diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-18 18:50:12 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-05-18 18:50:12 +0000 |
commit | 8665bd53f2f2e27e5511d90428cb3f60e6d0ce15 (patch) | |
tree | 8d58900dc0ebd4a3011f92c128d2fe45bc7c4bf2 /net/core | |
parent | Adding debian version 6.7.12-1. (diff) | |
download | linux-8665bd53f2f2e27e5511d90428cb3f60e6d0ce15.tar.xz linux-8665bd53f2f2e27e5511d90428cb3f60e6d0ce15.zip |
Merging upstream version 6.8.9.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/Makefile | 2 | ||||
-rw-r--r-- | net/core/bpf_sk_storage.c | 3 | ||||
-rw-r--r-- | net/core/dev.c | 153 | ||||
-rw-r--r-- | net/core/dev.h | 3 | ||||
-rw-r--r-- | net/core/dev_ioctl.c | 7 | ||||
-rw-r--r-- | net/core/drop_monitor.c | 2 | ||||
-rw-r--r-- | net/core/fib_rules.c | 4 | ||||
-rw-r--r-- | net/core/filter.c | 29 | ||||
-rw-r--r-- | net/core/gro.c | 3 | ||||
-rw-r--r-- | net/core/link_watch.c | 8 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 17 | ||||
-rw-r--r-- | net/core/net_namespace.c | 49 | ||||
-rw-r--r-- | net/core/netdev-genl-gen.c | 110 | ||||
-rw-r--r-- | net/core/netdev-genl-gen.h | 16 | ||||
-rw-r--r-- | net/core/netdev-genl.c | 339 | ||||
-rw-r--r-- | net/core/page_pool.c | 117 | ||||
-rw-r--r-- | net/core/page_pool_priv.h | 12 | ||||
-rw-r--r-- | net/core/page_pool_user.c | 409 | ||||
-rw-r--r-- | net/core/pktgen.c | 6 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 103 | ||||
-rw-r--r-- | net/core/scm.c | 2 | ||||
-rw-r--r-- | net/core/skbuff.c | 94 | ||||
-rw-r--r-- | net/core/sock.c | 9 | ||||
-rw-r--r-- | net/core/sock_map.c | 6 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 24 | ||||
-rw-r--r-- | net/core/xdp.c | 33 |
26 files changed, 1392 insertions, 168 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 0cb734cbc2..821aec06ab 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -18,7 +18,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o obj-y += net-sysfs.o -obj-$(CONFIG_PAGE_POOL) += page_pool.o +obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_NETPOLL) += netpoll.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index cca7594be9..6c4d90b24d 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 e3c06ccf21..c365aa06f8 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 @@ -337,7 +336,7 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name) return -ENOMEM; netdev_name_node_add(net, name_node); /* The node that holds dev->name acts as a head of per-device list. */ - list_add_tail(&name_node->list, &dev->name_node->list); + list_add_tail_rcu(&name_node->list, &dev->name_node->list); return 0; } @@ -3757,6 +3756,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); + tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_DROP); + if (q->flags & TCQ_F_NOLOCK) { if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) && qdisc_run_begin(q)) { @@ -3786,10 +3787,14 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, no_lock_out: if (unlikely(to_free)) kfree_skb_list_reason(to_free, - SKB_DROP_REASON_QDISC_DROP); + tcf_get_drop_reason(to_free)); return rc; } + if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) { + kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP); + return NET_XMIT_DROP; + } /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. @@ -3829,7 +3834,9 @@ no_lock_out: qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { + WRITE_ONCE(q->owner, smp_processor_id()); rc = dev_qdisc_enqueue(skb, q, &to_free, txq); + WRITE_ONCE(q->owner, -1); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -3841,7 +3848,8 @@ no_lock_out: } spin_unlock(root_lock); if (unlikely(to_free)) - kfree_skb_list_reason(to_free, SKB_DROP_REASON_QDISC_DROP); + kfree_skb_list_reason(to_free, + tcf_get_drop_reason(to_free)); if (unlikely(contended)) spin_unlock(&q->busylock); return rc; @@ -3927,14 +3935,14 @@ static int tc_run(struct tcx_entry *entry, struct sk_buff *skb, tc_skb_cb(skb)->mru = 0; tc_skb_cb(skb)->post_ct = false; - res.drop_reason = *drop_reason; + tcf_set_drop_reason(skb, *drop_reason); mini_qdisc_bstats_cpu_update(miniq, skb); ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false); /* Only tcf related quirks below. */ switch (ret) { case TC_ACT_SHOT: - *drop_reason = res.drop_reason; + *drop_reason = tcf_get_drop_reason(skb); mini_qdisc_qstats_cpu_drop(miniq); break; case TC_ACT_OK: @@ -6142,7 +6150,7 @@ 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; @@ -6403,6 +6411,43 @@ 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) { @@ -6438,6 +6483,7 @@ 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); @@ -9037,28 +9083,6 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) } EXPORT_SYMBOL(netdev_port_same_parent_id); -static void netdev_dpll_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin) -{ -#if IS_ENABLED(CONFIG_DPLL) - rtnl_lock(); - dev->dpll_pin = dpll_pin; - rtnl_unlock(); -#endif -} - -void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) -{ - WARN_ON(!dpll_pin); - netdev_dpll_pin_assign(dev, dpll_pin); -} -EXPORT_SYMBOL(netdev_dpll_pin_set); - -void netdev_dpll_pin_clear(struct net_device *dev) -{ - netdev_dpll_pin_assign(dev, NULL); -} -EXPORT_SYMBOL(netdev_dpll_pin_clear); - /** * dev_change_proto_down - set carrier according to proto_down. * @@ -10517,7 +10541,7 @@ 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)) { @@ -11242,17 +11266,19 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, dev_net_set(dev, net); dev->ifindex = new_ifindex; - /* Send a netdev-add uevent to the new namespace */ - kobject_uevent(&dev->dev.kobj, KOBJ_ADD); - netdev_adjacent_add_links(dev); - if (new_name[0]) /* Rename the netdev to prepared name */ strscpy(dev->name, new_name, IFNAMSIZ); /* Fixup kobjects */ + dev_set_uevent_suppress(&dev->dev, 1); err = device_rename(&dev->dev, dev->name); + dev_set_uevent_suppress(&dev->dev, 0); WARN_ON(err); + /* Send a netdev-add uevent to the new namespace */ + kobject_uevent(&dev->dev.kobj, KOBJ_ADD); + netdev_adjacent_add_links(dev); + /* Adapt owner in case owning user namespace of target network * namespace is different from the original one. */ @@ -11585,6 +11611,63 @@ 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, gso_partial_features); + 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, 160); + + /* TXRX read-mostly hotpath */ + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state); + 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, 46); + + /* 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, 104); +} + /* * Initialize the DEV module. At boot time this walks the device list and * unhooks any devices that fail to initialise (normally hardware not @@ -11602,6 +11685,8 @@ 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 3f5eb92396..7480b4c842 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); @@ -148,4 +147,6 @@ 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/dev_ioctl.c b/net/core/dev_ioctl.c index feeddf95f4..9a66cf5015 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -322,9 +322,9 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in * dev->priv_flags. */ -static int dev_set_hwtstamp_phylib(struct net_device *dev, - struct kernel_hwtstamp_config *cfg, - struct netlink_ext_ack *extack) +int dev_set_hwtstamp_phylib(struct net_device *dev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; bool phy_ts = phy_has_hwtstamp(dev->phydev); @@ -363,6 +363,7 @@ static int dev_set_hwtstamp_phylib(struct net_device *dev, return 0; } +EXPORT_SYMBOL_GPL(dev_set_hwtstamp_phylib); static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) { diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index b240d9aae4..b0f221d658 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", .cap_sys_admin = 1 }, + { .name = "events", .flags = GENL_MCAST_CAP_SYS_ADMIN, }, }; static void send_dm_alert(struct work_struct *work) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 75282222e0..3f933ffcef 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -53,7 +53,7 @@ bool fib_rule_matchall(const struct fib_rule *rule) EXPORT_SYMBOL_GPL(fib_rule_matchall); int fib_default_rule_add(struct fib_rules_ops *ops, - u32 pref, u32 table, u32 flags) + u32 pref, u32 table) { struct fib_rule *r; @@ -65,7 +65,6 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->action = FR_ACT_TO_TBL; r->pref = pref; r->table = table; - r->flags = flags; r->proto = RTPROT_KERNEL; r->fr_net = ops->fro_net; r->uid_range = fib_kuid_range_unset; @@ -594,7 +593,6 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[FRA_TUN_ID]) nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); - err = -EINVAL; if (tb[FRA_L3MDEV] && fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0) goto errout_free; diff --git a/net/core/filter.c b/net/core/filter.c index cee5383831..ef3e78b6a3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -204,7 +204,7 @@ BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) return 0; nla = (struct nlattr *) &skb->data[a]; - if (nla->nla_len > skb->len - a) + if (!nla_ok(nla, skb->len - a)) return 0; nla = nla_find_nested(nla, x); @@ -1220,8 +1220,8 @@ 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 && @@ -1551,12 +1551,13 @@ 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); @@ -1595,7 +1596,7 @@ 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; @@ -1623,7 +1624,8 @@ 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; } @@ -7289,7 +7291,6 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES - u32 cookie; int ret; if (unlikely(!sk || th_len < sizeof(*th))) @@ -7311,8 +7312,6 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; - cookie = ntohl(th->ack_seq) - 1; - /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ @@ -7321,7 +7320,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; - ret = __cookie_v4_check((struct iphdr *)iph, th, cookie); + ret = __cookie_v4_check((struct iphdr *)iph, th); break; #if IS_BUILTIN(CONFIG_IPV6) @@ -7332,7 +7331,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (sk->sk_family != AF_INET6) return -EINVAL; - ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie); + ret = __cookie_v6_check((struct ipv6hdr *)iph, th); break; #endif /* CONFIG_IPV6 */ @@ -7785,9 +7784,7 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph, struct tcphdr *, th) { - u32 cookie = ntohl(th->ack_seq) - 1; - - if (__cookie_v4_check(iph, th, cookie) > 0) + if (__cookie_v4_check(iph, th) > 0) return 0; return -EACCES; @@ -7808,9 +7805,7 @@ BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph, struct tcphdr *, th) { #if IS_BUILTIN(CONFIG_IPV6) - u32 cookie = ntohl(th->ack_seq) - 1; - - if (__cookie_v6_check(iph, th, cookie) > 0) + if (__cookie_v6_check(iph, th) > 0) return 0; return -EACCES; diff --git a/net/core/gro.c b/net/core/gro.c index 0759277dc1..cefddf65f7 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -195,8 +195,9 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) } merge: - /* sk owenrship - if any - completely transferred to the aggregated packet */ + /* sk ownership - if any - completely transferred to the aggregated packet */ skb->destructor = NULL; + skb->sk = NULL; delta_truesize = skb->truesize; if (offset > headlen) { unsigned int eat = offset - headlen; diff --git a/net/core/link_watch.c b/net/core/link_watch.c index c469d1c4db..429571c258 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/net-sysfs.c b/net/core/net-sysfs.c index fccaa5bac0..a09d507c5b 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 f4183c4c1e..7279953342 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 ea9231378a..be7f2ebd61 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -10,11 +10,64 @@ #include <uapi/linux/netdev.h> +/* Integer value ranges */ +static const struct netlink_range_validation netdev_a_page_pool_id_range = { + .min = 1ULL, + .max = 4294967295ULL, +}; + +static const struct netlink_range_validation netdev_a_page_pool_ifindex_range = { + .min = 1ULL, + .max = 2147483647ULL, +}; + +/* Common nested types */ +const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1] = { + [NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range), + [NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range), +}; + /* NETDEV_CMD_DEV_GET - do */ static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; +/* NETDEV_CMD_PAGE_POOL_GET - do */ +#ifdef CONFIG_PAGE_POOL +static const struct nla_policy netdev_page_pool_get_nl_policy[NETDEV_A_PAGE_POOL_ID + 1] = { + [NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range), +}; +#endif /* CONFIG_PAGE_POOL */ + +/* NETDEV_CMD_PAGE_POOL_STATS_GET - do */ +#ifdef CONFIG_PAGE_POOL_STATS +static const struct nla_policy netdev_page_pool_stats_get_nl_policy[NETDEV_A_PAGE_POOL_STATS_INFO + 1] = { + [NETDEV_A_PAGE_POOL_STATS_INFO] = NLA_POLICY_NESTED(netdev_page_pool_info_nl_policy), +}; +#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[] = { { @@ -29,10 +82,67 @@ static const struct genl_split_ops netdev_nl_ops[] = { .dumpit = netdev_nl_dev_get_dumpit, .flags = GENL_CMD_CAP_DUMP, }, +#ifdef CONFIG_PAGE_POOL + { + .cmd = NETDEV_CMD_PAGE_POOL_GET, + .doit = netdev_nl_page_pool_get_doit, + .policy = netdev_page_pool_get_nl_policy, + .maxattr = NETDEV_A_PAGE_POOL_ID, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_PAGE_POOL_GET, + .dumpit = netdev_nl_page_pool_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, +#endif /* CONFIG_PAGE_POOL */ +#ifdef CONFIG_PAGE_POOL_STATS + { + .cmd = NETDEV_CMD_PAGE_POOL_STATS_GET, + .doit = netdev_nl_page_pool_stats_get_doit, + .policy = netdev_page_pool_stats_get_nl_policy, + .maxattr = NETDEV_A_PAGE_POOL_STATS_INFO, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_PAGE_POOL_STATS_GET, + .dumpit = netdev_nl_page_pool_stats_get_dumpit, + .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[] = { [NETDEV_NLGRP_MGMT] = { "mgmt", }, + [NETDEV_NLGRP_PAGE_POOL] = { "page-pool", }, }; struct genl_family netdev_nl_family __ro_after_init = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 7b370c073e..a47f2bcbe4 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -11,11 +11,27 @@ #include <uapi/linux/netdev.h> +/* Common nested types */ +extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1]; + int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +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, + NETDEV_NLGRP_PAGE_POOL, }; extern struct genl_family netdev_nl_family; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index fe61f85bcf..918b109e0c 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -6,13 +6,32 @@ #include <net/net_namespace.h> #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, const struct genl_info *info) { + u64 xsk_features = 0; u64 xdp_rx_meta = 0; void *hdr; @@ -26,11 +45,20 @@ netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC + if (netdev->xsk_tx_metadata_ops) { + if (netdev->xsk_tx_metadata_ops->tmo_fill_timestamp) + xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP; + if (netdev->xsk_tx_metadata_ops->tmo_request_checksum) + xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM; + } + if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES, netdev->xdp_features, NETDEV_A_DEV_PAD) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, - xdp_rx_meta, NETDEV_A_DEV_PAD)) { + xdp_rx_meta, NETDEV_A_DEV_PAD) || + nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES, + xsk_features, NETDEV_A_DEV_PAD)) { genlmsg_cancel(rsp, hdr); return -EINVAL; } @@ -111,22 +139,325 @@ 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; } rtnl_unlock(); - if (err != -EMSGSIZE) + return err; +} + +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(); + + return err; +} + +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; - return skb->len; + 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(); + + return err; } static int netdev_genl_netdevice_event(struct notifier_block *nb, diff --git a/net/core/page_pool.c b/net/core/page_pool.c index dec5443372..4933762e5a 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -23,10 +23,12 @@ #include <trace/events/page_pool.h> +#include "page_pool_priv.h" + #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 */ @@ -69,7 +71,7 @@ static const char pp_stats[][ETH_GSTRING_LEN] = { * is passed to this API which is filled in. The caller can then report * those stats to the user (perhaps via ethtool, debugfs, etc.). */ -bool page_pool_get_stats(struct page_pool *pool, +bool page_pool_get_stats(const struct page_pool *pool, struct page_pool_stats *stats) { int cpu = 0; @@ -173,7 +175,8 @@ static int page_pool_init(struct page_pool *pool, { unsigned int ring_qsize = 1024; /* Default */ - memcpy(&pool->p, params, sizeof(pool->p)); + memcpy(&pool->p, ¶ms->fast, sizeof(pool->p)); + memcpy(&pool->slow, ¶ms->slow, sizeof(pool->slow)); /* Validate only known flags were used */ if (pool->p.flags & ~(PP_FLAG_ALL)) @@ -211,6 +214,8 @@ static int page_pool_init(struct page_pool *pool, */ } + pool->has_init_callback = !!pool->slow.init_callback; + #ifdef CONFIG_PAGE_POOL_STATS pool->recycle_stats = alloc_percpu(struct page_pool_recycle_stats); if (!pool->recycle_stats) @@ -235,6 +240,18 @@ static int page_pool_init(struct page_pool *pool, return 0; } +static void page_pool_uninit(struct page_pool *pool) +{ + ptr_ring_cleanup(&pool->ring, NULL); + + if (pool->p.flags & PP_FLAG_DMA_MAP) + put_device(pool->p.dev); + +#ifdef CONFIG_PAGE_POOL_STATS + free_percpu(pool->recycle_stats); +#endif +} + /** * page_pool_create() - create a page pool. * @params: parameters, see struct page_pool_params @@ -249,13 +266,21 @@ struct page_pool *page_pool_create(const struct page_pool_params *params) return ERR_PTR(-ENOMEM); err = page_pool_init(pool, params); - if (err < 0) { - pr_warn("%s() gave up with errno %d\n", __func__, err); - kfree(pool); - return ERR_PTR(err); - } + if (err < 0) + goto err_free; + + err = page_pool_list(pool); + if (err) + goto err_uninit; return pool; + +err_uninit: + page_pool_uninit(pool); +err_free: + pr_warn("%s() gave up with errno %d\n", __func__, err); + kfree(pool); + return ERR_PTR(err); } EXPORT_SYMBOL(page_pool_create); @@ -388,8 +413,8 @@ static void page_pool_set_pp_info(struct page_pool *pool, * the overhead is negligible. */ page_pool_fragment_page(page, 1); - if (pool->p.init_callback) - pool->p.init_callback(page, pool->p.init_arg); + if (pool->has_init_callback) + pool->slow.init_callback(page, pool->slow.init_arg); } static void page_pool_clear_pp_info(struct page *page) @@ -504,7 +529,7 @@ EXPORT_SYMBOL(page_pool_alloc_pages); */ #define _distance(a, b) (s32)((a) - (b)) -static s32 page_pool_inflight(struct page_pool *pool) +s32 page_pool_inflight(const struct page_pool *pool, bool strict) { u32 release_cnt = atomic_read(&pool->pages_state_release_cnt); u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt); @@ -512,27 +537,27 @@ static s32 page_pool_inflight(struct page_pool *pool) inflight = _distance(hold_cnt, release_cnt); - trace_page_pool_release(pool, inflight, hold_cnt, release_cnt); - WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight); + if (strict) { + trace_page_pool_release(pool, inflight, hold_cnt, release_cnt); + WARN(inflight < 0, "Negative(%d) inflight packet-pages", + inflight); + } else { + inflight = max(0, inflight); + } 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); @@ -541,7 +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 @@ -647,8 +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)) { @@ -657,7 +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 @@ -684,7 +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); @@ -726,7 +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)) { @@ -747,7 +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); @@ -818,14 +855,8 @@ static void __page_pool_destroy(struct page_pool *pool) if (pool->disconnect) pool->disconnect(pool); - ptr_ring_cleanup(&pool->ring, NULL); - - if (pool->p.flags & PP_FLAG_DMA_MAP) - put_device(pool->p.dev); - -#ifdef CONFIG_PAGE_POOL_STATS - free_percpu(pool->recycle_stats); -#endif + page_pool_unlist(pool); + page_pool_uninit(pool); kfree(pool); } @@ -862,7 +893,7 @@ static int page_pool_release(struct page_pool *pool) int inflight; page_pool_scrub(pool); - inflight = page_pool_inflight(pool); + inflight = page_pool_inflight(pool, true); if (!inflight) __page_pool_destroy(pool); @@ -873,18 +904,21 @@ static void page_pool_release_retry(struct work_struct *wq) { struct delayed_work *dwq = to_delayed_work(wq); struct page_pool *pool = container_of(dwq, typeof(*pool), release_dw); + void *netdev; int inflight; inflight = page_pool_release(pool); if (!inflight) return; - /* Periodic warning */ - if (time_after_eq(jiffies, pool->defer_warn)) { + /* Periodic warning for page pools the user can't see */ + netdev = READ_ONCE(pool->slow.netdev); + if (time_after_eq(jiffies, pool->defer_warn) && + (!netdev || netdev == NET_PTR_POISON)) { int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ; - pr_warn("%s() stalled pool shutdown %d inflight %d sec\n", - __func__, inflight, sec); + pr_warn("%s() stalled pool shutdown: id %u, %d inflight %d sec\n", + __func__, pool->user.id, inflight, sec); pool->defer_warn = jiffies + DEFER_WARN_INTERVAL; } @@ -929,6 +963,7 @@ void page_pool_destroy(struct page_pool *pool) if (!page_pool_release(pool)) return; + page_pool_detached(pool); pool->defer_start = jiffies; pool->defer_warn = jiffies + DEFER_WARN_INTERVAL; diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h new file mode 100644 index 0000000000..90665d40f1 --- /dev/null +++ b/net/core/page_pool_priv.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __PAGE_POOL_PRIV_H +#define __PAGE_POOL_PRIV_H + +s32 page_pool_inflight(const struct page_pool *pool, bool strict); + +int page_pool_list(struct page_pool *pool); +void page_pool_detached(struct page_pool *pool); +void page_pool_unlist(struct page_pool *pool); + +#endif diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c new file mode 100644 index 0000000000..3a3277ba16 --- /dev/null +++ b/net/core/page_pool_user.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/mutex.h> +#include <linux/netdevice.h> +#include <linux/xarray.h> +#include <net/net_debug.h> +#include <net/page_pool/types.h> +#include <net/page_pool/helpers.h> +#include <net/sock.h> + +#include "page_pool_priv.h" +#include "netdev-genl-gen.h" + +static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1); +/* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user. + * Ordering: inside rtnl_lock + */ +static DEFINE_MUTEX(page_pools_lock); + +/* Page pools are only reachable from user space (via netlink) if they are + * linked to a netdev at creation time. Following page pool "visibility" + * states are possible: + * - normal + * - user.list: linked to real netdev, netdev: real netdev + * - orphaned - real netdev has disappeared + * - user.list: linked to lo, netdev: lo + * - invisible - either (a) created without netdev linking, (b) unlisted due + * to error, or (c) the entire namespace which owned this pool disappeared + * - user.list: unhashed, netdev: unknown + */ + +typedef int (*pp_nl_fill_cb)(struct sk_buff *rsp, const struct page_pool *pool, + const struct genl_info *info); + +static int +netdev_nl_page_pool_get_do(struct genl_info *info, u32 id, pp_nl_fill_cb fill) +{ + struct page_pool *pool; + struct sk_buff *rsp; + int err; + + mutex_lock(&page_pools_lock); + pool = xa_load(&page_pools, id); + if (!pool || hlist_unhashed(&pool->user.list) || + !net_eq(dev_net(pool->slow.netdev), genl_info_net(info))) { + err = -ENOENT; + goto err_unlock; + } + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) { + err = -ENOMEM; + goto err_unlock; + } + + err = fill(rsp, pool, info); + if (err) + goto err_free_msg; + + mutex_unlock(&page_pools_lock); + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); +err_unlock: + mutex_unlock(&page_pools_lock); + return err; +} + +struct page_pool_dump_cb { + unsigned long ifindex; + u32 pp_id; +}; + +static int +netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, + pp_nl_fill_cb fill) +{ + struct page_pool_dump_cb *state = (void *)cb->ctx; + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + struct page_pool *pool; + int err = 0; + + rtnl_lock(); + mutex_lock(&page_pools_lock); + for_each_netdev_dump(net, netdev, state->ifindex) { + hlist_for_each_entry(pool, &netdev->page_pools, user.list) { + if (state->pp_id && state->pp_id < pool->user.id) + continue; + + state->pp_id = pool->user.id; + err = fill(skb, pool, info); + if (err) + goto out; + } + + state->pp_id = 0; + } +out: + mutex_unlock(&page_pools_lock); + rtnl_unlock(); + + return err; +} + +static int +page_pool_nl_stats_fill(struct sk_buff *rsp, const struct page_pool *pool, + const struct genl_info *info) +{ +#ifdef CONFIG_PAGE_POOL_STATS + struct page_pool_stats stats = {}; + struct nlattr *nest; + void *hdr; + + if (!page_pool_get_stats(pool, &stats)) + return 0; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + nest = nla_nest_start(rsp, NETDEV_A_PAGE_POOL_STATS_INFO); + + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id) || + (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && + nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, + pool->slow.netdev->ifindex))) + goto err_cancel_nest; + + nla_nest_end(rsp, nest); + + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST, + stats.alloc_stats.fast) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW, + stats.alloc_stats.slow) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER, + stats.alloc_stats.slow_high_order) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY, + stats.alloc_stats.empty) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL, + stats.alloc_stats.refill) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE, + stats.alloc_stats.waive) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED, + stats.recycle_stats.cached) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL, + stats.recycle_stats.cache_full) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING, + stats.recycle_stats.ring) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL, + stats.recycle_stats.ring_full) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT, + stats.recycle_stats.released_refcnt)) + goto err_cancel_msg; + + genlmsg_end(rsp, hdr); + + return 0; +err_cancel_nest: + nla_nest_cancel(rsp, nest); +err_cancel_msg: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +#else + GENL_SET_ERR_MSG(info, "kernel built without CONFIG_PAGE_POOL_STATS"); + return -EOPNOTSUPP; +#endif +} + +int netdev_nl_page_pool_stats_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *tb[ARRAY_SIZE(netdev_page_pool_info_nl_policy)]; + struct nlattr *nest; + int err; + u32 id; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_STATS_INFO)) + return -EINVAL; + + nest = info->attrs[NETDEV_A_PAGE_POOL_STATS_INFO]; + err = nla_parse_nested(tb, ARRAY_SIZE(tb) - 1, nest, + netdev_page_pool_info_nl_policy, + info->extack); + if (err) + return err; + + if (NL_REQ_ATTR_CHECK(info->extack, nest, tb, NETDEV_A_PAGE_POOL_ID)) + return -EINVAL; + if (tb[NETDEV_A_PAGE_POOL_IFINDEX]) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NETDEV_A_PAGE_POOL_IFINDEX], + "selecting by ifindex not supported"); + return -EINVAL; + } + + id = nla_get_uint(tb[NETDEV_A_PAGE_POOL_ID]); + + return netdev_nl_page_pool_get_do(info, id, page_pool_nl_stats_fill); +} + +int netdev_nl_page_pool_stats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_stats_fill); +} + +static int +page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, + const struct genl_info *info) +{ + size_t inflight, refsz; + void *hdr; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_ID, pool->user.id)) + goto err_cancel; + + if (pool->slow.netdev->ifindex != LOOPBACK_IFINDEX && + nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, + pool->slow.netdev->ifindex)) + goto err_cancel; + if (pool->user.napi_id && + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id)) + goto err_cancel; + + inflight = page_pool_inflight(pool, false); + refsz = PAGE_SIZE << pool->p.order; + if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT, inflight) || + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, + inflight * refsz)) + goto err_cancel; + if (pool->user.detach_time && + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME, + pool->user.detach_time)) + goto err_cancel; + + genlmsg_end(rsp, hdr); + + return 0; +err_cancel: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +static void netdev_nl_page_pool_event(const struct page_pool *pool, u32 cmd) +{ + struct genl_info info; + struct sk_buff *ntf; + struct net *net; + + lockdep_assert_held(&page_pools_lock); + + /* 'invisible' page pools don't matter */ + if (hlist_unhashed(&pool->user.list)) + return; + net = dev_net(pool->slow.netdev); + + if (!genl_has_listeners(&netdev_nl_family, net, NETDEV_NLGRP_PAGE_POOL)) + return; + + genl_info_init_ntf(&info, &netdev_nl_family, cmd); + + ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!ntf) + return; + + if (page_pool_nl_fill(ntf, pool, &info)) { + nlmsg_free(ntf); + return; + } + + genlmsg_multicast_netns(&netdev_nl_family, net, ntf, + 0, NETDEV_NLGRP_PAGE_POOL, GFP_KERNEL); +} + +int netdev_nl_page_pool_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + u32 id; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_PAGE_POOL_ID)) + return -EINVAL; + + id = nla_get_uint(info->attrs[NETDEV_A_PAGE_POOL_ID]); + + return netdev_nl_page_pool_get_do(info, id, page_pool_nl_fill); +} + +int netdev_nl_page_pool_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + return netdev_nl_page_pool_get_dump(skb, cb, page_pool_nl_fill); +} + +int page_pool_list(struct page_pool *pool) +{ + static u32 id_alloc_next; + int err; + + mutex_lock(&page_pools_lock); + err = xa_alloc_cyclic(&page_pools, &pool->user.id, pool, xa_limit_32b, + &id_alloc_next, GFP_KERNEL); + if (err < 0) + goto err_unlock; + + INIT_HLIST_NODE(&pool->user.list); + if (pool->slow.netdev) { + hlist_add_head(&pool->user.list, + &pool->slow.netdev->page_pools); + pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0; + + netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF); + } + + mutex_unlock(&page_pools_lock); + return 0; + +err_unlock: + mutex_unlock(&page_pools_lock); + return err; +} + +void page_pool_detached(struct page_pool *pool) +{ + mutex_lock(&page_pools_lock); + pool->user.detach_time = ktime_get_boottime_seconds(); + netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); + mutex_unlock(&page_pools_lock); +} + +void page_pool_unlist(struct page_pool *pool) +{ + mutex_lock(&page_pools_lock); + netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_DEL_NTF); + xa_erase(&page_pools, pool->user.id); + if (!hlist_unhashed(&pool->user.list)) + hlist_del(&pool->user.list); + mutex_unlock(&page_pools_lock); +} + +static void page_pool_unreg_netdev_wipe(struct net_device *netdev) +{ + struct page_pool *pool; + struct hlist_node *n; + + mutex_lock(&page_pools_lock); + hlist_for_each_entry_safe(pool, n, &netdev->page_pools, user.list) { + hlist_del_init(&pool->user.list); + pool->slow.netdev = NET_PTR_POISON; + } + mutex_unlock(&page_pools_lock); +} + +static void page_pool_unreg_netdev(struct net_device *netdev) +{ + struct page_pool *pool, *last; + struct net_device *lo; + + lo = dev_net(netdev)->loopback_dev; + + mutex_lock(&page_pools_lock); + last = NULL; + hlist_for_each_entry(pool, &netdev->page_pools, user.list) { + pool->slow.netdev = lo; + netdev_nl_page_pool_event(pool, + NETDEV_CMD_PAGE_POOL_CHANGE_NTF); + last = pool; + } + if (last) + hlist_splice_init(&netdev->page_pools, &last->user.list, + &lo->page_pools); + mutex_unlock(&page_pools_lock); +} + +static int +page_pool_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + + if (hlist_empty(&netdev->page_pools)) + return NOTIFY_OK; + + if (netdev->ifindex != LOOPBACK_IFINDEX) + page_pool_unreg_netdev(netdev); + else + page_pool_unreg_netdev_wipe(netdev); + return NOTIFY_OK; +} + +static struct notifier_block page_pool_netdevice_nb = { + .notifier_call = page_pool_netdevice_event, +}; + +static int __init page_pool_user_init(void) +{ + return register_netdevice_notifier(&page_pool_netdevice_nb); +} + +subsys_initcall(page_pool_user_init); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 57cea67b75..ea55a758a4 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3669,10 +3669,8 @@ static int pktgen_thread_worker(void *arg) if (unlikely(!pkt_dev && t->control == 0)) { if (t->net->pktgen_exiting) break; - wait_event_interruptible_timeout(t->queue, - t->control != 0, - HZ/10); - try_to_freeze(); + wait_event_freezable_timeout(t->queue, + t->control != 0, HZ / 10); continue; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8f9cd6b792..bd50e9fe32 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(); @@ -1026,14 +1020,17 @@ static size_t rtnl_xdp_size(void) static size_t rtnl_prop_list_size(const struct net_device *dev) { struct netdev_name_node *name_node; - size_t size; + unsigned int cnt = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(name_node, &dev->name_node->list, list) + cnt++; + rcu_read_unlock(); - if (list_empty(&dev->name_node->list)) + if (!cnt) return 0; - size = nla_total_size(0); - list_for_each_entry(name_node, &dev->name_node->list, list) - size += nla_total_size(ALTIFNAMSIZ); - return size; + + return nla_total_size(0) + cnt * nla_total_size(ALTIFNAMSIZ); } static size_t rtnl_proto_down_size(const struct net_device *dev) @@ -1060,7 +1057,7 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev) { size_t size = nla_total_size(0); /* nest IFLA_DPLL_PIN */ - size += dpll_msg_pin_handle_size(netdev_dpll_pin(dev)); + size += dpll_netdev_pin_handle_size(dev); return size; } @@ -1795,7 +1792,7 @@ static int rtnl_fill_dpll_pin(struct sk_buff *skb, if (!dpll_pin_nest) return -EMSGSIZE; - ret = dpll_msg_add_pin_handle(skb, netdev_dpll_pin(dev)); + ret = dpll_netdev_add_pin_handle(skb, dev); if (ret < 0) goto nest_cancel; @@ -3849,10 +3846,18 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; err = -ENOBUFS; - nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL); + nskb = nlmsg_new_large(if_nlmsg_size(dev, ext_filter_mask)); 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, @@ -6407,17 +6412,64 @@ static int rtnl_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, return dev->netdev_ops->ndo_mdb_add(dev, tb, nlh->nlmsg_flags, extack); } +static int rtnl_validate_mdb_entry_del_bulk(const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct br_mdb_entry *entry = nla_data(attr); + struct br_mdb_entry zero_entry = {}; + + if (nla_len(attr) != sizeof(struct br_mdb_entry)) { + NL_SET_ERR_MSG_ATTR(extack, attr, "Invalid attribute length"); + return -EINVAL; + } + + if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) { + NL_SET_ERR_MSG(extack, "Unknown entry state"); + return -EINVAL; + } + + if (entry->flags) { + NL_SET_ERR_MSG(extack, "Entry flags cannot be set"); + return -EINVAL; + } + + if (entry->vid >= VLAN_N_VID - 1) { + NL_SET_ERR_MSG(extack, "Invalid entry VLAN id"); + return -EINVAL; + } + + if (memcmp(&entry->addr, &zero_entry.addr, sizeof(entry->addr))) { + NL_SET_ERR_MSG(extack, "Entry address cannot be set"); + return -EINVAL; + } + + return 0; +} + +static const struct nla_policy mdba_del_bulk_policy[MDBA_SET_ENTRY_MAX + 1] = { + [MDBA_SET_ENTRY] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, + rtnl_validate_mdb_entry_del_bulk, + sizeof(struct br_mdb_entry)), + [MDBA_SET_ENTRY_ATTRS] = { .type = NLA_NESTED }, +}; + static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + bool del_bulk = !!(nlh->nlmsg_flags & NLM_F_BULK); struct nlattr *tb[MDBA_SET_ENTRY_MAX + 1]; struct net *net = sock_net(skb->sk); struct br_port_msg *bpm; struct net_device *dev; int err; - err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb, - MDBA_SET_ENTRY_MAX, mdba_policy, extack); + if (!del_bulk) + err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb, + MDBA_SET_ENTRY_MAX, mdba_policy, + extack); + else + err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY_MAX, + mdba_del_bulk_policy, extack); if (err) return err; @@ -6438,6 +6490,14 @@ static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, return -EINVAL; } + if (del_bulk) { + if (!dev->netdev_ops->ndo_mdb_del_bulk) { + NL_SET_ERR_MSG(extack, "Device does not support MDB bulk deletion"); + return -EOPNOTSUPP; + } + return dev->netdev_ops->ndo_mdb_del_bulk(dev, tb, extack); + } + if (!dev->netdev_ops->ndo_mdb_del) { NL_SET_ERR_MSG(extack, "Device does not support MDB operations"); return -EOPNOTSUPP; @@ -6683,5 +6743,6 @@ void __init rtnetlink_init(void) rtnl_register(PF_BRIDGE, RTM_GETMDB, rtnl_mdb_get, rtnl_mdb_dump, 0); rtnl_register(PF_BRIDGE, RTM_NEWMDB, rtnl_mdb_add, NULL, 0); - rtnl_register(PF_BRIDGE, RTM_DELMDB, rtnl_mdb_del, NULL, 0); + rtnl_register(PF_BRIDGE, RTM_DELMDB, rtnl_mdb_del, NULL, + RTNL_FLAG_BULK_DEL_SUPPORTED); } diff --git a/net/core/scm.c b/net/core/scm.c index 737917c7ac..d0e0852a24 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -325,7 +325,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) } for (i = 0; i < fdmax; i++) { - err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags); + err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); if (err < 0) break; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 78cb3304fb..71dee435d5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -337,7 +337,7 @@ static struct sk_buff *napi_skb_cache_get(void) } skb = nc->skb_cache[--nc->skb_count]; - kasan_unpoison_object_data(skbuff_cache, skb); + kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache)); return skb; } @@ -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) @@ -1309,13 +1345,15 @@ static void napi_skb_cache_put(struct sk_buff *skb) struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); u32 i; - kasan_poison_object_data(skbuff_cache, skb); + if (!kasan_mempool_poison_object(skb)) + return; + nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) - kasan_unpoison_object_data(skbuff_cache, - nc->skb_cache[i]); + kasan_mempool_unpoison_object(nc->skb_cache[i], + kmem_cache_size(skbuff_cache)); kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); @@ -5767,17 +5805,12 @@ 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)) { @@ -5834,8 +5867,10 @@ 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; @@ -5962,6 +5997,31 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) } EXPORT_SYMBOL(skb_ensure_writable); +int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev) +{ + int needed_headroom = dev->needed_headroom; + int needed_tailroom = dev->needed_tailroom; + + /* For tail taggers, we need to pad short frames ourselves, to ensure + * that the tail tag does not fail at its role of being at the end of + * the packet, once the conduit interface pads the frame. Account for + * that pad length here, and pad later. + */ + if (unlikely(needed_tailroom && skb->len < ETH_ZLEN)) + needed_tailroom += ETH_ZLEN - skb->len; + /* skb_headroom() returns unsigned int... */ + needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0); + needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0); + + if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb))) + /* No reallocation needed, yay! */ + return 0; + + return pskb_expand_head(skb, needed_headroom, needed_tailroom, + GFP_ATOMIC); +} +EXPORT_SYMBOL(skb_ensure_writable_head_tail); + /* remove VLAN header from packet and update csum accordingly. * expects a non skb_vlan_tag_present skb with a vlan tag payload */ diff --git a/net/core/sock.c b/net/core/sock.c index 20160865ed..9cf404e803 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -283,10 +283,7 @@ __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; - -/* 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_mem_pcpu_rsv __read_mostly = SK_MEMORY_PCPU_RESERVE; int sysctl_tstamp_allow_data __read_mostly = 1; @@ -2658,7 +2655,7 @@ 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); @@ -2676,7 +2673,7 @@ 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/sock_map.c b/net/core/sock_map.c index 27d733c0f6..8598466a38 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -411,6 +411,9 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -933,6 +936,9 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 03f1edb948..986f15e5d6 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -30,6 +30,7 @@ static int int_3600 = 3600; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; +static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -408,6 +409,14 @@ static struct ctl_table net_core_table[] = { .extra1 = &min_rcvbuf, }, { + .procname = "mem_pcpu_rsv", + .data = &sysctl_mem_pcpu_rsv, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_mem_pcpu_rsv, + }, + { .procname = "dev_weight", .data = &weight_p, .maxlen = sizeof(int), @@ -509,13 +518,6 @@ 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 +676,14 @@ 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/core/xdp.c b/net/core/xdp.c index b6f1d6dab3..4869c1c2d8 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -736,6 +736,39 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, return -EOPNOTSUPP; } +/** + * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag + * @ctx: XDP context pointer. + * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID). + * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP) + * + * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*, + * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use + * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)** + * and should be used as follows: + * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();`` + * + * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag. + * Driver is expected to provide those in **host byte order (usually LE)**, + * so the bpf program should not perform byte conversion. + * According to 802.1Q standard, *VLAN TCI (Tag control information)* + * is a bit field that contains: + * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``, + * *Drop eligible indicator (DEI)* - 1 bit, + * *Priority code point (PCP)* - 3 bits. + * For detailed meaning of DEI and PCP, please refer to other sources. + * + * Return: + * * Returns 0 on success or ``-errno`` on error. + * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc + * * ``-ENODATA`` : VLAN tag was not stripped or is not available + */ +__bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, + __be16 *vlan_proto, u16 *vlan_tci) +{ + return -EOPNOTSUPP; +} + __bpf_kfunc_end_defs(); BTF_SET8_START(xdp_metadata_kfunc_ids) |