diff options
Diffstat (limited to 'net')
108 files changed, 2159 insertions, 707 deletions
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 9ba04a69ec2a..a852ec093fa8 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1775,15 +1775,14 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } case TIOCINQ: { - /* - * These two are safe on a single CPU system as only - * user tasks fiddle here - */ - struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + struct sk_buff *skb; long amount = 0; + spin_lock_irq(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len - sizeof(struct ddpehdr); + spin_unlock_irq(&sk->sk_receive_queue.lock); rc = put_user(amount, (int __user *)argp); break; } diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index 838ebf0cabbf..f81f8d56f5c0 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -73,14 +73,17 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, case SIOCINQ: { struct sk_buff *skb; + int amount; if (sock->state != SS_CONNECTED) { error = -EINVAL; goto done; } + spin_lock_irq(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); - error = put_user(skb ? skb->len : 0, - (int __user *)argp) ? -EFAULT : 0; + amount = skb ? skb->len : 0; + spin_unlock_irq(&sk->sk_receive_queue.lock); + error = put_user(amount, (int __user *)argp) ? -EFAULT : 0; goto done; } case ATM_SETSC: diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 6b7f36769d03..051ea81864ac 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -186,6 +186,7 @@ enum { * struct net_bridge_vlan - per-vlan entry * * @vnode: rhashtable member + * @tnode: rhashtable member * @vid: VLAN id * @flags: bridge vlan flags * @priv_flags: private (in-kernel) bridge vlan flags @@ -196,6 +197,7 @@ enum { * @refcnt: if MASTER flag set, this is bumped for each port referencing it * @brvlan: if MASTER flag unset, this points to the global per-VLAN context * for this VLAN entry + * @tinfo: bridge tunnel info * @br_mcast_ctx: if MASTER flag set, this is the global vlan multicast context * @port_mcast_ctx: if MASTER flag unset, this is the per-port/vlan multicast * context diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index cca7594be92e..6c4d90b24d46 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -275,9 +275,10 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { - int optmem_max = READ_ONCE(sysctl_optmem_max); struct sock *sk = (struct sock *)owner; + int optmem_max; + optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); /* same check as in sock_kmalloc() */ if (size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { diff --git a/net/core/dev.c b/net/core/dev.c index 3950ced396b5..0432b04cf9b0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -165,7 +165,6 @@ 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); -static struct napi_struct *napi_by_id(unsigned int napi_id); /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl @@ -6139,7 +6138,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) EXPORT_SYMBOL(napi_complete_done); /* must be called under rcu_read_lock(), as we dont take a reference */ -static struct napi_struct *napi_by_id(unsigned int napi_id) +struct napi_struct *napi_by_id(unsigned int napi_id) { unsigned int hash = napi_id % HASH_SIZE(napi_hash); struct napi_struct *napi; @@ -6400,6 +6399,43 @@ int dev_set_threaded(struct net_device *dev, bool threaded) } EXPORT_SYMBOL(dev_set_threaded); +/** + * netif_queue_set_napi - Associate queue with the napi + * @dev: device to which NAPI and queue belong + * @queue_index: Index of queue + * @type: queue type as RX or TX + * @napi: NAPI context, pass NULL to clear previously set NAPI + * + * Set queue with its corresponding napi context. This should be done after + * registering the NAPI handler for the queue-vector and the queues have been + * mapped to the corresponding interrupt vector. + */ +void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, + enum netdev_queue_type type, struct napi_struct *napi) +{ + struct netdev_rx_queue *rxq; + struct netdev_queue *txq; + + if (WARN_ON_ONCE(napi && !napi->dev)) + return; + if (dev->reg_state >= NETREG_REGISTERED) + ASSERT_RTNL(); + + switch (type) { + case NETDEV_QUEUE_TYPE_RX: + rxq = __netif_get_rx_queue(dev, queue_index); + rxq->napi = napi; + return; + case NETDEV_QUEUE_TYPE_TX: + txq = netdev_get_tx_queue(dev, queue_index); + txq->napi = napi; + return; + default: + return; + } +} +EXPORT_SYMBOL(netif_queue_set_napi); + void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { @@ -6435,6 +6471,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, */ if (dev->threaded && napi_kthread_create(napi)) dev->threaded = 0; + netif_napi_set_irq(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight); @@ -10511,7 +10548,7 @@ void netdev_run_todo(void) write_lock(&dev_base_lock); dev->reg_state = NETREG_UNREGISTERED; write_unlock(&dev_base_lock); - linkwatch_forget_dev(dev); + linkwatch_sync_dev(dev); } while (!list_empty(&list)) { @@ -11572,6 +11609,60 @@ static struct pernet_operations __net_initdata default_device_ops = { .exit_batch = default_device_exit_batch, }; +static void __init net_dev_struct_check(void) +{ + /* TX read-mostly hotpath */ + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, real_num_tx_queues); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tc_to_txq); +#ifdef CONFIG_XPS + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, xps_maps); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, nf_hooks_egress); +#endif +#ifdef CONFIG_NET_XGRESS + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress); +#endif + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 152); + + /* TXRX read-mostly hotpath */ + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30); + + /* RX read-mostly hotpath */ + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ifindex); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_flush_timeout); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, napi_defer_hard_irqs); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler_data); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, nd_net); +#ifdef CONFIG_NETPOLL + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, npinfo); +#endif +#ifdef CONFIG_NET_XGRESS + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress); +#endif + CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 96); +} + /* * Initialize the DEV module. At boot time this walks the device list and * unhooks any devices that fail to initialise (normally hardware not @@ -11589,6 +11680,8 @@ static int __init net_dev_init(void) BUG_ON(!dev_boot_phase); + net_dev_struct_check(); + if (dev_proc_init()) goto out; diff --git a/net/core/dev.h b/net/core/dev.h index 5aa45f0fd4ae..cf93e188785b 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -30,7 +30,6 @@ int __init dev_proc_init(void); #endif void linkwatch_init_dev(struct net_device *dev); -void linkwatch_forget_dev(struct net_device *dev); void linkwatch_run_queue(void); void dev_addr_flush(struct net_device *dev); @@ -145,4 +144,6 @@ void xdp_do_check_flushed(struct napi_struct *napi); #else static inline void xdp_do_check_flushed(struct napi_struct *napi) { } #endif + +struct napi_struct *napi_by_id(unsigned int napi_id); #endif diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index aff31cd944c2..b240d9aae4a6 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -183,7 +183,7 @@ out: } static const struct genl_multicast_group dropmon_mcgrps[] = { - { .name = "events", }, + { .name = "events", .cap_sys_admin = 1 }, }; static void send_dm_alert(struct work_struct *work) @@ -1619,11 +1619,13 @@ static const struct genl_small_ops dropmon_ops[] = { .cmd = NET_DM_CMD_START, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_STOP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_CONFIG_GET, diff --git a/net/core/filter.c b/net/core/filter.c index adcfc2c25754..4ff6100c6a27 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1219,8 +1219,8 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) */ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) { + int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); u32 filter_size = bpf_prog_size(fp->prog->len); - int optmem_max = READ_ONCE(sysctl_optmem_max); /* same check as in sock_kmalloc() */ if (filter_size <= optmem_max && @@ -1550,12 +1550,13 @@ EXPORT_SYMBOL_GPL(sk_attach_filter); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); - int err; + int err, optmem_max; if (IS_ERR(prog)) return PTR_ERR(prog); - if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) + optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); + if (bpf_prog_size(prog->len) > optmem_max) err = -ENOMEM; else err = reuseport_attach_prog(sk, prog); @@ -1594,7 +1595,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog; - int err; + int err, optmem_max; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; @@ -1622,7 +1623,8 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) } } else { /* BPF_PROG_TYPE_SOCKET_FILTER */ - if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) { + optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); + if (bpf_prog_size(prog->len) > optmem_max) { err = -ENOMEM; goto err_prog_put; } @@ -2602,6 +2604,22 @@ BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes) return 0; } +static void sk_msg_reset_curr(struct sk_msg *msg) +{ + u32 i = msg->sg.start; + u32 len = 0; + + do { + len += sk_msg_elem(msg, i)->length; + sk_msg_iter_var_next(i); + if (len >= msg->sg.size) + break; + } while (i != msg->sg.end); + + msg->sg.curr = i; + msg->sg.copybreak = 0; +} + static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .func = bpf_msg_cork_bytes, .gpl_only = false, @@ -2721,6 +2739,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: + sk_msg_reset_curr(msg); msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; msg->data_end = msg->data + bytes; return 0; @@ -2857,6 +2876,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, msg->sg.data[new] = rsge; } + sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } @@ -3025,6 +3045,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, sk_mem_uncharge(msg->sk, len - pop); msg->sg.size -= (len - pop); + sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } diff --git a/net/core/link_watch.c b/net/core/link_watch.c index c469d1c4db5d..429571c258da 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -192,7 +192,10 @@ static void __linkwatch_run_queue(int urgent_only) #define MAX_DO_DEV_PER_LOOP 100 int do_dev = MAX_DO_DEV_PER_LOOP; - struct net_device *dev; + /* Use a local list here since we add non-urgent + * events back to the global one when called with + * urgent_only=1. + */ LIST_HEAD(wrk); /* Give urgent case more budget */ @@ -218,6 +221,7 @@ static void __linkwatch_run_queue(int urgent_only) list_splice_init(&lweventlist, &wrk); while (!list_empty(&wrk) && do_dev > 0) { + struct net_device *dev; dev = list_first_entry(&wrk, struct net_device, link_watch_list); list_del_init(&dev->link_watch_list); @@ -245,7 +249,7 @@ static void __linkwatch_run_queue(int urgent_only) spin_unlock_irq(&lweventlist_lock); } -void linkwatch_forget_dev(struct net_device *dev) +void linkwatch_sync_dev(struct net_device *dev) { unsigned long flags; int clean = 0; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index df81c1f0a570..552719c3bbc3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -253,9 +253,11 @@ static int neigh_forced_gc(struct neigh_table *tbl) { int max_clean = atomic_read(&tbl->gc_entries) - READ_ONCE(tbl->gc_thresh2); + u64 tmax = ktime_get_ns() + NSEC_PER_MSEC; unsigned long tref = jiffies - 5 * HZ; struct neighbour *n, *tmp; int shrunk = 0; + int loop = 0; NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs); @@ -278,11 +280,16 @@ static int neigh_forced_gc(struct neigh_table *tbl) shrunk++; if (shrunk >= max_clean) break; + if (++loop == 16) { + if (ktime_get_ns() > tmax) + goto unlock; + loop = 0; + } } } WRITE_ONCE(tbl->last_flush, jiffies); - +unlock: write_unlock_bh(&tbl->lock); return shrunk; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index fccaa5bac0ed..a09d507c5b03 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -193,11 +193,22 @@ static ssize_t carrier_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); + int ret = -EINVAL; - if (netif_running(netdev)) - return sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev)); + if (!rtnl_trylock()) + return restart_syscall(); - return -EINVAL; + if (netif_running(netdev)) { + /* Synchronize carrier state with link watch, + * see also rtnl_getlink(). + */ + linkwatch_sync_dev(netdev); + + ret = sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev)); + } + rtnl_unlock(); + + return ret; } static DEVICE_ATTR_RW(carrier); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index f4183c4c1ec8..72799533426b 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -372,6 +372,10 @@ out_undo: static int __net_init net_defaults_init_net(struct net *net) { net->core.sysctl_somaxconn = SOMAXCONN; + /* Limits per socket sk_omem_alloc usage. + * TCP zerocopy regular usage needs 128 KB. + */ + net->core.sysctl_optmem_max = 128 * 1024; net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; return 0; @@ -1099,11 +1103,56 @@ out: rtnl_set_sk_err(net, RTNLGRP_NSID, err); } +#ifdef CONFIG_NET_NS +static void __init netns_ipv4_struct_check(void) +{ + /* TX readonly hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_early_retrans); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_tso_win_divisor); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_tso_rtt_log); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_autocorking); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_min_snd_mss); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_notsent_lowat); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_limit_output_bytes); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_min_rtt_wlen); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_tcp_wmem); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, + sysctl_ip_fwd_use_pmtu); + CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_tx, 33); + + /* TXRX readonly hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_txrx, + sysctl_tcp_moderate_rcvbuf); + CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_txrx, 1); + + /* RX readonly hotpath cache line */ + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, + sysctl_ip_early_demux); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, + sysctl_tcp_early_demux); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, + sysctl_tcp_reordering); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, + sysctl_tcp_rmem); + CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_rx, 18); +} +#endif + void __init net_ns_init(void) { struct net_generic *ng; #ifdef CONFIG_NET_NS + netns_ipv4_struct_check(); net_cachep = kmem_cache_create("net_namespace", sizeof(struct net), SMP_CACHE_BYTES, SLAB_PANIC|SLAB_ACCOUNT, NULL); diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index dccd8c3a141e..be7f2ebd61b2 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -46,6 +46,28 @@ static const struct nla_policy netdev_page_pool_stats_get_nl_policy[NETDEV_A_PAG }; #endif /* CONFIG_PAGE_POOL_STATS */ +/* NETDEV_CMD_QUEUE_GET - do */ +static const struct nla_policy netdev_queue_get_do_nl_policy[NETDEV_A_QUEUE_TYPE + 1] = { + [NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), + [NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1), + [NETDEV_A_QUEUE_ID] = { .type = NLA_U32, }, +}; + +/* NETDEV_CMD_QUEUE_GET - dump */ +static const struct nla_policy netdev_queue_get_dump_nl_policy[NETDEV_A_QUEUE_IFINDEX + 1] = { + [NETDEV_A_QUEUE_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + +/* NETDEV_CMD_NAPI_GET - do */ +static const struct nla_policy netdev_napi_get_do_nl_policy[NETDEV_A_NAPI_ID + 1] = { + [NETDEV_A_NAPI_ID] = { .type = NLA_U32, }, +}; + +/* NETDEV_CMD_NAPI_GET - dump */ +static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFINDEX + 1] = { + [NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -88,6 +110,34 @@ static const struct genl_split_ops netdev_nl_ops[] = { .flags = GENL_CMD_CAP_DUMP, }, #endif /* CONFIG_PAGE_POOL_STATS */ + { + .cmd = NETDEV_CMD_QUEUE_GET, + .doit = netdev_nl_queue_get_doit, + .policy = netdev_queue_get_do_nl_policy, + .maxattr = NETDEV_A_QUEUE_TYPE, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_QUEUE_GET, + .dumpit = netdev_nl_queue_get_dumpit, + .policy = netdev_queue_get_dump_nl_policy, + .maxattr = NETDEV_A_QUEUE_IFINDEX, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = NETDEV_CMD_NAPI_GET, + .doit = netdev_nl_napi_get_doit, + .policy = netdev_napi_get_do_nl_policy, + .maxattr = NETDEV_A_NAPI_ID, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_NAPI_GET, + .dumpit = netdev_nl_napi_get_dumpit, + .policy = netdev_napi_get_dump_nl_policy, + .maxattr = NETDEV_A_NAPI_IFINDEX, + .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 649e4b46eccf..a47f2bcbe4fa 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -23,6 +23,11 @@ int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info); +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); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 10f2124e9e23..fd98936da3ae 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -7,8 +7,25 @@ #include <net/sock.h> #include <net/xdp.h> #include <net/xdp_sock.h> +#include <net/netdev_rx_queue.h> +#include <net/busy_poll.h> #include "netdev-genl-gen.h" +#include "dev.h" + +struct netdev_nl_dump_ctx { + unsigned long ifindex; + unsigned int rxq_idx; + unsigned int txq_idx; + unsigned int napi_id; +}; + +static struct netdev_nl_dump_ctx *netdev_dump_ctx(struct netlink_callback *cb) +{ + NL_ASSERT_DUMP_CTX_FITS(struct netdev_nl_dump_ctx); + + return (struct netdev_nl_dump_ctx *)cb->ctx; +} static int netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, @@ -122,12 +139,13 @@ err_free_msg: int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { + struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); struct net *net = sock_net(skb->sk); struct net_device *netdev; int err = 0; rtnl_lock(); - for_each_netdev_dump(net, netdev, cb->args[0]) { + for_each_netdev_dump(net, netdev, ctx->ifindex) { err = netdev_nl_dev_fill(netdev, skb, genl_info_dump(cb)); if (err < 0) break; @@ -140,6 +158,317 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } +static int +netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, + const struct genl_info *info) +{ + void *hdr; + pid_t pid; + + if (WARN_ON_ONCE(!napi->dev)) + return -EINVAL; + if (!(napi->dev->flags & IFF_UP)) + return 0; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + if (napi->napi_id >= MIN_NAPI_ID && + nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id)) + goto nla_put_failure; + + if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex)) + goto nla_put_failure; + + if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq)) + goto nla_put_failure; + + if (napi->thread) { + pid = task_pid_nr(napi->thread); + if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid)) + goto nla_put_failure; + } + + genlmsg_end(rsp, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct napi_struct *napi; + struct sk_buff *rsp; + u32 napi_id; + int err; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_NAPI_ID)) + return -EINVAL; + + napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + rtnl_lock(); + + napi = napi_by_id(napi_id); + if (napi) + err = netdev_nl_napi_fill_one(rsp, napi, info); + else + err = -EINVAL; + + rtnl_unlock(); + + if (err) + goto err_free_msg; + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); + return err; +} + +static int +netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info, + struct netdev_nl_dump_ctx *ctx) +{ + struct napi_struct *napi; + int err = 0; + + if (!(netdev->flags & IFF_UP)) + return err; + + list_for_each_entry(napi, &netdev->napi_list, dev_list) { + if (ctx->napi_id && napi->napi_id >= ctx->napi_id) + continue; + + err = netdev_nl_napi_fill_one(rsp, napi, info); + if (err) + return err; + ctx->napi_id = napi->napi_id; + } + return err; +} + +int netdev_nl_napi_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; + u32 ifindex = 0; + int err = 0; + + if (info->attrs[NETDEV_A_NAPI_IFINDEX]) + ifindex = nla_get_u32(info->attrs[NETDEV_A_NAPI_IFINDEX]); + + rtnl_lock(); + if (ifindex) { + netdev = __dev_get_by_index(net, ifindex); + if (netdev) + err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); + else + err = -ENODEV; + } else { + for_each_netdev_dump(net, netdev, ctx->ifindex) { + err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); + if (err < 0) + break; + ctx->napi_id = 0; + } + } + rtnl_unlock(); + + if (err != -EMSGSIZE) + return err; + + return skb->len; +} + +static int +netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, + u32 q_idx, u32 q_type, const struct genl_info *info) +{ + struct netdev_rx_queue *rxq; + struct netdev_queue *txq; + void *hdr; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u32(rsp, NETDEV_A_QUEUE_ID, q_idx) || + nla_put_u32(rsp, NETDEV_A_QUEUE_TYPE, q_type) || + nla_put_u32(rsp, NETDEV_A_QUEUE_IFINDEX, netdev->ifindex)) + goto nla_put_failure; + + switch (q_type) { + case NETDEV_QUEUE_TYPE_RX: + rxq = __netif_get_rx_queue(netdev, q_idx); + if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, + rxq->napi->napi_id)) + goto nla_put_failure; + break; + case NETDEV_QUEUE_TYPE_TX: + txq = netdev_get_tx_queue(netdev, q_idx); + if (txq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, + txq->napi->napi_id)) + goto nla_put_failure; + } + + genlmsg_end(rsp, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +static int netdev_nl_queue_validate(struct net_device *netdev, u32 q_id, + u32 q_type) +{ + switch (q_type) { + case NETDEV_QUEUE_TYPE_RX: + if (q_id >= netdev->real_num_rx_queues) + return -EINVAL; + return 0; + case NETDEV_QUEUE_TYPE_TX: + if (q_id >= netdev->real_num_tx_queues) + return -EINVAL; + } + return 0; +} + +static int +netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, + u32 q_type, const struct genl_info *info) +{ + int err = 0; + + if (!(netdev->flags & IFF_UP)) + return err; + + err = netdev_nl_queue_validate(netdev, q_idx, q_type); + if (err) + return err; + + return netdev_nl_queue_fill_one(rsp, netdev, q_idx, q_type, info); +} + +int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + u32 q_id, q_type, ifindex; + struct net_device *netdev; + struct sk_buff *rsp; + int err; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_ID) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_TYPE) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_QUEUE_IFINDEX)) + return -EINVAL; + + q_id = nla_get_u32(info->attrs[NETDEV_A_QUEUE_ID]); + q_type = nla_get_u32(info->attrs[NETDEV_A_QUEUE_TYPE]); + ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + rtnl_lock(); + + netdev = __dev_get_by_index(genl_info_net(info), ifindex); + if (netdev) + err = netdev_nl_queue_fill(rsp, netdev, q_id, q_type, info); + else + err = -ENODEV; + + rtnl_unlock(); + + if (err) + goto err_free_msg; + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); + return err; +} + +static int +netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info, + struct netdev_nl_dump_ctx *ctx) +{ + int err = 0; + int i; + + if (!(netdev->flags & IFF_UP)) + return err; + + for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) { + err = netdev_nl_queue_fill_one(rsp, netdev, i, + NETDEV_QUEUE_TYPE_RX, info); + if (err) + return err; + ctx->rxq_idx = i++; + } + for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) { + err = netdev_nl_queue_fill_one(rsp, netdev, i, + NETDEV_QUEUE_TYPE_TX, info); + if (err) + return err; + ctx->txq_idx = i++; + } + + return err; +} + +int netdev_nl_queue_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; + u32 ifindex = 0; + int err = 0; + + if (info->attrs[NETDEV_A_QUEUE_IFINDEX]) + ifindex = nla_get_u32(info->attrs[NETDEV_A_QUEUE_IFINDEX]); + + rtnl_lock(); + if (ifindex) { + netdev = __dev_get_by_index(net, ifindex); + if (netdev) + err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); + else + err = -ENODEV; + } else { + for_each_netdev_dump(net, netdev, ctx->ifindex) { + err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); + if (err < 0) + break; + ctx->rxq_idx = 0; + ctx->txq_idx = 0; + } + } + rtnl_unlock(); + + if (err != -EMSGSIZE) + return err; + + return skb->len; +} + static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { diff --git a/net/core/page_pool.c b/net/core/page_pool.c index c2e7c9a6efbe..4933762e5a6b 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -28,7 +28,7 @@ #define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) -#define BIAS_MAX LONG_MAX +#define BIAS_MAX (LONG_MAX >> 1) #ifdef CONFIG_PAGE_POOL_STATS /* alloc_stat_inc is intended to be used in softirq context */ @@ -548,21 +548,16 @@ s32 page_pool_inflight(const struct page_pool *pool, bool strict) return inflight; } -/* Disconnects a page (from a page_pool). API users can have a need - * to disconnect a page (from a page_pool), to allow it to be used as - * a regular page (that will eventually be returned to the normal - * page-allocator via put_page). - */ -static void page_pool_return_page(struct page_pool *pool, struct page *page) +static __always_inline +void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) { dma_addr_t dma; - int count; if (!(pool->p.flags & PP_FLAG_DMA_MAP)) /* Always account for inflight pages, even if we didn't * map them */ - goto skip_dma_unmap; + return; dma = page_pool_get_dma_addr(page); @@ -571,7 +566,19 @@ static void page_pool_return_page(struct page_pool *pool, struct page *page) PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); page_pool_set_dma_addr(page, 0); -skip_dma_unmap: +} + +/* Disconnects a page (from a page_pool). API users can have a need + * to disconnect a page (from a page_pool), to allow it to be used as + * a regular page (that will eventually be returned to the normal + * page-allocator via put_page). + */ +void page_pool_return_page(struct page_pool *pool, struct page *page) +{ + int count; + + __page_pool_release_page_dma(pool, page); + page_pool_clear_pp_info(page); /* This may be the last page returned, releasing the pool, so @@ -677,8 +684,8 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, return NULL; } -void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct) +void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct) { page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct); if (page && !page_pool_recycle_in_ring(pool, page)) { @@ -687,7 +694,7 @@ void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, page_pool_return_page(pool, page); } } -EXPORT_SYMBOL(page_pool_put_defragged_page); +EXPORT_SYMBOL(page_pool_put_unrefed_page); /** * page_pool_put_page_bulk() - release references on multiple pages @@ -714,7 +721,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, struct page *page = virt_to_head_page(data[i]); /* It is not the last user for the page frag case */ - if (!page_pool_is_last_frag(page)) + if (!page_pool_is_last_ref(page)) continue; page = __page_pool_put_page(pool, page, -1, false); @@ -756,7 +763,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool, long drain_count = BIAS_MAX - pool->frag_users; /* Some user is still using the page frag */ - if (likely(page_pool_defrag_page(page, drain_count))) + if (likely(page_pool_unref_page(page, drain_count))) return NULL; if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) { @@ -777,7 +784,7 @@ static void page_pool_free_frag(struct page_pool *pool) pool->frag_page = NULL; - if (!page || page_pool_defrag_page(page, drain_count)) + if (!page || page_pool_unref_page(page, drain_count)) return; page_pool_return_page(pool, page); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 592164c2a540..94c4572512b8 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -342,8 +342,7 @@ int rtnl_unregister(int protocol, int msgtype) return -ENOENT; } - link = rtnl_dereference(tab[msgindex]); - RCU_INIT_POINTER(tab[msgindex], NULL); + link = rcu_replace_pointer_rtnl(tab[msgindex], NULL); rtnl_unlock(); kfree_rcu(link, rcu); @@ -368,18 +367,13 @@ void rtnl_unregister_all(int protocol) BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); rtnl_lock(); - tab = rtnl_dereference(rtnl_msg_handlers[protocol]); + tab = rcu_replace_pointer_rtnl(rtnl_msg_handlers[protocol], NULL); if (!tab) { rtnl_unlock(); return; } - RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL); for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) { - link = rtnl_dereference(tab[msgindex]); - if (!link) - continue; - - RCU_INIT_POINTER(tab[msgindex], NULL); + link = rcu_replace_pointer_rtnl(tab[msgindex], NULL); kfree_rcu(link, rcu); } rtnl_unlock(); @@ -3853,6 +3847,14 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (nskb == NULL) goto out; + /* Synchronize the carrier state so we don't report a state + * that we're not actually going to honour immediately; if + * the driver just did a carrier off->on transition, we can + * only TX if link watch work has run, but without this we'd + * already report carrier on, even if it doesn't work yet. + */ + linkwatch_sync_dev(dev); + err = rtnl_fill_ifinfo(nskb, dev, net, RTM_NEWLINK, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, 0, ext_filter_mask, diff --git a/net/core/scm.c b/net/core/scm.c index 880027ecf516..7dc47c17d863 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -26,6 +26,7 @@ #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/errqueue.h> +#include <linux/io_uring.h> #include <linux/uaccess.h> @@ -103,6 +104,11 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; + /* don't allow io_uring files */ + if (io_uring_get_socket(file)) { + fput(file); + return -EINVAL; + } *fpp++ = file; fpl->count++; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b157efea5dea..4d4b11b0a83d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -890,6 +890,11 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } +static bool is_pp_page(struct page *page) +{ + return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; +} + #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(struct page *page, bool napi_safe) { @@ -905,7 +910,7 @@ bool napi_pp_put_page(struct page *page, bool napi_safe) * and page_is_pfmemalloc() is checked in __page_pool_put_page() * to avoid recycling the pfmemalloc page. */ - if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE)) + if (unlikely(!is_pp_page(page))) return false; pp = page->pp; @@ -942,6 +947,37 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe) return napi_pp_put_page(virt_to_page(data), napi_safe); } +/** + * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb + * @skb: page pool aware skb + * + * Increase the fragment reference count (pp_ref_count) of a skb. This is + * intended to gain fragment references only for page pool aware skbs, + * i.e. when skb->pp_recycle is true, and not for fragments in a + * non-pp-recycling skb. It has a fallback to increase references on normal + * pages, as page pool aware skbs may also have normal page fragments. + */ +static int skb_pp_frag_ref(struct sk_buff *skb) +{ + struct skb_shared_info *shinfo; + struct page *head_page; + int i; + + if (!skb->pp_recycle) + return -EINVAL; + + shinfo = skb_shinfo(skb); + + for (i = 0; i < shinfo->nr_frags; i++) { + head_page = compound_head(skb_frag_page(&shinfo->frags[i])); + if (likely(is_pp_page(head_page))) + page_pool_ref_page(head_page); + else + page_ref_inc(head_page); + } + return 0; +} + static void skb_kfree_head(void *head, unsigned int end_offset) { if (end_offset == SKB_SMALL_HEAD_HEADROOM) @@ -4522,8 +4558,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. + * Cap len to not accidentally hit GSO_BY_FRAGS. */ - partial_segs = len / mss; + partial_segs = min(len, GSO_BY_FRAGS - 1) / mss; if (partial_segs > 1) mss *= partial_segs; else @@ -5764,17 +5801,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, return false; /* In general, avoid mixing page_pool and non-page_pool allocated - * pages within the same SKB. Additionally avoid dealing with clones - * with page_pool pages, in case the SKB is using page_pool fragment - * references (page_pool_alloc_frag()). Since we only take full page - * references for cloned SKBs at the moment that would result in - * inconsistent reference counts. - * In theory we could take full references if @from is cloned and - * !@to->pp_recycle but its tricky (due to potential race with - * the clone disappearing) and rare, so not worth dealing with. + * pages within the same SKB. In theory we could take full + * references if @from is cloned and !@to->pp_recycle but its + * tricky (due to potential race with the clone disappearing) and + * rare, so not worth dealing with. */ - if (to->pp_recycle != from->pp_recycle || - (from->pp_recycle && skb_cloned(from))) + if (to->pp_recycle != from->pp_recycle) return false; if (len <= skb_tailroom(to)) { @@ -5831,8 +5863,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, /* if the skb is not cloned this does nothing * since we set nr_frags to 0. */ - for (i = 0; i < from_shinfo->nr_frags; i++) - __skb_frag_ref(&from_shinfo->frags[i]); + if (skb_pp_frag_ref(from)) { + for (i = 0; i < from_shinfo->nr_frags; i++) + __skb_frag_ref(&from_shinfo->frags[i]); + } to->truesize += delta; to->len += len; diff --git a/net/core/sock.c b/net/core/sock.c index fef349dd72fa..446e945f736b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -283,10 +283,6 @@ EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; -/* Maximal space eaten by iovec or ancillary data plus some space */ -int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); -EXPORT_SYMBOL(sysctl_optmem_max); - int sysctl_tstamp_allow_data __read_mostly = 1; DEFINE_STATIC_KEY_FALSE(memalloc_socks_key); @@ -2651,7 +2647,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */ if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) > - READ_ONCE(sysctl_optmem_max)) + READ_ONCE(sock_net(sk)->core.sysctl_optmem_max)) return NULL; skb = alloc_skb(size, priority); @@ -2669,7 +2665,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { - int optmem_max = READ_ONCE(sysctl_optmem_max); + int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if ((unsigned int)size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 03f1edb948d7..0f0cb1465e08 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -509,13 +509,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec, }, { - .procname = "optmem_max", - .data = &sysctl_optmem_max, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tstamp_allow_data", .data = &sysctl_tstamp_allow_data, .maxlen = sizeof(int), @@ -674,6 +667,14 @@ static struct ctl_table netns_core_table[] = { .proc_handler = proc_dointvec_minmax }, { + .procname = "optmem_max", + .data = &init_net.core.sysctl_optmem_max, + .maxlen = sizeof(int), + .mode = 0644, + .extra1 = SYSCTL_ZERO, + .proc_handler = proc_dointvec_minmax + }, + { .procname = "txrehash", .data = &init_net.core.sysctl_txrehash, .maxlen = sizeof(u8), diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 4550b680665a..06d7324276ec 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -669,7 +669,7 @@ discard: ipv6_pktoptions: if (!((1 << sk->sk_state) & (DCCPF_CLOSED | DCCPF_LISTEN))) { if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo) - np->mcast_oif = inet6_iif(opt_skb); + WRITE_ONCE(np->mcast_oif, inet6_iif(opt_skb)); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) WRITE_ONCE(np->mcast_hops, ipv6_hdr(opt_skb)->hop_limit); if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) diff --git a/net/dns_resolver/Kconfig b/net/dns_resolver/Kconfig index 155b06163409..7c2dba273e35 100644 --- a/net/dns_resolver/Kconfig +++ b/net/dns_resolver/Kconfig @@ -23,6 +23,6 @@ config DNS_RESOLVER information. To compile this as a module, choose M here: the module will be called - dnsresolver. + dns_resolver. If unsure, say N. diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 11d8797f63f6..6b2a360dcdf0 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -589,8 +589,8 @@ err_free_info: int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max) { + struct ethtool_rxfh_param rxfh = {}; u32 dev_size, current_max = 0; - u32 *indir; int ret; if (!dev->ethtool_ops->get_rxfh_indir_size || @@ -600,21 +600,21 @@ int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max) if (dev_size == 0) return -EOPNOTSUPP; - indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); - if (!indir) + rxfh.indir = kcalloc(dev_size, sizeof(rxfh.indir[0]), GFP_USER); + if (!rxfh.indir) return -ENOMEM; - ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL); + ret = dev->ethtool_ops->get_rxfh(dev, &rxfh); if (ret) goto out; while (dev_size--) - current_max = max(current_max, indir[dev_size]); + current_max = max(current_max, rxfh.indir[dev_size]); *max = current_max; out: - kfree(indir); + kfree(rxfh.indir); return ret; } diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 0b0ce4f81c01..86d47425038b 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -58,6 +58,9 @@ static struct devlink *netdev_to_devlink_get(struct net_device *dev) u32 ethtool_op_get_link(struct net_device *dev) { + /* Synchronize carrier state with link watch, see also rtnl_getlink() */ + linkwatch_sync_dev(dev); + return netif_carrier_ok(dev) ? 1 : 0; } EXPORT_SYMBOL(ethtool_op_get_link); @@ -969,18 +972,35 @@ static int ethtool_rxnfc_copy_to_user(void __user *useraddr, static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, u32 cmd, void __user *useraddr) { + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxfh_param rxfh = {}; struct ethtool_rxnfc info; size_t info_size = sizeof(info); int rc; - if (!dev->ethtool_ops->set_rxnfc) + if (!ops->set_rxnfc || !ops->get_rxfh) return -EOPNOTSUPP; rc = ethtool_rxnfc_copy_struct(cmd, &info, &info_size, useraddr); if (rc) return rc; - rc = dev->ethtool_ops->set_rxnfc(dev, &info); + rc = ops->get_rxfh(dev, &rxfh); + if (rc) + return rc; + + /* Sanity check: if symmetric-xor is set, then: + * 1 - no other fields besides IP src/dst and/or L4 src/dst + * 2 - If src is set, dst must also be set + */ + if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) && + ((info.data & ~(RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3)) || + (!!(info.data & RXH_IP_SRC) ^ !!(info.data & RXH_IP_DST)) || + (!!(info.data & RXH_L4_B_0_1) ^ !!(info.data & RXH_L4_B_2_3)))) + return -EINVAL; + + rc = ops->set_rxnfc(dev, &info); if (rc) return rc; @@ -1058,15 +1078,15 @@ EXPORT_SYMBOL(netdev_rss_key_fill); static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, void __user *useraddr) { - u32 user_size, dev_size; - u32 *indir; + struct ethtool_rxfh_param rxfh = {}; + u32 user_size; int ret; if (!dev->ethtool_ops->get_rxfh_indir_size || !dev->ethtool_ops->get_rxfh) return -EOPNOTSUPP; - dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); - if (dev_size == 0) + rxfh.indir_size = dev->ethtool_ops->get_rxfh_indir_size(dev); + if (rxfh.indir_size == 0) return -EOPNOTSUPP; if (copy_from_user(&user_size, @@ -1075,41 +1095,41 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, return -EFAULT; if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, size), - &dev_size, sizeof(dev_size))) + &rxfh.indir_size, sizeof(rxfh.indir_size))) return -EFAULT; /* If the user buffer size is 0, this is just a query for the * device table size. Otherwise, if it's smaller than the * device table size it's an error. */ - if (user_size < dev_size) + if (user_size < rxfh.indir_size) return user_size == 0 ? 0 : -EINVAL; - indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); - if (!indir) + rxfh.indir = kcalloc(rxfh.indir_size, sizeof(rxfh.indir[0]), GFP_USER); + if (!rxfh.indir) return -ENOMEM; - ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL); + ret = dev->ethtool_ops->get_rxfh(dev, &rxfh); if (ret) goto out; - if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, ring_index[0]), - indir, dev_size * sizeof(indir[0]))) + rxfh.indir, rxfh.indir_size * sizeof(*rxfh.indir))) ret = -EFAULT; out: - kfree(indir); + kfree(rxfh.indir); return ret; } static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, void __user *useraddr) { - struct ethtool_rxnfc rx_rings; - u32 user_size, dev_size, i; - u32 *indir; const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxfh_param rxfh_dev = {}; + struct netlink_ext_ack *extack = NULL; + struct ethtool_rxnfc rx_rings; + u32 user_size, i; int ret; u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]); @@ -1117,8 +1137,8 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, !ops->get_rxnfc) return -EOPNOTSUPP; - dev_size = ops->get_rxfh_indir_size(dev); - if (dev_size == 0) + rxfh_dev.indir_size = ops->get_rxfh_indir_size(dev); + if (rxfh_dev.indir_size == 0) return -EOPNOTSUPP; if (copy_from_user(&user_size, @@ -1126,11 +1146,12 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, sizeof(user_size))) return -EFAULT; - if (user_size != 0 && user_size != dev_size) + if (user_size != 0 && user_size != rxfh_dev.indir_size) return -EINVAL; - indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); - if (!indir) + rxfh_dev.indir = kcalloc(rxfh_dev.indir_size, + sizeof(rxfh_dev.indir[0]), GFP_USER); + if (!rxfh_dev.indir) return -ENOMEM; rx_rings.cmd = ETHTOOL_GRXRINGS; @@ -1139,18 +1160,21 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, goto out; if (user_size == 0) { - for (i = 0; i < dev_size; i++) + u32 *indir = rxfh_dev.indir; + + for (i = 0; i < rxfh_dev.indir_size; i++) indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data); } else { - ret = ethtool_copy_validate_indir(indir, + ret = ethtool_copy_validate_indir(rxfh_dev.indir, useraddr + ringidx_offset, &rx_rings, - dev_size); + rxfh_dev.indir_size); if (ret) goto out; } - ret = ops->set_rxfh(dev, indir, NULL, ETH_RSS_HASH_NO_CHANGE); + rxfh_dev.hfunc = ETH_RSS_HASH_NO_CHANGE; + ret = ops->set_rxfh(dev, &rxfh_dev, extack); if (ret) goto out; @@ -1161,32 +1185,29 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, dev->priv_flags |= IFF_RXFH_CONFIGURED; out: - kfree(indir); + kfree(rxfh_dev.indir); return ret; } static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, void __user *useraddr) { - int ret; const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxfh_param rxfh_dev = {}; u32 user_indir_size, user_key_size; - u32 dev_indir_size = 0, dev_key_size = 0; struct ethtool_rxfh rxfh; - u32 total_size; u32 indir_bytes; - u32 *indir = NULL; - u8 dev_hfunc = 0; - u8 *hkey = NULL; u8 *rss_config; + u32 total_size; + int ret; if (!ops->get_rxfh) return -EOPNOTSUPP; if (ops->get_rxfh_indir_size) - dev_indir_size = ops->get_rxfh_indir_size(dev); + rxfh_dev.indir_size = ops->get_rxfh_indir_size(dev); if (ops->get_rxfh_key_size) - dev_key_size = ops->get_rxfh_key_size(dev); + rxfh_dev.key_size = ops->get_rxfh_key_size(dev); if (copy_from_user(&rxfh, useraddr, sizeof(rxfh))) return -EFAULT; @@ -1194,44 +1215,41 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, user_key_size = rxfh.key_size; /* Check that reserved fields are 0 for now */ - if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32) + if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ - if (rxfh.rss_context && !ops->get_rxfh_context) + if (rxfh.rss_context && !ops->cap_rss_ctx_supported) return -EOPNOTSUPP; - rxfh.indir_size = dev_indir_size; - rxfh.key_size = dev_key_size; + rxfh.indir_size = rxfh_dev.indir_size; + rxfh.key_size = rxfh_dev.key_size; if (copy_to_user(useraddr, &rxfh, sizeof(rxfh))) return -EFAULT; - if ((user_indir_size && (user_indir_size != dev_indir_size)) || - (user_key_size && (user_key_size != dev_key_size))) + if ((user_indir_size && user_indir_size != rxfh_dev.indir_size) || + (user_key_size && user_key_size != rxfh_dev.key_size)) return -EINVAL; - indir_bytes = user_indir_size * sizeof(indir[0]); + indir_bytes = user_indir_size * sizeof(rxfh_dev.indir[0]); total_size = indir_bytes + user_key_size; rss_config = kzalloc(total_size, GFP_USER); if (!rss_config) return -ENOMEM; if (user_indir_size) - indir = (u32 *)rss_config; + rxfh_dev.indir = (u32 *)rss_config; if (user_key_size) - hkey = rss_config + indir_bytes; + rxfh_dev.key = rss_config + indir_bytes; - if (rxfh.rss_context) - ret = dev->ethtool_ops->get_rxfh_context(dev, indir, hkey, - &dev_hfunc, - rxfh.rss_context); - else - ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey, &dev_hfunc); + rxfh_dev.rss_context = rxfh.rss_context; + + ret = dev->ethtool_ops->get_rxfh(dev, &rxfh_dev); if (ret) goto out; if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, hfunc), - &dev_hfunc, sizeof(rxfh.hfunc))) { + &rxfh_dev.hfunc, sizeof(rxfh.hfunc))) { ret = -EFAULT; } else if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_config[0]), @@ -1247,16 +1265,16 @@ out: static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, void __user *useraddr) { - int ret; + u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]); const struct ethtool_ops *ops = dev->ethtool_ops; + u32 dev_indir_size = 0, dev_key_size = 0, i; + struct ethtool_rxfh_param rxfh_dev = {}; + struct netlink_ext_ack *extack = NULL; struct ethtool_rxnfc rx_rings; struct ethtool_rxfh rxfh; - u32 dev_indir_size = 0, dev_key_size = 0, i; - u32 *indir = NULL, indir_bytes = 0; - u8 *hkey = NULL; + u32 indir_bytes = 0; u8 *rss_config; - u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]); - bool delete = false; + int ret; if (!ops->get_rxnfc || !ops->set_rxfh) return -EOPNOTSUPP; @@ -1270,10 +1288,14 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, return -EFAULT; /* Check that reserved fields are 0 for now */ - if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32) + if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ - if (rxfh.rss_context && !ops->set_rxfh_context) + if (rxfh.rss_context && !ops->cap_rss_ctx_supported) + return -EOPNOTSUPP; + /* Check input data transformation capabilities */ + if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) && + !ops->cap_rss_sym_xor_supported) return -EOPNOTSUPP; /* If either indir, hash key or function is valid, proceed further. @@ -1288,7 +1310,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, return -EINVAL; if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) - indir_bytes = dev_indir_size * sizeof(indir[0]); + indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER); if (!rss_config) @@ -1305,8 +1327,9 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, */ if (rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) { - indir = (u32 *)rss_config; - ret = ethtool_copy_validate_indir(indir, + rxfh_dev.indir = (u32 *)rss_config; + rxfh_dev.indir_size = dev_indir_size; + ret = ethtool_copy_validate_indir(rxfh_dev.indir, useraddr + rss_cfg_offset, &rx_rings, rxfh.indir_size); @@ -1314,17 +1337,22 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, goto out; } else if (rxfh.indir_size == 0) { if (rxfh.rss_context == 0) { - indir = (u32 *)rss_config; + u32 *indir; + + rxfh_dev.indir = (u32 *)rss_config; + rxfh_dev.indir_size = dev_indir_size; + indir = rxfh_dev.indir; for (i = 0; i < dev_indir_size; i++) indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data); } else { - delete = true; + rxfh_dev.rss_delete = true; } } if (rxfh.key_size) { - hkey = rss_config + indir_bytes; - if (copy_from_user(hkey, + rxfh_dev.key_size = dev_key_size; + rxfh_dev.key = rss_config + indir_bytes; + if (copy_from_user(rxfh_dev.key, useraddr + rss_cfg_offset + indir_bytes, rxfh.key_size)) { ret = -EFAULT; @@ -1332,19 +1360,19 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, } } - if (rxfh.rss_context) - ret = ops->set_rxfh_context(dev, indir, hkey, rxfh.hfunc, - &rxfh.rss_context, delete); - else - ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc); + rxfh_dev.hfunc = rxfh.hfunc; + rxfh_dev.rss_context = rxfh.rss_context; + rxfh_dev.input_xfrm = rxfh.input_xfrm; + + ret = ops->set_rxfh(dev, &rxfh_dev, extack); if (ret) goto out; if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_context), - &rxfh.rss_context, sizeof(rxfh.rss_context))) + &rxfh_dev.rss_context, sizeof(rxfh_dev.rss_context))) ret = -EFAULT; - if (!rxfh.rss_context) { + if (!rxfh_dev.rss_context) { /* indicate whether rxfh was set to default */ if (rxfh.indir_size == 0) dev->priv_flags &= ~IFF_RXFH_CONFIGURED; @@ -1991,6 +2019,13 @@ __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...) } EXPORT_SYMBOL(ethtool_sprintf); +void ethtool_puts(u8 **data, const char *str) +{ + strscpy(*data, str, ETH_GSTRING_LEN); + *data += ETH_GSTRING_LEN; +} +EXPORT_SYMBOL(ethtool_puts); + static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) { struct ethtool_value id; diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index fb09f774ea01..b7865a14fdf8 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -124,6 +124,8 @@ const struct nla_policy ethnl_rings_set_policy[] = { [ETHTOOL_A_RINGS_RX_JUMBO] = { .type = NLA_U32 }, [ETHTOOL_A_RINGS_TX] = { .type = NLA_U32 }, [ETHTOOL_A_RINGS_RX_BUF_LEN] = NLA_POLICY_MIN(NLA_U32, 1), + [ETHTOOL_A_RINGS_TCP_DATA_SPLIT] = + NLA_POLICY_MAX(NLA_U8, ETHTOOL_TCP_DATA_SPLIT_ENABLED), [ETHTOOL_A_RINGS_CQE_SIZE] = NLA_POLICY_MIN(NLA_U32, 1), [ETHTOOL_A_RINGS_TX_PUSH] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_RINGS_RX_PUSH] = NLA_POLICY_MAX(NLA_U8, 1), @@ -145,6 +147,14 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info, return -EOPNOTSUPP; } + if (tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT] && + !(ops->supported_ring_params & ETHTOOL_RING_USE_TCP_DATA_SPLIT)) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT], + "setting TCP data split is not supported"); + return -EOPNOTSUPP; + } + if (tb[ETHTOOL_A_RINGS_CQE_SIZE] && !(ops->supported_ring_params & ETHTOOL_RING_USE_CQE_SIZE)) { NL_SET_ERR_MSG_ATTR(info->extack, @@ -202,6 +212,8 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) ethnl_update_u32(&ringparam.tx_pending, tb[ETHTOOL_A_RINGS_TX], &mod); ethnl_update_u32(&kernel_ringparam.rx_buf_len, tb[ETHTOOL_A_RINGS_RX_BUF_LEN], &mod); + ethnl_update_u8(&kernel_ringparam.tcp_data_split, + tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT], &mod); ethnl_update_u32(&kernel_ringparam.cqe_size, tb[ETHTOOL_A_RINGS_CQE_SIZE], &mod); ethnl_update_u8(&kernel_ringparam.tx_push, diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 5764202e6cb6..71679137eff2 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -13,6 +13,7 @@ struct rss_reply_data { u32 indir_size; u32 hkey_size; u32 hfunc; + u32 input_xfrm; u32 *indir_table; u8 *hkey; }; @@ -48,9 +49,9 @@ rss_prepare_data(const struct ethnl_req_info *req_base, struct rss_reply_data *data = RSS_REPDATA(reply_base); struct rss_req_info *request = RSS_REQINFO(req_base); struct net_device *dev = reply_base->dev; + struct ethtool_rxfh_param rxfh = {}; const struct ethtool_ops *ops; u32 total_size, indir_bytes; - u8 dev_hfunc = 0; u8 *rss_config; int ret; @@ -59,7 +60,7 @@ rss_prepare_data(const struct ethnl_req_info *req_base, return -EOPNOTSUPP; /* Some drivers don't handle rss_context */ - if (request->rss_context && !ops->get_rxfh_context) + if (request->rss_context && !ops->cap_rss_ctx_supported) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); @@ -83,21 +84,21 @@ rss_prepare_data(const struct ethnl_req_info *req_base, if (data->indir_size) data->indir_table = (u32 *)rss_config; - if (data->hkey_size) data->hkey = rss_config + indir_bytes; - if (request->rss_context) - ret = ops->get_rxfh_context(dev, data->indir_table, data->hkey, - &dev_hfunc, request->rss_context); - else - ret = ops->get_rxfh(dev, data->indir_table, data->hkey, - &dev_hfunc); + rxfh.indir_size = data->indir_size; + rxfh.indir = data->indir_table; + rxfh.key_size = data->hkey_size; + rxfh.key = data->hkey; + rxfh.rss_context = request->rss_context; + ret = ops->get_rxfh(dev, &rxfh); if (ret) goto out_ops; - data->hfunc = dev_hfunc; + data->hfunc = rxfh.hfunc; + data->input_xfrm = rxfh.input_xfrm; out_ops: ethnl_ops_complete(dev); return ret; @@ -111,6 +112,7 @@ rss_reply_size(const struct ethnl_req_info *req_base, int len; len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ + nla_total_size(sizeof(u32)) + /* _RSS_INPUT_XFRM */ nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */ nla_total_size(data->hkey_size); /* _RSS_HKEY */ @@ -125,6 +127,8 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, if ((data->hfunc && nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || + (data->input_xfrm && + nla_put_u32(skb, ETHTOOL_A_RSS_INPUT_XFRM, data->input_xfrm)) || (data->indir_size && nla_put(skb, ETHTOOL_A_RSS_INDIR, sizeof(u32) * data->indir_size, data->indir_table)) || diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index fb81de10d332..835f4f9d98d2 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1633,6 +1633,7 @@ int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) #endif return -EINVAL; } +EXPORT_SYMBOL(inet_recv_error); int inet_gro_complete(struct sk_buff *skb, int nhoff) { @@ -1847,9 +1848,7 @@ static __net_init int inet_init_net(struct net *net) /* * Set defaults for local port range */ - seqlock_init(&net->ipv4.ip_local_ports.lock); - net->ipv4.ip_local_ports.range[0] = 32768; - net->ipv4.ip_local_ports.range[1] = 60999; + net->ipv4.ip_local_ports.range = 60999u << 16 | 32768u; seqlock_init(&net->ipv4.ping_group_range.lock); /* diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 394a498c2823..bd325b029dd1 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -117,37 +117,39 @@ bool inet_rcv_saddr_any(const struct sock *sk) return !sk->sk_rcv_saddr; } -void inet_get_local_port_range(const struct net *net, int *low, int *high) -{ - unsigned int seq; - - do { - seq = read_seqbegin(&net->ipv4.ip_local_ports.lock); - - *low = net->ipv4.ip_local_ports.range[0]; - *high = net->ipv4.ip_local_ports.range[1]; - } while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq)); -} -EXPORT_SYMBOL(inet_get_local_port_range); - -void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high) +/** + * inet_sk_get_local_port_range - fetch ephemeral ports range + * @sk: socket + * @low: pointer to low port + * @high: pointer to high port + * + * Fetch netns port range (/proc/sys/net/ipv4/ip_local_port_range) + * Range can be overridden if socket got IP_LOCAL_PORT_RANGE option. + * Returns true if IP_LOCAL_PORT_RANGE was set on this socket. + */ +bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high) { - const struct inet_sock *inet = inet_sk(sk); - const struct net *net = sock_net(sk); int lo, hi, sk_lo, sk_hi; + bool local_range = false; + u32 sk_range; - inet_get_local_port_range(net, &lo, &hi); + inet_get_local_port_range(sock_net(sk), &lo, &hi); - sk_lo = inet->local_port_range.lo; - sk_hi = inet->local_port_range.hi; + sk_range = READ_ONCE(inet_sk(sk)->local_port_range); + if (unlikely(sk_range)) { + sk_lo = sk_range & 0xffff; + sk_hi = sk_range >> 16; - if (unlikely(lo <= sk_lo && sk_lo <= hi)) - lo = sk_lo; - if (unlikely(lo <= sk_hi && sk_hi <= hi)) - hi = sk_hi; + if (lo <= sk_lo && sk_lo <= hi) + lo = sk_lo; + if (lo <= sk_hi && sk_hi <= hi) + hi = sk_hi; + local_range = true; + } *low = lo; *high = hi; + return local_range; } EXPORT_SYMBOL(inet_sk_get_local_port_range); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 7d0e7aaa71e0..46b13962ad02 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -1077,10 +1077,94 @@ skip_listen_ht: s_i = num = s_num = 0; } +/* Process a maximum of SKARR_SZ sockets at a time when walking hash buckets + * with bh disabled. + */ +#define SKARR_SZ 16 + + /* Dump bound but inactive (not listening, connecting, etc.) sockets */ + if (cb->args[0] == 1) { + if (!(idiag_states & TCPF_BOUND_INACTIVE)) + goto skip_bind_ht; + + for (i = s_i; i < hashinfo->bhash_size; i++) { + struct inet_bind_hashbucket *ibb; + struct inet_bind2_bucket *tb2; + struct sock *sk_arr[SKARR_SZ]; + int num_arr[SKARR_SZ]; + int idx, accum, res; + +resume_bind_walk: + num = 0; + accum = 0; + ibb = &hashinfo->bhash2[i]; + + spin_lock_bh(&ibb->lock); + inet_bind_bucket_for_each(tb2, &ibb->chain) { + if (!net_eq(ib2_net(tb2), net)) + continue; + + sk_for_each_bound_bhash2(sk, &tb2->owners) { + struct inet_sock *inet = inet_sk(sk); + + if (num < s_num) + goto next_bind; + + if (sk->sk_state != TCP_CLOSE || + !inet->inet_num) + goto next_bind; + + if (r->sdiag_family != AF_UNSPEC && + r->sdiag_family != sk->sk_family) + goto next_bind; + + if (!inet_diag_bc_sk(bc, sk)) + goto next_bind; + + sock_hold(sk); + num_arr[accum] = num; + sk_arr[accum] = sk; + if (++accum == SKARR_SZ) + goto pause_bind_walk; +next_bind: + num++; + } + } +pause_bind_walk: + spin_unlock_bh(&ibb->lock); + + res = 0; + for (idx = 0; idx < accum; idx++) { + if (res >= 0) { + res = inet_sk_diag_fill(sk_arr[idx], + NULL, skb, cb, + r, NLM_F_MULTI, + net_admin); + if (res < 0) + num = num_arr[idx]; + } + sock_put(sk_arr[idx]); + } + if (res < 0) + goto done; + + cond_resched(); + + if (accum == SKARR_SZ) { + s_num = num + 1; + goto resume_bind_walk; + } + + s_num = 0; + } +skip_bind_ht: + cb->args[0] = 2; + s_i = num = s_num = 0; + } + if (!(idiag_states & ~TCPF_LISTEN)) goto out; -#define SKARR_SZ 16 for (i = s_i; i <= hashinfo->ehash_mask; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; spinlock_t *lock = inet_ehash_lockp(hashinfo, i); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index a532f749e477..9ff201bc4e6d 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1012,7 +1012,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, bool tb_created = false; u32 remaining, offset; int ret, i, low, high; - int l3mdev; + bool local_ports; + int step, l3mdev; u32 index; if (port) { @@ -1024,10 +1025,12 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, l3mdev = inet_sk_bound_l3mdev(sk); - inet_sk_get_local_port_range(sk, &low, &high); + local_ports = inet_sk_get_local_port_range(sk, &low, &high); + step = local_ports ? 1 : 2; + high++; /* [32768, 60999] -> [32768, 61000[ */ remaining = high - low; - if (likely(remaining > 1)) + if (!local_ports && remaining > 1) remaining &= ~1U; get_random_sleepable_once(table_perturb, @@ -1040,10 +1043,11 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, /* In first pass we try ports of @low parity. * inet_csk_get_port() does the opposite choice. */ - offset &= ~1U; + if (!local_ports) + offset &= ~1U; other_parity_scan: port = low + offset; - for (i = 0; i < remaining; i += 2, port += 2) { + for (i = 0; i < remaining; i += step, port += step) { if (unlikely(port >= high)) port -= remaining; if (inet_is_local_reserved_port(net, port)) @@ -1083,10 +1087,11 @@ next_port: cond_resched(); } - offset++; - if ((offset & 1) && remaining > 1) - goto other_parity_scan; - + if (!local_ports) { + offset++; + if ((offset & 1) && remaining > 1) + goto other_parity_scan; + } return -EADDRNOTAVAIL; ok: @@ -1109,8 +1114,8 @@ ok: * on low contention the randomness is maximal and on high contention * it may be inexistent. */ - i = max_t(int, i, get_random_u32_below(8) * 2); - WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); + i = max_t(int, i, get_random_u32_below(8) * step); + WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + step); /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, tb2, port); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 22a26d1d29a0..5169c3c72cff 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -635,15 +635,18 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { + int pull_len = tunnel->hlen + sizeof(struct iphdr); + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; - /* Pull skb since ip_tunnel_xmit() needs skb->data pointing - * to gre header. - */ - skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); + if (!pskb_network_may_pull(skb, pull_len)) + goto free_skb; + + /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ + skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 2efc53526a38..66247e8b429e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -775,7 +775,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) if (optlen < GROUP_FILTER_SIZE(0)) return -EINVAL; - if (optlen > READ_ONCE(sysctl_optmem_max)) + if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max)) return -ENOBUFS; gsf = memdup_sockptr(optval, optlen); @@ -811,7 +811,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (optlen < size0) return -EINVAL; - if (optlen > READ_ONCE(sysctl_optmem_max) - 4) + if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4) return -ENOBUFS; p = kmalloc(optlen + 4, GFP_KERNEL); @@ -1055,6 +1055,19 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, case IP_TOS: /* This sets both TOS and Precedence */ ip_sock_set_tos(sk, val); return 0; + case IP_LOCAL_PORT_RANGE: + { + u16 lo = val; + u16 hi = val >> 16; + + if (optlen != sizeof(u32)) + return -EINVAL; + if (lo != 0 && hi != 0 && lo > hi) + return -EINVAL; + + WRITE_ONCE(inet->local_port_range, val); + return 0; + } } err = 0; @@ -1241,7 +1254,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, if (optlen < IP_MSFILTER_SIZE(0)) goto e_inval; - if (optlen > READ_ONCE(sysctl_optmem_max)) { + if (optlen > READ_ONCE(net->core.sysctl_optmem_max)) { err = -ENOBUFS; break; } @@ -1332,20 +1345,6 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, err = xfrm_user_policy(sk, optname, optval, optlen); break; - case IP_LOCAL_PORT_RANGE: - { - const __u16 lo = val; - const __u16 hi = val >> 16; - - if (optlen != sizeof(__u32)) - goto e_inval; - if (lo != 0 && hi != 0 && lo > hi) - goto e_inval; - - inet->local_port_range.lo = lo; - inet->local_port_range.hi = hi; - break; - } default: err = -ENOPROTOOPT; break; @@ -1692,6 +1691,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; return 0; } + case IP_LOCAL_PORT_RANGE: + val = READ_ONCE(inet->local_port_range); + goto copyval; } if (needs_rtnl) @@ -1721,9 +1723,6 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, else err = ip_get_mcast_msfilter(sk, optval, optlen, len); goto out; - case IP_LOCAL_PORT_RANGE: - val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; - break; case IP_PROTOCOL: val = inet_sk(sk)->inet_num; break; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9e222a57bc2b..0063a237253b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1025,6 +1025,10 @@ static int ipmr_cache_report(const struct mr_table *mrt, struct sk_buff *skb; int ret; + mroute_sk = rcu_dereference(mrt->mroute_sk); + if (!mroute_sk) + return -EINVAL; + if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) skb = skb_realloc_headroom(pkt, sizeof(struct iphdr)); else @@ -1069,7 +1073,8 @@ static int ipmr_cache_report(const struct mr_table *mrt, msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; msg->im_vif_hi = vifi >> 8; - skb_dst_set(skb, dst_clone(skb_dst(pkt))); + ipv4_pktinfo_prepare(mroute_sk, pkt); + memcpy(skb->cb, pkt->cb, sizeof(skb->cb)); /* Add our header */ igmp = skb_put(skb, sizeof(struct igmphdr)); igmp->type = assert; @@ -1079,12 +1084,6 @@ static int ipmr_cache_report(const struct mr_table *mrt, skb->transport_header = skb->network_header; } - mroute_sk = rcu_dereference(mrt->mroute_sk); - if (!mroute_sk) { - kfree_skb(skb); - return -EINVAL; - } - igmpmsg_netlink_event(mrt, skb); /* Deliver to mrouted */ diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index f63a545a7374..7e4f16a7dcc1 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -50,26 +50,22 @@ static int tcp_plb_max_cong_thresh = 256; static int sysctl_tcp_low_latency __read_mostly; /* Update system visible IP port range */ -static void set_local_port_range(struct net *net, int range[2]) +static void set_local_port_range(struct net *net, unsigned int low, unsigned int high) { - bool same_parity = !((range[0] ^ range[1]) & 1); + bool same_parity = !((low ^ high) & 1); - write_seqlock_bh(&net->ipv4.ip_local_ports.lock); if (same_parity && !net->ipv4.ip_local_ports.warned) { net->ipv4.ip_local_ports.warned = true; pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n"); } - net->ipv4.ip_local_ports.range[0] = range[0]; - net->ipv4.ip_local_ports.range[1] = range[1]; - write_sequnlock_bh(&net->ipv4.ip_local_ports.lock); + WRITE_ONCE(net->ipv4.ip_local_ports.range, high << 16 | low); } /* Validate changes from /proc interface. */ static int ipv4_local_port_range(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = - container_of(table->data, struct net, ipv4.ip_local_ports.range); + struct net *net = table->data; int ret; int range[2]; struct ctl_table tmp = { @@ -93,7 +89,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, (range[0] < READ_ONCE(net->ipv4.sysctl_ip_prot_sock))) ret = -EINVAL; else - set_local_port_range(net, range); + set_local_port_range(net, range[0], range[1]); } return ret; @@ -733,8 +729,8 @@ static struct ctl_table ipv4_net_table[] = { }, { .procname = "ip_local_port_range", - .maxlen = sizeof(init_net.ipv4.ip_local_ports.range), - .data = &init_net.ipv4.ip_local_ports.range, + .maxlen = 0, + .data = &init_net, .mode = 0644, .proc_handler = ipv4_local_port_range, }, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 53bcc17c91e4..1d6b80145efb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2605,6 +2605,7 @@ void tcp_set_state(struct sock *sk, int state) BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN); BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING); BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV); + BUILD_BUG_ON((int)BPF_TCP_BOUND_INACTIVE != (int)TCP_BOUND_INACTIVE); BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES); /* bpf uapi header bpf.h defines an anonymous enum with values @@ -3368,9 +3369,25 @@ int tcp_set_window_clamp(struct sock *sk, int val) return -EINVAL; tp->window_clamp = 0; } else { - tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ? - SOCK_MIN_RCVBUF / 2 : val; - tp->rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); + u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; + u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? + SOCK_MIN_RCVBUF / 2 : val; + + if (new_window_clamp == old_window_clamp) + return 0; + + tp->window_clamp = new_window_clamp; + if (new_window_clamp < old_window_clamp) { + /* need to apply the reserved mem provisioning only + * when shrinking the window clamp + */ + __tcp_adjust_rcv_ssthresh(sk, tp->window_clamp); + + } else { + new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); + tp->rcv_ssthresh = max(new_rcv_ssthresh, + tp->rcv_ssthresh); + } } return 0; } @@ -3594,6 +3611,10 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, break; case TCP_AO_REPAIR: + if (!tcp_can_repair_sock(sk)) { + err = -EPERM; + break; + } err = tcp_ao_set_repair(sk, optval, optlen); break; #ifdef CONFIG_TCP_AO @@ -4293,6 +4314,8 @@ zerocopy_rcv_out: } #endif case TCP_AO_REPAIR: + if (!tcp_can_repair_sock(sk)) + return -EPERM; return tcp_ao_get_repair(sk, optval, optlen); case TCP_AO_GET_KEYS: case TCP_AO_INFO: { @@ -4563,6 +4586,97 @@ static void __init tcp_init_mem(void) sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; /* 9.37 % */ } +static void __init tcp_struct_check(void) +{ + /* TX read-mostly hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, max_window); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, rcv_ssthresh); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40); + + /* TXRX read-mostly hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_wnd); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, mss_cache); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_cwnd); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31); + + /* RX read-mostly hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rcv_tstamp); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_wl1); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, tlp_high_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rttvar_us); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, retrans_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, advmss); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, urg_data); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, lost); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rtt_min); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, out_of_order_queue); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_ssthresh); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_rx, 69); + + /* TX read-write hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, segs_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, data_segs_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, bytes_sent); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, snd_sml); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_start); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_stat); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, write_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, pushed_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_clock_cache); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_mstamp); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq); + 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); + + /* TXRX read-write hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, window_clamp); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, srtt_us); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, packets_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_up); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 76); + + /* RX read-write hotpath cache lines */ + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, segs_in); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, data_segs_in); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_wup); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, max_packets_out); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, cwnd_usage_seq); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_delivered); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 99); +} + void __init tcp_init(void) { int max_rshare, max_wshare, cnt; @@ -4573,6 +4687,8 @@ void __init tcp_init(void) BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof_field(struct sk_buff, cb)); + tcp_struct_check(); + percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE); diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index c4cd1e09eb6b..87db432c6bb4 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -862,7 +862,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, #endif treq->af_specific = &tcp_request_sock_ipv4_ops; - treq->maclen = 0; + treq->used_tcp_ao = false; if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh) return; @@ -875,7 +875,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, treq->ao_rcv_next = aoh->keyid; treq->ao_keyid = aoh->rnext_keyid; - treq->maclen = tcp_ao_maclen(key); + treq->used_tcp_ao = true; } static enum skb_drop_reason @@ -1112,7 +1112,7 @@ void tcp_ao_connect_init(struct sock *sk) ao_info->current_key = key; if (!ao_info->rnext_key) ao_info->rnext_key = key; - tp->tcp_header_len += tcp_ao_len(key); + tp->tcp_header_len += tcp_ao_len_aligned(key); ao_info->lisn = htonl(tp->write_seq); ao_info->snd_sne = 0; @@ -1358,7 +1358,7 @@ static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key) syn_tcp_option_space -= TCPOLEN_MSS_ALIGNED; syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED; syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED; - if (tcp_ao_len(key) > syn_tcp_option_space) { + if (tcp_ao_len_aligned(key) > syn_tcp_option_space) { err = -EMSGSIZE; goto err_kfree; } @@ -1620,6 +1620,15 @@ static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family, if (!dev || !l3index) return -EINVAL; + if (!bound_dev_if || bound_dev_if != cmd.ifindex) { + /* tcp_ao_established_key() doesn't expect having + * non peer-matching key on an established TCP-AO + * connection. + */ + if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) + return -EINVAL; + } + /* It's still possible to bind after adding keys or even * re-bind to a different dev (with CAP_NET_RAW). * So, no reason to return error here, rather try to be diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bcb55d98004c..df7b13f0e5e0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -202,23 +202,17 @@ static void bpf_skops_established(struct sock *sk, int bpf_op, } #endif -static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, - unsigned int len) +static __cold void tcp_gro_dev_warn(const struct sock *sk, const struct sk_buff *skb, + unsigned int len) { - static bool __once __read_mostly; + struct net_device *dev; - if (!__once) { - struct net_device *dev; - - __once = true; - - rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); - if (!dev || len >= dev->mtu) - pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", - dev ? dev->name : "Unknown driver"); - rcu_read_unlock(); - } + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); + if (!dev || len >= READ_ONCE(dev->mtu)) + pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", + dev ? dev->name : "Unknown driver"); + rcu_read_unlock(); } /* Adapt the MSS value used to make delayed ack decision to the @@ -250,9 +244,8 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); /* Account for possibly-removed options */ - if (unlikely(len > icsk->icsk_ack.rcv_mss + - MAX_TCP_OPTION_SPACE)) - tcp_gro_dev_warn(sk, skb, len); + DO_ONCE_LITE_IF(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE, + tcp_gro_dev_warn, sk, skb, len); /* If the skb has a len of exactly 1*MSS and has the PSH bit * set then it is likely the end of an application write. So * more data may not be arriving soon, and yet the data sender @@ -3871,8 +3864,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * then we can probably ignore it. */ if (before(ack, prior_snd_una)) { + u32 max_window; + + /* do not accept ACK for bytes we never sent. */ + max_window = min_t(u64, tp->max_window, tp->bytes_acked); /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ - if (before(ack, prior_snd_una - tp->max_window)) { + if (before(ack, prior_snd_una - max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) tcp_send_challenge_ack(sk); return -SKB_DROP_REASON_TCP_TOO_OLD_ACK; @@ -4364,6 +4361,23 @@ EXPORT_SYMBOL(tcp_do_parse_auth_options); * up to bandwidth of 18Gigabit/sec. 8) ] */ +/* Estimates max number of increments of remote peer TSval in + * a replay window (based on our current RTO estimation). + */ +static u32 tcp_tsval_replay(const struct sock *sk) +{ + /* If we use usec TS resolution, + * then expect the remote peer to use the same resolution. + */ + if (tcp_sk(sk)->tcp_usec_ts) + return inet_csk(sk)->icsk_rto * (USEC_PER_SEC / HZ); + + /* RFC 7323 recommends a TSval clock between 1ms and 1sec. + * We know that some OS (including old linux) can use 1200 Hz. + */ + return inet_csk(sk)->icsk_rto * 1200 / HZ; +} + static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); @@ -4371,7 +4385,7 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) u32 seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; - return (/* 1. Pure ACK with correct sequence number. */ + return /* 1. Pure ACK with correct sequence number. */ (th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) && /* 2. ... and duplicate ACK. */ @@ -4381,7 +4395,8 @@ static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) !tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) && /* 4. ... and sits in replay window. */ - (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ); + (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= + tcp_tsval_replay(sk); } static inline bool tcp_paws_discard(const struct sock *sk, @@ -7182,11 +7197,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) goto drop_and_release; /* Invalid TCP options */ if (aoh) { - tcp_rsk(req)->maclen = aoh->length - sizeof(struct tcp_ao_hdr); + tcp_rsk(req)->used_tcp_ao = true; tcp_rsk(req)->ao_rcv_next = aoh->keyid; tcp_rsk(req)->ao_keyid = aoh->rnext_keyid; + } else { - tcp_rsk(req)->maclen = 0; + tcp_rsk(req)->used_tcp_ao = false; } #endif tcp_rsk(req)->snt_isn = isn; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 86cc6d36f818..4bac6e319aca 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -696,7 +696,7 @@ static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb, reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) | (aoh->rnext_keyid << 8) | keyid); - arg->iov[0].iov_len += round_up(tcp_ao_len(key), 4); + arg->iov[0].iov_len += tcp_ao_len_aligned(key); reply->doff = arg->iov[0].iov_len / 4; if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1], @@ -984,7 +984,7 @@ static void tcp_v4_send_ack(const struct sock *sk, (tcp_ao_len(key->ao_key) << 16) | (key->ao_key->sndid << 8) | key->rcv_next); - arg.iov[0].iov_len += round_up(tcp_ao_len(key->ao_key), 4); + arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key); rep.th.doff = arg.iov[0].iov_len / 4; tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset], diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a9807eeb311c..9e85f2a0bddd 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -615,7 +615,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, ao_key = treq->af_specific->ao_lookup(sk, req, tcp_rsk(req)->ao_keyid, -1); if (ao_key) - newtp->tcp_header_len += tcp_ao_len(ao_key); + newtp->tcp_header_len += tcp_ao_len_aligned(ao_key); #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index eb13a55d660c..e3167ad96567 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -825,7 +825,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps); if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; - remaining -= tcp_ao_len(key->ao_key); + remaining -= tcp_ao_len_aligned(key->ao_key); } } @@ -915,7 +915,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, ireq->tstamp_ok &= !ireq->sack_ok; } else if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; - remaining -= tcp_ao_len(key->ao_key); + remaining -= tcp_ao_len_aligned(key->ao_key); ireq->tstamp_ok &= !ireq->sack_ok; } @@ -982,7 +982,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb size += TCPOLEN_MD5SIG_ALIGNED; } else if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; - size += tcp_ao_len(key->ao_key); + size += tcp_ao_len_aligned(key->ao_key); } if (likely(tp->rx_opt.tstamp_ok)) { @@ -3293,7 +3293,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (skb_still_in_host_queue(sk, skb)) return -EBUSY; +start: if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { + if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; + TCP_SKB_CB(skb)->seq++; + goto start; + } if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); return -EINVAL; @@ -3720,7 +3726,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, if (tcp_rsk_used_ao(req)) { #ifdef CONFIG_TCP_AO struct tcp_ao_key *ao_key = NULL; - u8 maclen = tcp_rsk(req)->maclen; u8 keyid = tcp_rsk(req)->ao_keyid; ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req), @@ -3730,13 +3735,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, * for another peer-matching key, but the peer has requested * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here. */ - if (unlikely(!ao_key || tcp_ao_maclen(ao_key) != maclen)) { - u8 key_maclen = ao_key ? tcp_ao_maclen(ao_key) : 0; - + if (unlikely(!ao_key)) { rcu_read_unlock(); kfree_skb(skb); - net_warn_ratelimited("TCP-AO: the keyid %u with maclen %u|%u from SYN packet is not present - not sending SYNACK\n", - keyid, maclen, key_maclen); + net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n", + keyid); return NULL; } key.ao_key = ao_key; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3aaea56b5166..2692a7b24c40 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6149,11 +6149,7 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, pmsg->prefix_len = pinfo->prefix_len; pmsg->prefix_type = pinfo->type; pmsg->prefix_pad3 = 0; - pmsg->prefix_flags = 0; - if (pinfo->onlink) - pmsg->prefix_flags |= IF_PREFIX_ONLINK; - if (pinfo->autoconf) - pmsg->prefix_flags |= IF_PREFIX_AUTOCONF; + pmsg->prefix_flags = pinfo->flags; if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix)) goto nla_put_failure; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index cc6a502db39d..fff78496803d 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -60,9 +60,9 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, if (!oif) { if (ipv6_addr_is_multicast(&fl6->daddr)) - oif = np->mcast_oif; + oif = READ_ONCE(np->mcast_oif); else - oif = np->ucast_oif; + oif = READ_ONCE(np->ucast_oif); } fl6->flowi6_oif = oif; @@ -229,7 +229,7 @@ ipv4_connected: } if (!sk->sk_bound_dev_if && (addr_type & IPV6_ADDR_MULTICAST)) - WRITE_ONCE(sk->sk_bound_dev_if, np->mcast_oif); + WRITE_ONCE(sk->sk_bound_dev_if, READ_ONCE(np->mcast_oif)); /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) { diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f62427097126..1635da07285f 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -584,9 +584,9 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, tmp_hdr.icmp6_pointer = htonl(info); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) - fl6.flowi6_oif = np->mcast_oif; + fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; + fl6.flowi6_oif = READ_ONCE(np->ucast_oif); ipcm6_init_sk(&ipc6, sk); ipc6.sockc.mark = mark; @@ -770,9 +770,9 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) np = inet6_sk(sk); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) - fl6.flowi6_oif = np->mcast_oif; + fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; + fl6.flowi6_oif = READ_ONCE(np->ucast_oif); if (ip6_dst_lookup(net, sk, &dst, &fl6)) goto out; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 28b01a068412..7772f42ff2b9 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1511,13 +1511,9 @@ out: if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); -#if RT6_DEBUG >= 2 - if (!pn_leaf) { - WARN_ON(!pn_leaf); + if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; - } -#endif fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 7d661735cb9d..56c3c467f9de 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -210,7 +210,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (optlen < GROUP_FILTER_SIZE(0)) return -EINVAL; - if (optlen > READ_ONCE(sysctl_optmem_max)) + if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max)) return -ENOBUFS; gsf = memdup_sockptr(optval, optlen); @@ -244,7 +244,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (optlen < size0) return -EINVAL; - if (optlen > READ_ONCE(sysctl_optmem_max) - 4) + if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4) return -ENOBUFS; p = kmalloc(optlen + 4, GFP_KERNEL); @@ -509,6 +509,59 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, if (optlen < sizeof(int)) return -EINVAL; return ip6_sock_set_addr_preferences(sk, val); + case IPV6_MULTICAST_IF: + if (sk->sk_type == SOCK_STREAM) + return -ENOPROTOOPT; + if (optlen < sizeof(int)) + return -EINVAL; + if (val) { + struct net_device *dev; + int bound_dev_if, midx; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, val); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + midx = l3mdev_master_ifindex_rcu(dev); + + rcu_read_unlock(); + + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + if (bound_dev_if && + bound_dev_if != val && + (!midx || midx != bound_dev_if)) + return -EINVAL; + } + WRITE_ONCE(np->mcast_oif, val); + return 0; + case IPV6_UNICAST_IF: + { + struct net_device *dev; + int ifindex; + + if (optlen != sizeof(int)) + return -EINVAL; + + ifindex = (__force int)ntohl((__force __be32)val); + if (!ifindex) { + WRITE_ONCE(np->ucast_oif, 0); + return 0; + } + + dev = dev_get_by_index(net, ifindex); + if (!dev) + return -EADDRNOTAVAIL; + dev_put(dev); + + if (READ_ONCE(sk->sk_bound_dev_if)) + return -EINVAL; + + WRITE_ONCE(np->ucast_oif, ifindex); + return 0; + } } if (needs_rtnl) rtnl_lock(); @@ -829,67 +882,6 @@ done: break; } - - case IPV6_UNICAST_IF: - { - struct net_device *dev = NULL; - int ifindex; - - if (optlen != sizeof(int)) - goto e_inval; - - ifindex = (__force int)ntohl((__force __be32)val); - if (ifindex == 0) { - np->ucast_oif = 0; - retv = 0; - break; - } - - dev = dev_get_by_index(net, ifindex); - retv = -EADDRNOTAVAIL; - if (!dev) - break; - dev_put(dev); - - retv = -EINVAL; - if (sk->sk_bound_dev_if) - break; - - np->ucast_oif = ifindex; - retv = 0; - break; - } - - case IPV6_MULTICAST_IF: - if (sk->sk_type == SOCK_STREAM) - break; - if (optlen < sizeof(int)) - goto e_inval; - - if (val) { - struct net_device *dev; - int midx; - - rcu_read_lock(); - - dev = dev_get_by_index_rcu(net, val); - if (!dev) { - rcu_read_unlock(); - retv = -ENODEV; - break; - } - midx = l3mdev_master_ifindex_rcu(dev); - - rcu_read_unlock(); - - if (sk->sk_bound_dev_if && - sk->sk_bound_dev_if != val && - (!midx || midx != sk->sk_bound_dev_if)) - goto e_inval; - } - np->mcast_oif = val; - retv = 0; - break; case IPV6_ADD_MEMBERSHIP: case IPV6_DROP_MEMBERSHIP: { @@ -1161,10 +1153,12 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, sockopt_release_sock(sk); if (!skb) { if (np->rxopt.bits.rxinfo) { + int mcast_oif = READ_ONCE(np->mcast_oif); struct in6_pktinfo src_info; - src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : + + src_info.ipi6_ifindex = mcast_oif ? : np->sticky_pktinfo.ipi6_ifindex; - src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr; + src_info.ipi6_addr = mcast_oif ? sk->sk_v6_daddr : np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxhlim) { @@ -1178,11 +1172,13 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } if (np->rxopt.bits.rxoinfo) { + int mcast_oif = READ_ONCE(np->mcast_oif); struct in6_pktinfo src_info; - src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : + + src_info.ipi6_ifindex = mcast_oif ? : np->sticky_pktinfo.ipi6_ifindex; - src_info.ipi6_addr = np->mcast_oif ? sk->sk_v6_daddr : - np->sticky_pktinfo.ipi6_addr; + src_info.ipi6_addr = mcast_oif ? sk->sk_v6_daddr : + np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { @@ -1359,7 +1355,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, break; case IPV6_MULTICAST_IF: - val = np->mcast_oif; + val = READ_ONCE(np->mcast_oif); break; case IPV6_MULTICAST_ALL: @@ -1367,7 +1363,7 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, break; case IPV6_UNICAST_IF: - val = (__force int)htonl((__u32) np->ucast_oif); + val = (__force int)htonl((__u32) READ_ONCE(np->ucast_oif)); break; case IPV6_MTU_DISCOVER: diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index d2098dd4ceae..ef2059c88955 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -107,9 +107,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) oif = np->sticky_pktinfo.ipi6_ifindex; if (!oif && ipv6_addr_is_multicast(daddr)) - oif = np->mcast_oif; + oif = READ_ONCE(np->mcast_oif); else if (!oif) - oif = np->ucast_oif; + oif = READ_ONCE(np->ucast_oif); addr_type = ipv6_addr_type(daddr); if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || @@ -157,9 +157,9 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rt = (struct rt6_info *) dst; if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) - fl6.flowi6_oif = np->mcast_oif; + fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; + fl6.flowi6_oif = READ_ONCE(np->ucast_oif); pfh.icmph.type = user_icmph.icmp6_type; pfh.icmph.code = user_icmph.icmp6_code; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index dd0a4e73e602..03dbb874c363 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -876,9 +876,9 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) final_p = fl6_update_dst(&fl6, opt, &final); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) - fl6.flowi6_oif = np->mcast_oif; + fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; + fl6.flowi6_oif = READ_ONCE(np->ucast_oif); security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); if (hdrincl) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 43deda49cc52..d1307d77a6f0 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -884,7 +884,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 if (tcp_key_is_md5(key)) tot_len += TCPOLEN_MD5SIG_ALIGNED; if (tcp_key_is_ao(key)) - tot_len += tcp_ao_len(key->ao_key); + tot_len += tcp_ao_len_aligned(key->ao_key); #ifdef CONFIG_MPTCP if (rst && !tcp_key_is_md5(key)) { @@ -1702,7 +1702,7 @@ ipv6_pktoptions: if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo) - np->mcast_oif = tcp_v6_iif(opt_skb); + WRITE_ONCE(np->mcast_oif, tcp_v6_iif(opt_skb)); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) WRITE_ONCE(np->mcast_hops, ipv6_hdr(opt_skb)->hop_limit); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 622b10a549f7..594e3f23c129 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1541,10 +1541,10 @@ do_udp_sendmsg: connected = false; if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr)) { - fl6->flowi6_oif = np->mcast_oif; + fl6->flowi6_oif = READ_ONCE(np->mcast_oif); connected = false; } else if (!fl6->flowi6_oif) - fl6->flowi6_oif = np->ucast_oif; + fl6->flowi6_oif = READ_ONCE(np->ucast_oif); security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index bb373e249237..dd3153966173 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -599,9 +599,9 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) final_p = fl6_update_dst(&fl6, opt, &final); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) - fl6.flowi6_oif = np->mcast_oif; + fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; + fl6.flowi6_oif = READ_ONCE(np->ucast_oif); security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index c9eb52768133..4406b4f8f3b9 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -67,4 +67,6 @@ mac80211-$(CONFIG_MAC80211_RC_MINSTREL) += $(rc80211_minstrel-y) obj-y += tests/ +mac80211-y += wbrf.o + ccflags-y += -DDEBUG diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 606b1b2e4123..e0a4f9eecb2c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1270,7 +1270,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, return -EALREADY; if (params->smps_mode != NL80211_SMPS_OFF) - return -ENOTSUPP; + return -EOPNOTSUPP; link->smps_mode = IEEE80211_SMPS_OFF; @@ -2556,7 +2556,7 @@ static int ieee80211_update_mesh_config(struct wiphy *wiphy, * devices that report signal in dBm. */ if (!ieee80211_hw_check(&sdata->local->hw, SIGNAL_DBM)) - return -ENOTSUPP; + return -EOPNOTSUPP; conf->rssi_threshold = nconf->rssi_threshold; } if (_chg_mesh_attr(NL80211_MESHCONF_HT_OPMODE, mask)) { diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 1d928f29ad6f..ef4c2cebc080 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -507,11 +507,16 @@ static void _ieee80211_change_chanctx(struct ieee80211_local *local, WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef)); + ieee80211_remove_wbrf(local, &ctx->conf.def); + ctx->conf.def = *chandef; /* check if min chanctx also changed */ changed = IEEE80211_CHANCTX_CHANGE_WIDTH | _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) { @@ -667,6 +672,8 @@ static int ieee80211_add_chanctx(struct ieee80211_local *local, lockdep_assert_wiphy(local->hw.wiphy); + ieee80211_add_wbrf(local, &ctx->conf.def); + if (!local->use_chanctx) local->hw.conf.radar_enabled = ctx->conf.radar_enabled; @@ -746,6 +753,8 @@ static void ieee80211_del_chanctx(struct ieee80211_local *local, } ieee80211_recalc_idle(local); + + ieee80211_remove_wbrf(local, &ctx->conf.def); } static void ieee80211_free_chanctx(struct ieee80211_local *local, @@ -858,7 +867,7 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, int ret = 0; if (WARN_ON(sdata->vif.type == NL80211_IFTYPE_NAN)) - return -ENOTSUPP; + return -EOPNOTSUPP; conf = rcu_dereference_protected(link->conf->chanctx_conf, lockdep_is_held(&local->hw.wiphy->mtx)); @@ -1106,7 +1115,7 @@ int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, curr_ctx = ieee80211_link_get_chanctx(link); if (curr_ctx && local->use_chanctx && !local->ops->switch_vif_chanctx) - return -ENOTSUPP; + return -EOPNOTSUPP; new_ctx = ieee80211_find_reservation_chanctx(local, chandef, mode); if (!new_ctx) { diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index b575ae90e57f..74be49191e70 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -497,6 +497,7 @@ static const char *hw_flag_names[] = { FLAG(SUPPORTS_CONC_MON_RX_DECAP), FLAG(DETECTS_COLOR_COLLISION), FLAG(MLO_MCAST_MULTI_LINK_TX), + FLAG(DISALLOW_PUNCTURING), #undef FLAG }; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index f690c385a345..e9219f927875 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -805,7 +805,7 @@ drv_cancel_remain_on_channel(struct ieee80211_local *local, static inline int drv_set_ringparam(struct ieee80211_local *local, u32 tx, u32 rx) { - int ret = -ENOTSUPP; + int ret = -EOPNOTSUPP; might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 8b1e02f2f9ae..8f2b445a5ec3 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -485,7 +485,7 @@ int ieee80211_ibss_csa_beacon(struct ieee80211_sub_if_data *sdata, ifibss->ssid_len, IEEE80211_BSS_TYPE_IBSS, IEEE80211_PRIVACY(ifibss->privacy)); - if (WARN_ON(!cbss)) + if (unlikely(!cbss)) return -EINVAL; rcu_read_lock(); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 84df104f272b..29312f6638a1 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -92,11 +92,14 @@ enum ieee80211_status_data { IEEE80211_STATUS_SUBDATA_MASK = 0xff0, }; -/* - * Keep a station's queues on the active list for deficit accounting purposes - * if it was active or queued during the last 100ms - */ -#define AIRTIME_ACTIVE_DURATION (HZ / 10) +static inline bool +ieee80211_sta_keep_active(struct sta_info *sta, u8 ac) +{ + /* Keep a station's queues on the active list for deficit accounting + * purposes if it was active or queued during the last 100ms. + */ + return time_before_eq(jiffies, sta->airtime[ac].last_active + HZ / 10); +} struct ieee80211_bss { u32 device_ts_beacon, device_ts_presp; @@ -1559,6 +1562,8 @@ struct ieee80211_local { /* extended capabilities provided by mac80211 */ u8 ext_capa[8]; + + bool wbrf_supported; }; static inline struct ieee80211_sub_if_data * @@ -2600,4 +2605,9 @@ 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_check_wbrf_support(struct ieee80211_local *local); +void ieee80211_add_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef); +void ieee80211_remove_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef); + #endif /* IEEE80211_I_H */ diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 033a5261ac3a..f2ece7793573 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1405,6 +1405,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) debugfs_hw_add(local); rate_control_add_debugfs(local); + ieee80211_check_wbrf_support(local); + rtnl_lock(); wiphy_lock(hw->wiphy); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 775d52561c54..024f48db6b05 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -151,7 +151,7 @@ static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags, break; default: kfree_skb(skb); - return -ENOTSUPP; + return -EOPNOTSUPP; } *pos++ = ie_len; *pos++ = flags; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 8a3f44ce3e04..735edde1bd81 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -676,10 +676,10 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, if (ether_addr_equal(dst, sdata->vif.addr)) /* never add ourselves as neighbours */ - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); if (is_multicast_ether_addr(dst)) - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); if (atomic_add_unless(&sdata->u.mesh.mpaths, 1, MESH_MAX_MPATHS) == 0) return ERR_PTR(-ENOSPC); @@ -719,10 +719,10 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, if (ether_addr_equal(dst, sdata->vif.addr)) /* never add ourselves as neighbours */ - return -ENOTSUPP; + return -EOPNOTSUPP; if (is_multicast_ether_addr(dst)) - return -ENOTSUPP; + return -EOPNOTSUPP; new_mpath = mesh_path_new(sdata, dst, GFP_ATOMIC); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 887b496f2b81..a693ca2cf8cd 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -135,6 +135,7 @@ ieee80211_handle_puncturing_bitmap(struct ieee80211_link_data *link, u16 bitmap, u64 *changed) { struct cfg80211_chan_def *chandef = &link->conf->chandef; + struct ieee80211_local *local = link->sdata->local; u16 extracted; u64 _changed = 0; @@ -147,7 +148,9 @@ ieee80211_handle_puncturing_bitmap(struct ieee80211_link_data *link, bitmap); if (cfg80211_valid_disable_subchannel_bitmap(&bitmap, - chandef)) + chandef) && + !(bitmap && ieee80211_hw_check(&local->hw, + DISALLOW_PUNCTURING))) break; link->u.mgd.conn_flags |= ieee80211_chandef_downgrade(chandef); @@ -1382,7 +1385,7 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) struct ieee80211_mgmt *mgmt; u8 *pos, qos_info, *ie_start; size_t offset, noffset; - u16 capab = WLAN_CAPABILITY_ESS, link_capab; + u16 capab = 0, link_capab; __le16 listen_int; struct element *ext_capa = NULL; enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); @@ -1529,6 +1532,17 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) *pos++ = assoc_data->ssid_len; memcpy(pos, assoc_data->ssid, assoc_data->ssid_len); + /* + * This bit is technically reserved, so it shouldn't matter for either + * the AP or us, but it also means we shouldn't set it. However, we've + * always set it in the past, and apparently some EHT APs check that + * we don't set it. To avoid interoperability issues with old APs that + * 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) + capab |= WLAN_CAPABILITY_ESS; + /* add the elements for the assoc (main) link */ link_capab = capab; offset = ieee80211_assoc_link_elems(sdata, skb, &link_capab, @@ -5682,6 +5696,7 @@ 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) && @@ -5713,6 +5728,9 @@ static bool ieee80211_config_puncturing(struct ieee80211_link_data *link, return false; } + if (bitmap && ieee80211_hw_check(&local->hw, DISALLOW_PUNCTURING)) + return false; + ieee80211_handle_puncturing_bitmap(link, eht_oper, bitmap, changed); return true; } @@ -7584,7 +7602,8 @@ ieee80211_setup_assoc_link(struct ieee80211_sub_if_data *sdata, bitmap = get_unaligned_le16(disable_subchannel_bitmap); if (cfg80211_valid_disable_subchannel_bitmap(&bitmap, - &link->conf->chandef)) + &link->conf->chandef) && + !(bitmap && ieee80211_hw_check(&local->hw, DISALLOW_PUNCTURING))) ieee80211_handle_puncturing_bitmap(link, eht_oper, bitmap, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 64352e4e6d00..bbfdcb0ade72 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -920,7 +920,7 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) * Drivers always need to pass packets that are aligned to two-byte boundaries * to the stack. * - * Additionally, should, if possible, align the payload data in a way that + * Additionally, they should, if possible, align the payload data in a way that * guarantees that the contained IP header is aligned to a four-byte * boundary. In the case of regular frames, this simply means aligning the * payload to a four-byte boundary (because either the IP header is directly @@ -936,7 +936,7 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) * subframe to a length that is a multiple of four. * * Padding like Atheros hardware adds which is between the 802.11 header and - * the payload is not supported, the driver is required to move the 802.11 + * the payload is not supported; the driver is required to move the 802.11 * header to be directly in front of the payload in that case. */ static void ieee80211_verify_alignment(struct ieee80211_rx_data *rx) diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 1d98877647d8..645355e5f1bc 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -1289,7 +1289,7 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, iebufsz = local->scan_ies_len + req->ie_len; if (!local->ops->sched_scan_start) - return -ENOTSUPP; + return -EOPNOTSUPP; for (i = 0; i < NUM_NL80211_BANDS; i++) { if (local->hw.wiphy->bands[i]) { @@ -1354,7 +1354,7 @@ int ieee80211_request_sched_scan_stop(struct ieee80211_local *local) lockdep_assert_wiphy(local->hw.wiphy); if (!local->ops->sched_scan_stop) - return -ENOTSUPP; + return -EOPNOTSUPP; /* We don't want to restart sched scan anymore. */ RCU_INIT_POINTER(local->sched_scan_req, NULL); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 0ba613dd1cc4..bf1adcd96b41 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -40,7 +40,7 @@ * either sta_info_insert() or sta_info_insert_rcu(); only in the latter * case (which acquires an rcu read section but must not be called from * within one) will the pointer still be valid after the call. Note that - * the caller may not do much with the STA info before inserting it, in + * the caller may not do much with the STA info before inserting it; in * particular, it may not start any mesh peer link management or add * encryption keys. * @@ -58,7 +58,7 @@ * In order to remove a STA info structure, various sta_info_destroy_*() * calls are available. * - * There is no concept of ownership on a STA entry, each structure is + * There is no concept of ownership on a STA entry; each structure is * owned by the global hash table/list until it is removed. All users of * the structure need to be RCU protected so that the structure won't be * freed before they are done using it. @@ -2268,7 +2268,6 @@ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, struct ieee80211_local *local = sta->sdata->local; u8 ac = ieee80211_ac_from_tid(tid); u32 airtime = 0; - u32 diff; if (sta->local->airtime_flags & AIRTIME_USE_TX) airtime += tx_airtime; @@ -2279,8 +2278,7 @@ void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, sta->airtime[ac].tx_airtime += tx_airtime; sta->airtime[ac].rx_airtime += rx_airtime; - diff = (u32)jiffies - sta->airtime[ac].last_active; - if (diff <= AIRTIME_ACTIVE_DURATION) + if (ieee80211_sta_keep_active(sta, ac)) sta->airtime[ac].deficit -= airtime; spin_unlock_bh(&local->active_txq_lock[ac]); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 7acf2223e47a..5ef1554f991f 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -138,7 +138,7 @@ enum ieee80211_agg_stop_reason { struct airtime_info { u64 rx_airtime; u64 tx_airtime; - u32 last_active; + unsigned long last_active; s32 deficit; atomic_t aql_tx_pending; /* Estimated airtime for frames pending */ u32 aql_limit_low; diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 05a7dff69fe9..49730b424141 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -1001,7 +1001,7 @@ ieee80211_tdls_build_mgmt_packet_data(struct ieee80211_sub_if_data *sdata, skb); break; default: - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; break; } @@ -1071,7 +1071,7 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev, /* any value is ok */ break; default: - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; break; } @@ -1177,7 +1177,7 @@ ieee80211_tdls_mgmt_setup(struct wiphy *wiphy, struct net_device *dev, smps_mode != IEEE80211_SMPS_OFF) { tdls_dbg(sdata, "Aborting TDLS setup due to SMPS mode %d\n", smps_mode); - return -ENOTSUPP; + return -EOPNOTSUPP; } lockdep_assert_wiphy(local->hw.wiphy); @@ -1289,7 +1289,7 @@ int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev, int ret; if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) - return -ENOTSUPP; + return -EOPNOTSUPP; /* make sure we are in managed mode, and associated */ if (sdata->vif.type != NL80211_IFTYPE_STATION || @@ -1446,7 +1446,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, lockdep_assert_wiphy(local->hw.wiphy); if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EINVAL; @@ -1459,7 +1459,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, case NL80211_TDLS_SETUP: case NL80211_TDLS_DISCOVERY_REQ: /* We don't support in-driver setup/teardown/discovery */ - return -ENOTSUPP; + return -EOPNOTSUPP; } /* protect possible bss_conf changes and avoid concurrency in @@ -1510,7 +1510,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, return ret; break; default: - return -ENOTSUPP; + return -EOPNOTSUPP; } if (ether_addr_equal(sdata->u.mgd.tdls_peer, peer)) { @@ -1673,7 +1673,7 @@ ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev, if (!test_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH)) { tdls_dbg(sdata, "TDLS channel switch unsupported by %pM\n", addr); - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; goto out; } @@ -1993,7 +1993,7 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, if (!sta->sta.deflink.ht_cap.ht_supported && elems->sec_chan_offs && elems->sec_chan_offs->sec_chan_offs) { tdls_dbg(sdata, "TDLS chan switch - wide chan unsupported\n"); - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; goto out; } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index ed4fdf655343..314998fdb1a5 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4013,14 +4013,13 @@ ieee80211_txq_set_active(struct txq_info *txqi) return; sta = container_of(txqi->txq.sta, struct sta_info, sta); - sta->airtime[txqi->txq.ac].last_active = (u32)jiffies; + sta->airtime[txqi->txq.ac].last_active = jiffies; } static bool ieee80211_txq_keep_active(struct txq_info *txqi) { struct sta_info *sta; - u32 diff; if (!txqi->txq.sta) return false; @@ -4029,9 +4028,7 @@ ieee80211_txq_keep_active(struct txq_info *txqi) if (ieee80211_sta_deficit(sta, txqi->txq.ac) >= 0) return false; - diff = (u32)jiffies - sta->airtime[txqi->txq.ac].last_active; - - return diff <= AIRTIME_ACTIVE_DURATION; + return ieee80211_sta_keep_active(sta, txqi->txq.ac); } struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac) diff --git a/net/mac80211/wbrf.c b/net/mac80211/wbrf.c new file mode 100644 index 000000000000..a05c5b971789 --- /dev/null +++ b/net/mac80211/wbrf.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Wifi Band Exclusion Interface for WLAN + * Copyright (C) 2023 Advanced Micro Devices + * + */ + +#include <linux/acpi_amd_wbrf.h> +#include <linux/units.h> +#include <net/cfg80211.h> +#include "ieee80211_i.h" + +void ieee80211_check_wbrf_support(struct ieee80211_local *local) +{ + struct wiphy *wiphy = local->hw.wiphy; + struct device *dev; + + if (!wiphy) + return; + + dev = wiphy->dev.parent; + if (!dev) + return; + + local->wbrf_supported = acpi_amd_wbrf_supported_producer(dev); + dev_dbg(dev, "WBRF is %s supported\n", + local->wbrf_supported ? "" : "not"); +} + +static void get_chan_freq_boundary(u32 center_freq, u32 bandwidth, u64 *start, u64 *end) +{ + bandwidth *= KHZ_PER_MHZ; + center_freq *= KHZ_PER_MHZ; + + *start = center_freq - bandwidth / 2; + *end = center_freq + bandwidth / 2; + + /* Frequency in Hz is expected */ + *start = *start * HZ_PER_KHZ; + *end = *end * HZ_PER_KHZ; +} + +static void get_ranges_from_chandef(struct cfg80211_chan_def *chandef, + struct wbrf_ranges_in_out *ranges_in) +{ + u64 start_freq1, end_freq1; + u64 start_freq2, end_freq2; + int bandwidth; + + bandwidth = nl80211_chan_width_to_mhz(chandef->width); + + get_chan_freq_boundary(chandef->center_freq1, bandwidth, &start_freq1, &end_freq1); + + ranges_in->band_list[0].start = start_freq1; + ranges_in->band_list[0].end = end_freq1; + ranges_in->num_of_ranges = 1; + + if (chandef->width == NL80211_CHAN_WIDTH_80P80) { + get_chan_freq_boundary(chandef->center_freq2, bandwidth, &start_freq2, &end_freq2); + + ranges_in->band_list[1].start = start_freq2; + ranges_in->band_list[1].end = end_freq2; + ranges_in->num_of_ranges++; + } +} + +void ieee80211_add_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef) +{ + struct wbrf_ranges_in_out ranges_in = {0}; + struct device *dev; + + if (!local->wbrf_supported) + return; + + dev = local->hw.wiphy->dev.parent; + + get_ranges_from_chandef(chandef, &ranges_in); + + acpi_amd_wbrf_add_remove(dev, WBRF_RECORD_ADD, &ranges_in); +} + +void ieee80211_remove_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef) +{ + struct wbrf_ranges_in_out ranges_in = {0}; + struct device *dev; + + if (!local->wbrf_supported) + return; + + dev = local->hw.wiphy->dev.parent; + + get_ranges_from_chandef(chandef, &ranges_in); + + acpi_amd_wbrf_add_remove(dev, WBRF_RECORD_REMOVE, &ranges_in); +} diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c index a2325e70ddab..670da7822e6c 100644 --- a/net/mptcp/mptcp_pm_gen.c +++ b/net/mptcp/mptcp_pm_gen.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/mptcp.yaml */ +/* Documentation/netlink/specs/mptcp_pm.yaml */ /* YNL-GEN kernel source */ #include <net/netlink.h> diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h index 10579d184587..ac9fc7225b6a 100644 --- a/net/mptcp/mptcp_pm_gen.h +++ b/net/mptcp/mptcp_pm_gen.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ -/* Documentation/netlink/specs/mptcp.yaml */ +/* Documentation/netlink/specs/mptcp_pm.yaml */ /* YNL-GEN kernel header */ #ifndef _LINUX_MPTCP_PM_GEN_H diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index eaf9f2ed0067..be74c0906dda 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1365,7 +1365,7 @@ static int set_mcast_if(struct sock *sk, struct net_device *dev) struct ipv6_pinfo *np = inet6_sk(sk); /* IPV6_MULTICAST_IF */ - np->mcast_oif = dev->ifindex; + WRITE_ONCE(np->mcast_oif, dev->ifindex); } #endif release_sock(sk); diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index 1969facac91c..5257d5e7eb09 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -31,7 +31,7 @@ struct bpf_nf_link { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) static const struct nf_defrag_hook * get_proto_defrag_hook(struct bpf_nf_link *link, - const struct nf_defrag_hook __rcu *global_hook, + const struct nf_defrag_hook __rcu **ptr_global_hook, const char *mod) { const struct nf_defrag_hook *hook; @@ -39,7 +39,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link, /* RCU protects us from races against module unloading */ rcu_read_lock(); - hook = rcu_dereference(global_hook); + hook = rcu_dereference(*ptr_global_hook); if (!hook) { rcu_read_unlock(); err = request_module(mod); @@ -47,7 +47,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link, return ERR_PTR(err < 0 ? err : -EINVAL); rcu_read_lock(); - hook = rcu_dereference(global_hook); + hook = rcu_dereference(*ptr_global_hook); } if (hook && try_module_get(hook->owner)) { @@ -78,7 +78,7 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link) switch (link->hook_ops.pf) { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) case NFPROTO_IPV4: - hook = get_proto_defrag_hook(link, nf_defrag_v4_hook, "nf_defrag_ipv4"); + hook = get_proto_defrag_hook(link, &nf_defrag_v4_hook, "nf_defrag_ipv4"); if (IS_ERR(hook)) return PTR_ERR(hook); @@ -87,7 +87,7 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link) #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) case NFPROTO_IPV6: - hook = get_proto_defrag_hook(link, nf_defrag_v6_hook, "nf_defrag_ipv6"); + hook = get_proto_defrag_hook(link, &nf_defrag_v6_hook, "nf_defrag_ipv6"); if (IS_ERR(hook)) return PTR_ERR(hook); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c0a42989b982..c5c17c6e80ed 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -803,7 +803,7 @@ static struct nft_table *nft_table_lookup(const struct net *net, static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, - u8 genmask, u32 nlpid) + int family, u8 genmask, u32 nlpid) { struct nftables_pernet *nft_net; struct nft_table *table; @@ -811,6 +811,7 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, nft_net = nft_pernet(net); list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && + table->family == family && nft_active_genmask(table, genmask)) { if (nft_table_has_owner(table) && nlpid && table->nlpid != nlpid) @@ -1544,7 +1545,7 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_TABLE_HANDLE]) { attr = nla[NFTA_TABLE_HANDLE]; - table = nft_table_lookup_byhandle(net, attr, genmask, + table = nft_table_lookup_byhandle(net, attr, family, genmask, NETLINK_CB(skb).portid); } else { attr = nla[NFTA_TABLE_NAME]; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index b18a79039125..c09dba57354c 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -280,10 +280,15 @@ static int nft_dynset_init(const struct nft_ctx *ctx, priv->expr_array[i] = dynset_expr; priv->num_exprs++; - if (set->num_exprs && - dynset_expr->ops != set->exprs[i]->ops) { - err = -EOPNOTSUPP; - goto err_expr_free; + if (set->num_exprs) { + if (i >= set->num_exprs) { + err = -EINVAL; + goto err_expr_free; + } + if (dynset_expr->ops != set->exprs[i]->ops) { + err = -EOPNOTSUPP; + goto err_expr_free; + } } i++; } diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 3fbaa7bf41f9..6eb571d0c3fd 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -214,7 +214,7 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr, offset = i + priv->offset; if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = 1; + nft_reg_store8(dest, 1); } else { if (priv->len % NFT_REG32_SIZE) dest[priv->len / NFT_REG32_SIZE] = 0; @@ -461,7 +461,7 @@ static void nft_exthdr_dccp_eval(const struct nft_expr *expr, type = bufp[0]; if (type == priv->type) { - *dest = 1; + nft_reg_store8(dest, 1); return; } diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 1bfe258018da..37cfe6dd712d 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -145,11 +145,15 @@ void nft_fib_store_result(void *reg, const struct nft_fib *priv, switch (priv->result) { case NFT_FIB_RESULT_OIF: index = dev ? dev->ifindex : 0; - *dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index; + if (priv->flags & NFTA_FIB_F_PRESENT) + nft_reg_store8(dreg, !!index); + else + *dreg = index; + break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_PRESENT) - *dreg = !!dev; + nft_reg_store8(dreg, !!dev); else strscpy_pad(reg, dev ? dev->name : "", IFNAMSIZ); break; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 701977af3ee8..7252fcdae349 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2043,6 +2043,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, e = f->mt[r].e; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + iter->err = iter->fn(ctx, set, iter, &e->priv); if (iter->err < 0) goto out; diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index e85ce69924ae..50332888c8d2 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -76,18 +76,23 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) */ return false; - filp = sk->sk_socket->file; - if (filp == NULL) + read_lock_bh(&sk->sk_callback_lock); + filp = sk->sk_socket ? sk->sk_socket->file : NULL; + if (filp == NULL) { + read_unlock_bh(&sk->sk_callback_lock); return ((info->match ^ info->invert) & (XT_OWNER_UID | XT_OWNER_GID)) == 0; + } if (info->match & XT_OWNER_UID) { kuid_t uid_min = make_kuid(net->user_ns, info->uid_min); kuid_t uid_max = make_kuid(net->user_ns, info->uid_max); if ((uid_gte(filp->f_cred->fsuid, uid_min) && uid_lte(filp->f_cred->fsuid, uid_max)) ^ - !(info->invert & XT_OWNER_UID)) + !(info->invert & XT_OWNER_UID)) { + read_unlock_bh(&sk->sk_callback_lock); return false; + } } if (info->match & XT_OWNER_GID) { @@ -112,10 +117,13 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) } } - if (match ^ !(info->invert & XT_OWNER_GID)) + if (match ^ !(info->invert & XT_OWNER_GID)) { + read_unlock_bh(&sk->sk_callback_lock); return false; + } } + read_unlock_bh(&sk->sk_callback_lock); return true; } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 92ef5ed2e7b0..9c7ffd10df2a 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1691,6 +1691,9 @@ static int genl_bind(struct net *net, int group) if ((grp->flags & GENL_UNS_ADMIN_PERM) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) ret = -EPERM; + if (grp->cap_sys_admin && + !ns_capable(net->user_ns, CAP_SYS_ADMIN)) + ret = -EPERM; break; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a84e00b5904b..5f1757a32842 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2121,13 +2121,13 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { + enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; - bool is_drop_n_account = false; if (skb->pkt_type == PACKET_LOOPBACK) goto drop; @@ -2217,9 +2217,9 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, return 0; drop_n_acct: - is_drop_n_account = true; atomic_inc(&po->tp_drops); atomic_inc(&sk->sk_drops); + drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { @@ -2227,16 +2227,14 @@ drop_n_restore: skb->len = skb_len; } drop: - if (!is_drop_n_account) - consume_skb(skb); - else - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; } static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { + enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk; struct packet_sock *po; struct sockaddr_ll *sll; @@ -2250,7 +2248,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; - bool is_drop_n_account = false; unsigned int slot_id = 0; int vnet_hdr_sz = 0; @@ -2498,19 +2495,16 @@ drop_n_restore: skb->len = skb_len; } drop: - if (!is_drop_n_account) - consume_skb(skb); - else - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; drop_n_account: spin_unlock(&sk->sk_receive_queue.lock); atomic_inc(&po->tp_drops); - is_drop_n_account = true; + drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); - kfree_skb(copy_skb); + kfree_skb_reason(copy_skb, drop_reason); goto drop_n_restore; } @@ -4300,7 +4294,7 @@ static void packet_mm_open(struct vm_area_struct *vma) struct sock *sk = sock->sk; if (sk) - atomic_inc(&pkt_sk(sk)->mapped); + atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) @@ -4310,7 +4304,7 @@ static void packet_mm_close(struct vm_area_struct *vma) struct sock *sk = sock->sk; if (sk) - atomic_dec(&pkt_sk(sk)->mapped); + atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { @@ -4405,7 +4399,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EBUSY; if (!closing) { - if (atomic_read(&po->mapped)) + if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; @@ -4508,7 +4502,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EBUSY; mutex_lock(&po->pg_vec_lock); - if (closing || atomic_read(&po->mapped) == 0) { + if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); @@ -4526,9 +4520,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); - if (atomic_read(&po->mapped)) - pr_err("packet_mmap: vma is busy: %d\n", - atomic_read(&po->mapped)); + if (atomic_long_read(&po->mapped)) + pr_err("packet_mmap: vma is busy: %ld\n", + atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); @@ -4606,7 +4600,7 @@ static int packet_mmap(struct file *file, struct socket *sock, } } - atomic_inc(&po->mapped); + atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; diff --git a/net/packet/internal.h b/net/packet/internal.h index d29c94c45159..d5d70712007a 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -122,7 +122,7 @@ struct packet_sock { __be16 num; struct packet_rollover *rollover; struct packet_mclist *mclist; - atomic_t mapped; + atomic_long_t mapped; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; diff --git a/net/psample/psample.c b/net/psample/psample.c index 81a794e36f53..c34e902855db 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -31,7 +31,8 @@ enum psample_nl_multicast_groups { static const struct genl_multicast_group psample_nl_mcgrps[] = { [PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME }, - [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME }, + [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME, + .flags = GENL_UNS_ADMIN_PERM }, }; static struct genl_family psample_nl_family __ro_after_init; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 53b3535a1e4a..05008ce5c421 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -165,7 +165,7 @@ int rds_tcp_accept_one(struct socket *sock) struct ipv6_pinfo *inet6; inet6 = inet6_sk(new_sock->sk); - dev_if = inet6->mcast_oif; + dev_if = READ_ONCE(inet6->mcast_oif); } else { dev_if = new_sock->sk->sk_bound_dev_if; } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 0cc5a4e19900..ecb91ad4ce63 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1315,9 +1315,11 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case TIOCINQ: { struct sk_buff *skb; long amount = 0L; - /* These two are safe on a single CPU system as only user tasks fiddle here */ + + spin_lock_irq(&sk->sk_receive_queue.lock); if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) amount = skb->len; + spin_unlock_irq(&sk->sk_receive_queue.lock); return put_user(amount, (unsigned int __user *) argp); } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index c39252d61ebb..3a7770eff52d 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -816,6 +816,9 @@ EXPORT_SYMBOL(tcf_idr_cleanup); * its reference and bind counters, and return 1. Otherwise insert temporary * error pointer (to prevent concurrent users from inserting actions with same * index) and return 0. + * + * May return -EAGAIN for binding actions in case of a parallel add/delete on + * the requested index. */ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, @@ -824,43 +827,61 @@ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tcf_idrinfo *idrinfo = tn->idrinfo; struct tc_action *p; int ret; + u32 max; -again: - mutex_lock(&idrinfo->lock); if (*index) { +again: + rcu_read_lock(); p = idr_find(&idrinfo->action_idr, *index); + if (IS_ERR(p)) { /* This means that another process allocated * index but did not assign the pointer yet. */ - mutex_unlock(&idrinfo->lock); + rcu_read_unlock(); goto again; } - if (p) { - refcount_inc(&p->tcfa_refcnt); - if (bind) - atomic_inc(&p->tcfa_bindcnt); - *a = p; - ret = 1; - } else { - *a = NULL; - ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index, - *index, GFP_KERNEL); - if (!ret) - idr_replace(&idrinfo->action_idr, - ERR_PTR(-EBUSY), *index); + if (!p) { + /* Empty slot, try to allocate it */ + max = *index; + rcu_read_unlock(); + goto new; + } + + if (!refcount_inc_not_zero(&p->tcfa_refcnt)) { + /* Action was deleted in parallel */ + rcu_read_unlock(); + return -EAGAIN; } + + if (bind) + atomic_inc(&p->tcfa_bindcnt); + *a = p; + + rcu_read_unlock(); + + return 1; } else { + /* Find a slot */ *index = 1; - *a = NULL; - ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index, - UINT_MAX, GFP_KERNEL); - if (!ret) - idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY), - *index); + max = UINT_MAX; } + +new: + *a = NULL; + + mutex_lock(&idrinfo->lock); + ret = idr_alloc_u32(&idrinfo->action_idr, ERR_PTR(-EBUSY), index, max, + GFP_KERNEL); mutex_unlock(&idrinfo->lock); + + /* N binds raced for action allocation, + * retry for all the ones that failed. + */ + if (ret == -ENOSPC && *index == max) + ret = -EAGAIN; + return ret; } EXPORT_SYMBOL(tcf_idr_check_alloc); @@ -1118,8 +1139,7 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) struct tc_action *a; int ret = 0, i; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { - a = actions[i]; + tcf_act_for_each_action(i, a, actions) { actions[i] = NULL; ops = a->ops; ret = __tcf_idr_release(a, bind, true); @@ -1136,18 +1156,29 @@ static int tcf_action_put(struct tc_action *p) return __tcf_action_put(p, false); } -/* Put all actions in this array, skip those NULL's. */ static void tcf_action_put_many(struct tc_action *actions[]) { + struct tc_action *a; + int i; + + tcf_act_for_each_action(i, a, actions) { + const struct tc_action_ops *ops = a->ops; + if (tcf_action_put(a)) + module_put(ops->owner); + } +} + +static void tca_put_bound_many(struct tc_action *actions[], int init_res[]) +{ + struct tc_action *a; int i; - for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { - struct tc_action *a = actions[i]; - const struct tc_action_ops *ops; + tcf_act_for_each_action(i, a, actions) { + const struct tc_action_ops *ops = a->ops; - if (!a) + if (init_res[i] == ACT_P_CREATED) continue; - ops = a->ops; + if (tcf_action_put(a)) module_put(ops->owner); } @@ -1211,8 +1242,7 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int err = -EINVAL, i; struct nlattr *nest; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { - a = actions[i]; + tcf_act_for_each_action(i, a, actions) { nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; @@ -1274,21 +1304,20 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { [TCA_ACT_HW_STATS] = NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY), }; -void tcf_idr_insert_many(struct tc_action *actions[]) +void tcf_idr_insert_many(struct tc_action *actions[], int init_res[]) { + struct tc_action *a; int i; - for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { - struct tc_action *a = actions[i]; + tcf_act_for_each_action(i, a, actions) { struct tcf_idrinfo *idrinfo; - if (!a) + if (init_res[i] == 0) /* Bound */ continue; + idrinfo = a->idrinfo; mutex_lock(&idrinfo->lock); - /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if - * it is just created, otherwise this is just a nop. - */ + /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ idr_replace(&idrinfo->action_idr, a, a->tcfa_index); mutex_unlock(&idrinfo->lock); } @@ -1488,7 +1517,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, /* We have to commit them all together, because if any error happened in * between, we could not handle the failure gracefully. */ - tcf_idr_insert_many(actions); + tcf_idr_insert_many(actions, init_res); *attr_size = tcf_action_full_attrs_size(sz); err = i - 1; @@ -1497,10 +1526,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, err: tcf_action_destroy(actions, flags & TCA_ACT_FLAGS_BIND); err_mod: - for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { - if (ops[i]) - module_put(ops[i]->owner); - } + for (i = 0; i < TCA_ACT_MAX_PRIO && ops[i]; i++) + module_put(ops[i]->owner); return err; } @@ -1753,10 +1780,10 @@ err_out: static int tcf_action_delete(struct net *net, struct tc_action *actions[]) { + struct tc_action *a; int i; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { - struct tc_action *a = actions[i]; + tcf_act_for_each_action(i, a, actions) { const struct tc_action_ops *ops = a->ops; /* Actions can be deleted concurrently so we must save their * type and id to search again after reference is released. @@ -1768,7 +1795,7 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) if (tcf_action_put(a)) { /* last reference, action was deleted concurrently */ module_put(ops->owner); - } else { + } else { int ret; /* now do the delete */ @@ -1780,31 +1807,45 @@ static int tcf_action_delete(struct net *net, struct tc_action *actions[]) return 0; } -static int -tcf_reoffload_del_notify(struct net *net, struct tc_action *action) +static struct sk_buff *tcf_reoffload_del_notify_msg(struct net *net, + struct tc_action *action) { size_t attr_size = tcf_action_fill_size(action); struct tc_action *actions[TCA_ACT_MAX_PRIO] = { [0] = action, }; - const struct tc_action_ops *ops = action->ops; struct sk_buff *skb; - int ret; - skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size, - GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) - return -ENOBUFS; + return ERR_PTR(-ENOBUFS); if (tca_get_fill(skb, actions, 0, 0, 0, RTM_DELACTION, 0, 1, NULL) <= 0) { kfree_skb(skb); - return -EINVAL; + return ERR_PTR(-EINVAL); + } + + return skb; +} + +static int tcf_reoffload_del_notify(struct net *net, struct tc_action *action) +{ + const struct tc_action_ops *ops = action->ops; + struct sk_buff *skb; + int ret; + + if (!rtnl_notify_needed(net, 0, RTNLGRP_TC)) { + skb = NULL; + } else { + skb = tcf_reoffload_del_notify_msg(net, action); + if (IS_ERR(skb)) + return PTR_ERR(skb); } ret = tcf_idr_release_unsafe(action); if (ret == ACT_P_DELETED) { module_put(ops->owner); - ret = rtnetlink_send(skb, net, 0, RTNLGRP_TC, 0); + ret = rtnetlink_maybe_send(skb, net, 0, RTNLGRP_TC, 0); } else { kfree_skb(skb); } @@ -1870,23 +1911,41 @@ int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb, return 0; } -static int -tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], - u32 portid, size_t attr_size, struct netlink_ext_ack *extack) +static struct sk_buff *tcf_del_notify_msg(struct net *net, struct nlmsghdr *n, + struct tc_action *actions[], + u32 portid, size_t attr_size, + struct netlink_ext_ack *extack) { - int ret; struct sk_buff *skb; - skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size, - GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) - return -ENOBUFS; + return ERR_PTR(-ENOBUFS); if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION, 0, 2, extack) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes"); kfree_skb(skb); - return -EINVAL; + return ERR_PTR(-EINVAL); + } + + return skb; +} + +static int tcf_del_notify(struct net *net, struct nlmsghdr *n, + struct tc_action *actions[], u32 portid, + size_t attr_size, struct netlink_ext_ack *extack) +{ + struct sk_buff *skb; + int ret; + + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) { + skb = NULL; + } else { + skb = tcf_del_notify_msg(net, n, actions, portid, attr_size, + extack); + if (IS_ERR(skb)) + return PTR_ERR(skb); } /* now do the delete */ @@ -1897,9 +1956,8 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], return ret; } - ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); - return ret; + return rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } static int @@ -1950,26 +2008,44 @@ err: return ret; } -static int -tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], - u32 portid, size_t attr_size, struct netlink_ext_ack *extack) +static struct sk_buff *tcf_add_notify_msg(struct net *net, struct nlmsghdr *n, + struct tc_action *actions[], + u32 portid, size_t attr_size, + struct netlink_ext_ack *extack) { struct sk_buff *skb; - skb = alloc_skb(attr_size <= NLMSG_GOODSIZE ? NLMSG_GOODSIZE : attr_size, - GFP_KERNEL); + skb = alloc_skb(max(attr_size, NLMSG_GOODSIZE), GFP_KERNEL); if (!skb) - return -ENOBUFS; + return ERR_PTR(-ENOBUFS); if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags, RTM_NEWACTION, 0, 0, extack) <= 0) { NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action"); kfree_skb(skb); - return -EINVAL; + return ERR_PTR(-EINVAL); } - return rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); + return skb; +} + +static int tcf_add_notify(struct net *net, struct nlmsghdr *n, + struct tc_action *actions[], u32 portid, + size_t attr_size, struct netlink_ext_ack *extack) +{ + struct sk_buff *skb; + + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) { + skb = NULL; + } else { + skb = tcf_add_notify_msg(net, n, actions, portid, attr_size, + extack); + if (IS_ERR(skb)) + return PTR_ERR(skb); + } + + return rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } static int tcf_action_add(struct net *net, struct nlattr *nla, @@ -1977,7 +2053,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { size_t attr_size = 0; - int loop, ret, i; + int loop, ret; struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; int init_res[TCA_ACT_MAX_PRIO] = {}; @@ -1990,13 +2066,11 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, if (ret < 0) return ret; + ret = tcf_add_notify(net, n, actions, portid, attr_size, extack); - /* only put existing actions */ - for (i = 0; i < TCA_ACT_MAX_PRIO; i++) - if (init_res[i] == ACT_P_CREATED) - actions[i] = NULL; - tcf_action_put_many(actions); + /* only put bound actions */ + tca_put_bound_many(actions, init_res); return ret; } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b3f4a503ee2b..f69c47945175 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -286,9 +286,31 @@ static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); } +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_get(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_get_ref(ct_ft); +} + +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_put(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_put(ct_ft); +} + static struct nf_flowtable_type flowtable_ct = { .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, + .get = tcf_ct_nf_get, + .put = tcf_ct_nf_put, .owner = THIS_MODULE, }; @@ -337,9 +359,13 @@ err_alloc: return err; } +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft) +{ + refcount_inc(&ct_ft->ref); +} + static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { - struct flow_block_cb *block_cb, *tmp_cb; struct tcf_ct_flow_table *ct_ft; struct flow_block *block; @@ -347,13 +373,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) rwork); nf_flow_table_free(&ct_ft->nf_ft); - /* Remove any remaining callbacks before cleanup */ block = &ct_ft->nf_ft.flow_block; down_write(&ct_ft->nf_ft.flow_block_lock); - list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) { - list_del(&block_cb->list); - flow_block_cb_free(block_cb); - } + WARN_ON(!list_empty(&block->cb_list)); up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 1976bd163986..dc1c19a25882 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -650,7 +650,7 @@ static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops, static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, void *tmplt_priv, u32 chain_index, struct tcf_block *block, struct sk_buff *oskb, - u32 seq, u16 flags, bool unicast); + u32 seq, u16 flags); static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, bool explicitly_created) @@ -685,8 +685,7 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, if (non_act_refcnt == chain->explicitly_created && !by_act) { if (non_act_refcnt == 0) tc_chain_notify_delete(tmplt_ops, tmplt_priv, - chain->index, block, NULL, 0, 0, - false); + chain->index, block, NULL, 0, 0); /* Last reference to chain, no need to lock. */ chain->flushing = false; } @@ -2053,6 +2052,9 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; int err = 0; + if (!unicast && !rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) + return 0; + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; @@ -2075,13 +2077,16 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, - u32 parent, void *fh, bool unicast, bool *last, - bool rtnl_held, struct netlink_ext_ack *extack) + u32 parent, void *fh, bool *last, bool rtnl_held, + struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; int err; + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) + return tp->ops->delete(tp, fh, last, rtnl_held, extack); + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; @@ -2100,11 +2105,8 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, return err; } - if (unicast) - err = rtnl_unicast(skb, net, portid); - else - err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, - n->nlmsg_flags & NLM_F_ECHO); + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send filter delete notification"); @@ -2499,9 +2501,8 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, } else { bool last; - err = tfilter_del_notify(net, skb, n, tp, block, - q, parent, fh, false, &last, - rtnl_held, extack); + err = tfilter_del_notify(net, skb, n, tp, block, q, parent, fh, + &last, rtnl_held, extack); if (err) goto errout; @@ -2906,6 +2907,9 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, struct sk_buff *skb; int err = 0; + if (!unicast && !rtnl_notify_needed(net, flags, RTNLGRP_TC)) + return 0; + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; @@ -2929,12 +2933,15 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, void *tmplt_priv, u32 chain_index, struct tcf_block *block, struct sk_buff *oskb, - u32 seq, u16 flags, bool unicast) + u32 seq, u16 flags) { u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; struct net *net = block->net; struct sk_buff *skb; + if (!rtnl_notify_needed(net, flags, RTNLGRP_TC)) + return 0; + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; @@ -2945,9 +2952,6 @@ static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, return -EINVAL; } - if (unicast) - return rtnl_unicast(skb, net, portid); - return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); } @@ -3309,7 +3313,7 @@ int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr ** act->type = exts->type = TCA_OLD_COMPAT; exts->actions[0] = act; exts->nr_actions = 1; - tcf_idr_insert_many(exts->actions); + tcf_idr_insert_many(exts->actions, init_res); } else if (exts->action && tb[exts->action]) { int err; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 7f89e43154c0..5fb02bbb4b34 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2099,6 +2099,9 @@ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, pr_debug("%s: sk:%p, msghdr:%p, len:%zd, flags:0x%x, addr_len:%p)\n", __func__, sk, msg, len, flags, addr_len); + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + lock_sock(sk); if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED) && diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c61666e5beed..7fc2f3c6d248 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -723,7 +723,7 @@ static void smcd_conn_save_peer_info(struct smc_sock *smc, int bufsize = smc_uncompress_bufsize(clc->d0.dmbe_size); smc->conn.peer_rmbe_idx = clc->d0.dmbe_idx; - smc->conn.peer_token = clc->d0.token; + smc->conn.peer_token = ntohll(clc->d0.token); /* msg header takes up space in the buffer */ smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg); atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); @@ -1415,7 +1415,7 @@ static int smc_connect_ism(struct smc_sock *smc, if (rc) return rc; } - ini->ism_peer_gid[ini->ism_selected] = aclc->d0.gid; + ini->ism_peer_gid[ini->ism_selected] = ntohll(aclc->d0.gid); /* there is only one lgr role for SMC-D; use server lock */ mutex_lock(&smc_server_lgr_pending); diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 0fda5156eef0..95e19aa3e769 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -1005,6 +1005,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, { struct smc_connection *conn = &smc->conn; struct smc_clc_first_contact_ext_v2x fce; + struct smcd_dev *smcd = conn->lgr->smcd; struct smc_clc_msg_accept_confirm *clc; struct smc_clc_fce_gid_ext gle; struct smc_clc_msg_trail trl; @@ -1022,17 +1023,15 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)); clc->hdr.typev1 = SMC_TYPE_D; - clc->d0.gid = - conn->lgr->smcd->ops->get_local_gid(conn->lgr->smcd); - clc->d0.token = conn->rmb_desc->token; + clc->d0.gid = htonll(smcd->ops->get_local_gid(smcd)); + clc->d0.token = htonll(conn->rmb_desc->token); clc->d0.dmbe_size = conn->rmbe_size_comp; clc->d0.dmbe_idx = 0; memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); if (version == SMC_V1) { clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); } else { - clc_v2->d1.chid = - htons(smc_ism_get_chid(conn->lgr->smcd)); + clc_v2->d1.chid = htons(smc_ism_get_chid(smcd)); if (eid && eid[0]) memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN); len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 89b258cedffe..1697b84d85be 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -204,8 +204,8 @@ struct smcr_clc_msg_accept_confirm { /* SMCR accept/confirm */ } __packed; struct smcd_clc_msg_accept_confirm_common { /* SMCD accept/confirm */ - u64 gid; /* Sender GID */ - u64 token; /* DMB token */ + __be64 gid; /* Sender GID */ + __be64 token; /* DMB token */ u8 dmbe_idx; /* DMBE index */ #if defined(__BIG_ENDIAN_BITFIELD) u8 dmbe_size : 4, /* buf size (compressed) */ diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 316f76187962..e37b4d2e2acd 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -952,6 +952,8 @@ static int tls_sw_sendmsg_splice(struct sock *sk, struct msghdr *msg, } sk_msg_page_add(msg_pl, page, part, off); + msg_pl->sg.copybreak = 0; + msg_pl->sg.curr = msg_pl->sg.end; sk_mem_charge(sk, part); *copied += part; try_to_copy -= part; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 816725af281f..54ba7316f808 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -2264,8 +2264,13 @@ static int vsock_set_rcvlowat(struct sock *sk, int val) transport = vsk->transport; - if (transport && transport->set_rcvlowat) - return transport->set_rcvlowat(vsk, val); + if (transport && transport->notify_set_rcvlowat) { + int err; + + err = transport->notify_set_rcvlowat(vsk, val); + if (err) + return err; + } WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); return 0; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 7cb1a9d2cdb4..e2157e387217 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -816,7 +816,7 @@ int hvs_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written, } static -int hvs_set_rcvlowat(struct vsock_sock *vsk, int val) +int hvs_notify_set_rcvlowat(struct vsock_sock *vsk, int val) { return -EOPNOTSUPP; } @@ -856,7 +856,7 @@ static struct vsock_transport hvs_transport = { .notify_send_pre_enqueue = hvs_notify_send_pre_enqueue, .notify_send_post_enqueue = hvs_notify_send_post_enqueue, - .set_rcvlowat = hvs_set_rcvlowat + .notify_set_rcvlowat = hvs_notify_set_rcvlowat }; static bool hvs_check_transport(struct vsock_sock *vsk) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index af5bab1acee1..f495b9e5186b 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -537,6 +537,7 @@ static struct virtio_transport virtio_transport = { .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, .notify_buffer_size = virtio_transport_notify_buffer_size, + .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, .read_skb = virtio_transport_read_skb, }, diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index f6dc896bf44c..16ff976a86e3 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -59,8 +59,7 @@ static bool virtio_transport_can_zcopy(const struct virtio_transport *t_ops, t_ops = virtio_transport_get_ops(info->vsk); if (t_ops->can_msgzerocopy) { - int pages_in_iov = iov_iter_npages(iov_iter, MAX_SKB_FRAGS); - int pages_to_send = min(pages_in_iov, MAX_SKB_FRAGS); + int pages_to_send = iov_iter_npages(iov_iter, MAX_SKB_FRAGS); /* +1 is for packet header. */ return t_ops->can_msgzerocopy(pages_to_send + 1); @@ -558,6 +557,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, struct virtio_vsock_sock *vvs = vsk->trans; size_t bytes, total = 0; struct sk_buff *skb; + u32 fwd_cnt_delta; + bool low_rx_bytes; int err = -EFAULT; u32 free_space; @@ -601,7 +602,10 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, } } - free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt); + fwd_cnt_delta = vvs->fwd_cnt - vvs->last_fwd_cnt; + free_space = vvs->buf_alloc - fwd_cnt_delta; + low_rx_bytes = (vvs->rx_bytes < + sock_rcvlowat(sk_vsock(vsk), 0, INT_MAX)); spin_unlock_bh(&vvs->rx_lock); @@ -611,9 +615,11 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, * too high causes extra messages. Too low causes transmitter * stalls. As stalls are in theory more expensive than extra * messages, we set the limit to a high value. TODO: experiment - * with different values. + * with different values. Also send credit update message when + * number of bytes in rx queue is not enough to wake up reader. */ - if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) + if (fwd_cnt_delta && + (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE || low_rx_bytes)) virtio_transport_send_credit_update(vsk); return total; @@ -844,7 +850,7 @@ static s64 virtio_transport_has_space(struct vsock_sock *vsk) struct virtio_vsock_sock *vvs = vsk->trans; s64 bytes; - bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); if (bytes < 0) bytes = 0; @@ -1684,6 +1690,36 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto } EXPORT_SYMBOL_GPL(virtio_transport_read_skb); +int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + bool send_update; + + spin_lock_bh(&vvs->rx_lock); + + /* If number of available bytes is less than new SO_RCVLOWAT value, + * kick sender to send more data, because sender may sleep in its + * 'send()' syscall waiting for enough space at our side. Also + * don't send credit update when peer already knows actual value - + * such transmission will be useless. + */ + send_update = (vvs->rx_bytes < val) && + (vvs->fwd_cnt != vvs->last_fwd_cnt); + + spin_unlock_bh(&vvs->rx_lock); + + if (send_update) { + int err; + + err = virtio_transport_send_credit_update(vsk); + if (err < 0) + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_set_rcvlowat); + MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Asias He"); MODULE_DESCRIPTION("common code for virtio vsock"); diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 048640167411..6dea6119f5b2 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -96,6 +96,7 @@ static struct virtio_transport loopback_transport = { .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, .notify_buffer_size = virtio_transport_notify_buffer_size, + .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, .read_skb = virtio_transport_read_skb, }, diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 089c841528c8..72074fd36df4 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -25,7 +25,7 @@ ifneq ($(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR),) cfg80211-y += extra-certs.o endif -$(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) +$(obj)/shipped-certs.c: $(sort $(wildcard $(srctree)/$(src)/certs/*.hex)) @$(kecho) " GEN $@" $(Q)(echo '#include "reg.h"'; \ echo 'const u8 shipped_regdb_certs[] = {'; \ @@ -35,7 +35,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) ) > $@ $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR) \ - $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR)/*.x509) + $(sort $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR)/*.x509)) @$(kecho) " GEN $@" $(Q)(set -e; \ allf=""; \ diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 2d21e423abdb..dfb4893421d7 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -141,7 +141,7 @@ static bool cfg80211_edmg_chandef_valid(const struct cfg80211_chan_def *chandef) return true; } -static int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width) +int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width) { int mhz; @@ -190,6 +190,7 @@ static int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width) } return mhz; } +EXPORT_SYMBOL(nl80211_chan_width_to_mhz); static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c) { diff --git a/net/wireless/core.h b/net/wireless/core.h index cb61d33d4f1e..1963958263d2 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -458,6 +458,9 @@ int cfg80211_scan(struct cfg80211_registered_device *rdev); extern struct work_struct cfg80211_disconnect_work; +#define NL80211_BSS_USE_FOR_ALL (NL80211_BSS_USE_FOR_NORMAL | \ + NL80211_BSS_USE_FOR_MLD_LINK) + void cfg80211_set_dfs_state(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef, enum nl80211_dfs_state dfs_state); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index bad9e4fd842f..f635a8b6ca2e 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -22,7 +22,7 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, - struct cfg80211_rx_assoc_resp_data *data) + const struct cfg80211_rx_assoc_resp_data *data) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d0f499227c29..8b45fb420f4c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -818,6 +818,9 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_HW_TIMESTAMP_ENABLED] = { .type = NLA_FLAG }, [NL80211_ATTR_EMA_RNR_ELEMS] = { .type = NLA_NESTED }, [NL80211_ATTR_MLO_LINK_DISABLED] = { .type = NLA_FLAG }, + [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), }; /* policy for the key attributes */ @@ -4855,7 +4858,7 @@ static struct cfg80211_acl_data *parse_acl_data(struct wiphy *wiphy, return ERR_PTR(n_entries); if (n_entries > wiphy->max_acl_mac_addrs) - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); acl = kzalloc(struct_size(acl, mac_addrs, n_entries), GFP_KERNEL); if (!acl) @@ -10410,6 +10413,15 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, break; } + if (nla_put_u32(msg, NL80211_BSS_USE_FOR, res->use_for)) + goto nla_put_failure; + + if (res->cannot_use_reasons && + nla_put_u64_64bit(msg, NL80211_BSS_CANNOT_USE_REASONS, + res->cannot_use_reasons, + NL80211_BSS_PAD)) + goto nla_put_failure; + nla_nest_end(msg, bss); genlmsg_end(msg, hdr); @@ -10427,15 +10439,27 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) struct cfg80211_registered_device *rdev; struct cfg80211_internal_bss *scan; struct wireless_dev *wdev; + struct nlattr **attrbuf; int start = cb->args[2], idx = 0; + bool dump_include_use_data; int err; - err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL); - if (err) + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), GFP_KERNEL); + if (!attrbuf) + return -ENOMEM; + + err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, attrbuf); + if (err) { + kfree(attrbuf); return err; + } /* nl80211_prepare_wdev_dump acquired it in the successful case */ __acquire(&rdev->wiphy.mtx); + dump_include_use_data = + attrbuf[NL80211_ATTR_BSS_DUMP_INCLUDE_USE_DATA]; + kfree(attrbuf); + spin_lock_bh(&rdev->bss_lock); /* @@ -10452,6 +10476,9 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) list_for_each_entry(scan, &rdev->bss_list, list) { if (++idx <= start) continue; + if (!dump_include_use_data && + !(scan->pub.use_for & NL80211_BSS_USE_FOR_NORMAL)) + continue; if (nl80211_send_bss(skb, cb, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wdev, scan) < 0) { @@ -10903,12 +10930,13 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device *rdev, const u8 *ssid, int ssid_len, - struct nlattr **attrs) + struct nlattr **attrs, + int assoc_link_id, int link_id) { struct ieee80211_channel *chan; struct cfg80211_bss *bss; const u8 *bssid; - u32 freq; + u32 freq, use_for = 0; if (!attrs[NL80211_ATTR_MAC] || !attrs[NL80211_ATTR_WIPHY_FREQ]) return ERR_PTR(-EINVAL); @@ -10923,10 +10951,16 @@ static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device if (!chan) return ERR_PTR(-EINVAL); - bss = cfg80211_get_bss(&rdev->wiphy, chan, bssid, - ssid, ssid_len, - IEEE80211_BSS_TYPE_ESS, - IEEE80211_PRIVACY_ANY); + if (assoc_link_id >= 0) + use_for = NL80211_BSS_USE_FOR_MLD_LINK; + if (assoc_link_id == link_id) + use_for |= NL80211_BSS_USE_FOR_NORMAL; + + bss = __cfg80211_get_bss(&rdev->wiphy, chan, bssid, + ssid, ssid_len, + IEEE80211_BSS_TYPE_ESS, + IEEE80211_PRIVACY_ANY, + use_for); if (!bss) return ERR_PTR(-ENOENT); @@ -11105,7 +11139,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto free; } req.links[link_id].bss = - nl80211_assoc_bss(rdev, ssid, ssid_len, attrs); + nl80211_assoc_bss(rdev, ssid, ssid_len, attrs, + req.link_id, link_id); if (IS_ERR(req.links[link_id].bss)) { err = PTR_ERR(req.links[link_id].bss); req.links[link_id].bss = NULL; @@ -11170,7 +11205,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) if (req.link_id >= 0) return -EINVAL; - req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs); + req.bss = nl80211_assoc_bss(rdev, ssid, ssid_len, info->attrs, + -1, -1); if (IS_ERR(req.bss)) return PTR_ERR(req.bss); ap_addr = req.bss->bssid; @@ -12179,16 +12215,18 @@ static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info) return err; } -static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) +static int nl80211_set_pmksa(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; - int (*rdev_ops)(struct wiphy *wiphy, struct net_device *dev, - struct cfg80211_pmksa *pmksa) = NULL; struct net_device *dev = info->user_ptr[1]; struct cfg80211_pmksa pmksa; + bool ap_pmksa_caching_support = false; memset(&pmksa, 0, sizeof(struct cfg80211_pmksa)); + ap_pmksa_caching_support = wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AP_PMKSA_CACHING); + if (!info->attrs[NL80211_ATTR_PMKID]) return -EINVAL; @@ -12197,16 +12235,15 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_MAC]) { pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); } else if (info->attrs[NL80211_ATTR_SSID] && - info->attrs[NL80211_ATTR_FILS_CACHE_ID] && - (info->genlhdr->cmd == NL80211_CMD_DEL_PMKSA || - info->attrs[NL80211_ATTR_PMK])) { + info->attrs[NL80211_ATTR_FILS_CACHE_ID] && + info->attrs[NL80211_ATTR_PMK]) { pmksa.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); pmksa.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - pmksa.cache_id = - nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]); + pmksa.cache_id = nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]); } else { return -EINVAL; } + if (info->attrs[NL80211_ATTR_PMK]) { pmksa.pmk = nla_data(info->attrs[NL80211_ATTR_PMK]); pmksa.pmk_len = nla_len(info->attrs[NL80211_ATTR_PMK]); @@ -12218,32 +12255,71 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD]) pmksa.pmk_reauth_threshold = - nla_get_u8( - info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD]); + nla_get_u8(info->attrs[NL80211_ATTR_PMK_REAUTH_THRESHOLD]); if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && - !(dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP && - wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_AP_PMKSA_CACHING))) + !((dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP || + dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO) && + ap_pmksa_caching_support)) return -EOPNOTSUPP; - switch (info->genlhdr->cmd) { - case NL80211_CMD_SET_PMKSA: - rdev_ops = rdev->ops->set_pmksa; - break; - case NL80211_CMD_DEL_PMKSA: - rdev_ops = rdev->ops->del_pmksa; - break; - default: - WARN_ON(1); - break; + if (!rdev->ops->set_pmksa) + return -EOPNOTSUPP; + + return rdev_set_pmksa(rdev, dev, &pmksa); +} + +static int nl80211_del_pmksa(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 cfg80211_pmksa pmksa; + bool sae_offload_support = false; + bool owe_offload_support = false; + bool ap_pmksa_caching_support = false; + + memset(&pmksa, 0, sizeof(struct cfg80211_pmksa)); + + sae_offload_support = wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_SAE_OFFLOAD); + owe_offload_support = wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_OWE_OFFLOAD); + ap_pmksa_caching_support = wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AP_PMKSA_CACHING); + + if (info->attrs[NL80211_ATTR_PMKID]) + pmksa.pmkid = nla_data(info->attrs[NL80211_ATTR_PMKID]); + + if (info->attrs[NL80211_ATTR_MAC]) { + pmksa.bssid = nla_data(info->attrs[NL80211_ATTR_MAC]); + } else if (info->attrs[NL80211_ATTR_SSID]) { + /* SSID based pmksa flush suppported only for FILS, + * OWE/SAE OFFLOAD cases + */ + if (info->attrs[NL80211_ATTR_FILS_CACHE_ID] && + info->attrs[NL80211_ATTR_PMK]) { + pmksa.cache_id = nla_data(info->attrs[NL80211_ATTR_FILS_CACHE_ID]); + } else if (!sae_offload_support && !owe_offload_support) { + return -EINVAL; + } + pmksa.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); + pmksa.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); + } else { + return -EINVAL; } - if (!rdev_ops) + if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && + !((dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP || + dev->ieee80211_ptr->iftype == NL80211_IFTYPE_P2P_GO) && + ap_pmksa_caching_support)) + return -EOPNOTSUPP; + + if (!rdev->ops->del_pmksa) return -EOPNOTSUPP; - return rdev_ops(&rdev->wiphy, dev, &pmksa); + return rdev_del_pmksa(rdev, dev, &pmksa); } static int nl80211_flush_pmksa(struct sk_buff *skb, struct genl_info *info) @@ -15847,7 +15923,7 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev, if (tid_conf->mask & ~mask) { NL_SET_ERR_MSG(extack, "unsupported TID configuration"); - return -ENOTSUPP; + return -EOPNOTSUPP; } return 0; @@ -16240,6 +16316,35 @@ static int nl80211_set_hw_timestamp(struct sk_buff *skb, return rdev_set_hw_timestamp(rdev, dev, &hwts); } +static int +nl80211_set_ttlm(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_ttlm_params params = {}; + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; + + if (!wdev->connected) + return -ENOLINK; + + if (!info->attrs[NL80211_ATTR_MLO_TTLM_DLINK] || + !info->attrs[NL80211_ATTR_MLO_TTLM_ULINK]) + return -EINVAL; + + nla_memcpy(params.dlink, + info->attrs[NL80211_ATTR_MLO_TTLM_DLINK], + sizeof(params.dlink)); + nla_memcpy(params.ulink, + info->attrs[NL80211_ATTR_MLO_TTLM_ULINK], + sizeof(params.ulink)); + + return rdev_set_ttlm(rdev, dev, ¶ms); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -16928,7 +17033,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { { .cmd = NL80211_CMD_SET_PMKSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = nl80211_setdel_pmksa, + .doit = nl80211_set_pmksa, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_CLEAR_SKB), @@ -16936,7 +17041,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { { .cmd = NL80211_CMD_DEL_PMKSA, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = nl80211_setdel_pmksa, + .doit = nl80211_del_pmksa, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), }, @@ -17421,6 +17526,12 @@ static const struct genl_small_ops nl80211_small_ops[] = { .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), }, + { + .cmd = NL80211_CMD_SET_TID_TO_LINK_MAPPING, + .doit = nl80211_set_ttlm, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + }, }; static struct genl_family nl80211_fam __ro_after_init = { @@ -17752,21 +17863,29 @@ nla_put_failure: nlmsg_free(msg); } +struct nl80211_mlme_event { + enum nl80211_commands cmd; + const u8 *buf; + size_t buf_len; + int uapsd_queues; + const u8 *req_ies; + size_t req_ies_len; + bool reconnect; +}; + static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, struct net_device *netdev, - const u8 *buf, size_t len, - enum nl80211_commands cmd, gfp_t gfp, - int uapsd_queues, const u8 *req_ies, - size_t req_ies_len, bool reconnect) + const struct nl80211_mlme_event *event, + gfp_t gfp) { struct sk_buff *msg; void *hdr; - msg = nlmsg_new(100 + len + req_ies_len, gfp); + msg = nlmsg_new(100 + event->buf_len + event->req_ies_len, gfp); if (!msg) return; - hdr = nl80211hdr_put(msg, 0, 0, 0, cmd); + hdr = nl80211hdr_put(msg, 0, 0, 0, event->cmd); if (!hdr) { nlmsg_free(msg); return; @@ -17774,22 +17893,24 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev, if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || - nla_put(msg, NL80211_ATTR_FRAME, len, buf) || - (req_ies && - nla_put(msg, NL80211_ATTR_REQ_IE, req_ies_len, req_ies))) + nla_put(msg, NL80211_ATTR_FRAME, event->buf_len, event->buf) || + (event->req_ies && + nla_put(msg, NL80211_ATTR_REQ_IE, event->req_ies_len, + event->req_ies))) goto nla_put_failure; - if (reconnect && nla_put_flag(msg, NL80211_ATTR_RECONNECT_REQUESTED)) + if (event->reconnect && + nla_put_flag(msg, NL80211_ATTR_RECONNECT_REQUESTED)) goto nla_put_failure; - if (uapsd_queues >= 0) { + if (event->uapsd_queues >= 0) { struct nlattr *nla_wmm = nla_nest_start_noflag(msg, NL80211_ATTR_STA_WME); if (!nla_wmm) goto nla_put_failure; if (nla_put_u8(msg, NL80211_STA_WME_UAPSD_QUEUES, - uapsd_queues)) + event->uapsd_queues)) goto nla_put_failure; nla_nest_end(msg, nla_wmm); @@ -17809,37 +17930,60 @@ void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, gfp_t gfp) { - nl80211_send_mlme_event(rdev, netdev, buf, len, - NL80211_CMD_AUTHENTICATE, gfp, -1, NULL, 0, - false); + struct nl80211_mlme_event event = { + .cmd = NL80211_CMD_AUTHENTICATE, + .buf = buf, + .buf_len = len, + .uapsd_queues = -1, + }; + + nl80211_send_mlme_event(rdev, netdev, &event, gfp); } void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev, struct net_device *netdev, - struct cfg80211_rx_assoc_resp_data *data) + const struct cfg80211_rx_assoc_resp_data *data) { - nl80211_send_mlme_event(rdev, netdev, data->buf, data->len, - NL80211_CMD_ASSOCIATE, GFP_KERNEL, - data->uapsd_queues, - data->req_ies, data->req_ies_len, false); + struct nl80211_mlme_event event = { + .cmd = NL80211_CMD_ASSOCIATE, + .buf = data->buf, + .buf_len = data->len, + .uapsd_queues = data->uapsd_queues, + .req_ies = data->req_ies, + .req_ies_len = data->req_ies_len, + }; + + nl80211_send_mlme_event(rdev, netdev, &event, GFP_KERNEL); } void nl80211_send_deauth(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, bool reconnect, gfp_t gfp) { - nl80211_send_mlme_event(rdev, netdev, buf, len, - NL80211_CMD_DEAUTHENTICATE, gfp, -1, NULL, 0, - reconnect); + struct nl80211_mlme_event event = { + .cmd = NL80211_CMD_DEAUTHENTICATE, + .buf = buf, + .buf_len = len, + .reconnect = reconnect, + .uapsd_queues = -1, + }; + + nl80211_send_mlme_event(rdev, netdev, &event, gfp); } void nl80211_send_disassoc(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, bool reconnect, gfp_t gfp) { - nl80211_send_mlme_event(rdev, netdev, buf, len, - NL80211_CMD_DISASSOCIATE, gfp, -1, NULL, 0, - reconnect); + struct nl80211_mlme_event event = { + .cmd = NL80211_CMD_DISASSOCIATE, + .buf = buf, + .buf_len = len, + .reconnect = reconnect, + .uapsd_queues = -1, + }; + + nl80211_send_mlme_event(rdev, netdev, &event, gfp); } void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf, @@ -17849,28 +17993,31 @@ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf, struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); const struct ieee80211_mgmt *mgmt = (void *)buf; - u32 cmd; + struct nl80211_mlme_event event = { + .buf = buf, + .buf_len = len, + .uapsd_queues = -1, + }; if (WARN_ON(len < 2)) return; if (ieee80211_is_deauth(mgmt->frame_control)) { - cmd = NL80211_CMD_UNPROT_DEAUTHENTICATE; + event.cmd = NL80211_CMD_UNPROT_DEAUTHENTICATE; } else if (ieee80211_is_disassoc(mgmt->frame_control)) { - cmd = NL80211_CMD_UNPROT_DISASSOCIATE; + event.cmd = NL80211_CMD_UNPROT_DISASSOCIATE; } else if (ieee80211_is_beacon(mgmt->frame_control)) { if (wdev->unprot_beacon_reported && elapsed_jiffies_msecs(wdev->unprot_beacon_reported) < 10000) return; - cmd = NL80211_CMD_UNPROT_BEACON; + event.cmd = NL80211_CMD_UNPROT_BEACON; wdev->unprot_beacon_reported = jiffies; } else { return; } trace_cfg80211_rx_unprot_mlme_mgmt(dev, buf, len); - nl80211_send_mlme_event(rdev, dev, buf, len, cmd, GFP_ATOMIC, -1, - NULL, 0, false); + nl80211_send_mlme_event(rdev, dev, &event, GFP_ATOMIC); } EXPORT_SYMBOL(cfg80211_rx_unprot_mlme_mgmt); diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index aad40240d9cb..6376f3a87f8a 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -60,7 +60,7 @@ void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev, const u8 *buf, size_t len, gfp_t gfp); void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev, struct net_device *netdev, - struct cfg80211_rx_assoc_resp_data *data); + const struct cfg80211_rx_assoc_resp_data *data); void nl80211_send_deauth(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *buf, size_t len, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 2214a90cf101..43897a5269b6 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1046,7 +1046,7 @@ rdev_nan_change_conf(struct cfg80211_registered_device *rdev, ret = rdev->ops->nan_change_conf(&rdev->wiphy, wdev, conf, changes); else - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; trace_rdev_return_int(&rdev->wiphy, ret); return ret; } @@ -1200,7 +1200,7 @@ rdev_start_radar_detection(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef, u32 cac_time_ms) { - int ret = -ENOTSUPP; + int ret = -EOPNOTSUPP; trace_rdev_start_radar_detection(&rdev->wiphy, dev, chandef, cac_time_ms); @@ -1226,7 +1226,7 @@ rdev_set_mcast_rate(struct cfg80211_registered_device *rdev, struct net_device *dev, int mcast_rate[NUM_NL80211_BANDS]) { - int ret = -ENOTSUPP; + int ret = -EOPNOTSUPP; trace_rdev_set_mcast_rate(&rdev->wiphy, dev, mcast_rate); if (rdev->ops->set_mcast_rate) @@ -1239,7 +1239,7 @@ static inline int rdev_set_coalesce(struct cfg80211_registered_device *rdev, struct cfg80211_coalesce *coalesce) { - int ret = -ENOTSUPP; + int ret = -EOPNOTSUPP; trace_rdev_set_coalesce(&rdev->wiphy, coalesce); if (rdev->ops->set_coalesce) @@ -1524,4 +1524,22 @@ rdev_set_hw_timestamp(struct cfg80211_registered_device *rdev, return ret; } + +static inline int +rdev_set_ttlm(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_ttlm_params *params) +{ + struct wiphy *wiphy = &rdev->wiphy; + int ret; + + if (!rdev->ops->set_ttlm) + return -EOPNOTSUPP; + + trace_rdev_set_ttlm(wiphy, dev, params); + ret = rdev->ops->set_ttlm(wiphy, dev, params); + trace_rdev_return_int(wiphy, ret); + + return ret; +} #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 9e5ccffd6868..3d260c99c348 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1535,12 +1535,13 @@ static bool cfg80211_bss_type_match(u16 capability, } /* Returned bss is reference counted and must be cleaned up appropriately. */ -struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, - struct ieee80211_channel *channel, - const u8 *bssid, - const u8 *ssid, size_t ssid_len, - enum ieee80211_bss_type bss_type, - enum ieee80211_privacy privacy) +struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy, + struct ieee80211_channel *channel, + const u8 *bssid, + const u8 *ssid, size_t ssid_len, + enum ieee80211_bss_type bss_type, + enum ieee80211_privacy privacy, + u32 use_for) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct cfg80211_internal_bss *bss, *res = NULL; @@ -1565,6 +1566,8 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, continue; if (!is_valid_ether_addr(bss->pub.bssid)) continue; + if ((bss->pub.use_for & use_for) != use_for) + continue; /* Don't get expired BSS structs */ if (time_after(now, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE) && !atomic_read(&bss->hold)) @@ -1582,7 +1585,7 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, trace_cfg80211_return_bss(&res->pub); return &res->pub; } -EXPORT_SYMBOL(cfg80211_get_bss); +EXPORT_SYMBOL(__cfg80211_get_bss); static void rb_insert_bss(struct cfg80211_registered_device *rdev, struct cfg80211_internal_bss *bss) @@ -1746,7 +1749,9 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, new->pub.proberesp_ies); if (old) kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head); - } else if (rcu_access_pointer(new->pub.beacon_ies)) { + } + + if (rcu_access_pointer(new->pub.beacon_ies)) { const struct cfg80211_bss_ies *old; if (known->pub.hidden_beacon_bss && @@ -1800,6 +1805,8 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, ether_addr_copy(known->parent_bssid, new->parent_bssid); known->pub.max_bssid_indicator = new->pub.max_bssid_indicator; known->pub.bssid_index = new->pub.bssid_index; + known->pub.use_for &= new->pub.use_for; + known->pub.cannot_use_reasons = new->pub.cannot_use_reasons; return true; } @@ -2044,6 +2051,9 @@ struct cfg80211_inform_single_bss_data { struct cfg80211_bss *source_bss; u8 max_bssid_indicator; u8 bssid_index; + + u8 use_for; + u64 cannot_use_reasons; }; /* Returned bss is reference counted and must be cleaned up appropriately. */ @@ -2089,6 +2099,8 @@ 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.use_for = data->use_for; + tmp.pub.cannot_use_reasons = data->cannot_use_reasons; if (data->bss_source != BSS_SOURCE_DIRECT) { tmp.pub.transmitted_bss = data->source_bss; @@ -2259,6 +2271,8 @@ cfg80211_parse_mbssid_data(struct wiphy *wiphy, .beacon_interval = tx_data->beacon_interval, .source_bss = source_bss, .bss_source = BSS_SOURCE_MBSSID, + .use_for = tx_data->use_for, + .cannot_use_reasons = tx_data->cannot_use_reasons, }; const u8 *mbssid_index_ie; const struct element *elem, *sub; @@ -2521,7 +2535,7 @@ error: return NULL; } -static bool +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) @@ -2540,6 +2554,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, u16 params; u8 length, i, count, mld_params_offset; u8 type, lid; + u32 use_for; info = (void *)pos; count = u8_get_bits(info->tbtt_info_hdr, @@ -2549,20 +2564,22 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, pos += sizeof(*info); if (count * length > end - pos) - return false; + return 0; type = u8_get_bits(info->tbtt_info_hdr, IEEE80211_AP_INFO_TBTT_HDR_TYPE); - /* Only accept full TBTT information. NSTR mobile APs - * use the shortened version, but we ignore them here. - */ 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; @@ -2580,7 +2597,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, *ap_info = info; *tbtt_info = pos; - return true; + return use_for; } pos += length; @@ -2588,7 +2605,7 @@ cfg80211_tbtt_info_for_mld_ap(const u8 *ie, size_t ielen, u8 mld_id, u8 link_id, } } - return false; + return 0; } static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy, @@ -2606,6 +2623,7 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy, const struct element *elem; struct cfg80211_mle *mle; u16 control; + u8 ml_common_len; u8 *new_ie; struct cfg80211_bss *bss; int mld_id; @@ -2636,6 +2654,8 @@ static void cfg80211_parse_ml_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; @@ -2676,7 +2696,7 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy, const u8 *profile; const u8 *tbtt_info; ssize_t profile_len; - u8 link_id; + u8 link_id, use_for; if (!ieee80211_mle_basic_sta_prof_size_ok((u8 *)mle->sta_prof[i], mle->sta_prof_len[i])) @@ -2718,9 +2738,11 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy, profile_len -= 2; /* Find in RNR to look up channel information */ - if (!cfg80211_tbtt_info_for_mld_ap(tx_data->ie, tx_data->ielen, - mld_id, link_id, - &ap_info, &tbtt_info)) + use_for = cfg80211_tbtt_info_for_mld_ap(tx_data->ie, + tx_data->ielen, + mld_id, link_id, + &ap_info, &tbtt_info); + if (!use_for) continue; /* We could sanity check the BSSID is included */ @@ -2732,6 +2754,14 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy, freq = ieee80211_channel_to_freq_khz(ap_info->channel, band); data.channel = ieee80211_get_channel_khz(wiphy, freq); + if (use_for == NL80211_BSS_USE_FOR_MLD_LINK && + !(wiphy->flags & WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY)) { + use_for = 0; + data.cannot_use_reasons = + NL80211_BSS_CANNOT_USE_NSTR_NONPRIMARY; + } + data.use_for = use_for; + /* Generate new elements */ memset(new_ie, 0, IEEE80211_MAX_DATA_LEN); data.ie = new_ie; @@ -2742,6 +2772,34 @@ static void cfg80211_parse_ml_sta_data(struct wiphy *wiphy, if (!data.ielen) continue; + /* The generated elements do not contain: + * - Basic ML element + * - A TBTT entry in the RNR for the transmitting AP + * + * This information is needed both internally and in userspace + * as such, we should append it here. + */ + if (data.ielen + 3 + sizeof(*ml_elem) + ml_common_len > + IEEE80211_MAX_DATA_LEN) + continue; + + /* Copy the Basic Multi-Link element including the common + * information, and then fix up the link ID. + * Note that the ML element length has been verified and we + * also checked that it contains the link ID. + */ + new_ie[data.ielen++] = WLAN_EID_EXTENSION; + new_ie[data.ielen++] = 1 + sizeof(*ml_elem) + ml_common_len; + new_ie[data.ielen++] = WLAN_EID_EXT_EHT_MULTI_LINK; + memcpy(new_ie + data.ielen, ml_elem, + sizeof(*ml_elem) + ml_common_len); + + new_ie[data.ielen + sizeof(*ml_elem) + 1 + ETH_ALEN] = link_id; + + data.ielen += sizeof(*ml_elem) + ml_common_len; + + /* TODO: Add an RNR containing only the reporting AP */ + bss = cfg80211_inform_single_bss_data(wiphy, &data, gfp); if (!bss) break; @@ -2769,6 +2827,10 @@ cfg80211_inform_bss_data(struct wiphy *wiphy, .beacon_interval = beacon_interval, .ie = ie, .ielen = ielen, + .use_for = data->restrict_use ? + data->use_for : + NL80211_BSS_USE_FOR_ALL, + .cannot_use_reasons = data->cannot_use_reasons, }; struct cfg80211_bss *res; @@ -2899,6 +2961,10 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, 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); @@ -2930,6 +2996,10 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, .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; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 30cd1bd58aac..1f374c8a17a5 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2928,7 +2928,7 @@ DEFINE_EVENT(netdev_evt_only, cfg80211_send_rx_auth, TRACE_EVENT(cfg80211_send_rx_assoc, TP_PROTO(struct net_device *netdev, - struct cfg80211_rx_assoc_resp_data *data), + const struct cfg80211_rx_assoc_resp_data *data), TP_ARGS(netdev, data), TP_STRUCT__entry( NETDEV_ENTRY @@ -3979,6 +3979,26 @@ TRACE_EVENT(cfg80211_links_removed, __entry->link_mask) ); +TRACE_EVENT(rdev_set_ttlm, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_ttlm_params *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __array(u8, dlink, sizeof(u16) * 8) + __array(u8, ulink, sizeof(u16) * 8) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + memcpy(__entry->dlink, params->dlink, sizeof(params->dlink)); + memcpy(__entry->ulink, params->ulink, sizeof(params->ulink)); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG) +); + #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 281d49b4fca4..9f13aa3353e3 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -991,7 +991,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, rcu_read_lock(); if (xsk_check_common(xs)) - goto skip_tx; + goto out; pool = xs->pool; @@ -1003,12 +1003,11 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, xsk_generic_xmit(sk); } -skip_tx: if (xs->rx && !xskq_prod_is_empty(xs->rx)) mask |= EPOLLIN | EPOLLRDNORM; if (xs->tx && xsk_tx_writeable(xs)) mask |= EPOLLOUT | EPOLLWRNORM; - +out: rcu_read_unlock(); return mask; } |