->lft, &x->lft, sizeof(p->lft)); if (x->xso.dev) - xfrm_dev_state_update_curlft(x); + xfrm_dev_state_update_stats(x); memcpy(&p->curlft, &x->curlft, sizeof(p->curlft)); put_unaligned(x->stats.replay_window, &p->stats.replay_window); put_unaligned(x->stats.replay, &p->stats.replay); |